added asm files and analysis output
This commit is contained in:
JanLJL
parent
d0277765c3
commit
95d63334fa
198
static_analysis/jan/analyses/gromacs-icc-avx512-dp-iaca.out
Normal file
198
static_analysis/jan/analyses/gromacs-icc-avx512-dp-iaca.out
Normal file
@ -0,0 +1,198 @@
|
|||||||
|
Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45
|
||||||
|
Analyzed File - gromacs-icc-avx512-dp.o
|
||||||
|
Binary Format - 64Bit
|
||||||
|
Architecture - SKX
|
||||||
|
Analysis Type - Throughput
|
||||||
|
|
||||||
|
Throughput Analysis Report
|
||||||
|
--------------------------
|
||||||
|
Block Throughput: 62.00 Cycles Throughput Bottleneck: Backend
|
||||||
|
Loop Count: 22
|
||||||
|
Port Binding In Cycles Per Iteration:
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Cycles | 58.0 0.0 | 16.0 | 16.0 15.0 | 16.0 15.0 | 2.0 | 58.0 | 16.0 | 0.0 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
DV - Divider pipe (on port 0)
|
||||||
|
D - Data fetch pipe (on ports 2 and 3)
|
||||||
|
F - Macro Fusion with the previous instruction occurred
|
||||||
|
* - instruction micro-ops not bound to a port
|
||||||
|
^ - Micro Fusion occurred
|
||||||
|
# - ESP Tracking sync uop was issued
|
||||||
|
@ - SSE instruction followed an AVX256/AVX512 instruction, dozens of cycles penalty is expected
|
||||||
|
X - instruction not supported, was not accounted in Analysis
|
||||||
|
|
||||||
|
| Num Of | Ports pressure in cycles | |
|
||||||
|
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
-----------------------------------------------------------------------------------------
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | mov edx, dword ptr [r10+rsi*4]
|
||||||
|
| 1 | | | | | | | 1.0 | | inc rsi
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm20, zmmword ptr [rsp+0x380]
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm25, zmmword ptr [rsp+0x340]
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm24, zmmword ptr [rsp+0x1c0]
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm23, zmmword ptr [rsp+0x2c0]
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm16, zmmword ptr [rsp+0x3c0]
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm14, zmmword ptr [rsp+0x300]
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm15, zmmword ptr [rsp+0x240]
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm12, zmmword ptr [rsp+0x180]
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm21, zmmword ptr [rsp+0x200]
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm18, zmmword ptr [rsp+0x140]
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm22, zmmword ptr [rsp+0x100]
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm17, zmmword ptr [rsp+0x280]
|
||||||
|
| 1 | | 1.0 | | | | | | | lea r12d, ptr [rdx+rdx*2]
|
||||||
|
| 1 | | | | | | | 1.0 | | shl r12d, 0x3
|
||||||
|
| 1 | | 1.0 | | | | | | | lea r13d, ptr [rdx+rdx*1]
|
||||||
|
| 1 | | | | | | | 1.0 | | movsxd r12, r12d
|
||||||
|
| 1 | | 1.0 | | | | | | | cmp r13d, r11d
|
||||||
|
| 1 | | 1.0 | | | | | | | lea eax, ptr [rdx+rdx*1+0x1]
|
||||||
|
| 1 | | | | | | | 1.0 | | mov edx, 0x0
|
||||||
|
| 1 | | | | | | | 1.0 | | setz dl
|
||||||
|
| 1 | | 1.0 | | | | | | | cmp eax, r11d
|
||||||
|
| 1 | | | | | | | 1.0 | | mov eax, 0x0
|
||||||
|
| 1* | | | | | | | | | mov r13d, edx
|
||||||
|
| 2 | 1.0 | | | 1.0 1.0 | | | | | vsubpd zmm29, zmm20, zmmword ptr [r8+r12*8+0x80]
|
||||||
|
| 1 | | | | | | | 1.0 | | setz al
|
||||||
|
| 2 | | | 1.0 1.0 | | | 1.0 | | | vsubpd zmm26, zmm25, zmmword ptr [r8+r12*8+0x80]
|
||||||
|
| 2 | 1.0 | | | 1.0 1.0 | | | | | vsubpd zmm25, zmm24, zmmword ptr [r8+r12*8]
|
||||||
|
| 2 | | | 1.0 1.0 | | | 1.0 | | | vsubpd zmm24, zmm23, zmmword ptr [r8+r12*8+0x40]
|
||||||
|
| 2 | 1.0 | | | 1.0 1.0 | | | | | vsubpd zmm23, zmm16, zmmword ptr [r8+r12*8+0x80]
|
||||||
|
| 2 | | | 1.0 1.0 | | | 1.0 | | | vsubpd zmm20, zmm14, zmmword ptr [r8+r12*8+0x80]
|
||||||
|
| 2 | 1.0 | | | 1.0 1.0 | | | | | vsubpd zmm27, zmm12, zmmword ptr [r8+r12*8+0x40]
|
||||||
|
| 2 | | | 1.0 1.0 | | | 1.0 | | | vsubpd zmm28, zmm15, zmmword ptr [r8+r12*8]
|
||||||
|
| 2 | 1.0 | | | 1.0 1.0 | | | | | vsubpd zmm30, zmm21, zmmword ptr [r8+r12*8+0x40]
|
||||||
|
| 2 | | | 1.0 1.0 | | | 1.0 | | | vsubpd zmm21, zmm18, zmmword ptr [r8+r12*8+0x40]
|
||||||
|
| 2 | 1.0 | | | 1.0 1.0 | | | | | vsubpd zmm31, zmm22, zmmword ptr [r8+r12*8]
|
||||||
|
| 2 | | | 1.0 1.0 | | | 1.0 | | | vsubpd zmm22, zmm17, zmmword ptr [r8+r12*8]
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm13, zmm29, zmm29
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm15, zmm26, zmm26
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm12, zmm23, zmm23
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm14, zmm20, zmm20
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm16, zmmword ptr [rsp+0xc0]
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm13, zmm30, zmm30
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm15, zmm27, zmm27
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm12, zmm24, zmm24
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm14, zmm21, zmm21
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm13, zmm31, zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm15, zmm28, zmm28
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm12, zmm25, zmm25
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm14, zmm22, zmm22
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm19, zmm13
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm18, zmm15
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm17, zmm12
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k1, zmm13, zmm16, 0x11
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k6, zmm15, zmm16, 0x11
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k7, zmm12, zmm16, 0x11
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k0, zmm14, zmm16, 0x11
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm15, zmm14
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm16, zmmword ptr [rsp+0x40]
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm12, zmmword ptr [rsp+0x80]
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm13, zmm19, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm13, zmm19, zmm13
|
||||||
|
| 1 | | 1.0 | | | | | | | neg r13d
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm14, zmm19, zmm13
|
||||||
|
| 1* | | | | | | | | | mov r12d, eax
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmsub213pd zmm13, zmm19, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm19, zmm19, zmm12
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm13, zmm13, zmm19
|
||||||
|
| 1 | | 1.0 | | | | | | | add r13d, 0xff
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm14, zmm14, zmm13
|
||||||
|
| 1 | | | | | | | 1.0 | | nop
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm13, zmmword ptr [rsp+0x400]
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm19, zmm10, zmm14
|
||||||
|
| 1 | | | | | | | 1.0 | | shl r12d, 0x4
|
||||||
|
| 1 | | 1.0 | | | | | | | sub r13d, r12d
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k5, r13d
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovw r13d, k1
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovb r12d, k5
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k5, r12d
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k1, r13d
|
||||||
|
| 1* | | | | | | | | | mov r13d, eax
|
||||||
|
| 1 | 1.0 | | | | | | | | kandb k5, k5, k1
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovb r12d, k5
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovw k5, r12d
|
||||||
|
| 1 | | 1.0 | | | | | | | lea r12d, ptr [rdx+rdx*1]
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm9{k5}, zmm19, zmm29
|
||||||
|
| 1 | | | | | | | 1.0 | | neg r12d
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm13{k5}, zmm19, zmm31
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm31, zmmword ptr [rsp+0x440]
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm29, zmm18, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm31{k5}, zmm19, zmm30
|
||||||
|
| 2^ | | | 1.0 | | 1.0 | | | | vmovups zmmword ptr [rsp+0x400], zmm13
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm30, zmm18, zmm29
|
||||||
|
| 2^ | | | | 1.0 | 1.0 | | | | vmovups zmmword ptr [rsp+0x440], zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm13, zmm18, zmm30
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmsub213pd zmm30, zmm18, zmm1
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm18, zmm18, zmm12
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm14, zmm30, zmm18
|
||||||
|
| 1 | | 1.0 | | | | | | | add r12d, 0xff
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm19, zmm13, zmm14
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm29, zmm10, zmm19
|
||||||
|
| 1 | | | | | | | 1.0 | | shl r13d, 0x5
|
||||||
|
| 1 | | 1.0 | | | | | | | sub r12d, r13d
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k1, r12d
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovw r12d, k6
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovb r13d, k1
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k1, r13d
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k6, r12d
|
||||||
|
| 1* | | | | | | | | | mov r12d, eax
|
||||||
|
| 1 | 1.0 | | | | | | | | kandb k1, k1, k6
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovb r13d, k1
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovw k1, r13d
|
||||||
|
| 1 | | 1.0 | | | | | | | lea r13d, ptr [rdx*4]
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm6{k1}, zmm29, zmm26
|
||||||
|
| 1 | | | | | | | 1.0 | | neg r13d
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm7{k1}, zmm29, zmm27
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm8{k1}, zmm29, zmm28
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm26, zmm17, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm28, zmm17, zmm12
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm15, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm12, zmm15, zmm12
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm27, zmm17, zmm26
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm19, zmm15, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm13, zmm17, zmm27
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmsub213pd zmm27, zmm17, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm14, zmm27, zmm28
|
||||||
|
| 1 | | | | | | | 1.0 | | add r13d, 0xff
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm17, zmm13, zmm14
|
||||||
|
| 1 | | | | | | | 1.0 | | shl edx, 0x3
|
||||||
|
| 1 | | | | | | | 1.0 | | shl r12d, 0x6
|
||||||
|
| 1 | | 1.0 | | | | | | | neg edx
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm18, zmm10, zmm17
|
||||||
|
| 1 | | 1.0 | | | | | | | sub r13d, r12d
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k6, r13d
|
||||||
|
| 1 | | 1.0 | | | | | | | add edx, 0xff
|
||||||
|
| 1 | | | | | | | 1.0 | | shl eax, 0x7
|
||||||
|
| 1 | | 1.0 | | | | | | | sub edx, eax
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovb eax, k6
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k6, eax
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovw eax, k7
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k7, eax
|
||||||
|
| 1 | 1.0 | | | | | | | | kandb k7, k6, k7
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k6, edx
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovb edx, k7
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovw k7, edx
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovw edx, k0
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm11{k7}, zmm18, zmm23
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm4{k7}, zmm18, zmm24
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm5{k7}, zmm18, zmm25
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm23, zmm15, zmm19
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmsub213pd zmm19, zmm15, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm15, zmm19, zmm12
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm24, zmm23, zmm15
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm25, zmm10, zmm24
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovb eax, k6
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k6, eax
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovb k0, edx
|
||||||
|
| 1 | 1.0 | | | | | | | | kandb k0, k6, k0
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovb r12d, k0
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovw k6, r12d
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm3{k6}, zmm25, zmm22
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm2{k6}, zmm25, zmm21
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm0{k6}, zmm25, zmm20
|
||||||
|
| 1* | | | | | | | | | cmp rsi, rdi
|
||||||
|
| 0*F | | | | | | | | | jl 0xfffffffffffffc6f
|
||||||
|
Total Num Of Uops: 187
|
||||||
|
Analysis Notes:
|
||||||
|
Backend allocation was stalled due to unavailable allocation resources.
|
||||||
152
static_analysis/jan/analyses/gromacs-icc-avx512-sp-iaca.out
Normal file
152
static_analysis/jan/analyses/gromacs-icc-avx512-sp-iaca.out
Normal file
@ -0,0 +1,152 @@
|
|||||||
|
Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45
|
||||||
|
Analyzed File - gromacs-icc-avx512-sp.o
|
||||||
|
Binary Format - 64Bit
|
||||||
|
Architecture - SKX
|
||||||
|
Analysis Type - Throughput
|
||||||
|
|
||||||
|
Throughput Analysis Report
|
||||||
|
--------------------------
|
||||||
|
Block Throughput: 51.00 Cycles Throughput Bottleneck: Backend
|
||||||
|
Loop Count: 22
|
||||||
|
Port Binding In Cycles Per Iteration:
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Cycles | 47.5 0.0 | 9.0 | 11.0 11.0 | 11.0 8.0 | 3.0 | 47.5 | 9.0 | 0.0 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
DV - Divider pipe (on port 0)
|
||||||
|
D - Data fetch pipe (on ports 2 and 3)
|
||||||
|
F - Macro Fusion with the previous instruction occurred
|
||||||
|
* - instruction micro-ops not bound to a port
|
||||||
|
^ - Micro Fusion occurred
|
||||||
|
# - ESP Tracking sync uop was issued
|
||||||
|
@ - SSE instruction followed an AVX256/AVX512 instruction, dozens of cycles penalty is expected
|
||||||
|
X - instruction not supported, was not accounted in Analysis
|
||||||
|
|
||||||
|
| Num Of | Ports pressure in cycles | |
|
||||||
|
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
-----------------------------------------------------------------------------------------
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | mov edi, dword ptr [rcx+rax*4]
|
||||||
|
| 1* | | | | | | | | | mov r12d, r13d
|
||||||
|
| 1 | | | | | | | 1.0 | | movsxd rdi, edi
|
||||||
|
| 1 | | 1.0 | | | | | | | inc rax
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm10, zmmword ptr [rsp+0x140]
|
||||||
|
| 1 | | | | | | | 1.0 | | test edi, 0x7fffffff
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm11, zmmword ptr [rsp+0x100]
|
||||||
|
| 1 | | | | 1.0 1.0 | | | | | vmovups zmm9, zmmword ptr [rsp+0xc0]
|
||||||
|
| 1 | | | | | | | 1.0 | | setz r12b
|
||||||
|
| 1 | | 1.0 | | | | | | | lea r14, ptr [rdi+rdi*2]
|
||||||
|
| 1 | | | | | | | 1.0 | | shl r14, 0x5
|
||||||
|
| 1* | | | | | | | | | mov r8d, r12d
|
||||||
|
| 1 | | 1.0 | | | | | | | neg r8d
|
||||||
|
| 1* | | | | | | | | | mov r11d, r12d
|
||||||
|
| 1 | | 1.0 | | | | | | | add r8d, 0xff
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovw k0, r8d
|
||||||
|
| 1 | | 1.0 | | | | | | | lea r9d, ptr [r12+r12*2]
|
||||||
|
| 2 | 1.0 | | 1.0 1.0 | | | | | | vsubps zmm3, zmm13, zmmword ptr [r14+rbx*1+0x40]
|
||||||
|
| 2 | 0.5 | | | 1.0 1.0 | | 0.5 | | | vsubps zmm4, zmm10, zmmword ptr [r14+rbx*1]
|
||||||
|
| 2 | 0.5 | | 1.0 1.0 | | | 0.5 | | | vsubps zmm10, zmm11, zmmword ptr [r14+rbx*1+0x40]
|
||||||
|
| 2 | 0.5 | | | 1.0 1.0 | | 0.5 | | | vsubps zmm5, zmm17, zmmword ptr [r14+rbx*1+0x20]
|
||||||
|
| 2 | 0.5 | | 1.0 1.0 | | | 0.5 | | | vsubps zmm27, zmm19, zmmword ptr [r14+rbx*1]
|
||||||
|
| 2 | 0.5 | | | 1.0 1.0 | | 0.5 | | | vsubps zmm8, zmm15, zmmword ptr [r14+rbx*1+0x20]
|
||||||
|
| 2 | 0.5 | | 1.0 1.0 | | | 0.5 | | | vsubps zmm11, zmm0, zmmword ptr [r14+rbx*1+0x40]
|
||||||
|
| 2 | 0.5 | | | 1.0 1.0 | | 0.5 | | | vsubps zmm7, zmm9, zmmword ptr [r14+rbx*1]
|
||||||
|
| 2 | 0.5 | | 1.0 1.0 | | | 0.5 | | | vsubps zmm9, zmm14, zmmword ptr [r14+rbx*1+0x20]
|
||||||
|
| 2 | 0.5 | | | 1.0 1.0 | | 0.5 | | | vsubps zmm29, zmm12, zmmword ptr [r14+rbx*1+0x40]
|
||||||
|
| 2 | 0.5 | | 1.0 1.0 | | | 0.5 | | | vsubps zmm28, zmm16, zmmword ptr [r14+rbx*1+0x20]
|
||||||
|
| 2 | 0.5 | | | 1.0 1.0 | | 0.5 | | | vsubps zmm25, zmm18, zmmword ptr [r14+rbx*1]
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm2, zmm3, zmm3
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm30, zmm10, zmm10
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm1, zmm11, zmm11
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm26, zmm29, zmm29
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm2, zmm5, zmm5
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm30, zmm8, zmm8
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm1, zmm9, zmm9
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm26, zmm28, zmm28
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm2, zmm27, zmm27
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm30, zmm4, zmm4
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm1, zmm7, zmm7
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm26, zmm25, zmm25
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14ps zmm31, zmm2
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmpps k7, zmm30, zmm24, 0x11
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14ps zmm6, zmm30
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmpps k3, zmm2, zmm24, 0x11
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14ps zmm2, zmm1
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmpps k5, zmm26, zmm24, 0x11
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14ps zmm26, zmm26
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm30, zmm31, zmm23
|
||||||
|
| 1 | 1.0 | | | | | | | | kandw k2, k0, k3
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmpps k3, zmm1, zmm24, 0x11
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm1, zmm31, zmm30
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm30, zmm31, zmm1
|
||||||
|
| 1 | | | | | | | 1.0 | | neg r9d
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmsub213ps zmm1, zmm31, zmm20
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm31, zmm31, zmm22
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm31, zmm1, zmm31
|
||||||
|
| 1 | | | | | | | 1.0 | | add r9d, 0xff
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovw k4, r9d
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm30, zmm30, zmm31
|
||||||
|
| 1 | 1.0 | | | | | | | | kandw k1, k4, k5
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm1, zmm21, zmm30
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm30, zmm26, zmm23
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm31, zmm26, zmm30
|
||||||
|
| 1 | | 1.0 | | | | | | | lea r10d, ptr [r12*8]
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm30, zmm26, zmm31
|
||||||
|
| 1 | | | | | | | 1.0 | | neg r10d
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmsub213ps zmm31, zmm26, zmm20
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm26, zmm26, zmm22
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm31, zmm31, zmm26
|
||||||
|
| 1 | | 1.0 | | | | | | | add r10d, r12d
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm30, zmm30, zmm31
|
||||||
|
| 1 | | | | | | | 1.0 | | add r10d, 0xff
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovw k6, r10d
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm26, zmm21, zmm30
|
||||||
|
| 1 | 1.0 | | | | | | | | kandw k4, k6, k7
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm25{k1}{z}, zmm25, zmm26
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm31{k1}{z}, zmm28, zmm26
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm28, zmm6, zmm23
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm30{k1}{z}, zmm29, zmm26
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm29, zmm2, zmm23
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm25{k2}, zmm27, zmm1
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm31{k2}, zmm5, zmm1
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm27, zmm6, zmm28
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm30{k2}, zmm3, zmm1
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm1, zmm2, zmm29
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm5, zmm6, zmm27
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmsub213ps zmm27, zmm6, zmm20
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm6, zmm6, zmm22
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm3, zmm2, zmm1
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmsub213ps zmm1, zmm2, zmm20
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm2, zmm2, zmm22
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm26, zmm27, zmm6
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm1, zmm1, zmm2
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm5, zmm5, zmm26
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm3, zmm3, zmm1
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm6, zmm21, zmm5
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulps zmm27, zmm21, zmm3
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm25{k4}, zmm4, zmm6
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm4, zmmword ptr [r14+rsi*1]
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm31{k4}, zmm8, zmm6
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm30{k4}, zmm10, zmm6
|
||||||
|
| 1 | | | | | | | 1.0 | | shl r11d, 0x4
|
||||||
|
| 1 | | 1.0 | | | | | | | sub r12d, r11d
|
||||||
|
| 1 | | 1.0 | | | | | | | add r12d, 0xff
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovw k0, r12d
|
||||||
|
| 1 | 1.0 | | | | | | | | kandw k5, k0, k3
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm25{k5}, zmm7, zmm27
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm31{k5}, zmm9, zmm27
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231ps zmm30{k5}, zmm11, zmm27
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vsubps zmm7, zmm4, zmm25
|
||||||
|
| 2 | | | | 1.0 | 1.0 | | | | vmovups zmmword ptr [r14+rsi*1], zmm7
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm8, zmmword ptr [r14+rsi*1+0x20]
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vsubps zmm4, zmm8, zmm31
|
||||||
|
| 2 | | | | 1.0 | 1.0 | | | | vmovups zmmword ptr [r14+rsi*1+0x20], zmm4
|
||||||
|
| 1 | | | 1.0 1.0 | | | | | | vmovups zmm1, zmmword ptr [r14+rsi*1+0x40]
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vsubps zmm2, zmm1, zmm30
|
||||||
|
| 2 | | | | 1.0 | 1.0 | | | | vmovups zmmword ptr [r14+rsi*1+0x40], zmm2
|
||||||
|
| 1* | | | | | | | | | cmp rax, rdx
|
||||||
|
| 0*F | | | | | | | | | jb 0xfffffffffffffd30
|
||||||
|
Total Num Of Uops: 142
|
||||||
|
Analysis Notes:
|
||||||
|
Backend allocation was stalled due to unavailable allocation resources.
|
||||||
154
static_analysis/jan/analyses/gromacs-icx-avx512-dp-iaca.out
Normal file
154
static_analysis/jan/analyses/gromacs-icx-avx512-dp-iaca.out
Normal file
@ -0,0 +1,154 @@
|
|||||||
|
Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45
|
||||||
|
Analyzed File - gromacs-icx-avx512-dp.o
|
||||||
|
Binary Format - 64Bit
|
||||||
|
Architecture - SKX
|
||||||
|
Analysis Type - Throughput
|
||||||
|
|
||||||
|
Throughput Analysis Report
|
||||||
|
--------------------------
|
||||||
|
Block Throughput: 49.26 Cycles Throughput Bottleneck: Backend
|
||||||
|
Loop Count: 22
|
||||||
|
Port Binding In Cycles Per Iteration:
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Cycles | 44.0 0.0 | 13.5 | 5.5 5.5 | 5.5 5.5 | 0.0 | 44.0 | 13.5 | 0.0 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
DV - Divider pipe (on port 0)
|
||||||
|
D - Data fetch pipe (on ports 2 and 3)
|
||||||
|
F - Macro Fusion with the previous instruction occurred
|
||||||
|
* - instruction micro-ops not bound to a port
|
||||||
|
^ - Micro Fusion occurred
|
||||||
|
# - ESP Tracking sync uop was issued
|
||||||
|
@ - SSE instruction followed an AVX256/AVX512 instruction, dozens of cycles penalty is expected
|
||||||
|
X - instruction not supported, was not accounted in Analysis
|
||||||
|
|
||||||
|
| Num Of | Ports pressure in cycles | |
|
||||||
|
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
-----------------------------------------------------------------------------------------
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | movsxd rcx, dword ptr [r10+rbx*4]
|
||||||
|
| 1 | | 1.0 | | | | | | | lea rdx, ptr [rcx+rcx*2]
|
||||||
|
| 1 | | | | | | | 1.0 | | shl rdx, 0x6
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm28, zmmword ptr [rsi+rdx*1]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm29, zmmword ptr [rsi+rdx*1+0x40]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm30, zmmword ptr [rsi+rdx*1+0x80]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm3, zmmword ptr [rsp+0x10]
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubpd zmm3, zmm3, zmm28
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubpd zmm31, zmm24, zmm30
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm16, zmmword ptr [rsp+0x150]
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubpd zmm16, zmm16, zmm29
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm17, zmm31, zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm17, zmm16, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm17, zmm3, zmm3
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm18, zmm17
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm19, zmm21, zmm18
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm19, zmm18, zmm19
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm19, zmm18, zmm19
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddpd zmm20, zmm19, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm18, zmm22, zmm18
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm18, zmm18, zmm20
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubpd zmm20, zmm25, zmm30
|
||||||
|
| 1 | | 1.0 | | | | | | | lea edx, ptr [rcx+rcx*1]
|
||||||
|
| 1 | | | | | | | 1.0 | | cmp r11, rdx
|
||||||
|
| 1 | | | | | | | 1.0 | | setnz dl
|
||||||
|
| 1 | | | | | | | 1.0 | | setz al
|
||||||
|
| 1 | | 1.0 | | | | | | | add ecx, ecx
|
||||||
|
| 1 | | 1.0 | | | | | | | inc ecx
|
||||||
|
| 1 | | 0.5 | | | | | 0.5 | | cmp r11, rcx
|
||||||
|
| 1 | | | | | | | 1.0 | | setz cl
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm18, zmm19, zmm18
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm19, zmmword ptr [rsp+0x210]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubpd zmm19, zmm19, zmm28
|
||||||
|
| 1 | | | | | | | 1.0 | | setnz dil
|
||||||
|
| 1* | | | | | | | | | mov ebp, edi
|
||||||
|
| 1 | | | | | | | 1.0 | | shl bpl, 0x4
|
||||||
|
| 1 | | 1.0 | | | | | | | sub bpl, al
|
||||||
|
| 1 | | 1.0 | | | | | | | add bpl, 0xef
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovd k1, ebp
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k1{k1}, zmm17, zmm0, 0x1
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm17, zmmword ptr [rsp+0x110]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubpd zmm17, zmm17, zmm29
|
||||||
|
| 1 | | 1.0 | | | | | | | lea eax, ptr [rdx+rdx*1]
|
||||||
|
| 1* | | | | | | | | | mov ebp, edi
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm18, zmm18, zmm2
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm14{k1}, zmm3, zmm18
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm3, zmm20, zmm20
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm3, zmm17, zmm17
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm3, zmm19, zmm19
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm11{k1}, zmm16, zmm18
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm16, zmm3
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm7{k1}, zmm31, zmm18
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm18, zmm21, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm18, zmm16, zmm18
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm18, zmm16, zmm18
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddpd zmm31, zmm18, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm22, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm16, zmm16, zmm31
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm31, zmmword ptr [rsp+0x1d0]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubpd zmm31, zmm31, zmm28
|
||||||
|
| 1 | | | | | | | 1.0 | | shl bpl, 0x5
|
||||||
|
| 1 | | 1.0 | | | | | | | or bpl, al
|
||||||
|
| 1 | | 0.5 | | | | | 0.5 | | or bpl, 0xdd
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovd k1, ebp
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k1{k1}, zmm3, zmm0, 0x1
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm3, zmmword ptr [rsp+0xd0]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubpd zmm3, zmm3, zmm29
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm18, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubpd zmm18, zmm26, zmm30
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm16, zmm2
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm15{k1}, zmm19, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm19, zmm18, zmm18
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm19, zmm3, zmm3
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm19, zmm31, zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm10{k1}, zmm17, zmm16
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm17, zmm19
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm6{k1}, zmm20, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm21, zmm17
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm16, zmm17, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm17, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddpd zmm20, zmm16, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm17, zmm22, zmm17
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm17, zmm17, zmm20
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm16, zmm17
|
||||||
|
| 1 | | 1.0 | | | | | | | lea eax, ptr [rdx*4]
|
||||||
|
| 1 | | | | | | | 1.0 | | shl dil, 0x6
|
||||||
|
| 1 | | 0.5 | | | | | 0.5 | | or dil, al
|
||||||
|
| 1 | | 0.5 | | | | | 0.5 | | or dil, 0xbb
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovd k1, edi
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k1{k1}, zmm19, zmm0, 0x1
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovupd zmm17, zmmword ptr [rsp+0x190]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubpd zmm17, zmm17, zmm28
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubpd zmm19, zmm23, zmm29
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubpd zmm20, zmm27, zmm30
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm16, zmm2
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm13{k1}, zmm31, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm28, zmm20, zmm20
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm28, zmm19, zmm19
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm28, zmm17, zmm17
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm9{k1}, zmm3, zmm16
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm3, zmm28
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm5{k1}, zmm18, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm21, zmm3
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm16, zmm3, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm16, zmm3, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddpd zmm18, zmm16, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm3, zmm22, zmm3
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm3, zmm3, zmm18
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm3, zmm16, zmm3
|
||||||
|
| 1 | | | | | | | 1.0 | | shl dl, 0x3
|
||||||
|
| 1 | | | | | | | 1.0 | | shl cl, 0x7
|
||||||
|
| 1 | | 1.0 | | | | | | | or cl, dl
|
||||||
|
| 1 | | 1.0 | | | | | | | add cl, 0xf7
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovd k1, ecx
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k1{k1}, zmm28, zmm0, 0x1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulpd zmm3, zmm3, zmm2
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm12{k1}, zmm17, zmm3
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231pd zmm8{k1}, zmm19, zmm3
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231pd zmm4{k1}, zmm20, zmm3
|
||||||
|
| 1 | | 0.5 | | | | | 0.5 | | inc rbx
|
||||||
|
| 1* | | | | | | | | | cmp r9, rbx
|
||||||
|
| 0*F | | | | | | | | | jnz 0xfffffffffffffd5a
|
||||||
|
Total Num Of Uops: 129
|
||||||
|
Analysis Notes:
|
||||||
|
Backend allocation was stalled due to unavailable allocation resources.
