From 11b2d4bcc1b613af101706e05075a7f4c040d202 Mon Sep 17 00:00:00 2001 From: Rafael Ravedutti Date: Thu, 29 Apr 2021 17:57:37 +0200 Subject: [PATCH] Update results for arch_analysis and stub script Signed-off-by: Rafael Ravedutti --- arch_analysis/iaca_force_aos_geq1200.txt | 79 +++ ...orce_soa.txt => iaca_force_aos_lt1200.txt} | 0 arch_analysis/iaca_force_aos_lt8.txt | 82 ++++ arch_analysis/iaca_force_soa_geq1200.txt | 74 +++ arch_analysis/iaca_force_soa_lt1200.txt | 72 +++ arch_analysis/iaca_force_soa_lt8.txt | 78 +++ arch_analysis/osaca_force_aos_geq1200.txt | 80 ++++ ...rce_soa.txt => osaca_force_aos_lt1200.txt} | 0 arch_analysis/osaca_force_aos_lt8.txt | 91 ++++ arch_analysis/osaca_force_soa_geq1200.txt | 71 +++ arch_analysis/osaca_force_soa_lt1200.txt | 69 +++ arch_analysis/osaca_force_soa_lt8.txt | 79 +++ scripts/results_aos_medusa.txt | 450 ++++++++++++++++++ scripts/results_aos_skylakesp2.txt | 450 ++++++++++++++++++ scripts/results_soa_skylakesp2.txt | 450 ++++++++++++++++++ scripts/run_stub.sh | 2 +- src/main-stub.c | 2 +- 17 files changed, 2127 insertions(+), 2 deletions(-) create mode 100644 arch_analysis/iaca_force_aos_geq1200.txt rename arch_analysis/{iaca_output_force_soa.txt => iaca_force_aos_lt1200.txt} (100%) create mode 100644 arch_analysis/iaca_force_aos_lt8.txt create mode 100644 arch_analysis/iaca_force_soa_geq1200.txt create mode 100644 arch_analysis/iaca_force_soa_lt1200.txt create mode 100644 arch_analysis/iaca_force_soa_lt8.txt create mode 100644 arch_analysis/osaca_force_aos_geq1200.txt rename arch_analysis/{osaca_output_force_soa.txt => osaca_force_aos_lt1200.txt} (100%) create mode 100644 arch_analysis/osaca_force_aos_lt8.txt create mode 100644 arch_analysis/osaca_force_soa_geq1200.txt create mode 100644 arch_analysis/osaca_force_soa_lt1200.txt create mode 100644 arch_analysis/osaca_force_soa_lt8.txt create mode 100644 scripts/results_aos_medusa.txt create mode 100644 scripts/results_aos_skylakesp2.txt create mode 100644 scripts/results_soa_skylakesp2.txt diff --git a/arch_analysis/iaca_force_aos_geq1200.txt b/arch_analysis/iaca_force_aos_geq1200.txt new file mode 100644 index 0000000..a10a778 --- /dev/null +++ b/arch_analysis/iaca_force_aos_geq1200.txt @@ -0,0 +1,79 @@ +iwia021h@testfront1:~/MD-Bench/asm$ iaca -arch SKX force_aos_geq1200_markers.o +Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45 +Analyzed File - force_aos_geq1200_markers.o +Binary Format - 64Bit +Architecture - SKX +Analysis Type - Throughput + +Throughput Analysis Report +-------------------------- +Block Throughput: 33.05 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 | 20.0 0.0 | 4.5 | 13.0 13.0 | 13.0 13.0 | 0.0 | 18.0 | 4.5 | 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 | | | | | | 1.0 | | | vpcmpgtd k3, ymm2, ymm3 +| 2 | | 1.0 | 1.0 1.0 | | | | | | vmovdqu32 ymm17{k3}{z}, ymmword ptr [r15+r13*4] +| 