153 lines
15 KiB
Plaintext
153 lines
15 KiB
Plaintext
|
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.
|