|
||||||
288
static_analysis/jan/analyses/gromacs-icx-avx512-dp-mca.out
Normal file
288
static_analysis/jan/analyses/gromacs-icx-avx512-dp-mca.out
Normal file
@ -0,0 +1,288 @@
|
|||||||
|
|
||||||
|
[0] Code Region
|
||||||
|
|
||||||
|
Iterations: 100
|
||||||
|
Instructions: 12200
|
||||||
|
Total Cycles: 4745
|
||||||
|
Total uOps: 14000
|
||||||
|
|
||||||
|
Dispatch Width: 6
|
||||||
|
uOps Per Cycle: 2.95
|
||||||
|
IPC: 2.57
|
||||||
|
Block RThroughput: 34.0
|
||||||
|
|
||||||
|
|
||||||
|
Instruction Info:
|
||||||
|
[1]: #uOps
|
||||||
|
[2]: Latency
|
||||||
|
[3]: RThroughput
|
||||||
|
[4]: MayLoad
|
||||||
|
[5]: MayStore
|
||||||
|
[6]: HasSideEffects (U)
|
||||||
|
|
||||||
|
[1] [2] [3] [4] [5] [6] Instructions:
|
||||||
|
1 5 0.50 * movslq (%r10,%rbx,4), %rcx
|
||||||
|
1 1 0.50 leaq (%rcx,%rcx,2), %rdx
|
||||||
|
1 1 0.50 shlq $6, %rdx
|
||||||
|
2 8 0.50 * vmovupd (%rsi,%rdx), %zmm28
|
||||||
|
2 8 0.50 * vmovupd 64(%rsi,%rdx), %zmm29
|
||||||
|
2 8 0.50 * vmovupd 128(%rsi,%rdx), %zmm30
|
||||||
|
2 8 0.50 * vmovupd 16(%rsp), %zmm3
|
||||||
|
1 4 0.50 vsubpd %zmm28, %zmm3, %zmm3
|
||||||
|
1 4 0.50 vsubpd %zmm30, %zmm24, %zmm31
|
||||||
|
2 8 0.50 * vmovupd 336(%rsp), %zmm16
|
||||||
|
1 4 0.50 vsubpd %zmm29, %zmm16, %zmm16
|
||||||
|
1 4 0.50 vmulpd %zmm31, %zmm31, %zmm17
|
||||||
|
1 4 0.50 vfmadd231pd %zmm16, %zmm16, %zmm17
|
||||||
|
1 4 0.50 vfmadd231pd %zmm3, %zmm3, %zmm17
|
||||||
|
3 4 2.00 vrcp14pd %zmm17, %zmm18
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm21, %zmm19
|
||||||
|
1 4 0.50 vmulpd %zmm19, %zmm18, %zmm19
|
||||||
|
1 4 0.50 vmulpd %zmm19, %zmm18, %zmm19
|
||||||
|
1 4 0.50 vaddpd %zmm1, %zmm19, %zmm20
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm22, %zmm18
|
||||||
|
1 4 0.50 vmulpd %zmm20, %zmm18, %zmm18
|
||||||
|
1 4 0.50 vsubpd %zmm30, %zmm25, %zmm20
|
||||||
|
1 1 0.50 leal (%rcx,%rcx), %edx
|
||||||
|
1 1 0.25 cmpq %rdx, %r11
|
||||||
|
1 1 0.50 setne %dl
|
||||||
|
1 1 0.50 sete %al
|
||||||
|
1 1 0.25 addl %ecx, %ecx
|
||||||
|
1 1 0.25 incl %ecx
|
||||||
|
1 1 0.25 cmpq %rcx, %r11
|
||||||
|
1 1 0.50 sete %cl
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm19, %zmm18
|
||||||
|
2 8 0.50 * vmovupd 528(%rsp), %zmm19
|
||||||
|
1 4 0.50 vsubpd %zmm28, %zmm19, %zmm19
|
||||||
|
1 1 0.50 setne %dil
|
||||||
|
1 1 0.25 movl %edi, %ebp
|
||||||
|
1 1 0.50 shlb $4, %bpl
|
||||||
|
1 1 0.25 subb %al, %bpl
|
||||||
|
1 1 0.25 addb $-17, %bpl
|
||||||
|
1 1 1.00 kmovd %ebp, %k1
|
||||||
|
1 4 1.00 vcmpltpd %zmm0, %zmm17, %k1 {%k1}
|
||||||
|
2 8 0.50 * vmovupd 272(%rsp), %zmm17
|
||||||
|
1 4 0.50 vsubpd %zmm29, %zmm17, %zmm17
|
||||||
|
1 1 0.50 leal (%rdx,%rdx), %eax
|
||||||
|
1 1 0.25 movl %edi, %ebp
|
||||||
|
1 4 0.50 vmulpd %zmm2, %zmm18, %zmm18
|
||||||
|
1 4 0.50 vfmadd231pd %zmm18, %zmm3, %zmm14 {%k1}
|
||||||
|
1 4 0.50 vmulpd %zmm20, %zmm20, %zmm3
|
||||||
|
1 4 0.50 vfmadd231pd %zmm17, %zmm17, %zmm3
|
||||||
|
1 4 0.50 vfmadd231pd %zmm19, %zmm19, %zmm3
|
||||||
|
1 4 0.50 vfmadd231pd %zmm18, %zmm16, %zmm11 {%k1}
|
||||||
|
3 4 2.00 vrcp14pd %zmm3, %zmm16
|
||||||
|
1 4 0.50 vfmadd231pd %zmm18, %zmm31, %zmm7 {%k1}
|
||||||
|
1 4 0.50 vmulpd %zmm16, %zmm21, %zmm18
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm16, %zmm18
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm16, %zmm18
|
||||||
|
1 4 0.50 vaddpd %zmm1, %zmm18, %zmm31
|
||||||
|
1 4 0.50 vmulpd %zmm16, %zmm22, %zmm16
|
||||||
|
1 4 0.50 vmulpd %zmm31, %zmm16, %zmm16
|
||||||
|
2 8 0.50 * vmovupd 464(%rsp), %zmm31
|
||||||
|
1 4 0.50 vsubpd %zmm28, %zmm31, %zmm31
|
||||||
|
1 1 0.50 shlb $5, %bpl
|
||||||
|
1 1 0.25 orb %al, %bpl
|
||||||
|
1 1 0.25 orb $-35, %bpl
|
||||||
|
1 1 1.00 kmovd %ebp, %k1
|
||||||
|
1 4 1.00 vcmpltpd %zmm0, %zmm3, %k1 {%k1}
|
||||||
|
2 8 0.50 * vmovupd 208(%rsp), %zmm3
|
||||||
|
1 4 0.50 vsubpd %zmm29, %zmm3, %zmm3
|
||||||
|
1 4 0.50 vmulpd %zmm16, %zmm18, %zmm16
|
||||||
|
1 4 0.50 vsubpd %zmm30, %zmm26, %zmm18
|
||||||
|
1 4 0.50 vmulpd %zmm2, %zmm16, %zmm16
|
||||||
|
1 4 0.50 vfmadd231pd %zmm16, %zmm19, %zmm15 {%k1}
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm18, %zmm19
|
||||||
|
1 4 0.50 vfmadd231pd %zmm3, %zmm3, %zmm19
|
||||||
|
1 4 0.50 vfmadd231pd %zmm31, %zmm31, %zmm19
|
||||||
|
1 4 0.50 vfmadd231pd %zmm16, %zmm17, %zmm10 {%k1}
|
||||||
|
3 4 2.00 vrcp14pd %zmm19, %zmm17
|
||||||
|
1 4 0.50 vfmadd231pd %zmm16, %zmm20, %zmm6 {%k1}
|
||||||
|
1 4 0.50 vmulpd %zmm17, %zmm21, %zmm16
|
||||||
|
1 4 0.50 vmulpd %zmm16, %zmm17, %zmm16
|
||||||
|
1 4 0.50 vmulpd %zmm16, %zmm17, %zmm16
|
||||||
|
1 4 0.50 vaddpd %zmm1, %zmm16, %zmm20
|
||||||
|
1 4 0.50 vmulpd %zmm17, %zmm22, %zmm17
|
||||||
|
1 4 0.50 vmulpd %zmm20, %zmm17, %zmm17
|
||||||
|
1 4 0.50 vmulpd %zmm17, %zmm16, %zmm16
|
||||||
|
1 1 0.50 leal (,%rdx,4), %eax
|
||||||
|
1 1 0.50 shlb $6, %dil
|
||||||
|
1 1 0.25 orb %al, %dil
|
||||||
|
1 1 0.25 orb $-69, %dil
|
||||||
|
1 1 1.00 kmovd %edi, %k1
|
||||||
|
1 4 1.00 vcmpltpd %zmm0, %zmm19, %k1 {%k1}
|
||||||
|
2 8 0.50 * vmovupd 400(%rsp), %zmm17
|
||||||
|
1 4 0.50 vsubpd %zmm28, %zmm17, %zmm17
|
||||||
|
1 4 0.50 vsubpd %zmm29, %zmm23, %zmm19
|
||||||
|
1 4 0.50 vsubpd %zmm30, %zmm27, %zmm20
|
||||||
|
1 4 0.50 vmulpd %zmm2, %zmm16, %zmm16
|
||||||
|
1 4 0.50 vfmadd231pd %zmm16, %zmm31, %zmm13 {%k1}
|
||||||
|
1 4 0.50 vmulpd %zmm20, %zmm20, %zmm28
|
||||||
|
1 4 0.50 vfmadd231pd %zmm19, %zmm19, %zmm28
|
||||||
|
1 4 0.50 vfmadd231pd %zmm17, %zmm17, %zmm28
|
||||||
|
1 4 0.50 vfmadd231pd %zmm16, %zmm3, %zmm9 {%k1}
|
||||||
|
3 4 2.00 vrcp14pd %zmm28, %zmm3
|
||||||
|
1 4 0.50 vfmadd231pd %zmm16, %zmm18, %zmm5 {%k1}
|
||||||
|
1 4 0.50 vmulpd %zmm3, %zmm21, %zmm16
|
||||||
|
1 4 0.50 vmulpd %zmm16, %zmm3, %zmm16
|
||||||
|
1 4 0.50 vmulpd %zmm16, %zmm3, %zmm16
|
||||||
|
1 4 0.50 vaddpd %zmm1, %zmm16, %zmm18
|
||||||
|
1 4 0.50 vmulpd %zmm3, %zmm22, %zmm3
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm3, %zmm3
|
||||||
|
1 4 0.50 vmulpd %zmm3, %zmm16, %zmm3
|
||||||
|
1 1 0.50 shlb $3, %dl
|
||||||
|
1 1 0.50 shlb $7, %cl
|
||||||
|
1 1 0.25 orb %dl, %cl
|
||||||
|
1 1 0.25 addb $-9, %cl
|
||||||
|
1 1 1.00 kmovd %ecx, %k1
|
||||||
|
1 4 1.00 vcmpltpd %zmm0, %zmm28, %k1 {%k1}
|
||||||
|
1 4 0.50 vmulpd %zmm2, %zmm3, %zmm3
|
||||||
|
1 4 0.50 vfmadd231pd %zmm3, %zmm17, %zmm12 {%k1}
|
||||||
|
1 4 0.50 vfmadd231pd %zmm3, %zmm19, %zmm8 {%k1}
|
||||||
|
1 4 0.50 vfmadd231pd %zmm3, %zmm20, %zmm4 {%k1}
|
||||||
|
1 1 0.25 incq %rbx
|
||||||
|
1 1 0.25 cmpq %rbx, %r9
|
||||||
|
1 1 0.50 jne .LBB5_12
|
||||||
|
|
||||||
|
|
||||||
|
Resources:
|
||||||
|
[0] - SKXDivider
|
||||||
|
[1] - SKXFPDivider
|
||||||
|
[2] - SKXPort0
|
||||||
|
[3] - SKXPort1
|
||||||
|
[4] - SKXPort2
|
||||||
|
[5] - SKXPort3
|
||||||
|
[6] - SKXPort4
|
||||||
|
[7] - SKXPort5
|
||||||
|
[8] - SKXPort6
|
||||||
|
[9] - SKXPort7
|
||||||
|
|
||||||
|
|
||||||
|
Resource pressure per iteration:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9]
|
||||||
|
- - 45.53 20.45 5.50 5.50 - 44.64 18.38 -
|
||||||
|
|
||||||
|
Resource pressure by instruction:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
|
||||||
|
- - - - 0.50 0.50 - - - - movslq (%r10,%rbx,4), %rcx
|
||||||
|
- - - 0.99 - - - 0.01 - - leaq (%rcx,%rcx,2), %rdx
|
||||||
|
- - 0.01 - - - - - 0.99 - shlq $6, %rdx
|
||||||
|
- - 0.01 0.99 0.49 0.51 - - - - vmovupd (%rsi,%rdx), %zmm28
|
||||||
|
- - 0.01 0.91 0.51 0.49 - 0.08 - - vmovupd 64(%rsi,%rdx), %zmm29
|
||||||
|
- - 0.01 0.56 0.49 0.51 - 0.43 - - vmovupd 128(%rsi,%rdx), %zmm30
|
||||||
|
- - - 0.99 0.50 0.50 - 0.01 - - vmovupd 16(%rsp), %zmm3
|
||||||
|
- - 0.95 - - - - 0.05 - - vsubpd %zmm28, %zmm3, %zmm3
|
||||||
|
- - 0.48 - - - - 0.52 - - vsubpd %zmm30, %zmm24, %zmm31
|
||||||
|
- - - 1.00 0.50 0.50 - - - - vmovupd 336(%rsp), %zmm16
|
||||||
|
- - 0.49 - - - - 0.51 - - vsubpd %zmm29, %zmm16, %zmm16
|
||||||
|
- - 0.48 - - - - 0.52 - - vmulpd %zmm31, %zmm31, %zmm17
|
||||||
|
- - 0.49 - - - - 0.51 - - vfmadd231pd %zmm16, %zmm16, %zmm17
|
||||||
|
- - 0.04 - - - - 0.96 - - vfmadd231pd %zmm3, %zmm3, %zmm17
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14pd %zmm17, %zmm18
|
||||||
|
- - 1.00 - - - - - - - vmulpd %zmm18, %zmm21, %zmm19
|
||||||
|
- - 0.51 - - - - 0.49 - - vmulpd %zmm19, %zmm18, %zmm19
|
||||||
|
- - 0.49 - - - - 0.51 - - vmulpd %zmm19, %zmm18, %zmm19
|
||||||
|
- - 0.07 - - - - 0.93 - - vaddpd %zmm1, %zmm19, %zmm20
|
||||||
|
- - - - - - - 1.00 - - vmulpd %zmm18, %zmm22, %zmm18
|
||||||
|
- - 0.95 - - - - 0.05 - - vmulpd %zmm20, %zmm18, %zmm18
|
||||||
|
- - 0.92 - - - - 0.08 - - vsubpd %zmm30, %zmm25, %zmm20
|
||||||
|
- - - 0.94 - - - 0.06 - - leal (%rcx,%rcx), %edx
|
||||||
|
- - - - - - - - 1.00 - cmpq %rdx, %r11
|
||||||
|
- - - - - - - - 1.00 - setne %dl
|
||||||
|
- - 0.44 - - - - - 0.56 - sete %al
|
||||||
|
- - - 0.07 - - - 0.02 0.91 - addl %ecx, %ecx
|
||||||
|
- - - 0.53 - - - 0.46 0.01 - incl %ecx
|
||||||
|
- - - 0.51 - - - 0.46 0.03 - cmpq %rcx, %r11
|
||||||
|
- - 0.02 - - - - - 0.98 - sete %cl
|
||||||
|
- - 0.94 - - - - 0.06 - - vmulpd %zmm18, %zmm19, %zmm18
|
||||||
|
- - 0.01 0.99 0.51 0.49 - - - - vmovupd 528(%rsp), %zmm19
|
||||||
|
- - 0.47 - - - - 0.53 - - vsubpd %zmm28, %zmm19, %zmm19
|
||||||
|
- - 0.04 - - - - - 0.96 - setne %dil
|
||||||
|
- - - 0.95 - - - 0.02 0.03 - movl %edi, %ebp
|
||||||
|
- - 0.01 - - - - - 0.99 - shlb $4, %bpl
|
||||||
|
- - - 0.96 - - - - 0.04 - subb %al, %bpl
|
||||||
|
- - - 0.06 - - - - 0.94 - addb $-17, %bpl
|
||||||
|
- - - - - - - 1.00 - - kmovd %ebp, %k1
|
||||||
|
- - - - - - - 1.00 - - vcmpltpd %zmm0, %zmm17, %k1 {%k1}
|
||||||
|
- - 0.02 0.97 0.50 0.50 - 0.01 - - vmovupd 272(%rsp), %zmm17
|
||||||
|
- - 0.96 - - - - 0.04 - - vsubpd %zmm29, %zmm17, %zmm17
|
||||||
|
- - - 1.00 - - - - - - leal (%rdx,%rdx), %eax
|
||||||
|
- - - 0.05 - - - - 0.95 - movl %edi, %ebp
|
||||||
|
- - 0.51 - - - - 0.49 - - vmulpd %zmm2, %zmm18, %zmm18
|
||||||
|
- - 0.53 - - - - 0.47 - - vfmadd231pd %zmm18, %zmm3, %zmm14 {%k1}
|
||||||
|
- - 0.45 - - - - 0.55 - - vmulpd %zmm20, %zmm20, %zmm3
|
||||||
|
- - 0.94 - - - - 0.06 - - vfmadd231pd %zmm17, %zmm17, %zmm3
|
||||||
|
- - 0.03 - - - - 0.97 - - vfmadd231pd %zmm19, %zmm19, %zmm3
|
||||||
|
- - 0.47 - - - - 0.53 - - vfmadd231pd %zmm18, %zmm16, %zmm11 {%k1}
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14pd %zmm3, %zmm16
|
||||||
|
- - 0.53 - - - - 0.47 - - vfmadd231pd %zmm18, %zmm31, %zmm7 {%k1}
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulpd %zmm16, %zmm21, %zmm18
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulpd %zmm18, %zmm16, %zmm18
|
||||||
|
- - 0.97 - - - - 0.03 - - vmulpd %zmm18, %zmm16, %zmm18
|
||||||
|
- - 0.52 - - - - 0.48 - - vaddpd %zmm1, %zmm18, %zmm31
|
||||||
|
- - 0.01 - - - - 0.99 - - vmulpd %zmm16, %zmm22, %zmm16
|
||||||
|
- - 0.52 - - - - 0.48 - - vmulpd %zmm31, %zmm16, %zmm16
|
||||||
|
- - - 0.99 0.50 0.50 - 0.01 - - vmovupd 464(%rsp), %zmm31
|
||||||
|
- - 0.03 - - - - 0.97 - - vsubpd %zmm28, %zmm31, %zmm31
|
||||||
|
- - 0.01 - - - - - 0.99 - shlb $5, %bpl
|
||||||
|
- - - 0.94 - - - - 0.06 - orb %al, %bpl
|
||||||
|
- - - 0.04 - - - - 0.96 - orb $-35, %bpl
|
||||||
|
- - - - - - - 1.00 - - kmovd %ebp, %k1
|
||||||
|
- - - - - - - 1.00 - - vcmpltpd %zmm0, %zmm3, %k1 {%k1}
|
||||||
|
- - - 0.99 0.50 0.50 - 0.01 - - vmovupd 208(%rsp), %zmm3
|
||||||
|
- - 0.95 - - - - 0.05 - - vsubpd %zmm29, %zmm3, %zmm3
|
||||||
|
- - 0.51 - - - - 0.49 - - vmulpd %zmm16, %zmm18, %zmm16
|
||||||
|
- - 0.01 - - - - 0.99 - - vsubpd %zmm30, %zmm26, %zmm18
|
||||||
|
- - 0.52 - - - - 0.48 - - vmulpd %zmm2, %zmm16, %zmm16
|
||||||
|
- - 1.00 - - - - - - - vfmadd231pd %zmm16, %zmm19, %zmm15 {%k1}
|
||||||
|
- - 0.03 - - - - 0.97 - - vmulpd %zmm18, %zmm18, %zmm19
|
||||||
|
- - 0.06 - - - - 0.94 - - vfmadd231pd %zmm3, %zmm3, %zmm19
|
||||||
|
- - 0.50 - - - - 0.50 - - vfmadd231pd %zmm31, %zmm31, %zmm19
|
||||||
|
- - - - - - - 1.00 - - vfmadd231pd %zmm16, %zmm17, %zmm10 {%k1}
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14pd %zmm19, %zmm17
|
||||||
|
- - 1.00 - - - - - - - vfmadd231pd %zmm16, %zmm20, %zmm6 {%k1}
|
||||||
|
- - 0.07 - - - - 0.93 - - vmulpd %zmm17, %zmm21, %zmm16
|
||||||
|
- - 0.50 - - - - 0.50 - - vmulpd %zmm16, %zmm17, %zmm16
|
||||||
|
- - 0.09 - - - - 0.91 - - vmulpd %zmm16, %zmm17, %zmm16
|
||||||
|
- - 0.07 - - - - 0.93 - - vaddpd %zmm1, %zmm16, %zmm20
|
||||||
|
- - 0.93 - - - - 0.07 - - vmulpd %zmm17, %zmm22, %zmm17
|
||||||
|
- - 0.94 - - - - 0.06 - - vmulpd %zmm20, %zmm17, %zmm17
|
||||||
|
- - 0.51 - - - - 0.49 - - vmulpd %zmm17, %zmm16, %zmm16
|
||||||
|
- - - 1.00 - - - - - - leal (,%rdx,4), %eax
|
||||||
|
- - - - - - - - 1.00 - shlb $6, %dil
|
||||||
|
- - - 0.02 - - - - 0.98 - orb %al, %dil
|
||||||
|
- - - 0.48 - - - - 0.52 - orb $-69, %dil
|
||||||
|
- - - - - - - 1.00 - - kmovd %edi, %k1
|
||||||
|
- - - - - - - 1.00 - - vcmpltpd %zmm0, %zmm19, %k1 {%k1}
|
||||||
|
- - - 1.00 0.50 0.50 - - - - vmovupd 400(%rsp), %zmm17
|
||||||
|
- - 0.49 - - - - 0.51 - - vsubpd %zmm28, %zmm17, %zmm17
|
||||||
|
- - 0.49 - - - - 0.51 - - vsubpd %zmm29, %zmm23, %zmm19
|
||||||
|
- - 0.02 - - - - 0.98 - - vsubpd %zmm30, %zmm27, %zmm20
|
||||||
|
- - 0.98 - - - - 0.02 - - vmulpd %zmm2, %zmm16, %zmm16
|
||||||
|
- - 0.50 - - - - 0.50 - - vfmadd231pd %zmm16, %zmm31, %zmm13 {%k1}
|
||||||
|
- - 0.94 - - - - 0.06 - - vmulpd %zmm20, %zmm20, %zmm28
|
||||||
|
- - 0.04 - - - - 0.96 - - vfmadd231pd %zmm19, %zmm19, %zmm28
|
||||||
|
- - 0.07 - - - - 0.93 - - vfmadd231pd %zmm17, %zmm17, %zmm28
|
||||||
|
- - 0.50 - - - - 0.50 - - vfmadd231pd %zmm16, %zmm3, %zmm9 {%k1}
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14pd %zmm28, %zmm3
|
||||||
|
- - 0.50 - - - - 0.50 - - vfmadd231pd %zmm16, %zmm18, %zmm5 {%k1}
|
||||||
|
- - 1.00 - - - - - - - vmulpd %zmm3, %zmm21, %zmm16
|
||||||
|
- - 0.55 - - - - 0.45 - - vmulpd %zmm16, %zmm3, %zmm16
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulpd %zmm16, %zmm3, %zmm16
|
||||||
|
- - 0.99 - - - - 0.01 - - vaddpd %zmm1, %zmm16, %zmm18
|
||||||
|
- - - - - - - 1.00 - - vmulpd %zmm3, %zmm22, %zmm3
|
||||||
|
- - 0.52 - - - - 0.48 - - vmulpd %zmm18, %zmm3, %zmm3
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulpd %zmm3, %zmm16, %zmm3
|
||||||
|
- - - - - - - - 1.00 - shlb $3, %dl
|
||||||
|
- - - - - - - - 1.00 - shlb $7, %cl
|
||||||
|
- - - 1.00 - - - - - - orb %dl, %cl
|
||||||
|
- - - 0.52 - - - - 0.48 - addb $-9, %cl
|
||||||
|
- - - - - - - 1.00 - - kmovd %ecx, %k1
|
||||||
|
- - - - - - - 1.00 - - vcmpltpd %zmm0, %zmm28, %k1 {%k1}
|
||||||
|
- - 0.98 - - - - 0.02 - - vmulpd %zmm2, %zmm3, %zmm3
|
||||||
|
- - 0.97 - - - - 0.03 - - vfmadd231pd %zmm3, %zmm17, %zmm12 {%k1}
|
||||||
|
- - 0.03 - - - - 0.97 - - vfmadd231pd %zmm3, %zmm19, %zmm8 {%k1}
|
||||||
|
- - 0.97 - - - - 0.03 - - vfmadd231pd %zmm3, %zmm20, %zmm4 {%k1}
|
||||||
|
- - - 0.48 - - - - 0.52 - incq %rbx
|
||||||
|
- - - 0.52 - - - - 0.48 - cmpq %rbx, %r9
|
||||||
|
- - - - - - - - 1.00 - jne .LBB5_12
|
||||||
167
static_analysis/jan/analyses/gromacs-icx-avx512-dp-osaca.out
Normal file
167
static_analysis/jan/analyses/gromacs-icx-avx512-dp-osaca.out
Normal file
@ -0,0 +1,167 @@
|
|||||||
|
Open Source Architecture Code Analyzer (OSACA) - 0.4.12
|
||||||
|
Analyzed file: gromacs-icx-avx512-dp.s
|
||||||
|
Architecture: CSX
|
||||||
|
Timestamp: 2023-02-10 16:30:53
|
||||||
|
|
||||||
|
|
||||||
|
P - Throughput of LOAD operation can be hidden behind a past or future STORE instruction
|
||||||
|
* - Instruction micro-ops not bound to a port
|
||||||
|
X - No throughput/latency information for this instruction in data file
|
||||||
|
|
||||||
|
|
||||||
|
Combined Analysis Report
|
||||||
|
------------------------
|
||||||
|
Port pressure in cycles
|
||||||
|
| 0 - 0DV | 1 | 2 - 2D | 3 - 3D | 4 | 5 | 6 | 7 || CP | LCD |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
2241 | | | | | | | | || | | # pointer_increment=64 da67166e5736661e6b03ea29ee7bfd67
|
||||||
|
2242 | | | | | | | | || | | # LLVM-MCA-BEGIN
|
||||||
|
2243 | | | | | | | | || | | .LBB5_12: # Parent Loop BB5_7 Depth=1
|
||||||
|
2244 | | | | | | | | || | | # => This Inner Loop Header: Depth=2
|
||||||
|
2245 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | movslq (%r10,%rbx,4), %rcx
|
||||||
|
2246 | | 1.00 | | | | 0.00 | | || 1.0 | | leaq (%rcx,%rcx,2), %rdx
|
||||||
|
2247 | 0.00 | | | | | | 1.00 | || 1.0 | | shlq $6, %rdx
|
||||||
|
2248 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd (%rsi,%rdx), %zmm28 # AlignMOV convert to UnAlignMOV
|
||||||
|
2249 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd 64(%rsi,%rdx), %zmm29 # AlignMOV convert to UnAlignMOV
|
||||||
|
2250 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | vmovupd 128(%rsi,%rdx), %zmm30 # AlignMOV convert to UnAlignMOV
|
||||||
|
2251 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd 16(%rsp), %zmm3 # 64-byte Reload
|
||||||
|
2252 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm28, %zmm3, %zmm3
|
||||||
|
2253 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubpd %zmm30, %zmm24, %zmm31
|
||||||
|
2254 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd 336(%rsp), %zmm16 # 64-byte Reload
|
||||||
|
2255 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm29, %zmm16, %zmm16
|
||||||
|
2256 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm31, %zmm31, %zmm17
|
||||||
|
2257 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm16, %zmm16, %zmm17 # zmm17 = (zmm16 * zmm16) + zmm17
|
||||||
|
2258 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm3, %zmm3, %zmm17 # zmm17 = (zmm3 * zmm3) + zmm17
|
||||||
|
2259 | 2.50 | | | | | 0.50 | | || 8.0 | | vrcp14pd %zmm17, %zmm18
|
||||||
|
2260 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm18, %zmm21, %zmm19
|
||||||
|
2261 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm19, %zmm18, %zmm19
|
||||||
|
2262 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm19, %zmm18, %zmm19
|
||||||
|
2263 | 0.50 | | | | | 0.50 | | || 4.0 | | vaddpd %zmm1, %zmm19, %zmm20
|
||||||
|
2264 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm18, %zmm22, %zmm18
|
||||||
|
2265 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm20, %zmm18, %zmm18
|
||||||
|
2266 | 1.00 | | | | | 0.00 | | || | | vsubpd %zmm30, %zmm25, %zmm20
|
||||||
|
2267 | | 1.00 | | | | 0.00 | | || | | leal (%rcx,%rcx), %edx
|
||||||
|
2268 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | cmpq %rdx, %r11
|
||||||
|
2269 | 0.00 | | | | | | 1.00 | || | | setne %dl
|
||||||
|
2270 | 0.00 | | | | | | 1.00 | || | | sete %al
|
||||||
|
2271 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | addl %ecx, %ecx
|
||||||
|
2272 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | incl %ecx
|
||||||
|
2273 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | cmpq %rcx, %r11
|
||||||
|
2274 | 0.00 | | | | | | 1.00 | || | | sete %cl
|
||||||
|
2275 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm18, %zmm19, %zmm18
|
||||||
|
2276 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd 528(%rsp), %zmm19 # 64-byte Reload
|
||||||
|
2277 | 1.00 | | | | | 0.00 | | || | | vsubpd %zmm28, %zmm19, %zmm19
|
||||||
|
2278 | 0.00 | | | | | | 1.00 | || | | setne %dil
|
||||||
|
2279 | 0.00 | 0.75 | | | | 0.00 | 0.25 | || | | movl %edi, %ebp
|
||||||
|
2280 | 0.00 | | | | | | 1.00 | || | 1.0 | shlb $4, %bpl
|
||||||
|
2281 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | 1.0 | subb %al, %bpl
|
||||||
|
2282 | 0.00 | 0.25 | | | | 0.00 | 0.75 | || | 1.0 | addb $-17, %bpl
|
||||||
|
2283 | 1.00 | | | | | | | || | | kmovd %ebp, %k1
|
||||||
|
2284 | | | | | | 1.00 | | || | | vcmpltpd %zmm0, %zmm17, %k1 {%k1}
|
||||||
|
2285 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd 272(%rsp), %zmm17 # 64-byte Reload
|
||||||
|
2286 | 0.25 | | | | | 0.75 | | || | | vsubpd %zmm29, %zmm17, %zmm17
|
||||||
|
2287 | | 1.00 | | | | 0.00 | | || | | leal (%rdx,%rdx), %eax
|
||||||
|
2288 | 0.00 | 0.75 | | | | 0.00 | 0.25 | || | | movl %edi, %ebp
|
||||||
|
2289 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm2, %zmm18, %zmm18
|
||||||
|
2290 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm18, %zmm3, %zmm14 {%k1} # zmm14 {%k1} = (zmm3 * zmm18) + zmm14
|
||||||
|
2291 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm20, %zmm20, %zmm3
|
||||||
|
2292 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm17, %zmm17, %zmm3 # zmm3 = (zmm17 * zmm17) + zmm3
|
||||||
|
2293 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm19, %zmm19, %zmm3 # zmm3 = (zmm19 * zmm19) + zmm3
|
||||||
|
2294 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm18, %zmm16, %zmm11 {%k1} # zmm11 {%k1} = (zmm16 * zmm18) + zmm11
|
||||||
|
2295 | 2.50 | | | | | 0.50 | | || | | vrcp14pd %zmm3, %zmm16
|
||||||
|
2296 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm18, %zmm31, %zmm7 {%k1} # zmm7 {%k1} = (zmm31 * zmm18) + zmm7
|
||||||
|
2297 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm16, %zmm21, %zmm18
|
||||||
|
2298 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm18, %zmm16, %zmm18
|
||||||
|
2299 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm18, %zmm16, %zmm18
|
||||||
|
2300 | 0.50 | | | | | 0.50 | | || | | vaddpd %zmm1, %zmm18, %zmm31
|
||||||
|
2301 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm16, %zmm22, %zmm16
|
||||||
|
2302 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm31, %zmm16, %zmm16
|
||||||
|
2303 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd 464(%rsp), %zmm31 # 64-byte Reload
|
||||||
|
2304 | 0.75 | | | | | 0.25 | | || | | vsubpd %zmm28, %zmm31, %zmm31
|
||||||
|
2305 | 0.00 | | | | | | 1.00 | || | 1.0 | shlb $5, %bpl
|
||||||
|
2306 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | 1.0 | orb %al, %bpl
|
||||||
|
2307 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | 1.0 | orb $-35, %bpl
|
||||||
|
2308 | 1.00 | | | | | | | || | | kmovd %ebp, %k1
|
||||||
|
2309 | | | | | | 1.00 | | || | | vcmpltpd %zmm0, %zmm3, %k1 {%k1}
|
||||||
|
2310 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd 208(%rsp), %zmm3 # 64-byte Reload
|
||||||
|
2311 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm29, %zmm3, %zmm3
|
||||||
|
2312 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm16, %zmm18, %zmm16
|
||||||
|
2313 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm30, %zmm26, %zmm18
|
||||||
|
2314 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm2, %zmm16, %zmm16
|
||||||
|
2315 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm16, %zmm19, %zmm15 {%k1} # zmm15 {%k1} = (zmm19 * zmm16) + zmm15
|
||||||
|
2316 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm18, %zmm18, %zmm19
|
||||||
|
2317 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm3, %zmm3, %zmm19 # zmm19 = (zmm3 * zmm3) + zmm19
|
||||||
|
2318 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm31, %zmm31, %zmm19 # zmm19 = (zmm31 * zmm31) + zmm19
|
||||||
|
2319 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm16, %zmm17, %zmm10 {%k1} # zmm10 {%k1} = (zmm17 * zmm16) + zmm10
|
||||||
|
2320 | 2.50 | | | | | 0.50 | | || | | vrcp14pd %zmm19, %zmm17
|
||||||
|
2321 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm16, %zmm20, %zmm6 {%k1} # zmm6 {%k1} = (zmm20 * zmm16) + zmm6
|
||||||
|
2322 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm17, %zmm21, %zmm16
|
||||||
|
2323 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm16, %zmm17, %zmm16
|
||||||
|
2324 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm16, %zmm17, %zmm16
|
||||||
|
2325 | 0.50 | | | | | 0.50 | | || | | vaddpd %zmm1, %zmm16, %zmm20
|
||||||
|
2326 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm17, %zmm22, %zmm17
|
||||||
|
2327 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm20, %zmm17, %zmm17
|
||||||
|
2328 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm17, %zmm16, %zmm16
|
||||||
|
2329 | | 1.00 | | | | 0.00 | | || | | leal (,%rdx,4), %eax
|
||||||
|
2330 | 0.00 | | | | | | 1.00 | || | | shlb $6, %dil
|
||||||
|
2331 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | orb %al, %dil
|
||||||
|
2332 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | orb $-69, %dil
|
||||||
|
2333 | 1.00 | | | | | | | || | | kmovd %edi, %k1
|
||||||
|
2334 | | | | | | 1.00 | | || | | vcmpltpd %zmm0, %zmm19, %k1 {%k1}
|
||||||
|
2335 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovupd 400(%rsp), %zmm17 # 64-byte Reload
|
||||||
|
2336 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm28, %zmm17, %zmm17
|
||||||
|
2337 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm29, %zmm23, %zmm19
|
||||||
|
2338 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm30, %zmm27, %zmm20
|
||||||
|
2339 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm2, %zmm16, %zmm16
|
||||||
|
2340 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm16, %zmm31, %zmm13 {%k1} # zmm13 {%k1} = (zmm31 * zmm16) + zmm13
|
||||||
|
2341 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm20, %zmm20, %zmm28
|
||||||
|
2342 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm19, %zmm19, %zmm28 # zmm28 = (zmm19 * zmm19) + zmm28
|
||||||
|
2343 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm17, %zmm17, %zmm28 # zmm28 = (zmm17 * zmm17) + zmm28
|
||||||
|
2344 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm16, %zmm3, %zmm9 {%k1} # zmm9 {%k1} = (zmm3 * zmm16) + zmm9
|
||||||
|
2345 | 2.50 | | | | | 0.50 | | || | | vrcp14pd %zmm28, %zmm3
|
||||||
|
2346 | 0.50 | | | | | 0.50 | | || | | vfmadd231pd %zmm16, %zmm18, %zmm5 {%k1} # zmm5 {%k1} = (zmm18 * zmm16) + zmm5
|
||||||
|
2347 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm3, %zmm21, %zmm16
|
||||||
|
2348 | 0.00 | | | | | 1.00 | | || | | vmulpd %zmm16, %zmm3, %zmm16
|
||||||
|
2349 | 0.00 | | | | | 1.00 | | || | | vmulpd %zmm16, %zmm3, %zmm16
|
||||||
|
2350 | 0.00 | | | | | 1.00 | | || | | vaddpd %zmm1, %zmm16, %zmm18
|
||||||
|
2351 | 0.00 | | | | | 1.00 | | || | | vmulpd %zmm3, %zmm22, %zmm3
|
||||||
|
2352 | 0.00 | | | | | 1.00 | | || | | vmulpd %zmm18, %zmm3, %zmm3
|
||||||
|
2353 | 0.00 | | | | | 1.00 | | || | | vmulpd %zmm3, %zmm16, %zmm3
|
||||||
|
2354 | 0.00 | | | | | | 1.00 | || | | shlb $3, %dl
|
||||||
|
2355 | 0.00 | | | | | | 1.00 | || | | shlb $7, %cl
|
||||||
|
2356 | 0.00 | 0.25 | | | | 0.00 | 0.75 | || | | orb %dl, %cl
|
||||||
|
2357 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | addb $-9, %cl
|
||||||
|
2358 | 1.00 | | | | | | | || | | kmovd %ecx, %k1
|
||||||
|
2359 | | | | | | 1.00 | | || | | vcmpltpd %zmm0, %zmm28, %k1 {%k1}
|
||||||
|
2360 | 0.00 | | | | | 1.00 | | || | | vmulpd %zmm2, %zmm3, %zmm3
|
||||||
|
2361 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm3, %zmm17, %zmm12 {%k1} # zmm12 {%k1} = (zmm17 * zmm3) + zmm12
|
||||||
|
2362 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm3, %zmm19, %zmm8 {%k1} # zmm8 {%k1} = (zmm19 * zmm3) + zmm8
|
||||||
|
2363 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm3, %zmm20, %zmm4 {%k1} # zmm4 {%k1} = (zmm20 * zmm3) + zmm4
|
||||||
|
2364 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | incq %rbx
|
||||||
|
2365 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | cmpq %rbx, %r9
|
||||||
|
2366 | | | | | | | | || | | * jne .LBB5_12
|
||||||
|
2367 | | | | | | | | || | | # LLVM-MCA-END
|
||||||
|
|
||||||
|
44.0 15.0 5.50 5.50 5.50 5.50 44.0 15.0 66.0 6.0
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loop-Carried Dependencies Analysis Report
|
||||||
|
-----------------------------------------
|
||||||
|
2280 | 6.0 | shlb $4, %bpl | [2280, 2281, 2282, 2305, 2306, 2307]
|
||||||
|
2363 | 4.0 | vfmadd231pd %zmm3, %zmm20, %zmm4 {%k1} # zmm4 {%k1} = (zmm20 * zmm3) + zmm4| [2363]
|
||||||
|
2362 | 4.0 | vfmadd231pd %zmm3, %zmm19, %zmm8 {%k1} # zmm8 {%k1} = (zmm19 * zmm3) + zmm8| [2362]
|
||||||
|
2361 | 4.0 | vfmadd231pd %zmm3, %zmm17, %zmm12 {%k1} # zmm12 {%k1} = (zmm17 * zmm3) + zmm12| [2361]
|
||||||
|
2346 | 4.0 | vfmadd231pd %zmm16, %zmm18, %zmm5 {%k1} # zmm5 {%k1} = (zmm18 * zmm16) + zmm5| [2346]
|
||||||
|
2344 | 4.0 | vfmadd231pd %zmm16, %zmm3, %zmm9 {%k1} # zmm9 {%k1} = (zmm3 * zmm16) + zmm9| [2344]
|
||||||
|
2340 | 4.0 | vfmadd231pd %zmm16, %zmm31, %zmm13 {%k1} # zmm13 {%k1} = (zmm31 * zmm16) + zmm13| [2340]
|
||||||
|
2321 | 4.0 | vfmadd231pd %zmm16, %zmm20, %zmm6 {%k1} # zmm6 {%k1} = (zmm20 * zmm16) + zmm6| [2321]
|
||||||
|
2319 | 4.0 | vfmadd231pd %zmm16, %zmm17, %zmm10 {%k1} # zmm10 {%k1} = (zmm17 * zmm16) + zmm10| [2319]
|
||||||
|
2315 | 4.0 | vfmadd231pd %zmm16, %zmm19, %zmm15 {%k1} # zmm15 {%k1} = (zmm19 * zmm16) + zmm15| [2315]
|
||||||
|
2296 | 4.0 | vfmadd231pd %zmm18, %zmm31, %zmm7 {%k1} # zmm7 {%k1} = (zmm31 * zmm18) + zmm7| [2296]
|
||||||
|
2294 | 4.0 | vfmadd231pd %zmm18, %zmm16, %zmm11 {%k1} # zmm11 {%k1} = (zmm16 * zmm18) + zmm11| [2294]
|
||||||
|
2290 | 4.0 | vfmadd231pd %zmm18, %zmm3, %zmm14 {%k1} # zmm14 {%k1} = (zmm3 * zmm18) + zmm14| [2290]
|
||||||
|
2330 | 3.0 | shlb $6, %dil | [2330, 2331, 2332]
|
||||||
|
2364 | 1.0 | incq %rbx | [2364]
|
||||||
|
|
||||||
162
static_analysis/jan/analyses/gromacs-icx-avx512-sp-iaca.out
Normal file
162
static_analysis/jan/analyses/gromacs-icx-avx512-sp-iaca.out
Normal file
@ -0,0 +1,162 @@
|
|||||||
|
Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45
|
||||||
|
Analyzed File - gromacs-icx-avx512-sp.o
|
||||||
|
Binary Format - 64Bit
|
||||||
|
Architecture - SKX
|
||||||
|
Analysis Type - Throughput
|
||||||
|
|
||||||
|
Throughput Analysis Report
|
||||||
|
--------------------------
|
||||||
|
Block Throughput: 64.00 Cycles Throughput Bottleneck: Backend
|
||||||
|
Loop Count: 22
|
||||||
|
Port Binding In Cycles Per Iteration:
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Cycles | 50.0 0.0 | 7.0 | 9.5 8.1 | 9.5 7.9 | 3.0 | 50.0 | 7.0 | 0.0 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
DV - Divider pipe (on port 0)
|
||||||
|
D - Data fetch pipe (on ports 2 and 3)
|
||||||
|
F - Macro Fusion with the previous instruction occurred
|
||||||
|
* - instruction micro-ops not bound to a port
|
||||||
|
^ - Micro Fusion occurred
|
||||||
|
# - ESP Tracking sync uop was issued
|
||||||
|
@ - SSE instruction followed an AVX256/AVX512 instruction, dozens of cycles penalty is expected
|
||||||
|
X - instruction not supported, was not accounted in Analysis
|
||||||
|
|
||||||
|
| Num Of | Ports pressure in cycles | |
|
||||||
|
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
-----------------------------------------------------------------------------------------
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | movsxd rax, dword ptr [r11+rdx*4]
|
||||||
|
| 1* | | | | | | | | | mov rsi, rax
|
||||||
|
| 1 | | | | | | | 1.0 | | shl rsi, 0x5
|
||||||
|
| 1 | | 1.0 | | | | | | | lea rbx, ptr [rsi+rsi*2]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm15, zmmword ptr [rdi+rbx*1]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm16, zmmword ptr [rdi+rbx*1+0x20]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm27, zmmword ptr [rdi+rbx*1+0x40]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm1, zmmword ptr [rsp+0x80]
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubps zmm24, zmm1, zmm15
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm1, zmmword ptr [rsp+0x140]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubps zmm25, zmm1, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubps zmm26, zmm9, zmm27
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm1, zmmword ptr [rsp]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubps zmm21, zmm1, zmm15
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm1, zmmword ptr [rsp+0x100]
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubps zmm22, zmm1, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubps zmm23, zmm10, zmm27
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm1, zmmword ptr [rsp+0x1c0]
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubps zmm17, zmm1, zmm15
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm1, zmmword ptr [rsp+0xc0]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubps zmm19, zmm1, zmm16
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubps zmm20, zmm11, zmm27
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm1, zmmword ptr [rsp+0x180]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubps zmm18, zmm1, zmm15
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubps zmm16, zmm8, zmm16
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubps zmm15, zmm12, zmm27
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm27, zmm26, zmm26
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231ps zmm27, zmm25, zmm25
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231ps zmm27, zmm24, zmm24
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm28, zmm23, zmm23
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231ps zmm28, zmm22, zmm22
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231ps zmm28, zmm21, zmm21
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm29, zmm20, zmm20
|
||||||
|
| 1 | 1.0 | | | | | | | | vfmadd231ps zmm29, zmm19, zmm19
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231ps zmm29, zmm17, zmm17
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm30, zmm15, zmm15
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231ps zmm30, zmm16, zmm16
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14ps zmm31, zmm27
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14ps zmm1, zmm28
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14ps zmm2, zmm29
|
||||||
|
| 1 | | | | | | 1.0 | | | vfmadd231ps zmm30, zmm18, zmm18
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14ps zmm3, zmm30
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm4, zmm6, zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm4, zmm31, zmm4
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm4, zmm31, zmm4
|
||||||
|
| 1 | 1.0 | | | | | | | | vaddps zmm5, zmm4, zmm13
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm31, zmm7, zmm31
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm5, zmm31, zmm5
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm31, zmm6, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm31, zmm1, zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm31, zmm1, zmm31
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm4, zmm4, zmm5
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddps zmm5, zmm31, zmm13
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm1, zmm7, zmm1
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm1, zmm1, zmm5
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm5, zmm6, zmm2
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm5, zmm2, zmm5
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm5, zmm2, zmm5
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm1, zmm31, zmm1
|
||||||
|
| 1 | 1.0 | | | | | | | | vaddps zmm31, zmm5, zmm13
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm2, zmm7, zmm2
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm2, zmm2, zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm31, zmm6, zmm3
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm31, zmm3, zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm31, zmm3, zmm31
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm2, zmm5, zmm2
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddps zmm5, zmm31, zmm13
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm3, zmm7, zmm3
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm3, zmm3, zmm5
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm3, zmm31, zmm3
|
||||||
|
| 1* | | | | | | | | | xor esi, esi
|
||||||
|
| 1* | | | | | | | | | xor edi, edi
|
||||||
|
| 1 | | 1.0 | | | | | | | test eax, 0x7fffffff
|
||||||
|
| 1 | | | | | | | 1.0 | | setz sil
|
||||||
|
| 1 | | | | | | | 1.0 | | setnz dil
|
||||||
|
| 1 | | 1.0 | | | | | | | mov eax, 0xff
|
||||||
|
| 1 | | | | | | | 1.0 | | cmovz eax, r8d
|
||||||
|
| 1 | | 1.0 | | | | | | | mov ecx, 0xff
|
||||||
|
| 1 | | | | | | | 1.0 | | cmovz ecx, r9d
|
||||||
|
| 1 | | 1.0 | | | | | | | xor esi, 0xff
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovd k1, esi
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmpps k1{k1}, zmm27, zmm0, 0x1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm4, zmm4, zmm14
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm5{k1}{z}, zmm24, zmm4
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm24{k1}{z}, zmm25, zmm4
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm4{k1}{z}, zmm26, zmm4
|
||||||
|
| 1 | | 1.0 | | | | | | | lea esi, ptr [rdi+rdi*2]
|
||||||
|
| 1 | | | | | | | 1.0 | | or esi, 0xfc
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovd k1, esi
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmpps k1{k1}, zmm28, zmm0, 0x1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm1, zmm1, zmm14
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm21{k1}{z}, zmm21, zmm1
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddps zmm5, zmm5, zmm21
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm21{k1}{z}, zmm22, zmm1
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddps zmm21, zmm24, zmm21
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm1{k1}{z}, zmm23, zmm1
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddps zmm1, zmm4, zmm1
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovd k1, eax
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmpps k1{k1}, zmm29, zmm0, 0x1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm2, zmm2, zmm14
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm4{k1}{z}, zmm17, zmm2
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm17{k1}{z}, zmm19, zmm2
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm2{k1}{z}, zmm20, zmm2
|
||||||
|
| 1 | | | | | | 1.0 | | | kmovd k1, ecx
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmpps k1{k1}, zmm30, zmm0, 0x1
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm3, zmm3, zmm14
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm18{k1}{z}, zmm18, zmm3
|
||||||
|
| 1 | 1.0 | | | | | | | | vaddps zmm4, zmm4, zmm18
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddps zmm4, zmm5, zmm4
|
||||||
|
| 1 | 1.0 | | | | | | | | vmulps zmm5{k1}{z}, zmm16, zmm3
|
||||||
|
| 1 | | | | | | 1.0 | | | vaddps zmm5, zmm17, zmm5
|
||||||
|
| 1 | 1.0 | | | | | | | | vaddps zmm5, zmm21, zmm5
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulps zmm3{k1}{z}, zmm15, zmm3
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | mov rax, qword ptr [r15+0xb0]
|
||||||
|
| 1 | 1.0 | | | | | | | | vaddps zmm2, zmm2, zmm3
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm3, zmmword ptr [rax+rbx*1]
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubps zmm3, zmm3, zmm4
|
||||||
|
| 2 | | | 0.5 | 0.5 | 1.0 | | | | vmovups zmmword ptr [rax+rbx*1], zmm3
|
||||||
|
| 1 | 1.0 | | | | | | | | vaddps zmm1, zmm1, zmm2
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm2, zmmword ptr [rax+rbx*1+0x20]
|
||||||
|
| 1 | | | | | | 1.0 | | | vsubps zmm2, zmm2, zmm5
|
||||||
|
| 2 | | | 0.5 | 0.5 | 1.0 | | | | vmovups zmmword ptr [rax+rbx*1+0x20], zmm2
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups zmm2, zmmword ptr [rax+rbx*1+0x40]
|
||||||
|
| 1 | 1.0 | | | | | | | | vsubps zmm1, zmm2, zmm1
|
||||||
|
| 2 | | | 0.5 | 0.5 | 1.0 | | | | vmovups zmmword ptr [rax+rbx*1+0x40], zmm1
|
||||||
|
| 1* | | | | | | | | | cmp r10, rdx
|
||||||
|
| 0*F | | | | | | | | | jz 0x34
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | mov rdi, qword ptr [r15+0xa0]
|
||||||
|
| 1 | | 1.0 | | | | | | | inc rdx
|
||||||
|
| 1 | | | | | | | 1.0 | | jmp 0xfffffffffffffcfc
|
||||||
|
Total Num Of Uops: 140
|
||||||
|
Analysis Notes:
|
||||||
|
Backend allocation was stalled due to unavailable allocation resources.