1 | 1.0 | | | | | | | | kmovw r9d, k3 +| 1 | | 1.0 | | | | | | | vpaddd ymm18, ymm17, ymm17 +| 1 | | 1.0 | | | | | | | vpaddd ymm17, ymm17, ymm18 +| 1 | 1.0 | | | | | | | | kmovw k1, k3 +| 1 | 1.0 | | | | | | | | kmovw k2, k3 +| 1* | | | | | | | | | vpxord zmm18, zmm18, zmm18 +| 1* | | | | | | | | | vpxord zmm19, zmm19, zmm19 +| 1* | | | | | | | | | vpxord zmm20, zmm20, zmm20 +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm18, k1, zmmword ptr [rdi+ymm17*8+0x10] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm19, k2, zmmword ptr [rdi+ymm17*8+0x8] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm20, k3, zmmword ptr [rdi+ymm17*8] +| 1 | | 0.5 | | | | | 0.5 | | add r13, 0x8 +| 1 | | 1.0 | | | | | | | vpaddd ymm3, ymm3, ymm16 +| 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm29, zmm4, zmm18 +| 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm27, zmm0, zmm19 +| 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm26, zmm1, zmm20 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm25, zmm27, zmm27 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm25, zmm26, zmm26 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm25, zmm29, zmm29 +| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm24, zmm25 +| 1 | | | | | | 1.0 | | | vcmppd k2, zmm25, zmm14, 0x1 +| 1 | | | | | | 1.0 | | | vfpclasspd k0, zmm24, 0x1e +| 1 | 1.0 | | | | | | | | kmovw edx, k2 +| 1 | 1.0 | | | | | | | | knotw k1, k0 +| 1* | | | | | | | | | vmovaps zmm17, zmm25 +| 1 | | | | | | | 1.0 | | and r9d, edx +| 2^ | | | | 1.0 1.0 | | 1.0 | | | vfnmadd213pd zmm17, zmm24, qword ptr [rip]{1to8} +| 1 | | | | | | 1.0 | | | kmovw k3, r9d +| 1 | 1.0 | | | | | | | | vmulpd zmm18, zmm17, zmm17 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd213pd zmm24{k1}, zmm17, zmm24 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd213pd zmm24{k1}, zmm18, zmm24 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm19, zmm24, zmm13 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm21, zmm24, zmm10 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm22, zmm24, zmm19 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm20, zmm24, zmm22 +| 1 | 0.5 | | | | | 0.5 | | | vfmsub213pd zmm24, zmm22, zmm5 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm23, zmm20, zmm21 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm28, zmm23, zmm24 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm9{k3}, zmm28, zmm26 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm8{k3}, zmm28, zmm27 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm11{k3}, zmm28, zmm29 +| 1* | | | | | | | | | cmp r13, rbx +| 0*F | | | | | | | | | jb 0xfffffffffffffef7 +Total Num Of Uops: 60 +Analysis Notes: +Backend allocation was stalled due to unavailable allocation resources. +There were bubbles in the frontend. diff --git a/arch_analysis/iaca_output_force_soa.txt