|
||||||
304
static_analysis/jan/analyses/gromacs-icx-avx512-sp-mca.out
Normal file
304
static_analysis/jan/analyses/gromacs-icx-avx512-sp-mca.out
Normal file
@ -0,0 +1,304 @@
|
|||||||
|
|
||||||
|
[0] Code Region
|
||||||
|
|
||||||
|
Iterations: 100
|
||||||
|
Instructions: 13000
|
||||||
|
Total Cycles: 5640
|
||||||
|
Total uOps: 15400
|
||||||
|
|
||||||
|
Dispatch Width: 6
|
||||||
|
uOps Per Cycle: 2.73
|
||||||
|
IPC: 2.30
|
||||||
|
Block RThroughput: 40.0
|
||||||
|
|
||||||
|
|
||||||
|
Instruction Info:
|
||||||
|
[1]: #uOps
|
||||||
|
[2]: Latency
|
||||||
|
[3]: RThroughput
|
||||||
|
[4]: MayLoad
|
||||||
|
[5]: MayStore
|
||||||
|
[6]: HasSideEffects (U)
|
||||||
|
|
||||||
|
[1] [2] [3] [4] [5] [6] Instructions:
|
||||||
|
1 5 0.50 * movslq (%r11,%rdx,4), %rax
|
||||||
|
1 1 0.25 movq %rax, %rsi
|
||||||
|
1 1 0.50 shlq $5, %rsi
|
||||||
|
1 1 0.50 leaq (%rsi,%rsi,2), %rbx
|
||||||
|
2 8 0.50 * vmovups (%rdi,%rbx), %zmm15
|
||||||
|
2 8 0.50 * vmovups 32(%rdi,%rbx), %zmm16
|
||||||
|
2 8 0.50 * vmovups 64(%rdi,%rbx), %zmm27
|
||||||
|
2 8 0.50 * vmovups 128(%rsp), %zmm1
|
||||||
|
1 4 0.50 vsubps %zmm15, %zmm1, %zmm24
|
||||||
|
2 8 0.50 * vmovups 320(%rsp), %zmm1
|
||||||
|
1 4 0.50 vsubps %zmm16, %zmm1, %zmm25
|
||||||
|
1 4 0.50 vsubps %zmm27, %zmm9, %zmm26
|
||||||
|
2 8 0.50 * vmovups (%rsp), %zmm1
|
||||||
|
1 4 0.50 vsubps %zmm15, %zmm1, %zmm21
|
||||||
|
2 8 0.50 * vmovups 256(%rsp), %zmm1
|
||||||
|
1 4 0.50 vsubps %zmm16, %zmm1, %zmm22
|
||||||
|
1 4 0.50 vsubps %zmm27, %zmm10, %zmm23
|
||||||
|
2 8 0.50 * vmovups 448(%rsp), %zmm1
|
||||||
|
1 4 0.50 vsubps %zmm15, %zmm1, %zmm17
|
||||||
|
2 8 0.50 * vmovups 192(%rsp), %zmm1
|
||||||
|
1 4 0.50 vsubps %zmm16, %zmm1, %zmm19
|
||||||
|
1 4 0.50 vsubps %zmm27, %zmm11, %zmm20
|
||||||
|
2 8 0.50 * vmovups 384(%rsp), %zmm1
|
||||||
|
1 4 0.50 vsubps %zmm15, %zmm1, %zmm18
|
||||||
|
1 4 0.50 vsubps %zmm16, %zmm8, %zmm16
|
||||||
|
1 4 0.50 vsubps %zmm27, %zmm12, %zmm15
|
||||||
|
1 4 0.50 vmulps %zmm26, %zmm26, %zmm27
|
||||||
|
1 4 0.50 vfmadd231ps %zmm25, %zmm25, %zmm27
|
||||||
|
1 4 0.50 vfmadd231ps %zmm24, %zmm24, %zmm27
|
||||||
|
1 4 0.50 vmulps %zmm23, %zmm23, %zmm28
|
||||||
|
1 4 0.50 vfmadd231ps %zmm22, %zmm22, %zmm28
|
||||||
|
1 4 0.50 vfmadd231ps %zmm21, %zmm21, %zmm28
|
||||||
|
1 4 0.50 vmulps %zmm20, %zmm20, %zmm29
|
||||||
|
1 4 0.50 vfmadd231ps %zmm19, %zmm19, %zmm29
|
||||||
|
1 4 0.50 vfmadd231ps %zmm17, %zmm17, %zmm29
|
||||||
|
1 4 0.50 vmulps %zmm15, %zmm15, %zmm30
|
||||||
|
1 4 0.50 vfmadd231ps %zmm16, %zmm16, %zmm30
|
||||||
|
3 4 2.00 vrcp14ps %zmm27, %zmm31
|
||||||
|
3 4 2.00 vrcp14ps %zmm28, %zmm1
|
||||||
|
3 4 2.00 vrcp14ps %zmm29, %zmm2
|
||||||
|
1 4 0.50 vfmadd231ps %zmm18, %zmm18, %zmm30
|
||||||
|
3 4 2.00 vrcp14ps %zmm30, %zmm3
|
||||||
|
1 4 0.50 vmulps %zmm31, %zmm6, %zmm4
|
||||||
|
1 4 0.50 vmulps %zmm4, %zmm31, %zmm4
|
||||||
|
1 4 0.50 vmulps %zmm4, %zmm31, %zmm4
|
||||||
|
1 4 0.50 vaddps %zmm13, %zmm4, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm31, %zmm7, %zmm31
|
||||||
|
1 4 0.50 vmulps %zmm5, %zmm31, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm1, %zmm6, %zmm31
|
||||||
|
1 4 0.50 vmulps %zmm31, %zmm1, %zmm31
|
||||||
|
1 4 0.50 vmulps %zmm31, %zmm1, %zmm31
|
||||||
|
1 4 0.50 vmulps %zmm5, %zmm4, %zmm4
|
||||||
|
1 4 0.50 vaddps %zmm13, %zmm31, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm1, %zmm7, %zmm1
|
||||||
|
1 4 0.50 vmulps %zmm5, %zmm1, %zmm1
|
||||||
|
1 4 0.50 vmulps %zmm2, %zmm6, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm5, %zmm2, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm5, %zmm2, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm1, %zmm31, %zmm1
|
||||||
|
1 4 0.50 vaddps %zmm13, %zmm5, %zmm31
|
||||||
|
1 4 0.50 vmulps %zmm2, %zmm7, %zmm2
|
||||||
|
1 4 0.50 vmulps %zmm31, %zmm2, %zmm2
|
||||||
|
1 4 0.50 vmulps %zmm3, %zmm6, %zmm31
|
||||||
|
1 4 0.50 vmulps %zmm31, %zmm3, %zmm31
|
||||||
|
1 4 0.50 vmulps %zmm31, %zmm3, %zmm31
|
||||||
|
1 4 0.50 vmulps %zmm2, %zmm5, %zmm2
|
||||||
|
1 4 0.50 vaddps %zmm13, %zmm31, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm3, %zmm7, %zmm3
|
||||||
|
1 4 0.50 vmulps %zmm5, %zmm3, %zmm3
|
||||||
|
1 4 0.50 vmulps %zmm3, %zmm31, %zmm3
|
||||||
|
1 0 0.17 xorl %esi, %esi
|
||||||
|
1 0 0.17 xorl %edi, %edi
|
||||||
|
1 1 0.25 testl $2147483647, %eax
|
||||||
|
1 1 0.50 sete %sil
|
||||||
|
1 1 0.50 setne %dil
|
||||||
|
1 1 0.25 movl $255, %eax
|
||||||
|
1 1 0.50 cmovel %r8d, %eax
|
||||||
|
1 1 0.25 movl $255, %ecx
|
||||||
|
1 1 0.50 cmovel %r9d, %ecx
|
||||||
|
1 1 0.25 xorl $255, %esi
|
||||||
|
1 1 1.00 kmovd %esi, %k1
|
||||||
|
1 4 1.00 vcmpltps %zmm0, %zmm27, %k1 {%k1}
|
||||||
|
1 4 0.50 vmulps %zmm14, %zmm4, %zmm4
|
||||||
|
1 4 0.50 vmulps %zmm4, %zmm24, %zmm5 {%k1} {z}
|
||||||
|
1 4 0.50 vmulps %zmm4, %zmm25, %zmm24 {%k1} {z}
|
||||||
|
1 4 0.50 vmulps %zmm4, %zmm26, %zmm4 {%k1} {z}
|
||||||
|
1 1 0.50 leal (%rdi,%rdi,2), %esi
|
||||||
|
1 1 0.25 orl $252, %esi
|
||||||
|
1 1 1.00 kmovd %esi, %k1
|
||||||
|
1 4 1.00 vcmpltps %zmm0, %zmm28, %k1 {%k1}
|
||||||
|
1 4 0.50 vmulps %zmm14, %zmm1, %zmm1
|
||||||
|
1 4 0.50 vmulps %zmm1, %zmm21, %zmm21 {%k1} {z}
|
||||||
|
1 4 0.50 vaddps %zmm21, %zmm5, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm1, %zmm22, %zmm21 {%k1} {z}
|
||||||
|
1 4 0.50 vaddps %zmm21, %zmm24, %zmm21
|
||||||
|
1 4 0.50 vmulps %zmm1, %zmm23, %zmm1 {%k1} {z}
|
||||||
|
1 4 0.50 vaddps %zmm1, %zmm4, %zmm1
|
||||||
|
1 1 1.00 kmovd %eax, %k1
|
||||||
|
1 4 1.00 vcmpltps %zmm0, %zmm29, %k1 {%k1}
|
||||||
|
1 4 0.50 vmulps %zmm14, %zmm2, %zmm2
|
||||||
|
1 4 0.50 vmulps %zmm2, %zmm17, %zmm4 {%k1} {z}
|
||||||
|
1 4 0.50 vmulps %zmm2, %zmm19, %zmm17 {%k1} {z}
|
||||||
|
1 4 0.50 vmulps %zmm2, %zmm20, %zmm2 {%k1} {z}
|
||||||
|
1 1 1.00 kmovd %ecx, %k1
|
||||||
|
1 4 1.00 vcmpltps %zmm0, %zmm30, %k1 {%k1}
|
||||||
|
1 4 0.50 vmulps %zmm14, %zmm3, %zmm3
|
||||||
|
1 4 0.50 vmulps %zmm3, %zmm18, %zmm18 {%k1} {z}
|
||||||
|
1 4 0.50 vaddps %zmm18, %zmm4, %zmm4
|
||||||
|
1 4 0.50 vaddps %zmm4, %zmm5, %zmm4
|
||||||
|
1 4 0.50 vmulps %zmm3, %zmm16, %zmm5 {%k1} {z}
|
||||||
|
1 4 0.50 vaddps %zmm5, %zmm17, %zmm5
|
||||||
|
1 4 0.50 vaddps %zmm5, %zmm21, %zmm5
|
||||||
|
1 4 0.50 vmulps %zmm3, %zmm15, %zmm3 {%k1} {z}
|
||||||
|
1 5 0.50 * movq 176(%r15), %rax
|
||||||
|
1 4 0.50 vaddps %zmm3, %zmm2, %zmm2
|
||||||
|
2 8 0.50 * vmovups (%rax,%rbx), %zmm3
|
||||||
|
1 4 0.50 vsubps %zmm4, %zmm3, %zmm3
|
||||||
|
2 1 1.00 * vmovups %zmm3, (%rax,%rbx)
|
||||||
|
1 4 0.50 vaddps %zmm2, %zmm1, %zmm1
|
||||||
|
2 8 0.50 * vmovups 32(%rax,%rbx), %zmm2
|
||||||
|
1 4 0.50 vsubps %zmm5, %zmm2, %zmm2
|
||||||
|
2 1 1.00 * vmovups %zmm2, 32(%rax,%rbx)
|
||||||
|
2 8 0.50 * vmovups 64(%rax,%rbx), %zmm2
|
||||||
|
1 4 0.50 vsubps %zmm1, %zmm2, %zmm1
|
||||||
|
2 1 1.00 * vmovups %zmm1, 64(%rax,%rbx)
|
||||||
|
1 1 0.25 cmpq %rdx, %r10
|
||||||
|
1 1 0.50 je .LBB4_18
|
||||||
|
1 5 0.50 * movq 160(%r15), %rdi
|
||||||
|
1 1 0.25 incq %rdx
|
||||||
|
1 1 0.50 jmp .LBB4_8
|
||||||
|
|
||||||
|
|
||||||
|
Resources:
|
||||||
|
[0] - SKXDivider
|
||||||
|
[1] - SKXFPDivider
|
||||||
|
[2] - SKXPort0
|
||||||
|
[3] - SKXPort1
|
||||||
|
[4] - SKXPort2
|
||||||
|
[5] - SKXPort3
|
||||||
|
[6] - SKXPort4
|
||||||
|
[7] - SKXPort5
|
||||||
|
[8] - SKXPort6
|
||||||
|
[9] - SKXPort7
|
||||||
|
|
||||||
|
|
||||||
|
Resource pressure per iteration:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9]
|
||||||
|
- - 52.01 14.97 8.49 8.51 3.00 52.02 11.00 2.00
|
||||||
|
|
||||||
|
Resource pressure by instruction:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
|
||||||
|
- - - - 0.49 0.51 - - - - movslq (%r11,%rdx,4), %rax
|
||||||
|
- - - - - - - - 1.00 - movq %rax, %rsi
|
||||||
|
- - - - - - - - 1.00 - shlq $5, %rsi
|
||||||
|
- - - 1.00 - - - - - - leaq (%rsi,%rsi,2), %rbx
|
||||||
|
- - 0.01 0.99 0.50 0.50 - - - - vmovups (%rdi,%rbx), %zmm15
|
||||||
|
- - - - 0.50 0.50 - 1.00 - - vmovups 32(%rdi,%rbx), %zmm16
|
||||||
|
- - - 1.00 0.50 0.50 - - - - vmovups 64(%rdi,%rbx), %zmm27
|
||||||
|
- - - 0.99 0.51 0.49 - 0.01 - - vmovups 128(%rsp), %zmm1
|
||||||
|
- - 0.01 - - - - 0.99 - - vsubps %zmm15, %zmm1, %zmm24
|
||||||
|
- - - 1.00 0.49 0.51 - - - - vmovups 320(%rsp), %zmm1
|
||||||
|
- - 0.99 - - - - 0.01 - - vsubps %zmm16, %zmm1, %zmm25
|
||||||
|
- - 0.01 - - - - 0.99 - - vsubps %zmm27, %zmm9, %zmm26
|
||||||
|
- - 0.01 0.99 0.51 0.49 - - - - vmovups (%rsp), %zmm1
|
||||||
|
- - - - - - - 1.00 - - vsubps %zmm15, %zmm1, %zmm21
|
||||||
|
- - - - 0.49 0.51 - 1.00 - - vmovups 256(%rsp), %zmm1
|
||||||
|
- - 0.01 - - - - 0.99 - - vsubps %zmm16, %zmm1, %zmm22
|
||||||
|
- - 0.99 - - - - 0.01 - - vsubps %zmm27, %zmm10, %zmm23
|
||||||
|
- - - 1.00 0.51 0.49 - - - - vmovups 448(%rsp), %zmm1
|
||||||
|
- - 0.01 - - - - 0.99 - - vsubps %zmm15, %zmm1, %zmm17
|
||||||
|
- - 0.01 - 0.49 0.51 - 0.99 - - vmovups 192(%rsp), %zmm1
|
||||||
|
- - - - - - - 1.00 - - vsubps %zmm16, %zmm1, %zmm19
|
||||||
|
- - 0.01 - - - - 0.99 - - vsubps %zmm27, %zmm11, %zmm20
|
||||||
|
- - 0.99 - 0.50 0.50 - 0.01 - - vmovups 384(%rsp), %zmm1
|
||||||
|
- - - - - - - 1.00 - - vsubps %zmm15, %zmm1, %zmm18
|
||||||
|
- - 0.01 - - - - 0.99 - - vsubps %zmm16, %zmm8, %zmm16
|
||||||
|
- - - - - - - 1.00 - - vsubps %zmm27, %zmm12, %zmm15
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm26, %zmm26, %zmm27
|
||||||
|
- - 1.00 - - - - - - - vfmadd231ps %zmm25, %zmm25, %zmm27
|
||||||
|
- - 0.99 - - - - 0.01 - - vfmadd231ps %zmm24, %zmm24, %zmm27
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm23, %zmm23, %zmm28
|
||||||
|
- - - - - - - 1.00 - - vfmadd231ps %zmm22, %zmm22, %zmm28
|
||||||
|
- - 0.01 - - - - 0.99 - - vfmadd231ps %zmm21, %zmm21, %zmm28
|
||||||
|
- - 0.01 - - - - 0.99 - - vmulps %zmm20, %zmm20, %zmm29
|
||||||
|
- - 0.01 - - - - 0.99 - - vfmadd231ps %zmm19, %zmm19, %zmm29
|
||||||
|
- - - - - - - 1.00 - - vfmadd231ps %zmm17, %zmm17, %zmm29
|
||||||
|
- - 0.01 - - - - 0.99 - - vmulps %zmm15, %zmm15, %zmm30
|
||||||
|
- - 0.01 - - - - 0.99 - - vfmadd231ps %zmm16, %zmm16, %zmm30
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14ps %zmm27, %zmm31
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14ps %zmm28, %zmm1
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14ps %zmm29, %zmm2
|
||||||
|
- - 1.00 - - - - - - - vfmadd231ps %zmm18, %zmm18, %zmm30
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14ps %zmm30, %zmm3
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm31, %zmm6, %zmm4
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm4, %zmm31, %zmm4
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm4, %zmm31, %zmm4
|
||||||
|
- - 1.00 - - - - - - - vaddps %zmm13, %zmm4, %zmm5
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm31, %zmm7, %zmm31
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm5, %zmm31, %zmm5
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm1, %zmm6, %zmm31
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm31, %zmm1, %zmm31
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulps %zmm31, %zmm1, %zmm31
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm5, %zmm4, %zmm4
|
||||||
|
- - - - - - - 1.00 - - vaddps %zmm13, %zmm31, %zmm5
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm1, %zmm7, %zmm1
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm5, %zmm1, %zmm1
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm2, %zmm6, %zmm5
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm5, %zmm2, %zmm5
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm5, %zmm2, %zmm5
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulps %zmm1, %zmm31, %zmm1
|
||||||
|
- - - - - - - 1.00 - - vaddps %zmm13, %zmm5, %zmm31
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm2, %zmm7, %zmm2
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm31, %zmm2, %zmm2
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm3, %zmm6, %zmm31
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm31, %zmm3, %zmm31
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm31, %zmm3, %zmm31
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm2, %zmm5, %zmm2
|
||||||
|
- - 1.00 - - - - - - - vaddps %zmm13, %zmm31, %zmm5
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm3, %zmm7, %zmm3
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm5, %zmm3, %zmm3
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm3, %zmm31, %zmm3
|
||||||
|
- - - - - - - - - - xorl %esi, %esi
|
||||||
|
- - - - - - - - - - xorl %edi, %edi
|
||||||
|
- - - - - - - - 1.00 - testl $2147483647, %eax
|
||||||
|
- - - - - - - - 1.00 - sete %sil
|
||||||
|
- - - - - - - - 1.00 - setne %dil
|
||||||
|
- - - 1.00 - - - - - - movl $255, %eax
|
||||||
|
- - - - - - - - 1.00 - cmovel %r8d, %eax
|
||||||
|
- - - 1.00 - - - - - - movl $255, %ecx
|
||||||
|
- - - - - - - - 1.00 - cmovel %r9d, %ecx
|
||||||
|
- - - 1.00 - - - - - - xorl $255, %esi
|
||||||
|
- - - - - - - 1.00 - - kmovd %esi, %k1
|
||||||
|
- - - - - - - 1.00 - - vcmpltps %zmm0, %zmm27, %k1 {%k1}
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm14, %zmm4, %zmm4
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm4, %zmm24, %zmm5 {%k1} {z}
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm4, %zmm25, %zmm24 {%k1} {z}
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm4, %zmm26, %zmm4 {%k1} {z}
|
||||||
|
- - - 1.00 - - - - - - leal (%rdi,%rdi,2), %esi
|
||||||
|
- - - - - - - - 1.00 - orl $252, %esi
|
||||||
|
- - - - - - - 1.00 - - kmovd %esi, %k1
|
||||||
|
- - - - - - - 1.00 - - vcmpltps %zmm0, %zmm28, %k1 {%k1}
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulps %zmm14, %zmm1, %zmm1
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulps %zmm1, %zmm21, %zmm21 {%k1} {z}
|
||||||
|
- - 1.00 - - - - - - - vaddps %zmm21, %zmm5, %zmm5
|
||||||
|
- - 0.01 - - - - 0.99 - - vmulps %zmm1, %zmm22, %zmm21 {%k1} {z}
|
||||||
|
- - - - - - - 1.00 - - vaddps %zmm21, %zmm24, %zmm21
|
||||||
|
- - 0.99 - - - - 0.01 - - vmulps %zmm1, %zmm23, %zmm1 {%k1} {z}
|
||||||
|
- - 1.00 - - - - - - - vaddps %zmm1, %zmm4, %zmm1
|
||||||
|
- - - - - - - 1.00 - - kmovd %eax, %k1
|
||||||
|
- - - - - - - 1.00 - - vcmpltps %zmm0, %zmm29, %k1 {%k1}
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm14, %zmm2, %zmm2
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm2, %zmm17, %zmm4 {%k1} {z}
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm2, %zmm19, %zmm17 {%k1} {z}
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm2, %zmm20, %zmm2 {%k1} {z}
|
||||||
|
- - - - - - - 1.00 - - kmovd %ecx, %k1
|
||||||
|
- - - - - - - 1.00 - - vcmpltps %zmm0, %zmm30, %k1 {%k1}
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm14, %zmm3, %zmm3
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm3, %zmm18, %zmm18 {%k1} {z}
|
||||||
|
- - 0.99 - - - - 0.01 - - vaddps %zmm18, %zmm4, %zmm4
|
||||||
|
- - 1.00 - - - - - - - vaddps %zmm4, %zmm5, %zmm4
|
||||||
|
- - - - - - - 1.00 - - vmulps %zmm3, %zmm16, %zmm5 {%k1} {z}
|
||||||
|
- - 1.00 - - - - - - - vaddps %zmm5, %zmm17, %zmm5
|
||||||
|
- - 0.99 - - - - 0.01 - - vaddps %zmm5, %zmm21, %zmm5
|
||||||
|
- - 1.00 - - - - - - - vmulps %zmm3, %zmm15, %zmm3 {%k1} {z}
|
||||||
|
- - - - 1.00 - - - - - movq 176(%r15), %rax
|
||||||
|
- - 0.99 - - - - 0.01 - - vaddps %zmm3, %zmm2, %zmm2
|
||||||
|
- - - 1.00 0.50 0.50 - - - - vmovups (%rax,%rbx), %zmm3
|
||||||
|
- - 0.99 - - - - 0.01 - - vsubps %zmm4, %zmm3, %zmm3
|
||||||
|
- - - - - - 1.00 - - 1.00 vmovups %zmm3, (%rax,%rbx)
|
||||||
|
- - 1.00 - - - - - - - vaddps %zmm2, %zmm1, %zmm1
|
||||||
|
- - - 1.00 0.50 0.50 - - - - vmovups 32(%rax,%rbx), %zmm2
|
||||||
|
- - 1.00 - - - - - - - vsubps %zmm5, %zmm2, %zmm2
|
||||||
|
- - - - - - 1.00 - - 1.00 vmovups %zmm2, 32(%rax,%rbx)
|
||||||
|
- - - 1.00 0.50 0.50 - - - - vmovups 64(%rax,%rbx), %zmm2
|
||||||
|
- - 0.99 - - - - 0.01 - - vsubps %zmm1, %zmm2, %zmm1
|
||||||
|
- - - - - 1.00 1.00 - - - vmovups %zmm1, 64(%rax,%rbx)
|
||||||
|
- - - - - - - - 1.00 - cmpq %rdx, %r10
|
||||||
|
- - - - - - - - 1.00 - je .LBB4_18
|
||||||
|
- - - - 0.50 0.50 - - - - movq 160(%r15), %rdi
|
||||||
|
- - - 1.00 - - - - - - incq %rdx
|
||||||
|
- - - - - - - - 1.00 - jmp .LBB4_8
|
||||||
161
static_analysis/jan/analyses/gromacs-icx-avx512-sp-osaca.out
Normal file
161
static_analysis/jan/analyses/gromacs-icx-avx512-sp-osaca.out
Normal file
@ -0,0 +1,161 @@
|
|||||||
|
Open Source Architecture Code Analyzer (OSACA) - 0.4.12
|
||||||
|
Analyzed file: gromacs-icx-avx512-sp.s
|
||||||
|
Architecture: CSX
|
||||||
|
Timestamp: 2023-02-10 16:31:04
|
||||||
|
|
||||||
|
|
||||||
|
P - Throughput of LOAD operation can be hidden behind a past or future STORE instruction
|
||||||
|
* - Instruction micro-ops not bound to a port
|
||||||
|
X - No throughput/latency information for this instruction in data file
|
||||||
|
|
||||||
|
|
||||||
|
Combined Analysis Report
|
||||||
|
------------------------
|
||||||
|
Port pressure in cycles
|
||||||
|
| 0 - 0DV | 1 | 2 - 2D | 3 - 3D | 4 | 5 | 6 | 7 || CP | LCD |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
1662 | | | | | | | | || | | # pointer_increment=64 0f91ac4f7fe1a70d0c899f7f3e745649
|
||||||
|
1663 | | | | | | | | || | | # LLVM-MCA-BEGIN
|
||||||
|
1664 | | | | | | | | || | | .LBB4_8: # =>This Inner Loop Header: Depth=1
|
||||||
|
1665 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | movslq (%r11,%rdx,4), %rax
|
||||||
|
1666 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || 1.0 | | movq %rax, %rsi
|
||||||
|
1667 | 0.00 | | | | | | 1.00 | || 1.0 | | shlq $5, %rsi
|
||||||
|
1668 | | 1.00 | | | | 0.00 | | || 1.0 | | leaq (%rsi,%rsi,2), %rbx
|
||||||
|
1669 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups (%rdi,%rbx), %zmm15 # AlignMOV convert to UnAlignMOV
|
||||||
|
1670 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 32(%rdi,%rbx), %zmm16 # AlignMOV convert to UnAlignMOV
|
||||||
|
1671 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | vmovups 64(%rdi,%rbx), %zmm27 # AlignMOV convert to UnAlignMOV
|
||||||
|
1672 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 128(%rsp), %zmm1 # 64-byte Reload
|
||||||
|
1673 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm15, %zmm1, %zmm24
|
||||||
|
1674 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 320(%rsp), %zmm1 # 64-byte Reload
|
||||||
|
1675 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm16, %zmm1, %zmm25
|
||||||
|
1676 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubps %zmm27, %zmm9, %zmm26
|
||||||
|
1677 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups (%rsp), %zmm1 # 64-byte Reload
|
||||||
|
1678 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm15, %zmm1, %zmm21
|
||||||
|
1679 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 256(%rsp), %zmm1 # 64-byte Reload
|
||||||
|
1680 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm16, %zmm1, %zmm22
|
||||||
|
1681 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm27, %zmm10, %zmm23
|
||||||
|
1682 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 448(%rsp), %zmm1 # 64-byte Reload
|
||||||
|
1683 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm15, %zmm1, %zmm17
|
||||||
|
1684 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 192(%rsp), %zmm1 # 64-byte Reload
|
||||||
|
1685 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm16, %zmm1, %zmm19
|
||||||
|
1686 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm27, %zmm11, %zmm20
|
||||||
|
1687 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 384(%rsp), %zmm1 # 64-byte Reload
|
||||||
|
1688 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm15, %zmm1, %zmm18
|
||||||
|
1689 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm16, %zmm8, %zmm16
|
||||||
|
1690 | 0.50 | | | | | 0.50 | | || | | vsubps %zmm27, %zmm12, %zmm15
|
||||||
|
1691 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm26, %zmm26, %zmm27
|
||||||
|
1692 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231ps %zmm25, %zmm25, %zmm27 # zmm27 = (zmm25 * zmm25) + zmm27
|
||||||
|
1693 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231ps %zmm24, %zmm24, %zmm27 # zmm27 = (zmm24 * zmm24) + zmm27
|
||||||
|
1694 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm23, %zmm23, %zmm28
|
||||||
|
1695 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm22, %zmm22, %zmm28 # zmm28 = (zmm22 * zmm22) + zmm28
|
||||||
|
1696 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm21, %zmm21, %zmm28 # zmm28 = (zmm21 * zmm21) + zmm28
|
||||||
|
1697 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm20, %zmm20, %zmm29
|
||||||
|
1698 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm19, %zmm19, %zmm29 # zmm29 = (zmm19 * zmm19) + zmm29
|
||||||
|
1699 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm17, %zmm17, %zmm29 # zmm29 = (zmm17 * zmm17) + zmm29
|
||||||
|
1700 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm15, %zmm15, %zmm30
|
||||||
|
1701 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm16, %zmm16, %zmm30 # zmm30 = (zmm16 * zmm16) + zmm30
|
||||||
|
1702 | 2.50 | | | | | 0.50 | | || 8.0 | | vrcp14ps %zmm27, %zmm31
|
||||||
|
1703 | 2.50 | | | | | 0.50 | | || | | vrcp14ps %zmm28, %zmm1
|
||||||
|
1704 | 2.50 | | | | | 0.50 | | || | | vrcp14ps %zmm29, %zmm2
|
||||||
|
1705 | 0.50 | | | | | 0.50 | | || | | vfmadd231ps %zmm18, %zmm18, %zmm30 # zmm30 = (zmm18 * zmm18) + zmm30
|
||||||
|
1706 | 2.50 | | | | | 0.50 | | || | | vrcp14ps %zmm30, %zmm3
|
||||||
|
1707 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm31, %zmm6, %zmm4
|
||||||
|
1708 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm4, %zmm31, %zmm4
|
||||||
|
1709 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm4, %zmm31, %zmm4
|
||||||
|
1710 | 0.50 | | | | | 0.50 | | || 4.0 | | vaddps %zmm13, %zmm4, %zmm5
|
||||||
|
1711 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm7, %zmm31
|
||||||
|
1712 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm5, %zmm31, %zmm5
|
||||||
|
1713 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm6, %zmm31
|
||||||
|
1714 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm1, %zmm31
|
||||||
|
1715 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm1, %zmm31
|
||||||
|
1716 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm5, %zmm4, %zmm4
|
||||||
|
1717 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm13, %zmm31, %zmm5
|
||||||
|
1718 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm7, %zmm1
|
||||||
|
1719 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm5, %zmm1, %zmm1
|
||||||
|
1720 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm6, %zmm5
|
||||||
|
1721 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm5, %zmm2, %zmm5
|
||||||
|
1722 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm5, %zmm2, %zmm5
|
||||||
|
1723 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm31, %zmm1
|
||||||
|
1724 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm13, %zmm5, %zmm31
|
||||||
|
1725 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm7, %zmm2
|
||||||
|
1726 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm2, %zmm2
|
||||||
|
1727 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm3, %zmm6, %zmm31
|
||||||
|
1728 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm3, %zmm31
|
||||||
|
1729 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm31, %zmm3, %zmm31
|
||||||
|
1730 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm5, %zmm2
|
||||||
|
1731 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm13, %zmm31, %zmm5
|
||||||
|
1732 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm3, %zmm7, %zmm3
|
||||||
|
1733 | 1.00 | | | | | 0.00 | | || | | vmulps %zmm5, %zmm3, %zmm3
|
||||||
|
1734 | 1.00 | | | | | 0.00 | | || | | vmulps %zmm3, %zmm31, %zmm3
|
||||||
|
1735 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | xorl %esi, %esi
|
||||||
|
1736 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | xorl %edi, %edi
|
||||||
|
1737 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | testl $2147483647, %eax # imm = 0x7FFFFFFF
|
||||||
|
1738 | 0.00 | | | | | | 1.00 | || | | sete %sil
|
||||||
|
1739 | 0.00 | | | | | | 1.00 | || | | setne %dil
|
||||||
|
1740 | 0.00 | 0.75 | | | | 0.00 | 0.25 | || | | movl $255, %eax
|
||||||
|
1741 | 0.00 | | | | | | 1.00 | || | | cmovel %r8d, %eax
|
||||||
|
1742 | 0.00 | 0.75 | | | | 0.00 | 0.25 | || | | movl $255, %ecx
|
||||||
|
1743 | 0.00 | | | | | | 1.00 | || | | cmovel %r9d, %ecx
|
||||||
|
1744 | 0.00 | 0.25 | | | | 0.00 | 0.75 | || | | xorl $255, %esi
|
||||||
|
1745 | 1.00 | | | | | | | || | | kmovd %esi, %k1
|
||||||
|
1746 | | | | | | 1.00 | | || | | vcmpltps %zmm0, %zmm27, %k1 {%k1}
|
||||||
|
1747 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm14, %zmm4, %zmm4
|
||||||
|
1748 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulps %zmm4, %zmm24, %zmm5 {%k1} {z}
|
||||||
|
1749 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm4, %zmm25, %zmm24 {%k1} {z}
|
||||||
|
1750 | 0.25 | | | | | 0.75 | | || | | vmulps %zmm4, %zmm26, %zmm4 {%k1} {z}
|
||||||
|
1751 | | 1.00 | | | | 0.00 | | || | | leal (%rdi,%rdi,2), %esi
|
||||||
|
1752 | 0.00 | 0.75 | | | | 0.00 | 0.25 | || | | orl $252, %esi
|
||||||
|
1753 | 1.00 | | | | | | | || | | kmovd %esi, %k1
|
||||||
|
1754 | | | | | | 1.00 | | || | | vcmpltps %zmm0, %zmm28, %k1 {%k1}
|
||||||
|
1755 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm14, %zmm1, %zmm1
|
||||||
|
1756 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm21, %zmm21 {%k1} {z}
|
||||||
|
1757 | 0.50 | | | | | 0.50 | | || 4.0 | | vaddps %zmm21, %zmm5, %zmm5
|
||||||
|
1758 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm22, %zmm21 {%k1} {z}
|
||||||
|
1759 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm21, %zmm24, %zmm21
|
||||||
|
1760 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm1, %zmm23, %zmm1 {%k1} {z}
|
||||||
|
1761 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm1, %zmm4, %zmm1
|
||||||
|
1762 | 1.00 | | | | | | | || | | kmovd %eax, %k1
|
||||||
|
1763 | | | | | | 1.00 | | || | | vcmpltps %zmm0, %zmm29, %k1 {%k1}
|
||||||
|
1764 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm14, %zmm2, %zmm2
|
||||||
|
1765 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm17, %zmm4 {%k1} {z}
|
||||||
|
1766 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm19, %zmm17 {%k1} {z}
|
||||||
|
1767 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm2, %zmm20, %zmm2 {%k1} {z}
|
||||||
|
1768 | 1.00 | | | | | | | || | | kmovd %ecx, %k1
|
||||||
|
1769 | | | | | | 1.00 | | || | | vcmpltps %zmm0, %zmm30, %k1 {%k1}
|
||||||
|
1770 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm14, %zmm3, %zmm3
|
||||||
|
1771 | 0.50 | | | | | 0.50 | | || | | vmulps %zmm3, %zmm18, %zmm18 {%k1} {z}
|
||||||
|
1772 | 0.50 | | | | | 0.50 | | || | | vaddps %zmm18, %zmm4, %zmm4
|
||||||
|
1773 | 0.25 | | | | | 0.75 | | || 4.0 | | vaddps %zmm4, %zmm5, %zmm4
|
||||||
|
1774 | 0.00 | | | | | 1.00 | | || | | vmulps %zmm3, %zmm16, %zmm5 {%k1} {z}
|
||||||
|
1775 | 0.00 | | | | | 1.00 | | || | | vaddps %zmm5, %zmm17, %zmm5
|
||||||
|
1776 | 0.00 | | | | | 1.00 | | || | | vaddps %zmm5, %zmm21, %zmm5
|
||||||
|
1777 | 0.00 | | | | | 1.00 | | || | | vmulps %zmm3, %zmm15, %zmm3 {%k1} {z}
|
||||||
|
1778 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | movq 176(%r15), %rax
|
||||||
|
1779 | 0.00 | | | | | 1.00 | | || | | vaddps %zmm3, %zmm2, %zmm2
|
||||||
|
1780 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups (%rax,%rbx), %zmm3 # AlignMOV convert to UnAlignMOV
|
||||||
|
1781 | 0.00 | | | | | 1.00 | | || 4.0 | | vsubps %zmm4, %zmm3, %zmm3
|
||||||
|
1782 | | | 0.50 | 0.50 | 1.00 | | | || 0.0 | | vmovups %zmm3, (%rax,%rbx) # AlignMOV convert to UnAlignMOV
|
||||||
|
1783 | 0.00 | | | | | 1.00 | | || | | vaddps %zmm2, %zmm1, %zmm1
|
||||||
|
1784 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 32(%rax,%rbx), %zmm2 # AlignMOV convert to UnAlignMOV
|
||||||
|
1785 | 0.00 | | | | | 1.00 | | || | | vsubps %zmm5, %zmm2, %zmm2
|
||||||
|
1786 | | | 0.50 | 0.50 | 1.00 | | | || | | vmovups %zmm2, 32(%rax,%rbx) # AlignMOV convert to UnAlignMOV
|
||||||
|
1787 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups 64(%rax,%rbx), %zmm2 # AlignMOV convert to UnAlignMOV
|
||||||
|
1788 | 0.00 | | | | | 1.00 | | || | | vsubps %zmm1, %zmm2, %zmm1
|
||||||
|
1789 | | | 0.50 | 0.50 | 1.00 | | | || | | vmovups %zmm1, 64(%rax,%rbx) # AlignMOV convert to UnAlignMOV
|
||||||
|
1790 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | | cmpq %rdx, %r10
|
||||||
|
1791 | | | | | | | | || | | * je .LBB4_18
|
||||||
|
1792 | | | | | | | | || | | # %bb.9: # in Loop: Header=BB4_8 Depth=1
|
||||||
|
1793 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | movq 160(%r15), %rdi
|
||||||
|
1794 | 0.00 | 1.00 | | | | 0.00 | 0.00 | || | 1.0 | incq %rdx
|
||||||
|
1795 | 0.00 | | | | | | 1.00 | || | | jmp .LBB4_8
|
||||||
|
1796 | | | | | | | | || | | # LLVM-MCA-END
|
||||||
|
|
||||||
|
50.0 9.00 9.50 8.00 9.50 8.00 3.00 50.0 9.00 79.0 1.0
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loop-Carried Dependencies Analysis Report
|
||||||
|
-----------------------------------------
|
||||||
|
1794 | 1.0 | incq %rdx | [1794]
|
||||||
|
|
||||||
88
static_analysis/jan/analyses/lammps-icc-avx2-iaca.out
Normal file
88
static_analysis/jan/analyses/lammps-icc-avx2-iaca.out
Normal file
@ -0,0 +1,88 @@
|
|||||||
|
Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45
|
||||||
|
Analyzed File - lammps-icc-avx2.o
|
||||||
|
Binary Format - 64Bit
|
||||||
|
Architecture - SKX
|
||||||
|
Analysis Type - Throughput
|
||||||
|
|
||||||
|
Throughput Analysis Report
|
||||||
|
--------------------------
|
||||||
|
Block Throughput: 25.58 Cycles Throughput Bottleneck: Backend
|
||||||
|
Loop Count: 22
|
||||||
|
Port Binding In Cycles Per Iteration:
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Cycles | 13.7 8.0 | 13.6 | 5.5 5.5 | 5.5 5.5 | 0.0 | 13.7 | 7.0 | 0.0 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
DV - Divider pipe (on port 0)
|
||||||
|
D - Data fetch pipe (on ports 2 and 3)
|
||||||
|
F - Macro Fusion with the previous instruction occurred
|
||||||
|
* - instruction micro-ops not bound to a port
|
||||||
|
^ - Micro Fusion occurred
|
||||||
|
# - ESP Tracking sync uop was issued
|
||||||
|
@ - SSE instruction followed an AVX256/AVX512 instruction, dozens of cycles penalty is expected
|
||||||
|
X - instruction not supported, was not accounted in Analysis
|
||||||
|
|
||||||
|
| Num Of | Ports pressure in cycles | |
|
||||||
|
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
-----------------------------------------------------------------------------------------
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovdqu xmm0, xmmword ptr [rbx+rdx*4]
|
||||||
|
| 1 | 1.0 | | | | | | | | vmovq rcx, xmm0
|
||||||
|
| 1 | | | | | | 1.0 | | | vpunpckhqdq xmm2, xmm0, xmm0
|
||||||
|
| 1 | 1.0 | | | | | | | | vmovq r15, xmm2
|
||||||
|
| 1* | | | | | | | | | mov r8d, ecx
|
||||||
|
| 1 | | | | | | | 1.0 | | shr rcx, 0x20
|
||||||
|
| 1 | | | | | | 1.0 | | | lea r14d, ptr [rcx+rcx*2]
|
||||||
|
| 1 | | | | | | 1.0 | | | lea r8d, ptr [r8+r8*2]
|
||||||
|
| 1 | | | | | | | 1.0 | | movsxd rcx, r8d
|
||||||
|
| 1 | | | | | | | 1.0 | | movsxd r8, r14d
|
||||||
|
| 1* | | | | | | | | | mov r14d, r15d
|
||||||
|
| 1 | | | | | | | 1.0 | | shr r15, 0x20
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups xmm7, xmmword ptr [r11+rcx*8]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovups xmm6, xmmword ptr [r11+r8*8]
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovq xmm14, qword ptr [r11+rcx*8+0x10]
|
||||||
|
| 1 | | 0.3 | | | | 0.7 | | | lea r14d, ptr [r14+r14*2]
|
||||||
|
| 1 | | | | | | | 1.0 | | movsxd r14, r14d
|
||||||
|
| 1 | | 0.7 | | | | 0.3 | | | lea r15d, ptr [r15+r15*2]
|
||||||
|
| 1 | | | | | | | 1.0 | | movsxd r15, r15d
|
||||||
|
| 2 | | | 0.5 0.5 | 0.5 0.5 | | 1.0 | | | vmovhpd xmm15, xmm14, qword ptr [r11+r8*8+0x10]
|
||||||
|
| 2 | | 1.0 | 0.5 0.5 | 0.5 0.5 | | | | | vinsertf128 ymm1, ymm7, xmmword ptr [r11+r14*8], 0x1
|
||||||
|
| 1 | | | 0.5 0.5 | 0.5 0.5 | | | | | vmovq xmm0, qword ptr [r11+r14*8+0x10]
|
||||||
|
| 2 | | 0.3 | 0.5 0.5 | 0.5 0.5 | | 0.7 | | | vinsertf128 ymm6, ymm6, xmmword ptr [r11+r15*8], 0x1
|
||||||
|
| 2 | | | 0.5 0.5 | 0.5 0.5 | | 1.0 | | | vmovhpd xmm2, xmm0, qword ptr [r11+r15*8+0x10]
|
||||||
|
| 1 | | | | | | 1.0 | | | vunpcklpd ymm14, ymm1, ymm6
|
||||||
|
| 1 | | | | | | 1.0 | | | vunpckhpd ymm1, ymm1, ymm6
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vsubpd ymm6, ymm10, ymm14
|
||||||
|
| 1 | | | | | | 1.0 | | | vinsertf128 ymm7, ymm15, xmm2, 0x1
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vsubpd ymm2, ymm9, ymm1
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vsubpd ymm0, ymm8, ymm7
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vmulpd ymm14, ymm2, ymm2
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vfmadd231pd ymm14, ymm6, ymm6
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vfmadd231pd ymm14, ymm0, ymm0
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vcmppd ymm1, ymm14, ymm5, 0x1
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vpcmpeqd ymm7, ymm7, ymm7
|
||||||
|
| 2 | 1.0 | | | | | 1.0 | | | vptest ymm1, ymm7
|
||||||
|
| 1 | 1.0 8.0 | | | | | | | | vdivpd ymm7, ymm4, ymm14
|
||||||
|
| 2^ | | 1.0 | 0.5 0.5 | 0.5 0.5 | | | | | vmulpd ymm14, ymm7, ymmword ptr [rsp+0x60]
|
||||||
|
| 1 | | 1.0 | | | | | | | vmulpd ymm14, ymm7, ymm14
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vmulpd ymm15, ymm7, ymm14
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vfmsub213pd ymm14, ymm7, ymm3
|
||||||
|
| 2^ | 0.7 | 0.3 | 0.5 0.5 | 0.5 0.5 | | | | | vmulpd ymm7, ymm7, ymmword ptr [rsp+0x40]
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vmulpd ymm15, ymm15, ymm7
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vmulpd ymm7, ymm15, ymm14
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vmulpd ymm6, ymm6, ymm7
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vmulpd ymm2, ymm2, ymm7
|
||||||
|
| 1 | | | | | | 1.0 | | | vandpd ymm6, ymm1, ymm6
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vaddpd ymm13, ymm13, ymm6
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vmulpd ymm6, ymm0, ymm7
|
||||||
|
| 1 | | | | | | 1.0 | | | vandpd ymm0, ymm1, ymm2
|
||||||
|
| 1 | | | | | | 1.0 | | | vandpd ymm1, ymm1, ymm6
|
||||||
|
| 1 | 0.3 | 0.7 | | | | | | | vaddpd ymm12, ymm12, ymm0
|
||||||
|
| 1 | 0.7 | 0.3 | | | | | | | vaddpd ymm11, ymm11, ymm1
|
||||||
|
| 1 | | | | | | | 1.0 | | add rdx, 0x4
|
||||||
|
| 1* | | | | | | | | | cmp rdx, rsi
|
||||||
|
| 0*F | | | | | | | | | jb 0xffffffffffffff02
|
||||||
|
Total Num Of Uops: 62
|
||||||
|
Analysis Notes:
|
||||||
|
Backend allocation was stalled due to unavailable allocation resources.
|
||||||
156
static_analysis/jan/analyses/lammps-icc-avx2-mca-csx.out
Normal file
156
static_analysis/jan/analyses/lammps-icc-avx2-mca-csx.out
Normal file
@ -0,0 +1,156 @@
|
|||||||
|
|
||||||
|
[0] Code Region
|
||||||
|
|
||||||
|
Iterations: 100
|
||||||
|
Instructions: 5600
|
||||||
|
Total Cycles: 2352
|
||||||
|
Total uOps: 6300
|
||||||
|
|
||||||
|
Dispatch Width: 6
|
||||||
|
uOps Per Cycle: 2.68
|
||||||
|
IPC: 2.38
|
||||||
|
Block RThroughput: 10.5
|
||||||
|
|
||||||
|
|
||||||
|
Instruction Info:
|
||||||
|
[1]: #uOps
|
||||||
|
[2]: Latency
|
||||||
|
[3]: RThroughput
|
||||||
|
[4]: MayLoad
|
||||||
|
[5]: MayStore
|
||||||
|
[6]: HasSideEffects (U)
|
||||||
|
|
||||||
|
[1] [2] [3] [4] [5] [6] Instructions:
|
||||||
|
1 6 0.50 * vmovdqu (%rbx,%rdx,4), %xmm0
|
||||||
|
1 2 1.00 vmovq %xmm0, %rcx
|
||||||
|
1 1 1.00 vpunpckhqdq %xmm0, %xmm0, %xmm2
|
||||||
|
1 2 1.00 vmovq %xmm2, %r15
|
||||||
|
1 1 0.25 movl %ecx, %r8d
|
||||||
|
1 1 0.50 shrq $32, %rcx
|
||||||
|
1 1 0.50 leal (%rcx,%rcx,2), %r14d
|
||||||
|
1 1 0.50 leal (%r8,%r8,2), %r8d
|
||||||
|
1 1 0.25 movslq %r8d, %rcx
|
||||||
|
1 1 0.25 movslq %r14d, %r8
|
||||||
|
1 1 0.25 movl %r15d, %r14d
|
||||||
|
1 1 0.50 shrq $32, %r15
|
||||||
|
1 6 0.50 * vmovups (%r11,%rcx,8), %xmm7
|
||||||
|
1 6 0.50 * vmovups (%r11,%r8,8), %xmm6
|
||||||
|
1 5 0.50 * vmovq 16(%r11,%rcx,8), %xmm14
|
||||||
|
1 1 0.50 leal (%r14,%r14,2), %r14d
|
||||||
|
1 1 0.25 movslq %r14d, %r14
|
||||||
|
1 1 0.50 leal (%r15,%r15,2), %r15d
|
||||||
|
1 1 0.25 movslq %r15d, %r15
|
||||||
|
2 6 1.00 * vmovhpd 16(%r11,%r8,8), %xmm14, %xmm15
|
||||||
|
2 7 0.50 * vinsertf128 $1, (%r11,%r14,8), %ymm7, %ymm1
|
||||||
|
1 5 0.50 * vmovq 16(%r11,%r14,8), %xmm0
|
||||||
|
2 7 0.50 * vinsertf128 $1, (%r11,%r15,8), %ymm6, %ymm6
|
||||||
|
2 6 1.00 * vmovhpd 16(%r11,%r15,8), %xmm0, %xmm2
|
||||||
|
1 1 1.00 vunpcklpd %ymm6, %ymm1, %ymm14
|
||||||
|
1 1 1.00 vunpckhpd %ymm6, %ymm1, %ymm1
|
||||||
|
1 4 0.50 vsubpd %ymm14, %ymm10, %ymm6
|
||||||
|
1 3 1.00 vinsertf128 $1, %xmm2, %ymm15, %ymm7
|
||||||
|
1 4 0.50 vsubpd %ymm1, %ymm9, %ymm2
|
||||||
|
1 4 0.50 vsubpd %ymm7, %ymm8, %ymm0
|
||||||
|
1 4 0.50 vmulpd %ymm2, %ymm2, %ymm14
|
||||||
|
1 4 0.50 vfmadd231pd %ymm6, %ymm6, %ymm14
|
||||||
|
1 4 0.50 vfmadd231pd %ymm0, %ymm0, %ymm14
|
||||||
|
1 4 0.50 vcmpltpd %ymm5, %ymm14, %ymm1
|
||||||
|
1 1 0.50 vpcmpeqd %ymm7, %ymm7, %ymm7
|
||||||
|
2 3 1.00 vptest %ymm7, %ymm1
|
||||||
|
1 14 5.00 vdivpd %ymm14, %ymm4, %ymm7
|
||||||
|
2 11 0.50 * vmulpd 96(%rsp), %ymm7, %ymm14
|
||||||
|
1 4 0.50 vmulpd %ymm14, %ymm7, %ymm14
|
||||||
|
1 4 0.50 vmulpd %ymm14, %ymm7, %ymm15
|
||||||
|
1 4 0.50 vfmsub213pd %ymm3, %ymm7, %ymm14
|
||||||
|
2 11 0.50 * vmulpd 64(%rsp), %ymm7, %ymm7
|
||||||
|
1 4 0.50 vmulpd %ymm7, %ymm15, %ymm15
|
||||||
|
1 4 0.50 vmulpd %ymm14, %ymm15, %ymm7
|
||||||
|
1 4 0.50 vmulpd %ymm7, %ymm6, %ymm6
|
||||||
|
1 4 0.50 vmulpd %ymm7, %ymm2, %ymm2
|
||||||
|
1 1 0.33 vandpd %ymm6, %ymm1, %ymm6
|
||||||
|
1 4 0.50 vaddpd %ymm6, %ymm13, %ymm13
|
||||||
|
1 4 0.50 vmulpd %ymm7, %ymm0, %ymm6
|
||||||
|
1 1 0.33 vandpd %ymm2, %ymm1, %ymm0
|
||||||
|
1 1 0.33 vandpd %ymm6, %ymm1, %ymm1
|
||||||
|
1 4 0.50 vaddpd %ymm0, %ymm12, %ymm12
|
||||||
|
1 4 0.50 vaddpd %ymm1, %ymm11, %ymm11
|
||||||
|
1 1 0.25 addq $4, %rdx
|
||||||
|
1 1 0.25 cmpq %rsi, %rdx
|
||||||
|
1 1 0.50 jb ..B1.22
|
||||||
|
|
||||||
|
|
||||||
|
Resources:
|
||||||
|
[0] - SKXDivider
|
||||||
|
[1] - SKXFPDivider
|
||||||
|
[2] - SKXPort0
|
||||||
|
[3] - SKXPort1
|
||||||
|
[4] - SKXPort2
|
||||||
|
[5] - SKXPort3
|
||||||
|
[6] - SKXPort4
|
||||||
|
[7] - SKXPort5
|
||||||
|
[8] - SKXPort6
|
||||||
|
[9] - SKXPort7
|
||||||
|
|
||||||
|
|
||||||
|
Resource pressure per iteration:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9]
|
||||||
|
- 5.00 16.00 14.12 5.50 5.50 - 13.47 8.41 -
|
||||||
|
|
||||||
|
Resource pressure by instruction:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
|
||||||
|
- - - - 0.50 0.50 - - - - vmovdqu (%rbx,%rdx,4), %xmm0
|
||||||
|
- - 1.00 - - - - - - - vmovq %xmm0, %rcx
|
||||||
|
- - - - - - - 1.00 - - vpunpckhqdq %xmm0, %xmm0, %xmm2
|
||||||
|
- - 1.00 - - - - - - - vmovq %xmm2, %r15
|
||||||
|
- - - - - - - - 1.00 - movl %ecx, %r8d
|
||||||
|
- - 0.06 - - - - - 0.94 - shrq $32, %rcx
|
||||||
|
- - - 0.02 - - - 0.98 - - leal (%rcx,%rcx,2), %r14d
|
||||||
|
- - - 0.02 - - - 0.98 - - leal (%r8,%r8,2), %r8d
|
||||||
|
- - 0.47 0.02 - - - - 0.51 - movslq %r8d, %rcx
|
||||||
|
- - 0.46 0.02 - - - 0.01 0.51 - movslq %r14d, %r8
|
||||||
|
- - 0.03 0.01 - - - 0.45 0.51 - movl %r15d, %r14d
|
||||||
|
- - 0.51 - - - - - 0.49 - shrq $32, %r15
|
||||||
|
- - - - 0.49 0.51 - - - - vmovups (%r11,%rcx,8), %xmm7
|
||||||
|
- - - - 0.49 0.51 - - - - vmovups (%r11,%r8,8), %xmm6
|
||||||
|
- - - - 0.52 0.48 - - - - vmovq 16(%r11,%rcx,8), %xmm14
|
||||||
|
- - - 0.02 - - - 0.98 - - leal (%r14,%r14,2), %r14d
|
||||||
|
- - 0.01 0.01 - - - 0.01 0.97 - movslq %r14d, %r14
|
||||||
|
- - - 0.03 - - - 0.97 - - leal (%r15,%r15,2), %r15d
|
||||||
|
- - 0.04 - - - - - 0.96 - movslq %r15d, %r15
|
||||||
|
- - - - 0.07 0.93 - 1.00 - - vmovhpd 16(%r11,%r8,8), %xmm14, %xmm15
|
||||||
|
- - 0.03 0.46 0.49 0.51 - 0.51 - - vinsertf128 $1, (%r11,%r14,8), %ymm7, %ymm1
|
||||||
|
- - - - 0.51 0.49 - - - - vmovq 16(%r11,%r14,8), %xmm0
|
||||||
|
- - 0.47 0.02 0.93 0.07 - 0.51 - - vinsertf128 $1, (%r11,%r15,8), %ymm6, %ymm6
|
||||||
|
- - - - 0.50 0.50 - 1.00 - - vmovhpd 16(%r11,%r15,8), %xmm0, %xmm2
|
||||||
|
- - - - - - - 1.00 - - vunpcklpd %ymm6, %ymm1, %ymm14
|
||||||
|
- - - - - - - 1.00 - - vunpckhpd %ymm6, %ymm1, %ymm1
|
||||||
|
- - 0.01 0.99 - - - - - - vsubpd %ymm14, %ymm10, %ymm6
|
||||||
|
- - - - - - - 1.00 - - vinsertf128 $1, %xmm2, %ymm15, %ymm7
|
||||||
|
- - 0.96 0.04 - - - - - - vsubpd %ymm1, %ymm9, %ymm2
|
||||||
|
- - 0.49 0.51 - - - - - - vsubpd %ymm7, %ymm8, %ymm0
|
||||||
|
- - 0.48 0.52 - - - - - - vmulpd %ymm2, %ymm2, %ymm14
|
||||||
|
- - 0.03 0.97 - - - - - - vfmadd231pd %ymm6, %ymm6, %ymm14
|
||||||
|
- - 0.94 0.06 - - - - - - vfmadd231pd %ymm0, %ymm0, %ymm14
|
||||||
|
- - 0.47 0.53 - - - - - - vcmpltpd %ymm5, %ymm14, %ymm1
|
||||||
|
- - 0.96 0.04 - - - - - - vpcmpeqd %ymm7, %ymm7, %ymm7
|
||||||
|
- - 1.00 - - - - 1.00 - - vptest %ymm7, %ymm1
|
||||||
|
- 5.00 1.00 - - - - - - - vdivpd %ymm14, %ymm4, %ymm7
|
||||||
|
- - 0.93 0.07 0.49 0.51 - - - - vmulpd 96(%rsp), %ymm7, %ymm14
|
||||||
|
- - 0.05 0.95 - - - - - - vmulpd %ymm14, %ymm7, %ymm14
|
||||||
|
- - 0.02 0.98 - - - - - - vmulpd %ymm14, %ymm7, %ymm15
|
||||||
|
- - 0.98 0.02 - - - - - - vfmsub213pd %ymm3, %ymm7, %ymm14
|
||||||
|
- - 0.07 0.93 0.51 0.49 - - - - vmulpd 64(%rsp), %ymm7, %ymm7
|
||||||
|
- - 0.01 0.99 - - - - - - vmulpd %ymm7, %ymm15, %ymm15
|
||||||
|
- - 0.01 0.99 - - - - - - vmulpd %ymm14, %ymm15, %ymm7
|
||||||
|
- - 0.03 0.97 - - - - - - vmulpd %ymm7, %ymm6, %ymm6
|
||||||
|
- - 0.97 0.03 - - - - - - vmulpd %ymm7, %ymm2, %ymm2
|
||||||
|
- - 0.03 0.90 - - - 0.07 - - vandpd %ymm6, %ymm1, %ymm6
|
||||||
|
- - 0.06 0.94 - - - - - - vaddpd %ymm6, %ymm13, %ymm13
|
||||||
|
- - 0.03 0.97 - - - - - - vmulpd %ymm7, %ymm0, %ymm6
|
||||||
|
- - 0.46 0.08 - - - 0.46 - - vandpd %ymm2, %ymm1, %ymm0
|
||||||
|
- - 0.47 0.01 - - - 0.52 - - vandpd %ymm6, %ymm1, %ymm1
|
||||||
|
- - 0.48 0.52 - - - - - - vaddpd %ymm0, %ymm12, %ymm12
|
||||||
|
- - 0.52 0.48 - - - - - - vaddpd %ymm1, %ymm11, %ymm11
|
||||||
|
- - 0.01 - - - - - 0.99 - addq $4, %rdx
|
||||||
|
- - - - - - - 0.02 0.98 - cmpq %rsi, %rdx
|
||||||
|
- - 0.45 - - - - - 0.55 - jb ..B1.22
|
||||||
158
static_analysis/jan/analyses/lammps-icc-avx2-mca-icx.out
Normal file
158
static_analysis/jan/analyses/lammps-icc-avx2-mca-icx.out
Normal file
@ -0,0 +1,158 @@
|
|||||||
|
|
||||||
|
[0] Code Region
|
||||||
|
|
||||||
|
Iterations: 100
|
||||||
|
Instructions: 5600
|
||||||
|
Total Cycles: 2306
|
||||||
|
Total uOps: 6300
|
||||||
|
|
||||||
|
Dispatch Width: 6
|
||||||
|
uOps Per Cycle: 2.73
|
||||||
|
IPC: 2.43
|
||||||
|
Block RThroughput: 10.5
|
||||||
|
|
||||||
|
|
||||||
|
Instruction Info:
|
||||||
|
[1]: #uOps
|
||||||
|
[2]: Latency
|
||||||
|
[3]: RThroughput
|
||||||
|
[4]: MayLoad
|
||||||
|
[5]: MayStore
|
||||||
|
[6]: HasSideEffects (U)
|
||||||
|
|
||||||
|
[1] [2] [3] [4] [5] [6] Instructions:
|
||||||
|
1 6 0.50 * vmovdqu (%rbx,%rdx,4), %xmm0
|
||||||
|
1 2 1.00 vmovq %xmm0, %rcx
|
||||||
|
1 1 0.50 vpunpckhqdq %xmm0, %xmm0, %xmm2
|
||||||
|
1 2 1.00 vmovq %xmm2, %r15
|
||||||
|
1 1 0.25 movl %ecx, %r8d
|
||||||
|
1 1 0.50 shrq $32, %rcx
|
||||||
|
1 1 0.50 leal (%rcx,%rcx,2), %r14d
|
||||||
|
1 1 0.50 leal (%r8,%r8,2), %r8d
|
||||||
|
1 1 0.25 movslq %r8d, %rcx
|
||||||
|
1 1 0.25 movslq %r14d, %r8
|
||||||
|
1 1 0.25 movl %r15d, %r14d
|
||||||
|
1 1 0.50 shrq $32, %r15
|
||||||
|
1 6 0.50 * vmovups (%r11,%rcx,8), %xmm7
|
||||||
|
1 6 0.50 * vmovups (%r11,%r8,8), %xmm6
|
||||||
|
1 5 0.50 * vmovq 16(%r11,%rcx,8), %xmm14
|
||||||
|
1 1 0.50 leal (%r14,%r14,2), %r14d
|
||||||
|
1 1 0.25 movslq %r14d, %r14
|
||||||
|
1 1 0.50 leal (%r15,%r15,2), %r15d
|
||||||
|
1 1 0.25 movslq %r15d, %r15
|
||||||
|
2 6 1.00 * vmovhpd 16(%r11,%r8,8), %xmm14, %xmm15
|
||||||
|
2 7 0.50 * vinsertf128 $1, (%r11,%r14,8), %ymm7, %ymm1
|
||||||
|
1 5 0.50 * vmovq 16(%r11,%r14,8), %xmm0
|
||||||
|
2 7 0.50 * vinsertf128 $1, (%r11,%r15,8), %ymm6, %ymm6
|
||||||
|
2 6 1.00 * vmovhpd 16(%r11,%r15,8), %xmm0, %xmm2
|
||||||
|
1 1 1.00 vunpcklpd %ymm6, %ymm1, %ymm14
|
||||||
|
1 1 1.00 vunpckhpd %ymm6, %ymm1, %ymm1
|
||||||
|
1 4 0.50 vsubpd %ymm14, %ymm10, %ymm6
|
||||||
|
1 3 1.00 vinsertf128 $1, %xmm2, %ymm15, %ymm7
|
||||||
|
1 4 0.50 vsubpd %ymm1, %ymm9, %ymm2
|
||||||
|
1 4 0.50 vsubpd %ymm7, %ymm8, %ymm0
|
||||||
|
1 4 0.50 vmulpd %ymm2, %ymm2, %ymm14
|
||||||
|
1 4 0.50 vfmadd231pd %ymm6, %ymm6, %ymm14
|
||||||
|
1 4 0.50 vfmadd231pd %ymm0, %ymm0, %ymm14
|
||||||
|
1 4 0.50 vcmpltpd %ymm5, %ymm14, %ymm1
|
||||||
|
1 1 0.50 vpcmpeqd %ymm7, %ymm7, %ymm7
|
||||||
|
2 3 1.00 vptest %ymm7, %ymm1
|
||||||
|
1 14 5.00 vdivpd %ymm14, %ymm4, %ymm7
|
||||||
|
2 11 0.50 * vmulpd 96(%rsp), %ymm7, %ymm14
|
||||||
|
1 4 0.50 vmulpd %ymm14, %ymm7, %ymm14
|
||||||
|
1 4 0.50 vmulpd %ymm14, %ymm7, %ymm15
|
||||||
|
1 4 0.50 vfmsub213pd %ymm3, %ymm7, %ymm14
|
||||||
|
2 11 0.50 * vmulpd 64(%rsp), %ymm7, %ymm7
|
||||||
|
1 4 0.50 vmulpd %ymm7, %ymm15, %ymm15
|
||||||
|
1 4 0.50 vmulpd %ymm14, %ymm15, %ymm7
|
||||||
|
1 4 0.50 vmulpd %ymm7, %ymm6, %ymm6
|
||||||
|
1 4 0.50 vmulpd %ymm7, %ymm2, %ymm2
|
||||||
|
1 1 0.33 vandpd %ymm6, %ymm1, %ymm6
|
||||||
|
1 4 0.50 vaddpd %ymm6, %ymm13, %ymm13
|
||||||
|
1 4 0.50 vmulpd %ymm7, %ymm0, %ymm6
|
||||||
|
1 1 0.33 vandpd %ymm2, %ymm1, %ymm0
|
||||||
|
1 1 0.33 vandpd %ymm6, %ymm1, %ymm1
|
||||||
|
1 4 0.50 vaddpd %ymm0, %ymm12, %ymm12
|
||||||
|
1 4 0.50 vaddpd %ymm1, %ymm11, %ymm11
|
||||||
|
1 1 0.25 addq $4, %rdx
|
||||||
|
1 1 0.25 cmpq %rsi, %rdx
|
||||||
|
1 1 0.50 jb ..B1.22
|
||||||
|
|
||||||
|
|
||||||
|
Resources:
|
||||||
|
[0] - ICXDivider
|
||||||
|
[1] - ICXFPDivider
|
||||||
|
[2] - ICXPort0
|
||||||
|
[3] - ICXPort1
|
||||||
|
[4] - ICXPort2
|
||||||
|
[5] - ICXPort3
|
||||||
|
[6] - ICXPort4
|
||||||
|
[7] - ICXPort5
|
||||||
|
[8] - ICXPort6
|
||||||
|
[9] - ICXPort7
|
||||||
|
[10] - ICXPort8
|
||||||
|
[11] - ICXPort9
|
||||||
|
|
||||||
|
|
||||||
|
Resource pressure per iteration:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11]
|
||||||
|
- 5.00 15.12 15.03 5.50 5.50 - 13.45 8.40 - - -
|
||||||
|
|
||||||
|
Resource pressure by instruction:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] Instructions:
|
||||||
|
- - - - 0.50 0.50 - - - - - - vmovdqu (%rbx,%rdx,4), %xmm0
|
||||||
|
- - 1.00 - - - - - - - - - vmovq %xmm0, %rcx
|
||||||
|
- - - 0.46 - - - 0.54 - - - - vpunpckhqdq %xmm0, %xmm0, %xmm2
|
||||||
|