b/arch_analysis/iaca_force_aos_lt1200.txt similarity index 100% rename from arch_analysis/iaca_output_force_soa.txt rename to arch_analysis/iaca_force_aos_lt1200.txt diff --git a/arch_analysis/iaca_force_aos_lt8.txt b/arch_analysis/iaca_force_aos_lt8.txt new file mode 100644 index 0000000..973db7c --- /dev/null +++ b/arch_analysis/iaca_force_aos_lt8.txt @@ -0,0 +1,82 @@ +Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45 +Analyzed File - force_aos_lt8_markers.o +Binary Format - 64Bit +Architecture - SKX +Analysis Type - Throughput + +Throughput Analysis Report +-------------------------- +Block Throughput: 69.79 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 | 21.0 0.0 | 5.5 | 13.0 13.0 | 13.0 13.0 | 0.0 | 21.0 | 5.5 | 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 | | 1.0 | | | | | | | imul rcx, r8 +| 1 | | | | | | 1.0 | | | vbroadcastsd zmm4, xmm6 +| 1 | | | | | | | 1.0 | | sub r11d, r14d +| 1 | | 0.5 | | | | | 0.5 | | add rcx, r10 +| 1 | | | | | | 1.0 | | | vpbroadcastd ymm0, r11d +| 1 | | | | | | 1.0 | | | vpcmpgtd k3, ymm0, ymm15 +| 1 | | 0.5 | | | | | 0.5 | | movsxd r14, r14d +| 1 | 1.0 | | | | | | | | kmovw ebx, k3 +| 2 | | 1.0 | 1.0 1.0 | | | | | | vmovdqu32 ymm1{k3}{z}, ymmword ptr [rcx+r14*4] +| 1 | | 1.0 | | | | | | | vpaddd ymm2, ymm1, ymm1 +| 1 | | 1.0 | | | | | | | vpaddd ymm0, ymm1, ymm2 +| 1 | 1.0 | | | | | | | | kmovw k1, k3 +| 1 | 1.0 | | | | | | | | kmovw k2, k3 +| 1* | | | | | | | | | vpxord zmm1, zmm1, zmm1 +| 1* | | | | | | | | | vpxord zmm2, zmm2, zmm2 +| 1* | | | | | | | | | vpxord zmm3, zmm3, zmm3 +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm1, k1, zmmword ptr [rdi+ymm0*8+0x10] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm2, k2, zmmword ptr [rdi+ymm0*8+0x8] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm3, k3, zmmword ptr [rdi+ymm0*8] +| 1 | | | | | | 1.0 | | | vbroadcastsd zmm7, xmm7 +| 1 | | | | | | 1.0 | | | vbroadcastsd zmm12, xmm12 +| 1 | 1.0 | | | | | | | | vsubpd zmm23, zmm12, zmm1 +| 1 | 1.0 | | | | | | | | vsubpd zmm21, zmm7, zmm2 +| 1 | 0.5 | | | | | 0.5 | | | vsubpd zmm20, zmm4, zmm3 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm19, zmm21, zmm21 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm19, zmm20, zmm20 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm19, zmm23, zmm23 +| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm18, zmm19 +| 1 | | | | | | 1.0 | | | vcmppd k2, zmm19, zmm14, 0x1 +| 1 | | | | | | 1.0 | | | vfpclasspd k0, zmm18, 0x1e +| 1 | 1.0 | | | | | | | | kmovw ecx, k2 +| 1 | 1.0 | | | | | | | | knotw k1, k0 +| 1* | | | | | | | | | vmovaps zmm0, zmm19 +| 1 | | 0.5 | | | | | 0.5 | | and ebx, ecx +| 2^ | | | | 1.0 1.0 | | 1.0 | | | vfnmadd213pd zmm0, zmm18, qword ptr [rip]{1to8} +| 1 | | | | | | 1.0 | | | kmovw k3, ebx +| 1 | 1.0 | | | | | | | | vmulpd zmm1, zmm0, zmm0 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd213pd