- - 1.00 - - - - - - - - - vmovq %xmm2, %r15
|
||||||
|
- - - - - - - - 1.00 - - - movl %ecx, %r8d
|
||||||
|
- - 0.96 - - - - - 0.04 - - - shrq $32, %rcx
|
||||||
|
- - - 0.01 - - - 0.99 - - - - leal (%rcx,%rcx,2), %r14d
|
||||||
|
- - - 0.03 - - - 0.97 - - - - leal (%r8,%r8,2), %r8d
|
||||||
|
- - 0.48 0.01 - - - - 0.51 - - - movslq %r8d, %rcx
|
||||||
|
- - 0.02 0.02 - - - 0.01 0.95 - - - movslq %r14d, %r8
|
||||||
|
- - 0.02 - - - - - 0.98 - - - movl %r15d, %r14d
|
||||||
|
- - 0.52 - - - - - 0.48 - - - shrq $32, %r15
|
||||||
|
- - - - 0.49 0.51 - - - - - - vmovups (%r11,%rcx,8), %xmm7
|
||||||
|
- - - - 0.49 0.51 - - - - - - vmovups (%r11,%r8,8), %xmm6
|
||||||
|
- - - - 0.52 0.48 - - - - - - vmovq 16(%r11,%rcx,8), %xmm14
|
||||||
|
- - - 0.47 - - - 0.53 - - - - leal (%r14,%r14,2), %r14d
|
||||||
|
- - 0.01 0.01 - - - 0.01 0.97 - - - movslq %r14d, %r14
|
||||||
|
- - - 0.04 - - - 0.96 - - - - leal (%r15,%r15,2), %r15d
|
||||||
|
- - 0.48 - - - - 0.01 0.51 - - - movslq %r15d, %r15
|
||||||
|
- - - - 0.51 0.49 - 1.00 - - - - vmovhpd 16(%r11,%r8,8), %xmm14, %xmm15
|
||||||
|
- - 0.02 0.01 0.95 0.05 - 0.97 - - - - vinsertf128 $1, (%r11,%r14,8), %ymm7, %ymm1
|
||||||
|
- - - - 0.05 0.95 - - - - - - vmovq 16(%r11,%r14,8), %xmm0
|
||||||
|
- - 0.02 0.49 0.49 0.51 - 0.49 - - - - vinsertf128 $1, (%r11,%r15,8), %ymm6, %ymm6
|
||||||
|
- - - - 0.50 0.50 - 1.00 - - - - vmovhpd 16(%r11,%r15,8), %xmm0, %xmm2
|
||||||
|
- - - - - - - 1.00 - - - - vunpcklpd %ymm6, %ymm1, %ymm14
|
||||||
|
- - - - - - - 1.00 - - - - vunpckhpd %ymm6, %ymm1, %ymm1
|
||||||
|
- - 0.47 0.53 - - - - - - - - vsubpd %ymm14, %ymm10, %ymm6
|
||||||
|
- - - - - - - 1.00 - - - - vinsertf128 $1, %xmm2, %ymm15, %ymm7
|
||||||
|
- - 0.50 0.50 - - - - - - - - vsubpd %ymm1, %ymm9, %ymm2
|
||||||
|
- - 0.94 0.06 - - - - - - - - vsubpd %ymm7, %ymm8, %ymm0
|
||||||
|
- - 0.06 0.94 - - - - - - - - vmulpd %ymm2, %ymm2, %ymm14
|
||||||
|
- - 0.04 0.96 - - - - - - - - vfmadd231pd %ymm6, %ymm6, %ymm14
|
||||||
|
- - 0.95 0.05 - - - - - - - - vfmadd231pd %ymm0, %ymm0, %ymm14
|
||||||
|
- - 0.02 0.98 - - - - - - - - vcmpltpd %ymm5, %ymm14, %ymm1
|
||||||
|
- - 0.05 0.95 - - - - - - - - vpcmpeqd %ymm7, %ymm7, %ymm7
|
||||||
|
- - 1.00 - - - - 1.00 - - - - vptest %ymm7, %ymm1
|
||||||
|
- 5.00 1.00 - - - - - - - - - vdivpd %ymm14, %ymm4, %ymm7
|
||||||
|
- - 0.51 0.49 0.49 0.51 - - - - - - vmulpd 96(%rsp), %ymm7, %ymm14
|
||||||
|
- - 0.04 0.96 - - - - - - - - vmulpd %ymm14, %ymm7, %ymm14
|
||||||
|
- - 0.01 0.99 - - - - - - - - vmulpd %ymm14, %ymm7, %ymm15
|
||||||
|
- - 0.99 0.01 - - - - - - - - vfmsub213pd %ymm3, %ymm7, %ymm14
|
||||||
|
- - 0.49 0.51 0.51 0.49 - - - - - - vmulpd 64(%rsp), %ymm7, %ymm7
|
||||||
|
- - 0.01 0.99 - - - - - - - - vmulpd %ymm7, %ymm15, %ymm15
|
||||||
|
- - 0.01 0.99 - - - - - - - - vmulpd %ymm14, %ymm15, %ymm7
|
||||||
|
- - 0.48 0.52 - - - - - - - - vmulpd %ymm7, %ymm6, %ymm6
|
||||||
|
- - 0.52 0.48 - - - - - - - - vmulpd %ymm7, %ymm2, %ymm2
|
||||||
|
- - 0.46 0.02 - - - 0.52 - - - - vandpd %ymm6, %ymm1, %ymm6
|
||||||
|
- - 0.49 0.51 - - - - - - - - vaddpd %ymm6, %ymm13, %ymm13
|
||||||
|
- - 0.48 0.52 - - - - - - - - vmulpd %ymm7, %ymm0, %ymm6
|
||||||
|
- - 0.02 0.52 - - - 0.46 - - - - vandpd %ymm2, %ymm1, %ymm0
|
||||||
|
- - 0.02 - - - - 0.98 - - - - vandpd %ymm6, %ymm1, %ymm1
|
||||||
|
- - 0.49 0.51 - - - - - - - - vaddpd %ymm0, %ymm12, %ymm12
|
||||||
|
- - 0.51 0.49 - - - - - - - - vaddpd %ymm1, %ymm11, %ymm11
|
||||||
|
- - 0.01 - - - - - 0.99 - - - addq $4, %rdx
|
||||||
|
- - 0.01 - - - - 0.01 0.98 - - - cmpq %rsi, %rdx
|
||||||
|
- - 0.01 - - - - - 0.99 - - - jb ..B1.22
|
||||||
97
static_analysis/jan/analyses/lammps-icc-avx2-osaca-csx.out
Normal file
97
static_analysis/jan/analyses/lammps-icc-avx2-osaca-csx.out
Normal file
@ -0,0 +1,97 @@
|
|||||||
|
Open Source Architecture Code Analyzer (OSACA) - 0.4.12
|
||||||
|
Analyzed file: lammps-icc-avx2.s
|
||||||
|
Architecture: CSX
|
||||||
|
Timestamp: 2023-02-10 16:29:58
|
||||||
|
|
||||||
|
|
||||||
|
P - Throughput of LOAD operation can be hidden behind a past or future STORE instruction
|
||||||
|
* - Instruction micro-ops not bound to a port
|
||||||
|
X - No throughput/latency information for this instruction in data file
|
||||||
|
|
||||||
|
|
||||||
|
Combined Analysis Report
|
||||||
|
------------------------
|
||||||
|
Port pressure in cycles
|
||||||
|
| 0 - 0DV | 1 | 2 - 2D | 3 - 3D | 4 | 5 | 6 | 7 || CP | LCD |
|
||||||
|
----------------------------------------------------------------------------------------------------
|
||||||
|
256 | | | | | | | | || | | # pointer_increment=32 724d27eafcb27eabca1528ddfdbdba3e
|
||||||
|
257 | | | | | | | | || | | # LLVM-MCA-BEGIN
|
||||||
|
258 | | | | | | | | || | | ..B1.22: # Preds ..B1.24 ..B1.21
|
||||||
|
259 | | | | | | | | || | | # Execution count [2.50e+01]
|
||||||
|
260 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | vmovdqu (%rbx,%rdx,4), %xmm0 #60.21
|
||||||
|
261 | 1.00 | | | | | | | || 1.0 | | vmovq %xmm0, %rcx #60.21
|
||||||
|
262 | | | | | | 1.000 | | || | | vpunpckhqdq %xmm0, %xmm0, %xmm2 #60.21
|
||||||
|
263 | 1.00 | | | | | | | || | | vmovq %xmm2, %r15 #60.21
|
||||||
|
264 | 0.00 | 0.000 | | | | 0.000 | 1.00 | || 1.0 | | movl %ecx, %r8d #60.21
|
||||||
|
265 | 0.00 | | | | | | 1.00 | || | | shrq $32, %rcx #60.21
|
||||||
|
266 | | 0.500 | | | | 0.500 | | || | | lea (%rcx,%rcx,2), %r14d #61.36
|
||||||
|
267 | | 0.500 | | | | 0.500 | | || 1.0 | | lea (%r8,%r8,2), %r8d #61.36
|
||||||
|
268 | 0.00 | 0.000 | | | | 0.000 | 1.00 | || 1.0 | | movslq %r8d, %rcx #61.36
|
||||||
|
269 | 0.00 | 0.000 | | | | 0.000 | 1.00 | || | | movslq %r14d, %r8 #61.36
|
||||||
|
270 | 0.00 | 0.000 | | | | 0.000 | 1.00 | || | | movl %r15d, %r14d #60.21
|
||||||
|
271 | 0.00 | | | | | | 1.00 | || | | shrq $32, %r15 #60.21
|
||||||
|
272 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | vmovups (%r11,%rcx,8), %xmm7 #61.36
|
||||||
|
273 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovups (%r11,%r8,8), %xmm6 #61.36
|
||||||
|
274 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovq 16(%r11,%rcx,8), %xmm14 #61.36
|
||||||
|
275 | | 0.500 | | | | 0.500 | | || | | lea (%r14,%r14,2), %r14d #61.36
|
||||||
|
276 | 0.00 | 0.000 | | | | 0.000 | 1.00 | || | | movslq %r14d, %r14 #61.36
|
||||||
|
277 | | 0.500 | | | | 0.500 | | || | | lea (%r15,%r15,2), %r15d #61.36
|
||||||
|
278 | 0.00 | 0.000 | | | | 0.000 | 1.00 | || | | movslq %r15d, %r15 #61.36
|
||||||
|
279 | | | 0.50 0.50 | 0.50 0.50 | | 1.000 | | || | | vmovhpd 16(%r11,%r8,8), %xmm14, %xmm15 #61.36
|
||||||
|
280 | | | 0.50 0.50 | 0.50 0.50 | | 1.000 | | || 3.0 | | vinsertf128 $1, (%r11,%r14,8), %ymm7, %ymm1 #61.36
|
||||||
|
281 | | | 0.50 0.50 | 0.50 0.50 | | | | || | | vmovq 16(%r11,%r14,8), %xmm0 #61.36
|
||||||
|
282 | | | 0.50 0.50 | 0.50 0.50 | | 1.000 | | || | | vinsertf128 $1, (%r11,%r15,8), %ymm6, %ymm6 #61.36
|
||||||
|
283 | | | 0.50 0.50 | 0.50 0.50 | | 1.000 | | || | | vmovhpd 16(%r11,%r15,8), %xmm0, %xmm2 #61.36
|
||||||
|
284 | | | | | | 1.000 | | || | | vunpcklpd %ymm6, %ymm1, %ymm14 #61.36
|
||||||
|
285 | | | | | | 1.000 | | || 1.0 | | vunpckhpd %ymm6, %ymm1, %ymm1 #61.36
|
||||||
|
286 | 0.50 | 0.500 | | | | | | || | | vsubpd %ymm14, %ymm10, %ymm6 #61.36
|
||||||
|
287 | | | | | | 1.000 | | || | | vinsertf128 $1, %xmm2, %ymm15, %ymm7 #61.36
|
||||||
|
288 | 0.50 | 0.500 | | | | | | || 4.0 | | vsubpd %ymm1, %ymm9, %ymm2 #62.36
|
||||||
|
289 | 0.50 | 0.500 | | | | | | || | | vsubpd %ymm7, %ymm8, %ymm0 #63.36
|
||||||
|
290 | 0.50 | 0.500 | | | | | | || 4.0 | | vmulpd %ymm2, %ymm2, %ymm14 #64.49
|
||||||
|
291 | 0.50 | 0.500 | | | | | | || 4.0 | | vfmadd231pd %ymm6, %ymm6, %ymm14 #64.49
|
||||||
|
292 | 0.50 | 0.500 | | | | | | || 4.0 | | vfmadd231pd %ymm0, %ymm0, %ymm14 #64.63
|
||||||
|
293 | | | | | | 1.000 | | || | | vcmpltpd %ymm5, %ymm14, %ymm1 #74.22
|
||||||
|
294 | 0.50 | 0.500 | | | | | | || | | vpcmpeqd %ymm7, %ymm7, %ymm7 #74.22
|
||||||
|
295 | 1.00 | | | | | 1.000 | | || | | vptest %ymm7, %ymm1 #74.22
|
||||||
|
296 | | | | | | | | || | | #je ..B1.24 # Prob 50% #74.22
|
||||||
|
297 | | | | | | | | || | | # LOE rax rdx rbx rsi rdi r9 r10 r11 r12 r13d ymm0 ymm1 ymm2 ymm3 ymm4 ymm5 ymm6 ymm8 ymm9 ymm10 ymm11 ymm12 ymm13 ymm14
|
||||||
|
298 | | | | | | | | || | | ..B1.23: # Preds ..B1.22
|
||||||
|
299 | | | | | | | | || | | # Execution count [1.25e+01]
|
||||||
|
300 | 1.00 8.00 | | | | | | | || 15.0 | | vdivpd %ymm14, %ymm4, %ymm7 #75.39
|
||||||
|
301 | 0.50 | 0.500 | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | vmulpd 96(%rsp), %ymm7, %ymm14 #76.38[spill]
|
||||||
|
302 | 0.50 | 0.500 | | | | | | || 4.0 | | vmulpd %ymm14, %ymm7, %ymm14 #76.44
|
||||||
|
303 | 0.50 | 0.500 | | | | | | || 4.0 | | vmulpd %ymm14, %ymm7, %ymm15 #76.50
|
||||||
|
304 | 0.50 | 0.500 | | | | | | || | | vfmsub213pd %ymm3, %ymm7, %ymm14 #77.55
|
||||||
|
305 | 0.50 | 0.500 | 0.50 0.50 | 0.50 0.50 | | | | || | | vmulpd 64(%rsp), %ymm7, %ymm7 #77.55[spill]
|
||||||
|
306 | 0.50 | 0.500 | | | | | | || 4.0 | | vmulpd %ymm7, %ymm15, %ymm15 #77.64
|
||||||
|
307 | 0.50 | 0.500 | | | | | | || 4.0 | | vmulpd %ymm14, %ymm15, %ymm7 #77.70
|
||||||
|
308 | 0.50 | 0.500 | | | | | | || 4.0 | | vmulpd %ymm7, %ymm6, %ymm6 #78.31
|
||||||
|
309 | 0.50 | 0.500 | | | | | | || | | vmulpd %ymm7, %ymm2, %ymm2 #79.31
|
||||||
|
310 | 0.25 | 0.253 | | | | 0.493 | | || 1.0 | | vandpd %ymm6, %ymm1, %ymm6 #78.31
|
||||||
|
311 | 0.50 | 0.500 | | | | | | || 4.0 | | vaddpd %ymm6, %ymm13, %ymm13 #78.17
|
||||||
|
312 | 0.25 | 0.750 | | | | | | || | | vmulpd %ymm7, %ymm0, %ymm6 #80.31
|
||||||
|
313 | 0.16 | 0.417 | | | | 0.423 | | || | | vandpd %ymm2, %ymm1, %ymm0 #79.31
|
||||||
|
314 | 0.00 | 0.250 | | | | 0.750 | | || | | vandpd %ymm6, %ymm1, %ymm1 #80.31
|
||||||
|
315 | 0.00 | 1.000 | | | | | | || | | vaddpd %ymm0, %ymm12, %ymm12 #79.17
|
||||||
|
316 | 0.50 | 0.500 | | | | | | || | 4.0 | vaddpd %ymm1, %ymm11, %ymm11 #80.17
|
||||||
|
317 | | | | | | | | || | | # LOE rax rdx rbx rsi rdi r9 r10 r11 r12 r13d ymm3 ymm4 ymm5 ymm8 ymm9 ymm10 ymm11 ymm12 ymm13
|
||||||
|
318 | | | | | | | | || | | ..B1.24: # Preds ..B1.23 ..B1.22
|
||||||
|
319 | | | | | | | | || | | # Execution count [2.50e+01]
|
||||||
|
320 | 0.00 | 0.000 | | | | -0.01 | 1.00 | || | | addq $4, %rdx #59.9
|
||||||
|
321 | 0.00 | -0.01 | | | | 0.000 | 1.00 | || | | cmpq %rsi, %rdx #59.9
|
||||||
|
322 | | | | | | | | || | | * jb ..B1.22 # Prob 82% #59.9
|
||||||
|
323 | | | | | | | | || | | # LLVM-MCA-END
|
||||||
|
|
||||||
|
13.7 8.00 13.66 5.50 5.50 5.50 5.50 13.66 10.0 76.0 4.0
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loop-Carried Dependencies Analysis Report
|
||||||
|
-----------------------------------------
|
||||||
|
316 | 4.0 | vaddpd %ymm1, %ymm11, %ymm11 #80.17| [316]
|
||||||
|
315 | 4.0 | vaddpd %ymm0, %ymm12, %ymm12 #79.17| [315]
|
||||||
|
311 | 4.0 | vaddpd %ymm6, %ymm13, %ymm13 #78.17| [311]
|
||||||
|
320 | 1.0 | addq $4, %rdx #59.9| [320]
|
||||||
|
|
||||||
97
static_analysis/jan/analyses/lammps-icc-avx2-osaca-icx.out
Normal file
97
static_analysis/jan/analyses/lammps-icc-avx2-osaca-icx.out
Normal file
@ -0,0 +1,97 @@
|
|||||||
|
Open Source Architecture Code Analyzer (OSACA) - 0.4.12
|
||||||
|
Analyzed file: lammps-icc-avx2.s
|
||||||
|
Architecture: ICX
|
||||||
|
Timestamp: 2023-02-10 16:29:48
|
||||||
|
|
||||||
|
|
||||||
|
P - Throughput of LOAD operation can be hidden behind a past or future STORE instruction
|
||||||
|
* - Instruction micro-ops not bound to a port
|
||||||
|
X - No throughput/latency information for this instruction in data file
|
||||||
|
|
||||||
|
|
||||||
|
Combined Analysis Report
|
||||||
|
------------------------
|
||||||
|
Port pressure in cycles
|
||||||
|
| 0 - 0DV | 1 - 1DV | 2 - 2D | 3 - 3D | 4 | 5 | 6 | 7 | 8 | 9 || CP | LCD |
|
||||||
|
-----------------------------------------------------------------------------------------------------------------------
|
||||||
|
256 | | | | | | | | | | || | | # pointer_increment=32 724d27eafcb27eabca1528ddfdbdba3e
|
||||||
|
257 | | | | | | | | | | || | | # LLVM-MCA-BEGIN
|
||||||
|
258 | | | | | | | | | | || | | ..B1.22: # Preds ..B1.24 ..B1.21
|
||||||
|
259 | | | | | | | | | | || | | # Execution count [2.50e+01]
|
||||||
|
260 | | | 0.50 0.50 | 0.50 0.50 | | | | | | || 5.0 | | vmovdqu (%rbx,%rdx,4), %xmm0 #60.21
|
||||||
|
261 | 1.00 | | | | | | | | | || 1.0 | | vmovq %xmm0, %rcx #60.21
|
||||||
|
262 | | 0.50 | | | | 0.50 | | | | || | | vpunpckhqdq %xmm0, %xmm0, %xmm2 #60.21
|
||||||
|
263 | 1.00 | | | | | | | | | || | | vmovq %xmm2, %r15 #60.21
|
||||||
|
264 | 0.37 | 0.00 | | | | 0.25 | 0.38 | | | || 1.0 | | movl %ecx, %r8d #60.21
|
||||||
|
265 | 0.50 | | | | | | 0.50 | | | || | | shrq $32, %rcx #60.21
|
||||||
|
266 | 0.13 | 0.00 | | | | 0.00 | 0.87 | | | || | | lea (%rcx,%rcx,2), %r14d #61.36
|
||||||
|
267 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || 6.0 | | lea (%r8,%r8,2), %r8d #61.36
|
||||||
|
268 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || 1.0 | | movslq %r8d, %rcx #61.36
|
||||||
|
269 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || | | movslq %r14d, %r8 #61.36
|
||||||
|
270 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || | | movl %r15d, %r14d #60.21
|
||||||
|
271 | 0.00 | | | | | | 1.00 | | | || | | shrq $32, %r15 #60.21
|
||||||
|
272 | | | 0.50 0.50 | 0.50 0.50 | | | | | | || 5.0 | | vmovups (%r11,%rcx,8), %xmm7 #61.36
|
||||||
|
273 | | | 0.50 0.50 | 0.50 0.50 | | | | | | || | | vmovups (%r11,%r8,8), %xmm6 #61.36
|
||||||
|
274 | | | 0.50 0.50 | 0.50 0.50 | | | | | | || | | vmovq 16(%r11,%rcx,8), %xmm14 #61.36
|
||||||
|
275 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || | | lea (%r14,%r14,2), %r14d #61.36
|
||||||
|
276 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || | | movslq %r14d, %r14 #61.36
|
||||||
|
277 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || | | lea (%r15,%r15,2), %r15d #61.36
|
||||||
|
278 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || | | movslq %r15d, %r15 #61.36
|
||||||
|
279 | | | 0.50 0.50 | 0.50 0.50 | | 1.00 | | | | || | | vmovhpd 16(%r11,%r8,8), %xmm14, %xmm15 #61.36
|
||||||
|
280 | | | 0.50 0.50 | 0.50 0.50 | | 1.00 | | | | || 3.0 | | vinsertf128 $1, (%r11,%r14,8), %ymm7, %ymm1 #61.36
|
||||||
|
281 | | | 0.50 0.50 | 0.50 0.50 | | | | | | || | | vmovq 16(%r11,%r14,8), %xmm0 #61.36
|
||||||
|
282 | | | 0.50 0.50 | 0.50 0.50 | | 1.00 | | | | || | | vinsertf128 $1, (%r11,%r15,8), %ymm6, %ymm6 #61.36
|
||||||
|
283 | | | 0.50 0.50 | 0.50 0.50 | | 1.00 | | | | || | | vmovhpd 16(%r11,%r15,8), %xmm0, %xmm2 #61.36
|
||||||
|
284 | | | | | | 1.00 | | | | || | | vunpcklpd %ymm6, %ymm1, %ymm14 #61.36
|
||||||
|
285 | | | | | | 1.00 | | | | || 1.0 | | vunpckhpd %ymm6, %ymm1, %ymm1 #61.36
|
||||||
|
286 | 0.50 | 0.50 | | | | | | | | || | | vsubpd %ymm14, %ymm10, %ymm6 #61.36
|
||||||
|
287 | | | | | | 1.00 | | | | || | | vinsertf128 $1, %xmm2, %ymm15, %ymm7 #61.36
|
||||||
|
288 | 0.50 | 0.50 | | | | | | | | || 4.0 | | vsubpd %ymm1, %ymm9, %ymm2 #62.36
|
||||||
|
289 | 0.50 | 0.50 | | | | | | | | || | | vsubpd %ymm7, %ymm8, %ymm0 #63.36
|
||||||
|
290 | 0.50 | 0.50 | | | | | | | | || 4.0 | | vmulpd %ymm2, %ymm2, %ymm14 #64.49
|
||||||
|
291 | 0.50 | 0.50 | | | | | | | | || 4.0 | | vfmadd231pd %ymm6, %ymm6, %ymm14 #64.49
|
||||||
|
292 | 0.75 | 0.25 | | | | | | | | || 4.0 | | vfmadd231pd %ymm0, %ymm0, %ymm14 #64.63
|
||||||
|
293 | 0.00 | | | | | 1.00 | | | | || | | vcmpltpd %ymm5, %ymm14, %ymm1 #74.22
|
||||||
|
294 | 0.50 | 0.50 | | | | | | | | || | | vpcmpeqd %ymm7, %ymm7, %ymm7 #74.22
|
||||||
|
295 | 1.00 | | | | | 1.00 | | | | || | | vptest %ymm7, %ymm1 #74.22
|
||||||
|
296 | | | | | | | | | | || | | #je ..B1.24 # Prob 50% #74.22
|
||||||
|
297 | | | | | | | | | | || | | # LOE rax rdx rbx rsi rdi r9 r10 r11 r12 r13d ymm0 ymm1 ymm2 ymm3 ymm4 ymm5 ymm6 ymm8 ymm9 ymm10 ymm11 ymm12 ymm13 ymm14
|
||||||
|
298 | | | | | | | | | | || | | ..B1.23: # Preds ..B1.22
|
||||||
|
299 | | | | | | | | | | || | | # Execution count [1.25e+01]
|
||||||
|
300 | 1.00 8.00 | | | | | | | | | || 13.0 | | vdivpd %ymm14, %ymm4, %ymm7 #75.39
|
||||||
|
301 | 0.50 | 0.50 | 0.50 0.50 | 0.50 0.50 | | | | | | || 4.0 | | vmulpd 96(%rsp), %ymm7, %ymm14 #76.38[spill]
|
||||||
|
302 | 0.50 | 0.50 | | | | | | | | || 4.0 | | vmulpd %ymm14, %ymm7, %ymm14 #76.44
|
||||||
|
303 | 0.50 | 0.50 | | | | | | | | || 4.0 | | vmulpd %ymm14, %ymm7, %ymm15 #76.50
|
||||||
|
304 | 0.50 | 0.50 | | | | | | | | || | | vfmsub213pd %ymm3, %ymm7, %ymm14 #77.55
|
||||||
|
305 | 0.50 | 0.50 | 0.50 0.50 | 0.50 0.50 | | | | | | || | | vmulpd 64(%rsp), %ymm7, %ymm7 #77.55[spill]
|
||||||
|
306 | 0.50 | 0.50 | | | | | | | | || 4.0 | | vmulpd %ymm7, %ymm15, %ymm15 #77.64
|
||||||
|
307 | 0.50 | 0.50 | | | | | | | | || 4.0 | | vmulpd %ymm14, %ymm15, %ymm7 #77.70
|
||||||
|
308 | 0.50 | 0.50 | | | | | | | | || 4.0 | | vmulpd %ymm7, %ymm6, %ymm6 #78.31
|
||||||
|
309 | 0.00 | 1.00 | | | | | | | | || | | vmulpd %ymm7, %ymm2, %ymm2 #79.31
|
||||||
|
310 | 0.00 | 0.00 | | | | 1.00 | | | | || 1.0 | | vandpd %ymm6, %ymm1, %ymm6 #78.31
|
||||||
|
311 | 0.00 | 1.00 | | | | | | | | || 4.0 | | vaddpd %ymm6, %ymm13, %ymm13 #78.17
|
||||||
|
312 | 0.00 | 1.00 | | | | | | | | || | | vmulpd %ymm7, %ymm0, %ymm6 #80.31
|
||||||
|
313 | 0.00 | 0.00 | | | | 1.00 | | | | || | | vandpd %ymm2, %ymm1, %ymm0 #79.31
|
||||||
|
314 | 0.00 | 0.00 | | | | 1.00 | | | | || | | vandpd %ymm6, %ymm1, %ymm1 #80.31
|
||||||
|
315 | 0.00 | 1.00 | | | | | | | | || | | vaddpd %ymm0, %ymm12, %ymm12 #79.17
|
||||||
|
316 | 0.00 | 1.00 | | | | | | | | || | 4.0 | vaddpd %ymm1, %ymm11, %ymm11 #80.17
|
||||||
|
317 | | | | | | | | | | || | | # LOE rax rdx rbx rsi rdi r9 r10 r11 r12 r13d ymm3 ymm4 ymm5 ymm8 ymm9 ymm10 ymm11 ymm12 ymm13
|
||||||
|
318 | | | | | | | | | | || | | ..B1.24: # Preds ..B1.23 ..B1.22
|
||||||
|
319 | | | | | | | | | | || | | # Execution count [2.50e+01]
|
||||||
|
320 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || | | addq $4, %rdx #59.9
|
||||||
|
321 | 0.00 | 0.00 | | | | 0.00 | 1.00 | | | || | | cmpq %rsi, %rdx #59.9
|
||||||
|
322 | | | | | | | | | | || | | * jb ..B1.22 # Prob 82% #59.9
|
||||||
|
323 | | | | | | | | | | || | | # LLVM-MCA-END
|
||||||
|
|
||||||
|
12.8 8.00 12.8 5.50 5.50 5.50 5.50 12.8 12.8 81 4.0
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loop-Carried Dependencies Analysis Report
|
||||||
|
-----------------------------------------
|
||||||
|
316 | 4.0 | vaddpd %ymm1, %ymm11, %ymm11 #80.17| [316]
|
||||||
|
315 | 4.0 | vaddpd %ymm0, %ymm12, %ymm12 #79.17| [315]
|
||||||
|
311 | 4.0 | vaddpd %ymm6, %ymm13, %ymm13 #78.17| [311]
|
||||||
|
320 | 1.0 | addq $4, %rdx #59.9| [320]
|
||||||
|
|
||||||
75
static_analysis/jan/analyses/lammps-icc-avx512-iaca.out
Normal file
75
static_analysis/jan/analyses/lammps-icc-avx512-iaca.out
Normal file
@ -0,0 +1,75 @@
|
|||||||
|
Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45
|
||||||
|
Analyzed File - lammps-icc-avx512.o
|
||||||
|
Binary Format - 64Bit
|
||||||
|
Architecture - SKX
|
||||||
|
Analysis Type - Throughput
|
||||||
|
|
||||||
|
Throughput Analysis Report
|
||||||
|
--------------------------
|
||||||
|
Block Throughput: 30.89 Cycles Throughput Bottleneck: Backend
|
||||||
|
Loop Count: 22
|
||||||
|
Port Binding In Cycles Per Iteration:
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
| Cycles | 19.0 0.0 | 4.0 | 13.0 13.0 | 13.0 13.0 | 0.0 | 17.0 | 4.0 | 0.0 |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
|
||||||
|
DV - Divider pipe (on port 0)
|
||||||
|
D - Data fetch pipe (on ports 2 and 3)
|
||||||
|
F - Macro Fusion with the previous instruction occurred
|
||||||
|
* - instruction micro-ops not bound to a port
|
||||||
|
^ - Micro Fusion occurred
|
||||||
|
# - ESP Tracking sync uop was issued
|
||||||
|
@ - SSE instruction followed an AVX256/AVX512 instruction, dozens of cycles penalty is expected
|
||||||
|
X - instruction not supported, was not accounted in Analysis
|
||||||
|
|
||||||
|
| Num Of | Ports pressure in cycles | |
|
||||||
|
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
|
||||||
|
-----------------------------------------------------------------------------------------
|
||||||
|
| 1 | | | | | | 1.0 | | | vpcmpgtd k5, ymm3, ymm4
|
||||||
|
| 1 | | 1.0 | | | | | | | vpaddd ymm4, ymm4, ymm15
|
||||||
|
| 2 | | 1.0 | 1.0 1.0 | | | | | | vmovdqu32 ymm17{k5}{z}, ymmword ptr [r10+r15*4]
|
||||||
|
| 1 | | 1.0 | | | | | | | vpaddd ymm18, ymm17, ymm17
|
||||||
|
| 1 | | | | | | | 1.0 | | add r15, 0x8
|
||||||
|
| 1 | | 1.0 | | | | | | | vpaddd ymm19, ymm17, ymm18
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovw k2, k5
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovw k3, k5
|
||||||
|
| 1 | 1.0 | | | | | | | | kmovw k1, k5
|
||||||
|
| 1* | | | | | | | | | vpxord zmm21, zmm21, zmm21
|
||||||
|
| 1* | | | | | | | | | vpxord zmm20, zmm20, zmm20
|
||||||
|
| 1* | | | | | | | | | vpxord zmm22, zmm22, zmm22
|
||||||
|
| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm21, k2, zmmword ptr [rbx+ymm19*8+0x8]
|
||||||
|
| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm20, k3, zmmword ptr [rbx+ymm19*8]
|
||||||
|
| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm22, k1, zmmword ptr [rbx+ymm19*8+0x10]
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm18, zmm1, zmm21
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm17, zmm2, zmm20
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm19, zmm0, zmm22
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm31, zmm18, zmm18
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm31, zmm17, zmm17
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm31, zmm19, zmm19
|
||||||
|
| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm30, zmm31
|
||||||
|
| 1 | | | | | | 1.0 | | | vcmppd k6{k5}, zmm31, zmm14, 0x1
|
||||||
|
| 1 | | | | | | 1.0 | | | vfpclasspd k0, zmm30, 0x1e
|
||||||
|
| 1* | | | | | | | | | vmovaps zmm23, zmm31
|
||||||
|
| 2^ | 1.0 | | | 1.0 1.0 | | | | | vfnmadd213pd zmm23, zmm30, qword ptr [rip]{1to8}
|
||||||
|
| 1 | 1.0 | | | | | | | | knotw k4, k0
|
||||||
|
| 1 | | | | | | 1.0 | | | vmulpd zmm24, zmm23, zmm23
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd213pd zmm30{k4}, zmm23, zmm30
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd213pd zmm30{k4}, zmm24, zmm30
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm25, zmm30, zmm13
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm27, zmm30, zmm12
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm28, zmm30, zmm25
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm26, zmm30, zmm28
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmsub213pd zmm30, zmm28, zmm5
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm29, zmm26, zmm27
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm23, zmm29, zmm30
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm10{k6}, zmm23, zmm17
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm9{k6}, zmm23, zmm18
|
||||||
|
| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm8{k6}, zmm23, zmm19
|
||||||
|
| 1* | | | | | | | | | cmp r15, r14
|
||||||
|
| 0*F | | | | | | | | | jb 0xffffffffffffff0c
|
||||||
|
Total Num Of Uops: 57
|
||||||
|
Analysis Notes:
|
||||||
|
Backend allocation was stalled due to unavailable allocation resources.
|
||||||
|
There were bubbles in the frontend.
|
||||||
128
static_analysis/jan/analyses/lammps-icc-avx512-mca-csx.out
Normal file
128
static_analysis/jan/analyses/lammps-icc-avx512-mca-csx.out
Normal file
@ -0,0 +1,128 @@
|
|||||||
|
|
||||||
|
[0] Code Region
|
||||||
|
|
||||||
|
Iterations: 100
|
||||||
|
Instructions: 4200
|
||||||
|
Total Cycles: 2465
|
||||||
|
Total uOps: 5800
|
||||||
|
|
||||||
|
Dispatch Width: 6
|
||||||
|
uOps Per Cycle: 2.35
|
||||||
|
IPC: 1.70
|
||||||
|
Block RThroughput: 13.0
|
||||||
|
|
||||||
|
|
||||||
|
Instruction Info:
|
||||||
|
[1]: #uOps
|
||||||
|
[2]: Latency
|
||||||
|
[3]: RThroughput
|
||||||
|
[4]: MayLoad
|
||||||
|
[5]: MayStore
|
||||||
|
[6]: HasSideEffects (U)
|
||||||
|
|
||||||
|
[1] [2] [3] [4] [5] [6] Instructions:
|
||||||
|
1 4 1.00 vpcmpgtd %ymm4, %ymm3, %k5
|
||||||
|
1 1 0.33 vpaddd %ymm15, %ymm4, %ymm4
|
||||||
|
2 8 0.50 * vmovdqu32 (%r10,%r15,4), %ymm17 {%k5} {z}
|
||||||
|
1 1 0.33 vpaddd %ymm17, %ymm17, %ymm18
|
||||||
|
1 1 0.25 addq $8, %r15
|
||||||
|
1 1 0.33 vpaddd %ymm18, %ymm17, %ymm19
|
||||||
|
1 1 1.00 kmovw %k5, %k2
|
||||||
|
1 1 1.00 kmovw %k5, %k3
|
||||||
|
1 1 1.00 kmovw %k5, %k1
|
||||||
|
1 0 0.17 vpxord %zmm21, %zmm21, %zmm21
|
||||||
|
1 0 0.17 vpxord %zmm20, %zmm20, %zmm20
|
||||||
|
1 0 0.17 vpxord %zmm22, %zmm22, %zmm22
|
||||||
|
5 21 4.00 * vgatherdpd 8(%rbx,%ymm19,8), %zmm21 {%k2}
|
||||||
|
5 21 4.00 * vgatherdpd (%rbx,%ymm19,8), %zmm20 {%k3}
|
||||||
|
5 21 4.00 * vgatherdpd 16(%rbx,%ymm19,8), %zmm22 {%k1}
|
||||||
|
1 4 0.50 vsubpd %zmm21, %zmm1, %zmm18
|
||||||
|
1 4 0.50 vsubpd %zmm20, %zmm2, %zmm17
|
||||||
|
1 4 0.50 vsubpd %zmm22, %zmm0, %zmm19
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm18, %zmm31
|
||||||
|
1 4 0.50 vfmadd231pd %zmm17, %zmm17, %zmm31
|
||||||
|
1 4 0.50 vfmadd231pd %zmm19, %zmm19, %zmm31
|
||||||
|
3 4 2.00 vrcp14pd %zmm31, %zmm30
|
||||||
|
1 4 1.00 vcmpltpd %zmm14, %zmm31, %k6 {%k5}
|
||||||
|
1 4 1.00 vfpclasspd $30, %zmm30, %k0
|
||||||
|
1 1 0.50 vmovaps %zmm31, %zmm23
|
||||||
|
2 11 0.50 * vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm30, %zmm23
|
||||||
|
1 1 1.00 knotw %k0, %k4
|
||||||
|
1 4 0.50 vmulpd %zmm23, %zmm23, %zmm24
|
||||||
|
1 4 0.50 vfmadd213pd %zmm30, %zmm23, %zmm30 {%k4}
|
||||||
|
1 4 0.50 vfmadd213pd %zmm30, %zmm24, %zmm30 {%k4}
|
||||||
|
1 4 0.50 vmulpd %zmm13, %zmm30, %zmm25
|
||||||
|
1 4 0.50 vmulpd %zmm12, %zmm30, %zmm27
|
||||||
|
1 4 0.50 vmulpd %zmm25, %zmm30, %zmm28
|
||||||
|
1 4 0.50 vmulpd %zmm28, %zmm30, %zmm26
|
||||||
|
1 4 0.50 vfmsub213pd %zmm5, %zmm28, %zmm30
|
||||||
|
1 4 0.50 vmulpd %zmm27, %zmm26, %zmm29
|
||||||
|
1 4 0.50 vmulpd %zmm30, %zmm29, %zmm23
|
||||||
|
1 4 0.50 vfmadd231pd %zmm17, %zmm23, %zmm10 {%k6}
|
||||||
|
1 4 0.50 vfmadd231pd %zmm18, %zmm23, %zmm9 {%k6}
|
||||||
|
1 4 0.50 vfmadd231pd %zmm19, %zmm23, %zmm8 {%k6}
|
||||||
|
1 1 0.25 cmpq %r14, %r15
|
||||||
|
1 1 0.50 jb ..B1.16
|
||||||
|
|
||||||
|
|
||||||
|
Resources:
|
||||||
|
[0] - SKXDivider
|
||||||
|
[1] - SKXFPDivider
|
||||||
|
[2] - SKXPort0
|
||||||
|
[3] - SKXPort1
|
||||||
|
[4] - SKXPort2
|
||||||
|
[5] - SKXPort3
|
||||||
|
[6] - SKXPort4
|
||||||
|
[7] - SKXPort5
|
||||||
|
[8] - SKXPort6
|
||||||
|
[9] - SKXPort7
|
||||||
|
|
||||||
|
|
||||||
|
Resource pressure per iteration:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9]
|
||||||
|
- - 19.02 6.79 12.64 13.36 - 16.03 5.16 -
|
||||||
|
|
||||||
|
Resource pressure by instruction:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] Instructions:
|
||||||
|
- - - - - - - 1.00 - - vpcmpgtd %ymm4, %ymm3, %k5
|
||||||
|
- - 0.28 0.72 - - - - - - vpaddd %ymm15, %ymm4, %ymm4
|
||||||
|
- - 0.14 0.71 0.55 0.45 - 0.15 - - vmovdqu32 (%r10,%r15,4), %ymm17 {%k5} {z}
|
||||||
|
- - - 0.97 - - - 0.03 - - vpaddd %ymm17, %ymm17, %ymm18
|
||||||
|
- - 0.14 0.41 - - - 0.13 0.32 - addq $8, %r15
|
||||||
|
- - - 0.99 - - - 0.01 - - vpaddd %ymm18, %ymm17, %ymm19
|
||||||
|
- - 1.00 - - - - - - - kmovw %k5, %k2
|
||||||
|
- - 1.00 - - - - - - - kmovw %k5, %k3
|
||||||
|
- - 1.00 - - - - - - - kmovw %k5, %k1
|
||||||
|
- - - - - - - - - - vpxord %zmm21, %zmm21, %zmm21
|
||||||
|
- - - - - - - - - - vpxord %zmm20, %zmm20, %zmm20
|
||||||
|
- - - - - - - - - - vpxord %zmm22, %zmm22, %zmm22
|
||||||
|
- - 1.00 0.99 3.52 4.48 - 0.01 1.00 - vgatherdpd 8(%rbx,%ymm19,8), %zmm21 {%k2}
|
||||||
|
- - 1.00 0.99 4.48 3.52 - 0.01 1.00 - vgatherdpd (%rbx,%ymm19,8), %zmm20 {%k3}
|
||||||
|
- - 1.00 1.00 3.52 4.48 - - 1.00 - vgatherdpd 16(%rbx,%ymm19,8), %zmm22 {%k1}
|
||||||
|
- - 0.02 - - - - 0.98 - - vsubpd %zmm21, %zmm1, %zmm18
|
||||||
|
- - 0.17 - - - - 0.83 - - vsubpd %zmm20, %zmm2, %zmm17
|
||||||
|
- - 0.18 - - - - 0.82 - - vsubpd %zmm22, %zmm0, %zmm19
|
||||||
|
- - 0.01 - - - - 0.99 - - vmulpd %zmm18, %zmm18, %zmm31
|
||||||
|
- - 0.69 - - - - 0.31 - - vfmadd231pd %zmm17, %zmm17, %zmm31
|
||||||
|
- - 0.68 - - - - 0.32 - - vfmadd231pd %zmm19, %zmm19, %zmm31
|
||||||
|
- - 2.00 - - - - 1.00 - - vrcp14pd %zmm31, %zmm30
|
||||||
|
- - - - - - - 1.00 - - vcmpltpd %zmm14, %zmm31, %k6 {%k5}
|
||||||
|
- - - - - - - 1.00 - - vfpclasspd $30, %zmm30, %k0
|
||||||
|
- - 0.83 - - - - 0.17 - - vmovaps %zmm31, %zmm23
|
||||||
|
- - 1.00 - 0.57 0.43 - - - - vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm30, %zmm23
|
||||||
|
- - 1.00 - - - - - - - knotw %k0, %k4
|
||||||
|
- - 0.44 - - - - 0.56 - - vmulpd %zmm23, %zmm23, %zmm24
|
||||||
|
- - 0.56 - - - - 0.44 - - vfmadd213pd %zmm30, %zmm23, %zmm30 {%k4}
|
||||||
|
- - 0.55 - - - - 0.45 - - vfmadd213pd %zmm30, %zmm24, %zmm30 {%k4}
|
||||||
|
- - 0.69 - - - - 0.31 - - vmulpd %zmm13, %zmm30, %zmm25
|
||||||
|
- - 0.31 - - - - 0.69 - - vmulpd %zmm12, %zmm30, %zmm27
|
||||||
|
- - 0.56 - - - - 0.44 - - vmulpd %zmm25, %zmm30, %zmm28
|
||||||
|
- - 0.02 - - - - 0.98 - - vmulpd %zmm28, %zmm30, %zmm26
|
||||||
|
- - 0.98 - - - - 0.02 - - vfmsub213pd %zmm5, %zmm28, %zmm30
|
||||||
|
- - 0.30 - - - - 0.70 - - vmulpd %zmm27, %zmm26, %zmm29
|
||||||
|
- - 0.16 - - - - 0.84 - - vmulpd %zmm30, %zmm29, %zmm23
|
||||||
|
- - 0.17 - - - - 0.83 - - vfmadd231pd %zmm17, %zmm23, %zmm10 {%k6}
|
||||||
|
- - 0.83 - - - - 0.17 - - vfmadd231pd %zmm18, %zmm23, %zmm9 {%k6}
|
||||||
|
- - 0.17 - - - - 0.83 - - vfmadd231pd %zmm19, %zmm23, %zmm8 {%k6}
|
||||||
|
- - - 0.01 - - - 0.01 0.98 - cmpq %r14, %r15
|
||||||
|
- - 0.14 - - - - - 0.86 - jb ..B1.16
|
||||||
130
static_analysis/jan/analyses/lammps-icc-avx512-mca-icx.out
Normal file
130
static_analysis/jan/analyses/lammps-icc-avx512-mca-icx.out
Normal file
@ -0,0 +1,130 @@
|
|||||||
|
|
||||||
|
[0] Code Region
|
||||||
|
|
||||||
|
Iterations: 100
|
||||||
|
Instructions: 4200
|
||||||
|
Total Cycles: 2465
|
||||||
|
Total uOps: 5800
|
||||||
|
|
||||||
|
Dispatch Width: 6
|
||||||
|
uOps Per Cycle: 2.35
|
||||||
|
IPC: 1.70
|
||||||
|
Block RThroughput: 13.0
|
||||||
|
|
||||||
|
|
||||||
|
Instruction Info:
|
||||||
|
[1]: #uOps
|
||||||
|
[2]: Latency
|
||||||
|
[3]: RThroughput
|
||||||
|
[4]: MayLoad
|
||||||
|
[5]: MayStore
|
||||||
|
[6]: HasSideEffects (U)
|
||||||
|
|
||||||
|
[1] [2] [3] [4] [5] [6] Instructions:
|
||||||
|
1 4 1.00 vpcmpgtd %ymm4, %ymm3, %k5
|
||||||
|
1 1 0.33 vpaddd %ymm15, %ymm4, %ymm4
|
||||||
|
2 8 0.50 * vmovdqu32 (%r10,%r15,4), %ymm17 {%k5} {z}
|
||||||
|
1 1 0.33 vpaddd %ymm17, %ymm17, %ymm18
|
||||||
|
1 1 0.25 addq $8, %r15
|
||||||
|
1 1 0.33 vpaddd %ymm18, %ymm17, %ymm19
|
||||||
|
1 1 1.00 kmovw %k5, %k2
|
||||||
|
1 1 1.00 kmovw %k5, %k3
|
||||||
|
1 1 1.00 kmovw %k5, %k1
|
||||||
|
1 0 0.17 vpxord %zmm21, %zmm21, %zmm21
|
||||||
|
1 0 0.17 vpxord %zmm20, %zmm20, %zmm20
|
||||||
|
1 0 0.17 vpxord %zmm22, %zmm22, %zmm22
|
||||||
|
5 21 4.00 * vgatherdpd 8(%rbx,%ymm19,8), %zmm21 {%k2}
|
||||||
|
5 21 4.00 * vgatherdpd (%rbx,%ymm19,8), %zmm20 {%k3}
|
||||||
|
5 21 4.00 * vgatherdpd 16(%rbx,%ymm19,8), %zmm22 {%k1}
|
||||||
|
1 4 0.50 vsubpd %zmm21, %zmm1, %zmm18
|
||||||
|
1 4 0.50 vsubpd %zmm20, %zmm2, %zmm17
|
||||||
|
1 4 0.50 vsubpd %zmm22, %zmm0, %zmm19
|
||||||
|
1 4 0.50 vmulpd %zmm18, %zmm18, %zmm31
|
||||||
|
1 4 0.50 vfmadd231pd %zmm17, %zmm17, %zmm31
|
||||||
|
1 4 0.50 vfmadd231pd %zmm19, %zmm19, %zmm31
|
||||||
|
3 4 2.00 vrcp14pd %zmm31, %zmm30
|
||||||
|
1 4 1.00 vcmpltpd %zmm14, %zmm31, %k6 {%k5}
|
||||||
|
1 4 1.00 vfpclasspd $30, %zmm30, %k0
|
||||||
|
1 1 0.50 vmovaps %zmm31, %zmm23
|
||||||
|
2 11 0.50 * vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm30, %zmm23
|
||||||
|
1 1 1.00 knotw %k0, %k4
|
||||||
|
1 4 0.50 vmulpd %zmm23, %zmm23, %zmm24
|
||||||
|
1 4 0.50 vfmadd213pd %zmm30, %zmm23, %zmm30 {%k4}
|
||||||
|
1 4 0.50 vfmadd213pd %zmm30, %zmm24, %zmm30 {%k4}
|
||||||
|
1 4 0.50 vmulpd %zmm13, %zmm30, %zmm25
|
||||||
|
1 4 0.50 vmulpd %zmm12, %zmm30, %zmm27
|
||||||
|
1 4 0.50 vmulpd %zmm25, %zmm30, %zmm28
|
||||||
|
1 4 0.50 vmulpd %zmm28, %zmm30, %zmm26
|
||||||
|
1 4 0.50 vfmsub213pd %zmm5, %zmm28, %zmm30
|
||||||
|
1 4 0.50 vmulpd %zmm27, %zmm26, %zmm29
|
||||||
|
1 4 0.50 vmulpd %zmm30, %zmm29, %zmm23
|
||||||
|
1 4 0.50 vfmadd231pd %zmm17, %zmm23, %zmm10 {%k6}
|
||||||
|
1 4 0.50 vfmadd231pd %zmm18, %zmm23, %zmm9 {%k6}
|
||||||
|
1 4 0.50 vfmadd231pd %zmm19, %zmm23, %zmm8 {%k6}
|
||||||
|
1 1 0.25 cmpq %r14, %r15
|
||||||
|
1 1 0.50 jb ..B1.16
|
||||||
|
|
||||||
|
|
||||||
|
Resources:
|
||||||
|
[0] - ICXDivider
|
||||||
|
[1] - ICXFPDivider
|
||||||
|
[2] - ICXPort0
|
||||||
|
[3] - ICXPort1
|
||||||
|
[4] - ICXPort2
|
||||||
|
[5] - ICXPort3
|
||||||
|
[6] - ICXPort4
|
||||||
|
[7] - ICXPort5
|
||||||
|
[8] - ICXPort6
|
||||||
|
[9] - ICXPort7
|
||||||
|
[10] - ICXPort8
|
||||||
|
[11] - ICXPort9
|
||||||
|
|
||||||
|
|
||||||
|
Resource pressure per iteration:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11]
|
||||||
|
- - 19.02 6.79 12.64 13.36 - 16.03 5.16 - - -
|
||||||
|
|
||||||
|
Resource pressure by instruction:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] Instructions:
|
||||||
|
- - - - - - - 1.00 - - - - vpcmpgtd %ymm4, %ymm3, %k5
|
||||||
|
- - 0.28 0.72 - - - - - - - - vpaddd %ymm15, %ymm4, %ymm4
|
||||||
|
- - 0.14 0.71 0.55 0.45 - 0.15 - - - - vmovdqu32 (%r10,%r15,4), %ymm17 {%k5} {z}
|
||||||
|
- - - 0.97 - - - 0.03 - - - - vpaddd %ymm17, %ymm17, %ymm18
|
||||||
|
- - 0.14 0.41 - - - 0.13 0.32 - - - addq $8, %r15
|
||||||
|
- - - 0.99 - - - 0.01 - - - - vpaddd %ymm18, %ymm17, %ymm19
|
||||||
|
- - 1.00 - - - - - - - - - kmovw %k5, %k2
|
||||||
|
- - 1.00 - - - - - - - - - kmovw %k5, %k3
|
||||||
|
- - 1.00 - - - - - - - - - kmovw %k5, %k1
|
||||||
|
- - - - - - - - - - - - vpxord %zmm21, %zmm21, %zmm21
|
||||||
|
- - - - - - - - - - - - vpxord %zmm20, %zmm20, %zmm20
|
||||||
|
- - - - - - - - - - - - vpxord %zmm22, %zmm22, %zmm22
|
||||||
|
- - 1.00 0.99 3.52 4.48 - 0.01 1.00 - - - vgatherdpd 8(%rbx,%ymm19,8), %zmm21 {%k2}
|
||||||
|
- - 1.00 0.99 4.48 3.52 - 0.01 1.00 - - - vgatherdpd (%rbx,%ymm19,8), %zmm20 {%k3}
|
||||||
|
- - 1.00 1.00 3.52 4.48 - - 1.00 - - - vgatherdpd 16(%rbx,%ymm19,8), %zmm22 {%k1}
|
||||||
|
- - 0.02 - - - - 0.98 - - - - vsubpd %zmm21, %zmm1, %zmm18
|
||||||
|
- - 0.17 - - - - 0.83 - - - - vsubpd %zmm20, %zmm2, %zmm17
|
||||||
|
- - 0.18 - - - - 0.82 - - - - vsubpd %zmm22, %zmm0, %zmm19
|
||||||
|
- - 0.01 - - - - 0.99 - - - - vmulpd %zmm18, %zmm18, %zmm31
|
||||||
|
- - 0.69 - - - - 0.31 - - - - vfmadd231pd %zmm17, %zmm17, %zmm31
|
||||||
|
- - 0.68 - - - - 0.32 - - - - vfmadd231pd %zmm19, %zmm19, %zmm31
|
||||||
|
- - 2.00 - - - - 1.00 - - - - vrcp14pd %zmm31, %zmm30
|
||||||
|
- - - - - - - 1.00 - - - - vcmpltpd %zmm14, %zmm31, %k6 {%k5}
|
||||||
|
- - - - - - - 1.00 - - - - vfpclasspd $30, %zmm30, %k0
|
||||||
|
- - 0.83 - - - - 0.17 - - - - vmovaps %zmm31, %zmm23
|
||||||
|
- - 1.00 - 0.57 0.43 - - - - - - vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm30, %zmm23
|
||||||
|
- - 1.00 - - - - - - - - - knotw %k0, %k4
|
||||||
|
- - 0.44 - - - - 0.56 - - - - vmulpd %zmm23, %zmm23, %zmm24
|
||||||
|
- - 0.56 - - - - 0.44 - - - - vfmadd213pd %zmm30, %zmm23, %zmm30 {%k4}
|
||||||
|
- - 0.55 - - - - 0.45 - - - - vfmadd213pd %zmm30, %zmm24, %zmm30 {%k4}
|
||||||
|
- - 0.69 - - - - 0.31 - - - - vmulpd %zmm13, %zmm30, %zmm25
|
||||||
|
- - 0.31 - - - - 0.69 - - - - vmulpd %zmm12, %zmm30, %zmm27
|
||||||
|
- - 0.56 - - - - 0.44 - - - - vmulpd %zmm25, %zmm30, %zmm28
|
||||||
|
- - 0.02 - - - - 0.98 - - - - vmulpd %zmm28, %zmm30, %zmm26
|
||||||
|
- - 0.98 - - - - 0.02 - - - - vfmsub213pd %zmm5, %zmm28, %zmm30
|
||||||
|
- - 0.30 - - - - 0.70 - - - - vmulpd %zmm27, %zmm26, %zmm29
|
||||||
|
- - 0.16 - - - - 0.84 - - - - vmulpd %zmm30, %zmm29, %zmm23
|
||||||
|
- - 0.17 - - - - 0.83 - - - - vfmadd231pd %zmm17, %zmm23, %zmm10 {%k6}
|
||||||
|
- - 0.83 - - - - 0.17 - - - - vfmadd231pd %zmm18, %zmm23, %zmm9 {%k6}
|
||||||
|
- - 0.17 - - - - 0.83 - - - - vfmadd231pd %zmm19, %zmm23, %zmm8 {%k6}
|
||||||
|
- - - 0.01 - - - 0.01 0.98 - - - cmpq %r14, %r15
|
||||||
|
- - 0.14 - - - - - 0.86 - - - jb ..B1.16
|
||||||
77
static_analysis/jan/analyses/lammps-icc-avx512-osaca-csx.out
Normal file
77
static_analysis/jan/analyses/lammps-icc-avx512-osaca-csx.out
Normal file
@ -0,0 +1,77 @@
|
|||||||
|
Open Source Architecture Code Analyzer (OSACA) - 0.4.12
|
||||||
|
Analyzed file: lammps-icc-avx512.s
|
||||||
|
Architecture: CSX
|
||||||
|
Timestamp: 2023-02-10 16:30:08
|
||||||
|
|
||||||
|
|
||||||
|
P - Throughput of LOAD operation can be hidden behind a past or future STORE instruction
|
||||||
|
* - Instruction micro-ops not bound to a port
|
||||||
|
X - No throughput/latency information for this instruction in data file
|
||||||
|
|
||||||
|
|
||||||
|
Combined Analysis Report
|
||||||
|
------------------------
|
||||||
|
Port pressure in cycles
|
||||||
|
| 0 - 0DV | 1 | 2 - 2D | 3 - 3D | 4 | 5 | 6 | 7 || CP | LCD |
|
||||||
|
--------------------------------------------------------------------------------------------------
|
||||||
|
200 | | | | | | | | || | | # pointer_increment=64 1303ca335e79351a96cfc07b8b9ec9d4
|
||||||
|
201 | | | | | | | | || | | # LLVM-MCA-BEGIN
|
||||||
|
202 | | | | | | | | || | | ..B1.16: # Preds ..B1.16 ..B1.15
|
||||||
|
203 | | | | | | | | || | | # Execution count [2.50e+01]
|
||||||
|
204 | | | | | | 1.00 | | || | | vpcmpgtd %ymm4, %ymm3, %k5 #59.9
|
||||||
|
205 | 0.00 | 1.00 | | | | 0.00 | | || | | vpaddd %ymm15, %ymm4, %ymm4 #59.9
|
||||||
|
206 | 0.00 | 1.00 | 0.50 0.50 | 0.50 0.50 | | 0.00 | | || 0.0 | | vmovdqu32 (%r10,%r15,4), %ymm17{%k5}{z} #60.21
|
||||||
|
207 | 0.00 | 1.00 | | | | 0.00 | | || 1.0 | | vpaddd %ymm17, %ymm17, %ymm18 #61.36
|
||||||
|
208 | 0.00 | 0.16 | | | | 0.00 | 0.84 | || | | addq $8, %r15 #59.9
|
||||||
|
209 | 0.00 | 1.00 | | | | 0.00 | | || 1.0 | | vpaddd %ymm18, %ymm17, %ymm19 #61.36
|
||||||
|
210 | 1.00 | | | | | | | || | | kmovw %k5, %k2 #61.36
|
||||||
|
211 | 1.00 | | | | | | | || | | kmovw %k5, %k3 #61.36
|
||||||
|
212 | 1.00 | | | | | | | || | | kmovw %k5, %k1 #61.36
|
||||||
|
213 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm21, %zmm21, %zmm21 #61.36
|
||||||
|
214 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm20, %zmm20, %zmm20 #61.36
|
||||||
|
215 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm22, %zmm22, %zmm22 #61.36
|
||||||
|
216 | 1.25 | 0.75 | 5.00 5.00 | 5.00 5.00 | | 0.25 | 0.75 | || 24.0 | | vgatherdpd 8(%rbx,%ymm19,8), %zmm21{%k2} #61.36
|
||||||
|
217 | 1.25 | 0.25 | 5.00 5.00 | 5.00 5.00 | | 0.25 | 1.25 | || | | vgatherdpd (%rbx,%ymm19,8), %zmm20{%k3} #61.36
|
||||||
|
218 | 1.25 | 0.09 | 5.00 5.00 | 5.00 5.00 | | 0.25 | 1.41 | || | | vgatherdpd 16(%rbx,%ymm19,8), %zmm22{%k1} #61.36
|
||||||
|
219 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubpd %zmm21, %zmm1, %zmm18 #62.36
|
||||||
|
220 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm20, %zmm2, %zmm17 #61.36
|
||||||
|
221 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm22, %zmm0, %zmm19 #63.36
|
||||||
|
222 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm18, %zmm18, %zmm31 #64.49
|
||||||
|
223 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm17, %zmm17, %zmm31 #64.49
|
||||||
|
224 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm19, %zmm19, %zmm31 #64.63
|
||||||
|
225 | 2.50 | | | | | 0.50 | | || 8.0 | | vrcp14pd %zmm31, %zmm30 #75.39
|
||||||
|
226 | | | | | | 1.00 | | || | | vcmppd $1, %zmm14, %zmm31, %k6{%k5} #74.22
|
||||||
|
227 | | | | | | 1.00 | | || | | vfpclasspd $30, %zmm30, %k0 #75.39
|
||||||
|
228 | | | | | | | | || | | * vmovaps %zmm31, %zmm23 #75.39
|
||||||
|
229 | 0.50 | | 0.50 0.50 | 0.50 0.50 | | 0.50 | | || 4.0 | | vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm30, %zmm23 #75.39
|
||||||
|
230 | 1.00 | | | | | | | || | | knotw %k0, %k4 #75.39
|
||||||
|
231 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm23, %zmm23, %zmm24 #75.39
|
||||||
|
232 | 0.50 | | | | | 0.50 | | || | | vfmadd213pd %zmm30, %zmm23, %zmm30{%k4} #75.39
|
||||||
|
233 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd213pd %zmm30, %zmm24, %zmm30{%k4} #75.39
|
||||||
|
234 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm13, %zmm30, %zmm25 #76.38
|
||||||
|
235 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm12, %zmm30, %zmm27 #77.55
|
||||||
|
236 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm25, %zmm30, %zmm28 #76.44
|
||||||
|
237 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm28, %zmm30, %zmm26 #76.50
|
||||||
|
238 | 0.00 | | | | | 1.00 | | || | | vfmsub213pd %zmm5, %zmm28, %zmm30 #77.55
|
||||||
|
239 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm27, %zmm26, %zmm29 #77.64
|
||||||
|
240 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm30, %zmm29, %zmm23 #77.70
|
||||||
|
241 | 0.00 | | | | | 1.00 | | || 4.0 | | vfmadd231pd %zmm17, %zmm23, %zmm10{%k6} #78.17
|
||||||
|
242 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm18, %zmm23, %zmm9{%k6} #79.17
|
||||||
|
243 | 0.00 | | | | | 1.00 | | || | 4.0 | vfmadd231pd %zmm19, %zmm23, %zmm8{%k6} #80.17
|
||||||
|
244 | 0.00 | 0.00 | | | | 0.00 | 1.00 | || | | cmpq %r14, %r15 #59.9
|
||||||
|
245 | | | | | | | | || | | * jb ..B1.16 # Prob 82% #59.9
|
||||||
|
246 | | | | | | | | || | | # LLVM-MCA-END
|
||||||
|
|
||||||
|
18.8 5.25 16.0 16.0 16.0 16.0 18.8 5.25 86.0 4.0
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loop-Carried Dependencies Analysis Report
|
||||||
|
-----------------------------------------
|
||||||
|
243 | 4.0 | vfmadd231pd %zmm19, %zmm23, %zmm8{%k6} #80.17| [243]
|
||||||
|
242 | 4.0 | vfmadd231pd %zmm18, %zmm23, %zmm9{%k6} #79.17| [242]
|
||||||
|
241 | 4.0 | vfmadd231pd %zmm17, %zmm23, %zmm10{%k6} #78.17| [241]
|
||||||
|
208 | 1.0 | addq $8, %r15 #59.9| [208]
|
||||||
|
205 | 1.0 | vpaddd %ymm15, %ymm4, %ymm4 #59.9| [205]
|
||||||
|
|
||||||
77
static_analysis/jan/analyses/lammps-icc-avx512-osaca-icx.out
Normal file
77
static_analysis/jan/analyses/lammps-icc-avx512-osaca-icx.out
Normal file
@ -0,0 +1,77 @@
|
|||||||
|
Open Source Architecture Code Analyzer (OSACA) - 0.4.12
|
||||||
|
Analyzed file: lammps-icc-avx512.s
|
||||||
|
Architecture: ICX
|
||||||
|
Timestamp: 2023-02-10 16:29:42
|
||||||
|
|
||||||
|
|
||||||
|
P - Throughput of LOAD operation can be hidden behind a past or future STORE instruction
|
||||||
|
* - Instruction micro-ops not bound to a port
|
||||||
|
X - No throughput/latency information for this instruction in data file
|
||||||
|
|
||||||
|
|
||||||
|
Combined Analysis Report
|
||||||
|
------------------------
|
||||||
|
Port pressure in cycles
|
||||||
|
| 0 - 0DV | 1 - 1DV | 2 - 2D | 3 - 3D | 4 | 5 | 6 | 7 | 8 | 9 || CP | LCD |
|
||||||
|
------------------------------------------------------------------------------------------------------------------------
|
||||||
|
200 | | | | | | | | | | || | | # pointer_increment=64 1303ca335e79351a96cfc07b8b9ec9d4
|
||||||
|
201 | | | | | | | | | | || | | # LLVM-MCA-BEGIN
|
||||||
|
202 | | | | | | | | | | || | | ..B1.16: # Preds ..B1.16 ..B1.15
|
||||||
|
203 | | | | | | | | | | || | | # Execution count [2.50e+01]
|
||||||
|
204 | | | | | | 1.000 | | | | || | | vpcmpgtd %ymm4, %ymm3, %k5 #59.9
|
||||||
|
205 | 0.00 | 1.00 | | | | 0.000 | | | | || | | vpaddd %ymm15, %ymm4, %ymm4 #59.9
|
||||||
|
206 | | | 0.50 0.50 | 0.50 0.50 | | | | | | || 5.0 | | vmovdqu32 (%r10,%r15,4), %ymm17{%k5}{z} #60.21
|
||||||
|
207 | 0.00 | 1.00 | | | | 0.000 | | | | || 1.0 | | vpaddd %ymm17, %ymm17, %ymm18 #61.36
|
||||||
|
208 | 0.00 | 0.00 | | | | 0.000 | 1.00 | | | || | | addq $8, %r15 #59.9
|
||||||
|
209 | 0.00 | 1.00 | | | | 0.000 | | | | || 1.0 | | vpaddd %ymm18, %ymm17, %ymm19 #61.36
|
||||||
|
210 | 1.00 | | | | | | | | | || | | kmovw %k5, %k2 #61.36
|
||||||
|
211 | 1.00 | | | | | | | | | || | | kmovw %k5, %k3 #61.36
|
||||||
|
212 | 1.00 | | | | | | | | | || | | kmovw %k5, %k1 #61.36
|
||||||
|
213 | 0.50 | | | | | 0.500 | | | | || | | vpxord %zmm21, %zmm21, %zmm21 #61.36
|
||||||
|
214 | 0.24 | | | | | 0.760 | | | | || | | vpxord %zmm20, %zmm20, %zmm20 #61.36
|
||||||
|
215 | 0.50 | | | | | 0.500 | | | | || | | vpxord %zmm22, %zmm22, %zmm22 #61.36
|
||||||
|
216 | 0.67 | 2.33 | 7.00 7.00 | 7.00 7.00 | | 0.000 | | | | || 24.0 | | vgatherdpd 8(%rbx,%ymm19,8), %zmm21{%k2} #61.36
|
||||||
|
217 | 0.67 | 2.33 | 7.00 7.00 | 7.00 7.00 | | 0.000 | | | | || | | vgatherdpd (%rbx,%ymm19,8), %zmm20{%k3} #61.36
|
||||||
|
218 | 0.67 | 2.33 | 7.00 7.00 | 7.00 7.00 | | 0.000 | | | | || | | vgatherdpd 16(%rbx,%ymm19,8), %zmm22{%k1} #61.36
|
||||||
|
219 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vsubpd %zmm21, %zmm1, %zmm18 #62.36
|
||||||
|
220 | 0.50 | | | | | 0.500 | | | | || | | vsubpd %zmm20, %zmm2, %zmm17 #61.36
|
||||||
|
221 | 0.50 | | | | | 0.500 | | | | || | | vsubpd %zmm22, %zmm0, %zmm19 #63.36
|
||||||
|
222 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vmulpd %zmm18, %zmm18, %zmm31 #64.49
|
||||||
|
223 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vfmadd231pd %zmm17, %zmm17, %zmm31 #64.49
|
||||||
|
224 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vfmadd231pd %zmm19, %zmm19, %zmm31 #64.63
|
||||||
|
225 | 2.50 | | | | | 0.500 | | | | || 6.0 | | vrcp14pd %zmm31, %zmm30 #75.39
|
||||||
|
226 | | | | | | 1.000 | | | | || | | vcmppd $1, %zmm14, %zmm31, %k6{%k5} #74.22
|
||||||
|
227 | | | | | | 1.000 | | | | || | | vfpclasspd $30, %zmm30, %k0 #75.39
|
||||||
|
228 | 0.50 | | | | | 0.500 | | | | || | | vmovaps %zmm31, %zmm23 #75.39
|
||||||
|
229 | 0.50 | | 0.50 0.50 | 0.50 0.50 | | 0.500 | | | | || 4.0 | | vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm30, %zmm23 #75.39
|
||||||
|
230 | 1.00 | | | | | | | | | || | | knotw %k0, %k4 #75.39
|
||||||
|
231 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vmulpd %zmm23, %zmm23, %zmm24 #75.39
|
||||||
|
232 | 0.50 | | | | | 0.500 | | | | || | | vfmadd213pd %zmm30, %zmm23, %zmm30{%k4} #75.39
|
||||||
|
233 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vfmadd213pd %zmm30, %zmm24, %zmm30{%k4} #75.39
|
||||||
|
234 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vmulpd %zmm13, %zmm30, %zmm25 #76.38
|
||||||
|
235 | 0.50 | | | | | 0.500 | | | | || | | vmulpd %zmm12, %zmm30, %zmm27 #77.55
|
||||||
|
236 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vmulpd %zmm25, %zmm30, %zmm28 #76.44