zmm18{k1}, zmm0, zmm18 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd213pd zmm18{k1}, zmm1, zmm18 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm2, zmm18, zmm13 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm4, zmm18, zmm10 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm6, zmm18, zmm2 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm3, zmm18, zmm6 +| 1 | 0.5 | | | | | 0.5 | | | vfmsub213pd zmm18, zmm6, zmm5 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm17, zmm3, zmm4 +| 1 | 0.5 | | | | | 0.5 | | | vmulpd zmm22, zmm17, zmm18 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm9{k3}, zmm22, zmm20 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm8{k3}, zmm22, zmm21 +| 1 | 0.5 | | | | | 0.5 | | | vfmadd231pd zmm11{k3}, zmm22, zmm23 +Total Num Of Uops: 65 +Analysis Notes: +Backend allocation was stalled due to unavailable allocation resources. +There were bubbles in the frontend. diff --git a/arch_analysis/iaca_force_soa_geq1200.txt b/arch_analysis/iaca_force_soa_geq1200.txt new file mode 100644 index 0000000..1deb2bc --- /dev/null +++ b/arch_analysis/iaca_force_soa_geq1200.txt @@ -0,0 +1,74 @@ +iwia021h@testfront1:~/MD-Bench/asm$ iaca -arch SKX force_soa_geq1200_markers.o +Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45 +Analyzed File - force_soa_geq1200_markers.o +Binary Format - 64Bit +Architecture - SKX +Analysis Type - Throughput + +Throughput Analysis Report +-------------------------- +Block Throughput: 31.47 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 | 18.0 0.0 | 3.0 | 13.0 13.0 | 13.0 13.0 | 0.0 | 18.0 | 3.0 | 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, ymm18 +| 2 | | 1.0 | 1.0 1.0 | | | | | | vmovdqu32 ymm20{k5}{z}, ymmword ptr [rcx+r15*4] +| 1* | | | | | | | | | vmovaps zmm22, zmm19 +| 1 | | 1.0 | | | | | | | add r15, 0x8 +| 1 | 1.0 | | | | | | | | kmovw k2, k5 +| 1* | | | | | | | | | vmovaps zmm21, zmm19 +| 1 | 1.0 | | | | | | | | kmovw k1, k5 +| 1* | | | | | | | | | vmovaps zmm23, zmm19 +| 1 | 1.0 | | | | | | | | kmovw k3, k5 +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm23, k3, zmmword ptr [rsi+ymm20*8] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm22, k2, zmmword ptr [rax+ymm20*8] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm21, k1, zmmword ptr [rdx+ymm20*8] +| 1 | | | | | | 1.0 | | | vsubpd zmm0, zmm5, zmm22 +| 1 | | | | | | 1.0 | | | vsubpd zmm1, zmm2, zmm21 +| 1 | | | | | | 1.0 | | | vsubpd zmm21, zmm6, zmm23 +| 1 | 1.0 | | | | | | | | vmulpd zmm20, zmm0, zmm0 +| 1 | | | | | | 1.0 | | | vfmadd231pd zmm20, zmm1, zmm1 +| 1 | 1.0 | | | | | | | | vfmadd231pd zmm20, zmm21, zmm21 +| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm31, zmm20 +| 1 | | | | | | 1.0 | | | vcmppd k6{k5}, zmm20, zmm16, 0x1 +| 1 | | | | | | 1.0 | | | vfpclasspd k0, zmm31, 0x1e +| 1* | | | | | | | | | vmovaps zmm24, zmm20 +| 2^ | 