|
||||||
|
237 | 0.50 | | | | | 0.500 | | | | || 4.0 | | vmulpd %zmm28, %zmm30, %zmm26 #76.50
|
||||||
|
238 | 0.50 | | | | | 0.500 | | | | || | | vfmsub213pd %zmm5, %zmm28, %zmm30 #77.55
|
||||||
|
239 | 0.25 | | | | | 0.750 | | | | || 4.0 | | vmulpd %zmm27, %zmm26, %zmm29 #77.64
|
||||||
|
240 | 0.00 | | | | | 1.000 | | | | || 4.0 | | vmulpd %zmm30, %zmm29, %zmm23 #77.70
|
||||||
|
241 | 0.00 | | | | | 1.000 | | | | || 4.0 | | vfmadd231pd %zmm17, %zmm23, %zmm10{%k6} #78.17
|
||||||
|
242 | 0.00 | | | | | 1.000 | | | | || | | vfmadd231pd %zmm18, %zmm23, %zmm9{%k6} #79.17
|
||||||
|
243 | 0.00 | | | | | 1.000 | | | | || | 4.0 | vfmadd231pd %zmm19, %zmm23, %zmm8{%k6} #80.17
|
||||||
|
244 | 0.00 | 0.00 | | | | -0.01 | 1.00 | | | || | | cmpq %r14, %r15 #59.9
|
||||||
|
245 | | | | | | | | | | || | | * jb ..B1.16 # Prob 82% #59.9
|
||||||
|
246 | | | | | | | | | | || | | # LLVM-MCA-END
|
||||||
|
|
||||||
|
18.0 9.98 22.0 22.0 22.0 22.0 18.00 2.00 89 4.0
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loop-Carried Dependencies Analysis Report
|
||||||
|
-----------------------------------------
|
||||||
|
243 | 4.0 | vfmadd231pd %zmm19, %zmm23, %zmm8{%k6} #80.17| [243]
|
||||||
|
242 | 4.0 | vfmadd231pd %zmm18, %zmm23, %zmm9{%k6} #79.17| [242]
|
||||||
|
241 | 4.0 | vfmadd231pd %zmm17, %zmm23, %zmm10{%k6} #78.17| [241]
|
||||||
|
208 | 1.0 | addq $8, %r15 #59.9| [208]
|
||||||
|
205 | 1.0 | vpaddd %ymm15, %ymm4, %ymm4 #59.9| [205]
|
||||||
|
|
||||||
197
static_analysis/jan/analyses/lammps-icx-avx2zen-mca.out
Normal file
197
static_analysis/jan/analyses/lammps-icx-avx2zen-mca.out
Normal file
@ -0,0 +1,197 @@
|
|||||||
|
|
||||||
|
[0] Code Region
|
||||||
|
|
||||||
|
Iterations: 100
|
||||||
|
Instructions: 7000
|
||||||
|
Total Cycles: 3866
|
||||||
|
Total uOps: 7900
|
||||||
|
|
||||||
|
Dispatch Width: 6
|
||||||
|
uOps Per Cycle: 2.04
|
||||||
|
IPC: 1.81
|
||||||
|
Block RThroughput: 21.5
|
||||||
|
|
||||||
|
|
||||||
|
Instruction Info:
|
||||||
|
[1]: #uOps
|
||||||
|
[2]: Latency
|
||||||
|
[3]: RThroughput
|
||||||
|
[4]: MayLoad
|
||||||
|
[5]: MayStore
|
||||||
|
[6]: HasSideEffects (U)
|
||||||
|
|
||||||
|
[1] [2] [3] [4] [5] [6] Instructions:
|
||||||
|
1 8 0.50 * vpbroadcastd .LCPI0_1(%rip), %xmm1
|
||||||
|
1 10 0.50 * vpmulld (%r11,%rbp,4), %xmm1, %xmm11
|
||||||
|
2 4 1.50 vpmovsxdq %xmm11, %ymm1
|
||||||
|
1 1 0.50 vpsllq $3, %ymm1, %ymm1
|
||||||
|
1 1 0.25 vpaddq %ymm1, %ymm3, %ymm1
|
||||||
|
1 1 1.00 vmovq %xmm1, %r14
|
||||||
|
2 1 1.00 vpextrq $1, %xmm1, %r9
|
||||||
|
1 4 1.00 vextracti128 $1, %ymm1, %xmm1
|
||||||
|
1 8 0.50 * vmovsd (%r14), %xmm2
|
||||||
|
1 8 0.50 * vpsubd .LCPI0_5, %xmm11, %xmm6
|
||||||
|
2 4 1.50 vpmovsxdq %xmm6, %ymm6
|
||||||
|
1 1 0.50 vpsllq $3, %ymm6, %ymm6
|
||||||
|
1 1 1.00 vmovq %xmm1, %rdi
|
||||||
|
1 1 0.25 vpaddq %ymm6, %ymm3, %ymm6
|
||||||
|
1 1 1.00 vmovq %xmm6, %rcx
|
||||||
|
2 1 1.00 vpextrq $1, %xmm1, %rbx
|
||||||
|
2 1 1.00 vpextrq $1, %xmm6, %rax
|
||||||
|
1 4 1.00 vextracti128 $1, %ymm6, %xmm1
|
||||||
|
1 8 0.50 * vmovsd (%rdi), %xmm6
|
||||||
|
1 1 1.00 vmovq %xmm1, %rdi
|
||||||
|
2 1 1.00 vpextrq $1, %xmm1, %rsi
|
||||||
|
1 8 0.50 * vmovsd (%rdi), %xmm1
|
||||||
|
1 8 0.50 * vmovsd (%rcx), %xmm7
|
||||||
|
1 8 0.50 * vpbroadcastd .LCPI0_2(%rip), %xmm12
|
||||||
|
1 8 0.50 * vmovhpd (%r9), %xmm2, %xmm2
|
||||||
|
1 1 0.25 vpaddd %xmm12, %xmm11, %xmm4
|
||||||
|
2 4 1.50 vpmovsxdq %xmm4, %ymm4
|
||||||
|
1 8 0.50 * vmovhpd (%rax), %xmm7, %xmm7
|
||||||
|
1 1 0.50 vpsllq $3, %ymm4, %ymm4
|
||||||
|
1 1 0.25 vpaddq %ymm4, %ymm3, %ymm4
|
||||||
|
1 8 0.50 * vmovhpd (%rbx), %xmm6, %xmm6
|
||||||
|
2 1 1.00 vpextrq $1, %xmm4, %rax
|
||||||
|
1 8 0.50 * vmovhpd (%rsi), %xmm1, %xmm1
|
||||||
|
1 1 1.00 vmovq %xmm4, %rcx
|
||||||
|
1 4 1.00 vextracti128 $1, %ymm4, %xmm4
|
||||||
|
1 1 1.00 vmovq %xmm4, %rsi
|
||||||
|
1 2 1.00 vinsertf128 $1, %xmm6, %ymm2, %ymm2
|
||||||
|
2 1 1.00 vpextrq $1, %xmm4, %rdi
|
||||||
|
1 8 0.50 * vmovsd (%rsi), %xmm4
|
||||||
|
1 3 0.50 vsubpd %ymm2, %ymm14, %ymm2
|
||||||
|
1 8 0.50 * vmovhpd (%rdi), %xmm4, %xmm4
|
||||||
|
1 8 0.50 * vmovsd (%rcx), %xmm6
|
||||||
|
1 2 1.00 vinsertf128 $1, %xmm1, %ymm7, %ymm1
|
||||||
|
1 8 0.50 * vmovhpd (%rax), %xmm6, %xmm6
|
||||||
|
1 2 1.00 vinsertf128 $1, %xmm4, %ymm6, %ymm4
|
||||||
|
1 3 0.50 vsubpd %ymm1, %ymm5, %ymm1
|
||||||
|
1 3 0.50 vsubpd %ymm4, %ymm10, %ymm4
|
||||||
|
1 3 0.50 vmulpd %ymm2, %ymm2, %ymm6
|
||||||
|
1 4 1.00 vfmadd231pd %ymm1, %ymm1, %ymm6
|
||||||
|
1 4 1.00 vfmadd231pd %ymm4, %ymm4, %ymm6
|
||||||
|
1 8 0.50 * vbroadcastsd .LCPI0_3(%rip), %ymm7
|
||||||
|
1 13 5.00 vdivpd %ymm6, %ymm7, %ymm7
|
||||||
|
1 3 0.50 vmulpd %ymm7, %ymm7, %ymm11
|
||||||
|
1 3 0.50 vmulpd %ymm9, %ymm11, %ymm11
|
||||||
|
1 8 0.50 * vbroadcastsd .LCPI0_4(%rip), %ymm12
|
||||||
|
1 3 0.50 vmulpd %ymm7, %ymm11, %ymm11
|
||||||
|
1 3 0.50 vaddpd %ymm12, %ymm11, %ymm12
|
||||||
|
1 10 0.50 * vmulpd 128(%rsp), %ymm7, %ymm7
|
||||||
|
1 3 0.50 vmulpd %ymm7, %ymm11, %ymm7
|
||||||
|
1 3 0.50 vmulpd %ymm7, %ymm12, %ymm7
|
||||||
|
1 1 0.50 vcmpltpd %ymm8, %ymm6, %ymm6
|
||||||
|
1 4 1.00 vfmadd213pd %ymm0, %ymm7, %ymm2
|
||||||
|
1 1 0.50 vblendvpd %ymm6, %ymm2, %ymm0, %ymm0
|
||||||
|
1 4 1.00 vfmadd213pd %ymm15, %ymm7, %ymm1
|
||||||
|
1 4 1.00 vfmadd213pd %ymm13, %ymm7, %ymm4
|
||||||
|
1 1 0.50 vblendvpd %ymm6, %ymm1, %ymm15, %ymm15
|
||||||
|
1 1 0.50 vblendvpd %ymm6, %ymm4, %ymm13, %ymm13
|
||||||
|
1 1 0.25 addq $4, %rbp
|
||||||
|
1 1 0.25 cmpq %rdx, %rbp
|
||||||
|
1 1 0.50 jb .LBB0_9
|
||||||
|
|
||||||
|
|
||||||
|
Resources:
|
||||||
|
[0] - Zn3AGU0
|
||||||
|
[1] - Zn3AGU1
|
||||||
|
[2] - Zn3AGU2
|
||||||
|
[3] - Zn3ALU0
|
||||||
|
[4] - Zn3ALU1
|
||||||
|
[5] - Zn3ALU2
|
||||||
|
[6] - Zn3ALU3
|
||||||
|
[7] - Zn3BRU1
|
||||||
|
[8] - Zn3FPP0
|
||||||
|
[9] - Zn3FPP1
|
||||||
|
[10] - Zn3FPP2
|
||||||
|
[11] - Zn3FPP3
|
||||||
|
[12.0] - Zn3FPP45
|
||||||
|
[12.1] - Zn3FPP45
|
||||||
|
[13] - Zn3FPSt
|
||||||
|
[14.0] - Zn3LSU
|
||||||
|
[14.1] - Zn3LSU
|
||||||
|
[14.2] - Zn3LSU
|
||||||
|
[15.0] - Zn3Load
|
||||||
|
[15.1] - Zn3Load
|
||||||
|
[15.2] - Zn3Load
|
||||||
|
[16.0] - Zn3Store
|
||||||
|
[16.1] - Zn3Store
|
||||||
|
|
||||||
|
|
||||||
|
Resource pressure per iteration:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12.0] [12.1] [13] [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
|
||||||
|
- - - 0.60 0.60 0.60 0.60 0.60 16.84 23.53 16.30 7.33 21.50 21.50 - 6.33 6.33 6.34 6.33 6.33 6.34 - -
|
||||||
|
|
||||||
|
Resource pressure by instruction:
|
||||||
|
[0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12.0] [12.1] [13] [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
|
||||||
|
- - - - - - - - - 0.03 0.97 - 0.51 0.49 - 0.34 0.33 0.33 0.34 0.33 0.33 - - vpbroadcastd .LCPI0_1(%rip), %xmm1
|
||||||
|
- - - - - - - - 0.65 - - 0.35 0.34 0.66 - 0.49 0.05 0.46 0.49 0.05 0.46 - - vpmulld (%r11,%rbp,4), %xmm1, %xmm11
|
||||||
|
- - - - - - - - - 0.06 2.94 - - - - - - - - - - - - vpmovsxdq %xmm11, %ymm1
|
||||||
|
- - - - - - - - - 0.65 0.35 - - - - - - - - - - - - vpsllq $3, %ymm1, %ymm1
|
||||||
|
- - - - - - - - - - - 1.00 - - - - - - - - - - - vpaddq %ymm1, %ymm3, %ymm1
|
||||||
|
- - - - - - - - - - - - 1.00 1.00 - - - - - - - - - vmovq %xmm1, %r14
|
||||||
|
- - - - - - - - - - - - 1.00 1.00 - - - - - - - - - vpextrq $1, %xmm1, %r9
|
||||||
|
- - - - - - - - 1.00 - - - - - - - - - - - - - - vextracti128 $1, %ymm1, %xmm1
|
||||||
|
- - - - - - - - - - - - 0.50 0.50 - 0.48 0.35 0.17 0.48 0.35 0.17 - - vmovsd (%r14), %xmm2
|
||||||
|
- - - - - - - - 0.01 0.18 0.17 0.64 0.47 0.53 - 0.34 0.33 0.33 0.34 0.33 0.33 - - vpsubd .LCPI0_5, %xmm11, %xmm6
|
||||||
|
- - - - - - - - - 1.92 1.08 - - - - - - - - - - - - vpmovsxdq %xmm6, %ymm6
|
||||||
|
- - - - - - - - - 0.32 0.68 - - - - - - - - - - - - vpsllq $3, %ymm6, %ymm6
|
||||||
|
- - - - - - - - - - - - 1.30 0.70 - - - - - - - - - vmovq %xmm1, %rdi
|
||||||
|
- - - - - - - - - - 0.32 0.68 - - - - - - - - - - - vpaddq %ymm6, %ymm3, %ymm6
|
||||||
|
- - - - - - - - - - - - 1.34 0.66 - - - - - - - - - vmovq %xmm6, %rcx
|
||||||
|
- - - - - - - - - - - - 1.00 1.00 - - - - - - - - - vpextrq $1, %xmm1, %rbx
|
||||||
|
- - - - - - - - - - - - 1.00 1.00 - - - - - - - - - vpextrq $1, %xmm6, %rax
|
||||||
|
- - - - - - - - 1.00 - - - - - - - - - - - - - - vextracti128 $1, %ymm6, %xmm1
|
||||||
|
- - - - - - - - - - - - 0.50 0.50 - 0.03 0.65 0.32 0.03 0.65 0.32 - - vmovsd (%rdi), %xmm6
|
||||||
|
- - - - - - - - - - - - 0.36 1.64 - - - - - - - - - vmovq %xmm1, %rdi
|
||||||
|
- - - - - - - - - - - - 1.64 0.36 - - - - - - - - - vpextrq $1, %xmm1, %rsi
|
||||||
|
- - - - - - - - - - - - 0.32 0.68 - 0.51 0.33 0.16 0.51 0.33 0.16 - - vmovsd (%rdi), %xmm1
|
||||||
|
- - - - - - - - - - - - 0.68 0.32 - 0.49 0.01 0.50 0.49 0.01 0.50 - - vmovsd (%rcx), %xmm7
|
||||||
|
- - - - - - - - - 0.48 0.52 - 0.67 0.33 - 0.17 0.62 0.21 0.17 0.62 0.21 - - vpbroadcastd .LCPI0_2(%rip), %xmm12
|
||||||
|
- - - - - - - - - 0.01 0.99 - 0.17 0.83 - 0.02 0.64 0.34 0.02 0.64 0.34 - - vmovhpd (%r9), %xmm2, %xmm2
|
||||||
|
- - - - - - - - 0.01 - - 0.99 - - - - - - - - - - - vpaddd %xmm12, %xmm11, %xmm4
|
||||||
|
- - - - - - - - - 0.57 2.43 - - - - - - - - - - - - vpmovsxdq %xmm4, %ymm4
|
||||||
|
- - - - - - - - - 0.34 0.66 - 0.82 0.18 - 0.49 0.35 0.16 0.49 0.35 0.16 - - vmovhpd (%rax), %xmm7, %xmm7
|
||||||
|
- - - - - - - - - 0.34 0.66 - - - - - - - - - - - - vpsllq $3, %ymm4, %ymm4
|
||||||
|
- - - - - - - - - - 0.01 0.99 - - - - - - - - - - - vpaddq %ymm4, %ymm3, %ymm4
|
||||||
|
- - - - - - - - - 0.51 0.49 - 0.49 0.51 - 0.35 0.16 0.49 0.35 0.16 0.49 - - vmovhpd (%rbx), %xmm6, %xmm6
|
||||||
|
- - - - - - - - - - - - 1.04 0.96 - - - - - - - - - vpextrq $1, %xmm4, %rax
|
||||||
|
- - - - - - - - - 0.49 0.51 - 0.17 0.83 - 0.16 0.49 0.35 0.16 0.49 0.35 - - vmovhpd (%rsi), %xmm1, %xmm1
|
||||||
|
- - - - - - - - - - - - 1.00 1.00 - - - - - - - - - vmovq %xmm4, %rcx
|
||||||
|
- - - - - - - - 1.00 - - - - - - - - - - - - - - vextracti128 $1, %ymm4, %xmm4
|
||||||
|
- - - - - - - - - - - - 1.00 1.00 - - - - - - - - - vmovq %xmm4, %rsi
|
||||||
|
- - - - - - - - - 1.00 - - - - - - - - - - - - - vinsertf128 $1, %xmm6, %ymm2, %ymm2
|
||||||
|
- - - - - - - - - - - - 1.00 1.00 - - - - - - - - - vpextrq $1, %xmm4, %rdi
|
||||||
|
- - - - - - - - - - - - 0.50 0.50 - 0.49 0.35 0.16 0.49 0.35 0.16 - - vmovsd (%rsi), %xmm4
|
||||||
|
- - - - - - - - - - 0.31 0.69 - - - - - - - - - - - vsubpd %ymm2, %ymm14, %ymm2
|
||||||
|
- - - - - - - - - 0.49 0.51 - 0.48 0.52 - 0.35 0.16 0.49 0.35 0.16 0.49 - - vmovhpd (%rdi), %xmm4, %xmm4
|
||||||
|
- - - - - - - - - - - - 0.52 0.48 - 0.16 0.49 0.35 0.16 0.49 0.35 - - vmovsd (%rcx), %xmm6
|
||||||
|
- - - - - - - - - 1.00 - - - - - - - - - - - - - vinsertf128 $1, %xmm1, %ymm7, %ymm1
|
||||||
|
- - - - - - - - - 0.35 0.65 - 0.50 0.50 - 0.47 0.35 0.18 0.47 0.35 0.18 - - vmovhpd (%rax), %xmm6, %xmm6
|
||||||
|
- - - - - - - - - 1.00 - - - - - - - - - - - - - vinsertf128 $1, %xmm4, %ymm6, %ymm4
|
||||||
|
- - - - - - - - - - 0.33 0.67 - - - - - - - - - - - vsubpd %ymm1, %ymm5, %ymm1
|
||||||
|
- - - - - - - - - - 0.51 0.49 - - - - - - - - - - - vsubpd %ymm4, %ymm10, %ymm4
|
||||||
|
- - - - - - - - 0.52 0.48 - - - - - - - - - - - - - vmulpd %ymm2, %ymm2, %ymm6
|
||||||
|
- - - - - - - - 1.00 1.00 - - - - - - - - - - - - - vfmadd231pd %ymm1, %ymm1, %ymm6
|
||||||
|
- - - - - - - - 1.34 0.66 - - - - - - - - - - - - - vfmadd231pd %ymm4, %ymm4, %ymm6
|
||||||
|
- - - - - - - - - 0.66 0.34 - 0.51 0.49 - 0.19 0.32 0.49 0.19 0.32 0.49 - - vbroadcastsd .LCPI0_3(%rip), %ymm7
|
||||||
|
- - - - - - - - - 5.00 - - - - - - - - - - - - - vdivpd %ymm6, %ymm7, %ymm7
|
||||||
|
- - - - - - - - 0.50 0.50 - - - - - - - - - - - - - vmulpd %ymm7, %ymm7, %ymm11
|
||||||
|
- - - - - - - - 0.99 0.01 - - - - - - - - - - - - - vmulpd %ymm9, %ymm11, %ymm11
|
||||||
|
- - - - - - - - - 0.30 0.70 - 0.49 0.51 - 0.34 0.33 0.33 0.34 0.33 0.33 - - vbroadcastsd .LCPI0_4(%rip), %ymm12
|
||||||
|
- - - - - - - - 0.82 0.18 - - - - - - - - - - - - - vmulpd %ymm7, %ymm11, %ymm11
|
||||||
|
- - - - - - - - - - 0.17 0.83 - - - - - - - - - - - vaddpd %ymm12, %ymm11, %ymm12
|
||||||
|
- - - - - - - - 0.01 0.99 - - 0.18 0.82 - 0.46 0.02 0.52 0.46 0.02 0.52 - - vmulpd 128(%rsp), %ymm7, %ymm7
|
||||||
|
- - - - - - - - 0.99 0.01 - - - - - - - - - - - - - vmulpd %ymm7, %ymm11, %ymm7
|
||||||
|
- - - - - - - - 0.67 0.33 - - - - - - - - - - - - - vmulpd %ymm7, %ymm12, %ymm7
|
||||||
|
- - - - - - - - 1.00 - - - - - - - - - - - - - - vcmpltpd %ymm8, %ymm6, %ymm6
|
||||||
|
- - - - - - - - 1.34 0.66 - - - - - - - - - - - - - vfmadd213pd %ymm0, %ymm7, %ymm2
|
||||||
|
- - - - - - - - 0.66 0.34 - - - - - - - - - - - - - vblendvpd %ymm6, %ymm2, %ymm0, %ymm0
|
||||||
|
- - - - - - - - 0.66 1.34 - - - - - - - - - - - - - vfmadd213pd %ymm15, %ymm7, %ymm1
|
||||||
|
- - - - - - - - 1.34 0.66 - - - - - - - - - - - - - vfmadd213pd %ymm13, %ymm7, %ymm4
|
||||||
|
- - - - - - - - 0.34 0.66 - - - - - - - - - - - - - vblendvpd %ymm6, %ymm1, %ymm15, %ymm15
|
||||||
|
- - - - - - - - 0.99 0.01 - - - - - - - - - - - - - vblendvpd %ymm6, %ymm4, %ymm13, %ymm13
|
||||||
|
- - - - 0.40 0.20 0.40 - - - - - - - - - - - - - - - - addq $4, %rbp
|
||||||
|
- - - 0.20 0.20 0.40 0.20 - - - - - - - - - - - - - - - - cmpq %rdx, %rbp
|
||||||
|
- - - 0.40 - - - 0.60 - - - - - - - - - - - - - - - jb .LBB0_9
|
||||||
108
static_analysis/jan/analyses/lammps-icx-avx2zen-osaca.out
Normal file
108
static_analysis/jan/analyses/lammps-icx-avx2zen-osaca.out
Normal file
@ -0,0 +1,108 @@
|
|||||||
|
Open Source Architecture Code Analyzer (OSACA) - 0.4.12
|
||||||
|
Analyzed file: lammps-icx-avx2zen.s
|
||||||
|
Architecture: ZEN3
|
||||||
|
Timestamp: 2023-02-10 16:31:30
|
||||||
|
|
||||||
|
|
||||||
|
P - Throughput of LOAD operation can be hidden behind a past or future STORE instruction
|
||||||
|
* - Instruction micro-ops not bound to a port
|
||||||
|
X - No throughput/latency information for this instruction in data file
|
||||||
|
|
||||||
|
|
||||||
|
Combined Analysis Report
|
||||||
|
------------------------
|
||||||
|
Port pressure in cycles
|
||||||
|
| 0 | 1 | 2 | 3 | DV0 | DV1 | 4 | 5 | 6 | 7 | 8 - 8DV | 9 | 10 | 11 | 12 | 13 || CP | LCD |
|
||||||
|
--------------------------------------------------------------------------------------------------------------------------------------------
|
||||||
|
175 | | | | | | | | | | | | | | | | || | | # pointer_increment=16 e95035fc9e97f63299dd5188a0872bfc
|
||||||
|
176 | | | | | | | | | | | | | | | | || | | # LLVM-MCA-BEGIN
|
||||||
|
177 | | | | | | | | | | | | | | | | || | | .LBB0_9: #
|
||||||
|
178 | | | | | | | | | | | | | | | | || | | # Parent Loop BB0_6 Depth=1
|
||||||
|
179 | | | | | | | | | | | | | | | | || | | # => This Inner Loop Header: Depth=2
|
||||||
|
180 | | 0.00 | 1.00 | | | | | | | | | | | 0.50 | 0.50 | || 1.0 | | vpbroadcastd .LCPI0_1(%rip), %xmm1 # xmm1 = [3,3,3,3]
|
||||||
|
181 | 0.00 | | | 1.00 | | | | | | | | | | 0.50 | 0.50 | || 3.0 | | vpmulld (%r11,%rbp,4), %xmm1, %xmm11
|
||||||
|
182 | 0.00 | 0.75 | 0.38 | 0.87 | | | | | | | | | | | | || 4.0 | | vpmovsxdq %xmm11, %ymm1
|
||||||
|
183 | | 0.00 | 1.00 | | | | | | | | | | | | | || 1.0 | | vpsllq $3, %ymm1, %ymm1
|
||||||
|
184 | 0.00 | 0.00 | 0.50 | 0.50 | | | | | | | | | | | | || 1.0 | | vpaddq %ymm1, %ymm3, %ymm1
|
||||||
|
185 | 0.00 | 0.00 | 0.50 | 0.50 | | | | | | | | | | | | || | | vmovq %xmm1, %r14
|
||||||
|
186 | 0.12 | 1.88 | | | | | | | | | | | | | | || | | vpextrq $1, %xmm1, %r9
|
||||||
|
187 | | 1.00 | | | | | | | | | | | | | | || 3.0 | | vextracti128 $1, %ymm1, %xmm1
|
||||||
|
188 | | | | | | | | | | | | | | 0.50 | 0.50 | || | | vmovsd (%r14), %xmm2 # xmm2 = mem[0],zero
|
||||||
|
189 | 0.00 | 0.00 | 0.50 | 0.50 | | | | | | | | | | | | || | | vpsubd .LCPI0_5, %xmm11, %xmm6
|
||||||
|
190 | 0.00 | 0.75 | 0.38 | 0.87 | | | | | | | | | | | | || | | vpmovsxdq %xmm6, %ymm6
|
||||||
|
191 | | 0.00 | 1.00 | | | | | | | | | | | | | || | | vpsllq $3, %ymm6, %ymm6
|
||||||
|
192 | 0.00 | 0.00 | 0.49 | 0.51 | | | | | | | | | | | | || | | vmovq %xmm1, %rdi
|
||||||
|
193 | 0.00 | 0.00 | 0.51 | 0.49 | | | | | | | | | | | | || | | vpaddq %ymm6, %ymm3, %ymm6
|
||||||
|
194 | 0.00 | 0.00 | 0.49 | 0.51 | | | | | | | | | | | | || | | vmovq %xmm6, %rcx
|
||||||
|
195 | 0.13 | 1.87 | | | | | | | | | | | | | | || 6.0 | | vpextrq $1, %xmm1, %rbx
|
||||||
|
196 | 0.00 | 2.00 | | | | | | | | | | | | | | || | | vpextrq $1, %xmm6, %rax
|
||||||
|
197 | | 1.00 | | | | | | | | | | | | | | || | | vextracti128 $1, %ymm6, %xmm1
|
||||||
|
198 | | | | | | | | | | | | | | 0.50 | 0.50 | || | | vmovsd (%rdi), %xmm6 # xmm6 = mem[0],zero
|
||||||
|
199 | 0.00 | 0.00 | 0.00 | 1.00 | | | | | | | | | | | | || | | vmovq %xmm1, %rdi
|
||||||
|
200 | 0.00 | 2.00 | | | | | | | | | | | | | | || | | vpextrq $1, %xmm1, %rsi
|
||||||
|
201 | | | | | | | | | | | | | | 0.50 | 0.50 | || | | vmovsd (%rdi), %xmm1 # xmm1 = mem[0],zero
|
||||||
|
202 | | | | | | | | | | | | | | 0.50 | 0.50 | || | | vmovsd (%rcx), %xmm7 # xmm7 = mem[0],zero
|
||||||
|
203 | | 0.00 | 1.00 | | | | | | | | | | | 0.50 | 0.50 | || | | vpbroadcastd .LCPI0_2(%rip), %xmm12 # xmm12 = [2,2,2,2]
|
||||||
|
204 | | 0.00 | 1.00 | | | | | | | | | | | 0.50 | 0.50 | || | | vmovhpd (%r9), %xmm2, %xmm2 # xmm2 = xmm2[0],mem[0]
|
||||||
|
205 | 0.00 | 0.00 | 0.63 | 0.37 | | | | | | | | | | | | || | | vpaddd %xmm12, %xmm11, %xmm4
|
||||||
|
206 | 0.00 | 0.75 | 0.00 | 1.25 | | | | | | | | | | | | || | | vpmovsxdq %xmm4, %ymm4
|
||||||
|
207 | | 0.00 | 1.00 | | | | | | | | | | | 0.50 | 0.50 | || | | vmovhpd (%rax), %xmm7, %xmm7 # xmm7 = xmm7[0],mem[0]
|
||||||
|
208 | | 0.00 | 1.00 | | | | | | | | | | | | | || | | vpsllq $3, %ymm4, %ymm4
|
||||||
|
209 | 0.00 | 0.00 | 0.00 | 1.00 | | | | | | | | | | | | || | | vpaddq %ymm4, %ymm3, %ymm4
|
||||||
|
210 | | 0.00 | 1.00 | | | | | | | | | | | 0.50 | 0.50 | || 5.0 | | vmovhpd (%rbx), %xmm6, %xmm6 # xmm6 = xmm6[0],mem[0]
|
||||||
|
211 | 0.75 | 1.25 | | | | | | | | | | | | | | || | | vpextrq $1, %xmm4, %rax
|
||||||
|
212 | | 0.00 | 1.00 | | | | | | | | | | | 0.50 | 0.50 | || | | vmovhpd (%rsi), %xmm1, %xmm1 # xmm1 = xmm1[0],mem[0]
|
||||||
|
213 | 0.00 | 0.00 | 0.50 | 0.50 | | | | | | | | | | | | || | | vmovq %xmm4, %rcx
|
||||||
|
214 | | 1.00 | | | | | | | | | | | | | | || | | vextracti128 $1, %ymm4, %xmm4
|
||||||
|
215 | 0.00 | 0.00 | 0.00 | 1.00 | | | | | | | | | | | | || | | vmovq %xmm4, %rsi
|
||||||
|
216 | | 1.00 | | | | | | | | | | | | | | || 1.0 | | vinsertf128 $1, %xmm6, %ymm2, %ymm2
|
||||||
|
217 | 1.00 | 1.00 | | | | | | | | | | | | | | || | | vpextrq $1, %xmm4, %rdi
|
||||||
|
218 | | | | | | | | | | | | | | 0.50 | 0.50 | || | | vmovsd (%rsi), %xmm4 # xmm4 = mem[0],zero
|
||||||
|
219 | | | 0.00 | 1.00 | | | | | | | | | | | | || 3.0 | | vsubpd %ymm2, %ymm14, %ymm2
|
||||||
|
220 | | 0.00 | 1.00 | | | | | | | | | | | 0.50 | 0.50 | || | | vmovhpd (%rdi), %xmm4, %xmm4 # xmm4 = xmm4[0],mem[0]
|
||||||
|
221 | | | | | | | | | | | | | | 0.50 | 0.50 | || | | vmovsd (%rcx), %xmm6 # xmm6 = mem[0],zero
|
||||||
|
222 | | 1.00 | | | | | | | | | | | | | | || | | vinsertf128 $1, %xmm1, %ymm7, %ymm1
|
||||||
|
223 | | 0.00 | 1.00 | | | | | | | | | | | 0.50 | 0.50 | || | | vmovhpd (%rax), %xmm6, %xmm6 # xmm6 = xmm6[0],mem[0]
|
||||||
|
224 | | 1.00 | | | | | | | | | | | | | | || | | vinsertf128 $1, %xmm4, %ymm6, %ymm4
|
||||||
|
225 | | | 0.00 | 1.00 | | | | | | | | | | | | || | | vsubpd %ymm1, %ymm5, %ymm1
|
||||||
|
226 | | | 0.00 | 1.00 | | | | | | | | | | | | || | | vsubpd %ymm4, %ymm10, %ymm4
|
||||||
|
227 | 1.00 | 0.00 | | | | | | | | | | | | | | || 3.0 | | vmulpd %ymm2, %ymm2, %ymm6
|
||||||
|
228 | 1.00 | 0.00 | | | | | | | | | | | | | | || 4.0 | | vfmadd231pd %ymm1, %ymm1, %ymm6 # ymm6 = (ymm1 * ymm1) + ymm6
|
||||||
|
229 | 1.00 | 0.00 | | | | | | | | | | | | | | || 4.0 | | vfmadd231pd %ymm4, %ymm4, %ymm6 # ymm6 = (ymm4 * ymm4) + ymm6
|
||||||
|
230 | 1.00 | | | | | | | | | | | | | 0.50 | 0.50 | || | | vbroadcastsd .LCPI0_3(%rip), %ymm7 # ymm7 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
|
||||||
|
231 | | | | | 4.50 | 4.50 | | | | | | | | | | || 13.0 | | vdivpd %ymm6, %ymm7, %ymm7
|
||||||
|
232 | 1.00 | 0.00 | | | | | | | | | | | | | | || 3.0 | | vmulpd %ymm7, %ymm7, %ymm11
|
||||||
|
233 | 1.00 | 0.00 | | | | | | | | | | | | | | || 3.0 | | vmulpd %ymm9, %ymm11, %ymm11
|
||||||
|
234 | 1.00 | | | | | | | | | | | | | 0.50 | 0.50 | || | | vbroadcastsd .LCPI0_4(%rip), %ymm12 # ymm12 = [-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1]
|
||||||
|
235 | 1.00 | 0.00 | | | | | | | | | | | | | | || 3.0 | | vmulpd %ymm7, %ymm11, %ymm11
|
||||||
|
236 | | | 0.00 | 1.00 | | | | | | | | | | | | || 3.0 | | vaddpd %ymm12, %ymm11, %ymm12
|
||||||
|
237 | 1.00 | 0.00 | | | | | | | | | | | | 0.50 | 0.50 | || | | vmulpd 128(%rsp), %ymm7, %ymm7 # 32-byte Folded Reload
|
||||||
|
238 | 1.00 | 0.00 | | | | | | | | | | | | | | || | | vmulpd %ymm7, %ymm11, %ymm7
|
||||||
|
239 | 1.00 | 0.00 | | | | | | | | | | | | | | || 3.0 | | vmulpd %ymm7, %ymm12, %ymm7
|
||||||
|
240 | | | 0.00 | 1.00 | | | | | | | | | | | | || | | vcmpltpd %ymm8, %ymm6, %ymm6
|
||||||
|
241 | 1.00 | 0.00 | | | | | | | | | | | | | | || 4.0 | | vfmadd213pd %ymm0, %ymm7, %ymm2 # ymm2 = (ymm7 * ymm2) + ymm0
|
||||||
|
242 | 1.00 | 0.00 | | | | | | | | | | | | | | || 1.0 | | vblendvpd %ymm6, %ymm2, %ymm0, %ymm0
|
||||||
|
243 | 1.00 | 0.00 | | | | | | | | | | | | | | || | | vfmadd213pd %ymm15, %ymm7, %ymm1 # ymm1 = (ymm7 * ymm1) + ymm15
|
||||||
|
244 | 1.00 | 0.00 | | | | | | | | | | | | | | || | 4.0 | vfmadd213pd %ymm13, %ymm7, %ymm4 # ymm4 = (ymm7 * ymm4) + ymm13
|
||||||
|
245 | 1.00 | 0.00 | | | | | | | | | | | | | | || | | vblendvpd %ymm6, %ymm1, %ymm15, %ymm15
|
||||||
|
246 | 0.75 | 0.25 | | | | | | | | | | | | | | || | 1.0 | vblendvpd %ymm6, %ymm4, %ymm13, %ymm13
|
||||||
|
247 | | | | | | | | | 0.25 | 0.25 | 0.25 | 0.25 | | | | || | | addq $4, %rbp
|
||||||
|
248 | | | | | | | | | 0.25 | 0.25 | 0.25 | 0.25 | | | | || | | cmpq %rdx, %rbp
|
||||||
|
249 | | | | | | | | | 0.00 | | | | 1.00 | | | || | | jb .LBB0_9
|
||||||
|
250 | | | | | | | | | | | | | | | | || | | # LLVM-MCA-END
|
||||||
|
|
||||||
|
18.8 18.5 15.9 15.9 4.50 4.50 0.50 0.50 0.50 0.50 9.00 9.00 72 5.0
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loop-Carried Dependencies Analysis Report
|
||||||
|
-----------------------------------------
|
||||||
|
244 | 5.0 | vfmadd213pd %ymm13, %ymm7, %ymm4 # ymm4 = (ymm7 * ymm4) + ymm13| [244, 246]
|
||||||
|
243 | 5.0 | vfmadd213pd %ymm15, %ymm7, %ymm1 # ymm1 = (ymm7 * ymm1) + ymm15| [243, 245]
|
||||||
|
241 | 5.0 | vfmadd213pd %ymm0, %ymm7, %ymm2 # ymm2 = (ymm7 * ymm2) + ymm0| [241, 242]
|
||||||
|
247 | 1.0 | addq $4, %rbp | [247]
|
||||||
|
246 | 1.0 | vblendvpd %ymm6, %ymm4, %ymm13, %ymm13| [246]
|
||||||
|
245 | 1.0 | vblendvpd %ymm6, %ymm1, %ymm15, %ymm15| [245]
|
||||||
|
242 | 1.0 | vblendvpd %ymm6, %ymm2, %ymm0, %ymm0| [242]
|
||||||
|
|
||||||
BIN
static_analysis/jan/gromacs-icc-avx512-dp.o
Normal file
BIN
static_analysis/jan/gromacs-icc-avx512-dp.o
Normal file
Binary file not shown.
4334
static_analysis/jan/gromacs-icc-avx512-dp.s
Normal file
4334
static_analysis/jan/gromacs-icc-avx512-dp.s
Normal file
File diff suppressed because it is too large
Load Diff
BIN
static_analysis/jan/gromacs-icc-avx512-sp.o
Normal file
BIN
static_analysis/jan/gromacs-icc-avx512-sp.o
Normal file
Binary file not shown.
4018
static_analysis/jan/gromacs-icc-avx512-sp.s
Normal file
4018
static_analysis/jan/gromacs-icc-avx512-sp.s
Normal file
File diff suppressed because it is too large
Load Diff
BIN
static_analysis/jan/gromacs-icx-avx512-dp.o
Normal file
BIN
static_analysis/jan/gromacs-icx-avx512-dp.o
Normal file
Binary file not shown.
@ -2238,8 +2238,8 @@ movl $111, %ebx # OSACA START MARKER
|
|||||||
.byte 100 # OSACA START MARKER
|
.byte 100 # OSACA START MARKER
|
||||||
.byte 103 # OSACA START MARKER
|
.byte 103 # OSACA START MARKER
|
||||||
.byte 144 # OSACA START MARKER
|
.byte 144 # OSACA START MARKER
|
||||||
|
# pointer_increment=64 da67166e5736661e6b03ea29ee7bfd67
|
||||||
# LLVM-MCA-BEGIN
|
# LLVM-MCA-BEGIN
|
||||||
# pointer_increment=256 da67166e5736661e6b03ea29ee7bfd67
|
|
||||||
.LBB5_12: # Parent Loop BB5_7 Depth=1
|
.LBB5_12: # Parent Loop BB5_7 Depth=1
|
||||||
# => This Inner Loop Header: Depth=2
|
# => This Inner Loop Header: Depth=2
|
||||||
movslq (%r10,%rbx,4), %rcx
|
movslq (%r10,%rbx,4), %rcx
|
||||||
BIN
static_analysis/jan/gromacs-icx-avx512-sp.o
Normal file
BIN
static_analysis/jan/gromacs-icx-avx512-sp.o
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
BIN
static_analysis/jan/lammps-icc-avx2.o
Normal file
BIN
static_analysis/jan/lammps-icc-avx2.o
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
BIN
static_analysis/jan/lammps-icc-avx512.o
Normal file
BIN
static_analysis/jan/lammps-icc-avx512.o
Normal file
Binary file not shown.
File diff suppressed because it is too large
Load Diff
BIN
static_analysis/jan/lammps-icx-avx2zen.o
Normal file
BIN
static_analysis/jan/lammps-icx-avx2zen.o
Normal file
Binary file not shown.
@ -172,8 +172,8 @@ movl $111, %ebx # OSACA START MARKER
|
|||||||
.byte 100 # OSACA START MARKER
|
.byte 100 # OSACA START MARKER
|
||||||
.byte 103 # OSACA START MARKER
|
.byte 103 # OSACA START MARKER
|
||||||
.byte 144 # OSACA START MARKER
|
.byte 144 # OSACA START MARKER
|
||||||
# LLVM-MCA-BEGIN
|
|
||||||
# pointer_increment=16 e95035fc9e97f63299dd5188a0872bfc
|
# pointer_increment=16 e95035fc9e97f63299dd5188a0872bfc
|
||||||
|
# LLVM-MCA-BEGIN
|
||||||
.LBB0_9: #
|
.LBB0_9: #
|
||||||
# Parent Loop BB0_6 Depth=1
|
# Parent Loop BB0_6 Depth=1
|
||||||
# => This Inner Loop Header: Depth=2
|
# => This Inner Loop Header: Depth=2
|
||||||
@ -386,8 +386,6 @@ movl $222, %ebx # OSACA END MARKER
|
|||||||
.quad 4607182418800017408 # 1
|
.quad 4607182418800017408 # 1
|
||||||
.LCPI1_2:
|
.LCPI1_2:
|
||||||
.quad -4620693217682128896 # -0.5
|
.quad -4620693217682128896 # -0.5
|
||||||
.LCPI1_3:
|
|
||||||
.quad 4741671816366391296 # 1.0E+9
|
|
||||||
.text
|
.text
|
||||||
.globl computeForceLJHalfNeigh
|
.globl computeForceLJHalfNeigh
|
||||||
.p2align 4, 0x90
|
.p2align 4, 0x90
|
||||||
@ -408,128 +406,125 @@ computeForceLJHalfNeigh: #
|
|||||||
.cfi_def_cfa_offset 48
|
.cfi_def_cfa_offset 48
|
||||||
pushq %rbx
|
pushq %rbx
|
||||||
.cfi_def_cfa_offset 56
|
.cfi_def_cfa_offset 56
|
||||||
subq $56, %rsp
|
subq $40, %rsp
|
||||||
.cfi_def_cfa_offset 112
|
.cfi_def_cfa_offset 96
|
||||||
.cfi_offset %rbx, -56
|
.cfi_offset %rbx, -56
|
||||||
.cfi_offset %r12, -48
|
.cfi_offset %r12, -48
|
||||||
.cfi_offset %r13, -40
|
.cfi_offset %r13, -40
|
||||||
.cfi_offset %r14, -32
|
.cfi_offset %r14, -32
|
||||||
.cfi_offset %r15, -24
|
.cfi_offset %r15, -24
|
||||||
.cfi_offset %rbp, -16
|
.cfi_offset %rbp, -16
|
||||||
movq %rcx, 24(%rsp) # 8-byte Spill
|
movq %rcx, 16(%rsp) # 8-byte Spill
|
||||||
movq %rdx, %r12
|
movq %rdx, %r15
|
||||||
movq %rsi, %r13
|
movq %rsi, %r12
|
||||||
movl 4(%rsi), %r15d
|
movl 4(%rsi), %r13d
|
||||||
vmovsd 144(%rdi), %xmm0 # xmm0 = mem[0],zero
|
vmovsd 144(%rdi), %xmm0 # xmm0 = mem[0],zero
|
||||||
vmovsd %xmm0, (%rsp) # 8-byte Spill
|
|
||||||
vmovsd 40(%rdi), %xmm0 # xmm0 = mem[0],zero
|
|
||||||
vmovsd %xmm0, 8(%rsp) # 8-byte Spill
|
vmovsd %xmm0, 8(%rsp) # 8-byte Spill
|
||||||
movq %rdi, 40(%rsp) # 8-byte Spill
|
vmovsd 40(%rdi), %xmm0 # xmm0 = mem[0],zero
|
||||||
|
vmovsd %xmm0, (%rsp) # 8-byte Spill
|
||||||
vmovsd 56(%rdi), %xmm0 # xmm0 = mem[0],zero
|
vmovsd 56(%rdi), %xmm0 # xmm0 = mem[0],zero
|
||||||
vmovsd %xmm0, 16(%rsp) # 8-byte Spill
|
vmovsd %xmm0, 32(%rsp) # 8-byte Spill
|
||||||
testl %r15d, %r15d
|
testl %r13d, %r13d
|
||||||
jle .LBB1_2
|
jle .LBB1_2
|
||||||
# %bb.1: #
|
# %bb.1: #
|
||||||
movq 64(%r13), %rdi
|
movq 64(%r12), %rdi
|
||||||
leaq (,%r15,8), %rax
|
leaq (,%r13,8), %rax
|
||||||
leaq (%rax,%rax,2), %rdx
|
leaq (%rax,%rax,2), %rdx
|
||||||
xorl %esi, %esi
|
xorl %esi, %esi
|
||||||
callq _intel_fast_memset
|
callq _intel_fast_memset
|
||||||
.LBB1_2: #
|
.LBB1_2: #
|
||||||
xorl %r14d, %r14d
|
|
||||||
xorl %eax, %eax
|
xorl %eax, %eax
|
||||||
callq getTimeStamp
|
callq getTimeStamp
|
||||||
vmovsd %xmm0, 32(%rsp) # 8-byte Spill
|
vmovsd %xmm0, 24(%rsp) # 8-byte Spill
|
||||||
movl $.L.str.1, %edi
|
movl $.L.str.1, %edi
|
||||||
callq likwid_markerStartRegion
|
callq likwid_markerStartRegion
|
||||||
testl %r15d, %r15d
|
testl %r13d, %r13d
|
||||||
jle .LBB1_8
|
jle .LBB1_8
|
||||||
# %bb.3: #
|
# %bb.3: #
|
||||||
vmovsd (%rsp), %xmm0 # 8-byte Reload
|
|
||||||
# xmm0 = mem[0],zero
|
|
||||||
vmulsd %xmm0, %xmm0, %xmm12
|
|
||||||
movq 16(%r12), %rax
|
|
||||||
movq 24(%r12), %rcx
|
|
||||||
movq %rcx, (%rsp) # 8-byte Spill
|
|
||||||
movslq 8(%r12), %rdx
|
|
||||||
movq 16(%r13), %rsi
|
|
||||||
movq 64(%r13), %rdi
|
|
||||||
vmovsd 8(%rsp), %xmm0 # 8-byte Reload
|
vmovsd 8(%rsp), %xmm0 # 8-byte Reload
|
||||||
# xmm0 = mem[0],zero
|
# xmm0 = mem[0],zero
|
||||||
|
vmulsd %xmm0, %xmm0, %xmm12
|
||||||
|
movq 16(%r15), %rax
|
||||||
|
movq 24(%r15), %rcx
|
||||||
|
movq %rcx, 8(%rsp) # 8-byte Spill
|
||||||
|
movslq 8(%r15), %rdx
|
||||||
|
movq 16(%r12), %rsi
|
||||||
|
movq 64(%r12), %rdi
|
||||||
|
vmovsd (%rsp), %xmm0 # 8-byte Reload
|
||||||
|
# xmm0 = mem[0],zero
|
||||||
vmulsd .LCPI1_0(%rip), %xmm0, %xmm11
|
vmulsd .LCPI1_0(%rip), %xmm0, %xmm11
|
||||||
movq 24(%rsp), %rcx # 8-byte Reload
|
movq 16(%rsp), %rcx # 8-byte Reload
|
||||||
vmovdqu (%rcx), %xmm10
|
vmovdqu (%rcx), %xmm10
|
||||||
shlq $2, %rdx
|
shlq $2, %rdx
|
||||||
movq %rdx, 48(%rsp) # 8-byte Spill
|
movq %rdx, (%rsp) # 8-byte Spill
|
||||||
xorl %r13d, %r13d
|
xorl %r12d, %r12d
|
||||||
xorl %r14d, %r14d
|
|
||||||
jmp .LBB1_4
|
jmp .LBB1_4
|
||||||
.p2align 4, 0x90
|
.p2align 4, 0x90
|
||||||
.LBB1_14: #
|
.LBB1_5: #
|
||||||
# in Loop: Header=BB1_4 Depth=1
|
# in Loop: Header=BB1_4 Depth=1
|
||||||
movq 8(%rsp), %rbp # 8-byte Reload
|
vxorpd %xmm13, %xmm13, %xmm13
|
||||||
|
movq %r9, %rdx
|
||||||
|
vxorpd %xmm9, %xmm9, %xmm9
|
||||||
|
vxorpd %xmm14, %xmm14, %xmm14
|
||||||
.LBB1_6: #
|
.LBB1_6: #
|
||||||
# in Loop: Header=BB1_4 Depth=1
|
# in Loop: Header=BB1_4 Depth=1
|
||||||
addl %r10d, %r14d
|
vaddsd (%rdi,%r15,8), %xmm14, %xmm0
|
||||||
vaddsd (%rdi,%r12,8), %xmm14, %xmm0
|
vmovsd %xmm0, (%rdi,%r15,8)
|
||||||
vmovsd %xmm0, (%rdi,%r12,8)
|
vaddsd (%rdi,%r10,8), %xmm9, %xmm0
|
||||||
vaddsd (%rdi,%rbp,8), %xmm15, %xmm0
|
vmovsd %xmm0, (%rdi,%r10,8)
|
||||||
vmovsd %xmm0, (%rdi,%rbp,8)
|
|
||||||
vaddsd (%rdi,%r11,8), %xmm13, %xmm0
|
vaddsd (%rdi,%r11,8), %xmm13, %xmm0
|
||||||
vmovsd %xmm0, (%rdi,%r11,8)
|
vmovsd %xmm0, (%rdi,%r11,8)
|
||||||
leal 3(%r10), %ecx
|
leal 3(%r9), %ecx
|
||||||
addl $6, %r10d
|
addl $6, %r9d
|
||||||
testl %ecx, %ecx
|
testl %ecx, %ecx
|
||||||
cmovnsl %ecx, %r10d
|
cmovnsl %ecx, %r9d
|
||||||
sarl $2, %r10d
|
sarl $2, %r9d
|
||||||
movslq %r10d, %rcx
|
movslq %r9d, %rcx
|
||||||
vmovq %rcx, %xmm0
|
vmovq %rcx, %xmm0
|
||||||
vmovq %rdx, %xmm1
|
vmovq %rdx, %xmm1
|
||||||
vpunpcklqdq %xmm0, %xmm1, %xmm0 # xmm0 = xmm1[0],xmm0[0]
|
vpunpcklqdq %xmm0, %xmm1, %xmm0 # xmm0 = xmm1[0],xmm0[0]
|
||||||
vpaddq %xmm0, %xmm10, %xmm10
|
vpaddq %xmm0, %xmm10, %xmm10
|
||||||
incq %r13
|
incq %r12
|
||||||
addq 48(%rsp), %rax # 8-byte Folded Reload
|
addq (%rsp), %rax # 8-byte Folded Reload
|
||||||
cmpq %r15, %r13
|
cmpq %r13, %r12
|
||||||
je .LBB1_7
|
je .LBB1_7
|
||||||
.LBB1_4: #
|
.LBB1_4: #
|
||||||
# =>This Loop Header: Depth=1
|
# =>This Loop Header: Depth=1
|
||||||
# Child Loop BB1_10 Depth 2
|
# Child Loop BB1_10 Depth 2
|
||||||
movq (%rsp), %rcx # 8-byte Reload
|
movq 8(%rsp), %rcx # 8-byte Reload
|
||||||
movslq (%rcx,%r13,4), %r10
|
movslq (%rcx,%r12,4), %r9
|
||||||
leaq (,%r13,2), %rcx
|
leaq (%r12,%r12,2), %rcx
|
||||||
addq %r13, %rcx
|
leal 1(%rcx), %r10d
|
||||||
leal 1(%rcx), %ebp
|
|
||||||
leal 2(%rcx), %r11d
|
leal 2(%rcx), %r11d
|
||||||
movl %ecx, %r12d
|
movl %ecx, %r15d
|
||||||
testq %r10, %r10
|
testq %r9, %r9
|
||||||
jle .LBB1_5
|
jle .LBB1_5
|
||||||
# %bb.9: #
|
# %bb.9: #
|
||||||
# in Loop: Header=BB1_4 Depth=1
|
# in Loop: Header=BB1_4 Depth=1
|
||||||
vmovsd (%rsi,%r12,8), %xmm9 # xmm9 = mem[0],zero
|
vmovsd (%rsi,%r15,8), %xmm15 # xmm15 = mem[0],zero
|
||||||
movq %rbp, 8(%rsp) # 8-byte Spill
|
vmovsd (%rsi,%r10,8), %xmm4 # xmm4 = mem[0],zero
|
||||||
vmovsd (%rsi,%rbp,8), %xmm4 # xmm4 = mem[0],zero
|
|
||||||
vmovsd (%rsi,%r11,8), %xmm1 # xmm1 = mem[0],zero
|
vmovsd (%rsi,%r11,8), %xmm1 # xmm1 = mem[0],zero
|
||||||
movl %r10d, %edx
|
movl %r9d, %edx
|
||||||
vxorpd %xmm14, %xmm14, %xmm14
|
vxorpd %xmm14, %xmm14, %xmm14
|
||||||
xorl %ebx, %ebx
|
xorl %ecx, %ecx
|
||||||
vxorpd %xmm15, %xmm15, %xmm15
|
vxorpd %xmm9, %xmm9, %xmm9
|
||||||
vxorpd %xmm13, %xmm13, %xmm13
|
vxorpd %xmm13, %xmm13, %xmm13
|
||||||
jmp .LBB1_10
|
jmp .LBB1_10
|
||||||
.p2align 4, 0x90
|
.p2align 4, 0x90
|
||||||
.LBB1_13: #
|
.LBB1_13: #
|
||||||
# in Loop: Header=BB1_10 Depth=2
|
# in Loop: Header=BB1_10 Depth=2
|
||||||
incq %rbx
|
incq %rcx
|
||||||
cmpq %rbx, %rdx
|
cmpq %rcx, %rdx
|
||||||
je .LBB1_14
|
je .LBB1_6
|
||||||
.LBB1_10: #
|
.LBB1_10: #
|
||||||
# Parent Loop BB1_4 Depth=1
|
# Parent Loop BB1_4 Depth=1
|
||||||
# => This Inner Loop Header: Depth=2
|
# => This Inner Loop Header: Depth=2
|
||||||
movslq (%rax,%rbx,4), %r9
|
movslq (%rax,%rcx,4), %r8
|
||||||
leaq (%r9,%r9,2), %r8
|
leaq (%r8,%r8,2), %r14
|
||||||
vsubsd (%rsi,%r8,8), %xmm9, %xmm2
|
vsubsd (%rsi,%r14,8), %xmm15, %xmm2
|
||||||
movslq %r8d, %rcx
|
movslq %r14d, %rbp
|
||||||
vsubsd 8(%rsi,%rcx,8), %xmm4, %xmm5
|
vsubsd 8(%rsi,%rbp,8), %xmm4, %xmm5
|
||||||
vsubsd 16(%rsi,%rcx,8), %xmm1, %xmm0
|
vsubsd 16(%rsi,%rbp,8), %xmm1, %xmm0
|
||||||
vmulsd %xmm2, %xmm2, %xmm6
|
vmulsd %xmm2, %xmm2, %xmm6
|
||||||
vfmadd231sd %xmm5, %xmm5, %xmm6 # xmm6 = (xmm5 * xmm5) + xmm6
|
vfmadd231sd %xmm5, %xmm5, %xmm6 # xmm6 = (xmm5 * xmm5) + xmm6
|
||||||
vfmadd231sd %xmm0, %xmm0, %xmm6 # xmm6 = (xmm0 * xmm0) + xmm6
|
vfmadd231sd %xmm0, %xmm0, %xmm6 # xmm6 = (xmm0 * xmm0) + xmm6
|
||||||
@ -539,70 +534,45 @@ computeForceLJHalfNeigh: #
|
|||||||
# in Loop: Header=BB1_10 Depth=2
|
# in Loop: Header=BB1_10 Depth=2
|
||||||
vmovsd .LCPI1_1(%rip), %xmm3 # xmm3 = mem[0],zero
|
vmovsd .LCPI1_1(%rip), %xmm3 # xmm3 = mem[0],zero
|
||||||
vdivsd %xmm6, %xmm3, %xmm6
|
vdivsd %xmm6, %xmm3, %xmm6
|
||||||
vmulsd 16(%rsp), %xmm6, %xmm7 # 8-byte Folded Reload
|
vmulsd 32(%rsp), %xmm6, %xmm3 # 8-byte Folded Reload
|
||||||
vmulsd %xmm6, %xmm6, %xmm8
|
vmulsd %xmm6, %xmm6, %xmm8
|
||||||
vmulsd %xmm7, %xmm8, %xmm7
|
vmulsd %xmm3, %xmm8, %xmm3
|
||||||
vaddsd .LCPI1_2(%rip), %xmm7, %xmm3
|
vaddsd .LCPI1_2(%rip), %xmm3, %xmm7
|
||||||
vmulsd %xmm6, %xmm11, %xmm6
|
vmulsd %xmm6, %xmm11, %xmm6
|
||||||
vmulsd %xmm7, %xmm6, %xmm6
|
|
||||||
vmulsd %xmm3, %xmm6, %xmm3
|
vmulsd %xmm3, %xmm6, %xmm3
|
||||||
|
vmulsd %xmm7, %xmm3, %xmm3
|
||||||
vmulsd %xmm2, %xmm3, %xmm6
|
vmulsd %xmm2, %xmm3, %xmm6
|
||||||
vaddsd %xmm6, %xmm14, %xmm14
|
vaddsd %xmm6, %xmm14, %xmm14
|
||||||
vmulsd %xmm5, %xmm3, %xmm2
|
vmulsd %xmm5, %xmm3, %xmm2
|
||||||
vaddsd %xmm2, %xmm15, %xmm15
|
vaddsd %xmm2, %xmm9, %xmm9
|
||||||
vmulsd %xmm0, %xmm3, %xmm0
|
vmulsd %xmm0, %xmm3, %xmm0
|
||||||
vaddsd %xmm0, %xmm13, %xmm13
|
vaddsd %xmm0, %xmm13, %xmm13
|
||||||
cmpl %r15d, %r9d
|
cmpl %r13d, %r8d
|
||||||
jge .LBB1_13
|
jge .LBB1_13
|
||||||
# %bb.12: #
|
# %bb.12: #
|
||||||
# in Loop: Header=BB1_10 Depth=2
|
# in Loop: Header=BB1_10 Depth=2
|
||||||
leaq 1(%rcx), %rbp
|
leaq 1(%rbp), %rbx
|
||||||
addq $2, %rcx
|
addq $2, %rbp
|
||||||
vmovsd (%rdi,%r8,8), %xmm3 # xmm3 = mem[0],zero
|
vmovsd (%rdi,%r14,8), %xmm3 # xmm3 = mem[0],zero
|
||||||
vsubsd %xmm6, %xmm3, %xmm3
|
vsubsd %xmm6, %xmm3, %xmm3
|
||||||
vmovsd %xmm3, (%rdi,%r8,8)
|
vmovsd %xmm3, (%rdi,%r14,8)
|
||||||
vmovsd (%rdi,%rbp,8), %xmm3 # xmm3 = mem[0],zero
|
vmovsd (%rdi,%rbx,8), %xmm3 # xmm3 = mem[0],zero
|
||||||
vsubsd %xmm2, %xmm3, %xmm2
|
vsubsd %xmm2, %xmm3, %xmm2
|
||||||
vmovsd %xmm2, (%rdi,%rbp,8)
|
vmovsd %xmm2, (%rdi,%rbx,8)
|
||||||
vmovsd (%rdi,%rcx,8), %xmm2 # xmm2 = mem[0],zero
|
vmovsd (%rdi,%rbp,8), %xmm2 # xmm2 = mem[0],zero
|
||||||
vsubsd %xmm0, %xmm2, %xmm0
|
vsubsd %xmm0, %xmm2, %xmm0
|
||||||
vmovsd %xmm0, (%rdi,%rcx,8)
|
vmovsd %xmm0, (%rdi,%rbp,8)
|
||||||
jmp .LBB1_13
|
jmp .LBB1_13
|
||||||
.p2align 4, 0x90
|
|
||||||
.LBB1_5: #
|
|
||||||
# in Loop: Header=BB1_4 Depth=1
|
|
||||||
vxorpd %xmm13, %xmm13, %xmm13
|
|
||||||
movq %r10, %rdx
|
|
||||||
vxorpd %xmm15, %xmm15, %xmm15
|
|
||||||
vxorpd %xmm14, %xmm14, %xmm14
|
|
||||||
jmp .LBB1_6
|
|
||||||
.LBB1_7: #
|
.LBB1_7: #
|
||||||
movq 24(%rsp), %rax # 8-byte Reload
|
movq 16(%rsp), %rax # 8-byte Reload
|
||||||
vmovdqu %xmm10, (%rax)
|
vmovdqu %xmm10, (%rax)
|
||||||
.LBB1_8: #
|
.LBB1_8: #
|
||||||
movl $.L.str.1, %edi
|
movl $.L.str.1, %edi
|
||||||
callq likwid_markerStopRegion
|
callq likwid_markerStopRegion
|
||||||
xorl %eax, %eax
|
xorl %eax, %eax
|
||||||
callq getTimeStamp
|
callq getTimeStamp
|
||||||
movq 40(%rsp), %rax # 8-byte Reload
|
vsubsd 24(%rsp), %xmm0, %xmm0 # 8-byte Folded Reload
|
||||||
vmovsd 264(%rax), %xmm3 # xmm3 = mem[0],zero
|
addq $40, %rsp
|
||||||
vsubsd 32(%rsp), %xmm0, %xmm2 # 8-byte Folded Reload
|
|
||||||
vmulsd .LCPI1_3(%rip), %xmm3, %xmm0
|
|
||||||
vmulsd %xmm2, %xmm0, %xmm0
|
|
||||||
vmovapd %xmm2, %xmm1
|
|
||||||
vmovsd %xmm2, 16(%rsp) # 8-byte Spill
|
|
||||||
movl %r14d, %eax
|
|
||||||
vxorps %xmm12, %xmm12, %xmm12
|
|
||||||
vcvtsi2sd %rax, %xmm12, %xmm2
|
|
||||||
vdivsd %xmm2, %xmm0, %xmm2
|
|
||||||
movl $.L.str.2, %edi
|
|
||||||
movl %r14d, %esi
|
|
||||||
vmovapd %xmm3, %xmm0
|
|
||||||
movb $3, %al
|
|
||||||
callq printf
|
|
||||||
vmovsd 16(%rsp), %xmm0 # 8-byte Reload
|
|
||||||
# xmm0 = mem[0],zero
|
|
||||||
addq $56, %rsp
|
|
||||||
.cfi_def_cfa_offset 56
|
.cfi_def_cfa_offset 56
|
||||||
popq %rbx
|
popq %rbx
|
||||||
.cfi_def_cfa_offset 48
|
.cfi_def_cfa_offset 48
|
||||||
@ -642,10 +612,8 @@ computeForceLJFullNeigh_simd: #
|
|||||||
.LBB2_2: #
|
.LBB2_2: #
|
||||||
xorl %eax, %eax
|
xorl %eax, %eax
|
||||||
callq getTimeStamp
|
callq getTimeStamp
|
||||||
movl $.L.str, %edi
|
|
||||||
callq likwid_markerStartRegion
|
|
||||||
movq stderr(%rip), %rcx
|
movq stderr(%rip), %rcx
|
||||||
movl $.L.str.3, %edi
|
movl $.L.str.2, %edi
|
||||||
movl $65, %esi
|
movl $65, %esi
|
||||||
movl $1, %edx
|
movl $1, %edx
|
||||||
callq fwrite
|
callq fwrite
|
||||||
@ -666,11 +634,7 @@ computeForceLJFullNeigh_simd: #
|
|||||||
.size .L.str.1, 18
|
.size .L.str.1, 18
|
||||||
.type .L.str.2,@object #
|
.type .L.str.2,@object #
|
||||||
.L.str.2:
|
.L.str.2:
|
||||||
.asciz "Its: %u Freq: %f Time: %f\nCy/it: %f (half-neigh)\n"
|
|
||||||
.size .L.str.2, 52
|
|
||||||
.type .L.str.3,@object #
|
|
||||||
.L.str.3:
|
|
||||||
.asciz "Error: SIMD kernel not implemented for specified instruction set!"
|
.asciz "Error: SIMD kernel not implemented for specified instruction set!"
|
||||||
.size .L.str.3, 66
|
.size .L.str.2, 66
|
||||||
.ident "Intel(R) oneAPI DPC++ Compiler 2021.1-beta05 (2020.2.0.0304)"
|
.ident "Intel(R) oneAPI DPC++ Compiler 2021.1-beta05 (2020.2.0.0304)"
|
||||||
.section ".note.GNU-stack","",@progbits
|
.section ".note.GNU-stack","",@progbits
|
||||||
Loading…
Reference in New Issue
Block a user