1.0 | | | 1.0 1.0 | | | | | vfnmadd213pd zmm24, zmm31, qword ptr [rip]{1to8} +| 1 | 1.0 | | | | | | | | knotw k4, k0 +| 1 | | | | | | 1.0 | | | vmulpd zmm25, zmm24, zmm24 +| 1 | | | | | | 1.0 | | | vfmadd213pd zmm31{k4}, zmm24, zmm31 +| 1 | 1.0 | | | | | | | | vfmadd213pd zmm31{k4}, zmm25, zmm31 +| 1 | | | | | | 1.0 | | | vmulpd zmm26, zmm31, zmm15 +| 1 | 1.0 | | | | | | | | vmulpd zmm28, zmm31, zmm14 +| 1 | | | | | | 1.0 | | | vmulpd zmm29, zmm31, zmm26 +| 1 | 1.0 | | | | | | | | vmulpd zmm27, zmm31, zmm29 +| 1 | | | | | | 1.0 | | | vfmsub213pd zmm31, zmm29, zmm7 +| 1 | 1.0 | | | | | | | | vmulpd zmm30, zmm27, zmm28 +| 1 | | | | | | 1.0 | | | vmulpd zmm24, zmm30, zmm31 +| 1 | 1.0 | | | | | | | | vfmadd231pd zmm13{k6}, zmm24, zmm1 +| 1 | | | | | | 1.0 | | | vfmadd231pd zmm12{k6}, zmm24, zmm0 +| 1 | 1.0 | | | | | | | | vfmadd231pd zmm11{k6}, zmm24, zmm21 +| 1* | | | | | | | | | cmp r15, r14 +| 0*F | | | | | | | | | jb 0xffffffffffffff19 +Total Num Of Uops: 55 +Analysis Notes: +Backend allocation was stalled due to unavailable allocation resources. +There were bubbles in the frontend. diff --git a/arch_analysis/iaca_force_soa_lt1200.txt b/arch_analysis/iaca_force_soa_lt1200.txt new file mode 100644 index 0000000..38f7014 --- /dev/null +++ b/arch_analysis/iaca_force_soa_lt1200.txt @@ -0,0 +1,72 @@ +iwia021h@testfront1:~/MD-Bench/asm$ iaca -arch SKX force_soa_lt1200_markers.o +Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45 +Analyzed File - force_soa_lt1200_markers.o +Binary Format - 64Bit +Architecture - SKX +Analysis Type - Throughput + +Throughput Analysis Report +-------------------------- +Block Throughput: 30.25 Cycles Throughput Bottleneck: Backend +Loop Count: 23 +Port Binding In Cycles Per Iteration: +-------------------------------------------------------------------------------------------------- +| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 | +-------------------------------------------------------------------------------------------------- +| Cycles | 16.0 0.0 | 2.0 | 13.0 13.0 | 13.0 13.0 | 0.0 | 19.0 | 3.0 | 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 | | | vpcmpeqb k2, xmm0, xmm0 +| 1 | | 1.0 | | | | | | | add r9d, 0x8 +| 1 | | | | | | 1.0 | | | vpcmpeqb k1, xmm0, xmm0 +| 1 | | | | | | 1.0 | | | vpcmpeqb k3, xmm0, xmm0 +| 1 | | | 1.0 1.0 | | | | | | vmovdqu ymm3, ymmword ptr [rcx+r14*4] +| 1 | | 1.0 | | | | | | | add r14, 0x8 +| 1* | | | | | | | | | vpxord zmm5, zmm5, zmm5 +| 1* | | | | | | | | | vpxord zmm4, zmm4, zmm4 +| 1* | | | | | | | | | vpxord zmm6, zmm6, zmm6 +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm5, k2, zmmword ptr [rax+ymm3*8] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm4, k1, zmmword ptr [rdx+ymm3*8] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm6, k3, zmmword ptr [rsi+ymm3*8] +| 1 | | | | | | 1.0 | | | vsubpd zmm29, zmm1, zmm5 +| 1 | 1.0 | | | | | | | | vsubpd zmm28, zmm0, zmm4 +| 1 | | | | | | 1.0 | | | vsubpd zmm31, zmm2, zmm6 +| 1 | 1.0 | | | | | | | | vmulpd zmm20, zmm29, zmm29 +| 1 | | | | | | 1.0 | | | vfmadd231pd zmm20, zmm28, zmm28 +| 1 | 1.0 | | | | | | | | vfmadd231pd zmm20, zmm31, zmm31 +| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm27, zmm20 +| 1 | | | | | | 1.0 | | | vcmppd k5, zmm20, zmm16, 0x1 +| 1 | | | | | | 1.0 | | | vfpclasspd k0, zmm27, 0x1e +| 2^ | 1.0 | | | 1.0 1.0 | | | | | vfnmadd213pd zmm20, zmm27, qword ptr [rip]{1to8} +| 1 | 1.0 | | | | | | | | knotw k4, k0 +| 1 | | | | | | 1.0 | | | vmulpd zmm21, zmm20, zmm20 +| 1 | | | | | | 1.0 | | | vfmadd213pd zmm27{k4}, zmm20, zmm27 +| 1 | 1.0 | | | | | | | | vfmadd213pd zmm27{k4}, zmm21, zmm27 +| 1 | | | | | | 1.0 | | | vmulpd zmm22, zmm27, zmm15 +| 1 | 1.0 | | | | | | | | vmulpd zmm24, zmm27, zmm14 +| 1 | | | | | | 1.0 | | | vmulpd zmm25, zmm27, zmm22 +| 1 | 1.0 | | | | | | | | vmulpd zmm23, zmm27, zmm25 +| 1 | | | | | | 1.0 | | | vfmsub213pd zmm27, zmm25, zmm7 +| 1 | 1.0 | | | | | | | | vmulpd zmm26, zmm23, zmm24 +| 1 | | | | | | 1.0 | | | vmulpd zmm30, zmm26, zmm27 +| 1 | 1.0 | | | | | | | | vfmadd231pd zmm13{k5}, zmm30, zmm28 +| 1 | | | | | | 1.0 | | | vfmadd231pd zmm12{k5}, zmm30, zmm29 +| 1 | 1.0 | | | | | | | | vfmadd231pd zmm11{k5}, zmm30, zmm31 +| 1* | | | | | | | | | cmp r9d, ebx +| 0*F | | | | | | | | | jb 0xffffffffffffff22 +Total Num Of Uops: 52 +Analysis Notes: +Backend allocation was stalled due to unavailable allocation resources. +There were bubbles in the frontend. diff --git a/arch_analysis/iaca_force_soa_lt8.txt b/arch_analysis/iaca_force_soa_lt8.txt new file mode 100644 index 0000000..c9782f9 --- /dev/null +++ b/arch_analysis/iaca_force_soa_lt8.txt @@ -0,0 +1,78 @@ +iwia021h@testfront1:~/MD-Bench/asm$ iaca -arch SKX force_soa_lt8_markers.o +Intel(R) Architecture Code Analyzer Version - v3.0-28-g1ba2cbb build date: 2017-10-23;16:42:45 +Analyzed File - force_soa_lt8_markers.o +Binary Format - 64Bit +Architecture - SKX +Analysis Type - Throughput + +Throughput Analysis Report +-------------------------- +Block Throughput: 35.00 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 | 20.0 0.0 | 4.0 | 13.0 13.0 | 13.0 13.0 | 0.0 | 20.0 | 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 | | | | | | | imul r8, r12 +| 1 | | | | | | 1.0 | | | vbroadcastsd zmm9, xmm9 +| 1 | | | | | | 1.0 | | | vbroadcastsd zmm2, xmm8 +| 1 | | | | | | 1.0 | | | vbroadcastsd zmm10, xmm10 +| 1 | | 1.0 | | | | | | | sub r13d, ebx +| 1 | | 1.0 | | | | | | | add r8, r11 +| 1 | | | | | | 1.0 | | | vpbroadcastd ymm0, r13d +| 1 | | | | | | 1.0 | | | vpcmpgtd k5, ymm0, ymm17 +| 1 | | | | | | | 1.0 | | movsxd rbx, ebx +| 1* | | | | | | | | | vmovaps zmm4, zmm19 +| 1 | 1.0 | | | | | | | | kmovw k2, k5 +| 1* | | | | | | | | | vmovaps zmm3, zmm19 +| 2 | | 1.0 | 1.0 1.0 | | | | | | vmovdqu32 ymm1{k5}{z}, ymmword ptr [r8+rbx*4] +| 1 | 1.0 | | | | | | | | kmovw k1, k5 +| 1* | | | | | | | | | vmovaps zmm5, zmm19 +| 1 | 1.0 | | | | | | | | kmovw k3, k5 +| 5^ | 2.0 | | 4.0 4.0 | 4.0 4.0 | | | 1.0 | | vgatherdpd zmm5, k3, zmmword ptr [rsi+ymm1*8] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm4, k2, zmmword ptr [rax+ymm1*8] +| 5^ | 1.0 | | 4.0 4.0 | 4.0 4.0 | | 1.0 | 1.0 | | vgatherdpd zmm3, k1, zmmword ptr [rdx+ymm1*8] +| 1 | 1.0 | | | | | | | | vsubpd zmm30, zmm10, zmm5 +| 1 | | | | | | 1.0 | | | vsubpd zmm28, zmm9, zmm4 +| 1 | 1.0 | | | | | | | | vsubpd zmm27, zmm2, zmm3 +| 1 | | | | | | 1.0 | | | vmulpd zmm26, zmm28, zmm28 +| 1 | 1.0 | | | | | | | | vfmadd231pd zmm26, zmm27, zmm27 +| 1 | | | | | | 1.0 | | | vfmadd231pd zmm26, zmm30, zmm30 +| 3 | 2.0 | | | | | 1.0 | | | vrcp14pd zmm25, zmm26 +| 1 | | | | | | 1.0 | | | vcmppd k6{k5}, zmm26, zmm16, 0x1 +| 1 | | | | | | 1.0 | | | vfpclasspd k0, zmm25, 0x1e +| 1* | | | | | | | | | vmovaps zmm6, zmm26 +| 2^ | 1.0 | | | 1.0 1.0 | | | | | vfnmadd213pd zmm6, zmm25, qword ptr [rip]{1to8} +| 1 | 1.0 | | | | | | | | knotw k4, k0 +| 1 | | | | | | 1.0 | | | vmulpd zmm8, zmm6, zmm6 +| 1 | 1.0 | | | | | | | | vfmadd213pd zmm25{k4}, zmm6, zmm25 +| 1 | | | | | | 1.0 | | | vfmadd213pd zmm25{k4}, zmm8, zmm25 +| 1 | 1.0 | | | | | | | | vmulpd zmm20, zmm25, zmm15 +| 1 | | | | | | 1.0 | | | vmulpd zmm22, zmm25, zmm14 +| 1 | 1.0 | | | | | | | | vmulpd zmm23, zmm25, zmm20 +| 1 | | | | | | 1.0 | | | vmulpd zmm21, zmm25, zmm23 +| 1 | 1.0 | | | | | | | | vfmsub213pd zmm25, zmm23, zmm7 +| 1 | | | | | | 1.0 | | | vmulpd zmm24, zmm21, zmm22 +| 1 | 1.0 | | | | | | | | vmulpd zmm29, zmm24, zmm25 +| 1 | | | | | | 1.0 | | | vfmadd231pd zmm13{k6}, zmm29, zmm27 +| 1 | 1.0 | | | | | | | | vfmadd231pd zmm12{k6}, zmm29, zmm28 +| 1 | | | | | | 1.0 | | | vfmadd231pd zmm11{k6}, zmm29, zmm30 +Total Num Of Uops: 60 +Analysis Notes: +Backend allocation was stalled due to unavailable allocation resources. +There were bubbles in the frontend. diff --git a/arch_analysis/osaca_force_aos_geq1200.txt b/arch_analysis/osaca_force_aos_geq1200.txt new file mode 100644 index 0000000..5e0907a --- /dev/null +++ b/arch_analysis/osaca_force_aos_geq1200.txt @@ -0,0 +1,80 @@ +iwia021h@testfront1:~/MD-Bench/asm$ /home/hpc/iwia/iwia021h/.local/bin/osaca --ignore-unknown --arch=CSX force_aos_geq1200_markers.s +Open Source Architecture Code Analyzer (OSACA) - 0.3.14 +Analyzed file: force_aos_geq1200_markers.s +Architecture: CSX +Timestamp: 2021-04-29 15:53:50 + + + 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 | +------------------------------------------------------------------------------------------------- + 196 | | | | | | 1.00 | | || | | vpcmpgtd %ymm3, %ymm2, %k3 #67.9 + 197 | 0.00 | 1.00 | 0.50 0.50 | 0.50 0.50 | | 0.00 | | || 4.0 | | vmovdqu32 (%r15,%r13,4), %ymm17{%k3}{z} #68.21 + 198 | 1.00 | | | | | | | || | | kmovw %k3, %r9d #67.9 + 199 | 0.00 | 1.00 | | | | 0.00 | | || 1.0 | | vpaddd %ymm17, %ymm17, %ymm18 #69.36 + 200 | 0.00 | 1.00 | | | | 0.00 | | || 1.0 | | vpaddd %ymm18, %ymm17, %ymm17 #69.36 + 201 | | | | | | | | || | | # LOE rax rcx rbx rbp rsi rdi r8 r10 r13 r15 r9d r11d r12d r14d xmm6 xmm7 xmm12 ymm2 ymm3 ymm15 ymm16 ymm17 zmm0 zmm1 zmm4 zmm5 zmm8 zmm9 zmm10 zmm11 zmm13 zmm14 k3 + 202 | | | | | | | | || | | ..B1.21: # Preds ..B1.18 + 203 | | | | | | | | || | | # Execution count [1.25e+01] + 204 | 1.00 | | | | | | | || | | kmovw %k3, %k1 #69.36 + 205 | 1.00 | | | | | | | || | | kmovw %k3, %k2 #69.36 + 206 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm18, %zmm18, %zmm18 #69.36 + 207 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm19, %zmm19, %zmm19 #69.36 + 208 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm20, %zmm20, %zmm20 #69.36 + 209 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd 16(%rdi,%ymm17,8), %zmm18{%k1} #69.36 + 210 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || 4.0 | | vgatherdpd 8(%rdi,%ymm17,8), %zmm19{%k2} #69.36 + 211 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd (%rdi,%ymm17,8), %zmm20{%k3} #69.36 + 212 | | | | | | | | || | | # LOE rax rcx rbx rbp rsi rdi r8 r10 r13 r15 r9d r11d r12d r14d xmm6 xmm7 xmm12 ymm2 ymm3 ymm15 ymm16 zmm0 zmm1 zmm4 zmm5 zmm8 zmm9 zmm10 zmm11 zmm13 zmm14 zmm18 zmm19 zmm20 + 213 | | | | | | | | || | | ..B1.22: # Preds ..B1.21 + 214 | | | | | | | | || | | # Execution count [2.50e+01] + 215 | 0.00 | 0.16 | | | | 0.00 | 0.84 | || | | addq $8, %r13 #67.9 + 216 | 0.00 | 1.00 | | | | 0.00 | | || | | vpaddd %ymm16, %ymm3, %ymm3 #67.9 + 217 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm18, %zmm4, %zmm29 #71.36 + 218 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubpd %zmm19, %zmm0, %zmm27 #70.36 + 219 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm20, %zmm1, %zmm26 #69.36 + 220 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm27, %zmm27, %zmm25 #72.49 + 221 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm26, %zmm26, %zmm25 #72.49 + 222 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm29, %zmm29, %zmm25 #72.63 + 223 | 2.50 | | | | | 0.50 | | || 8.0 | | vrcp14pd %zmm25, %zmm24 #75.38 + 224 | | | | | | 1.00 | | || | | vcmppd $1, %zmm14, %zmm25, %k2 #74.22 + 225 | | | | | | 1.00 | | || | | vfpclasspd $30, %zmm24, %k0 #75.38 + 226 | 1.00 | | | | | | | || | | kmovw %k2, %edx #74.22 + 227 | 1.00 | | | | | | | || | | knotw %k0, %k1 #75.38 + 228 | | | | | | | | || | | * vmovaps %zmm25, %zmm17 #75.38 + 229 | 0.00 | 0.34 | | | | 0.00 | 0.66 | || | | andl %edx, %r9d #74.22 + 230 | 0.50 | | 0.50 0.50 | 0.50 0.50 | | 0.50 | | || 4.0 | | vfnmadd213pd .L_2il0floatpacket.9(%rip){1to8}, %zmm24, %zmm17 #75.38 + 231 | 1.00 | | | | | | | || | | kmovw %r9d, %k3 #78.17 + 232 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm17, %zmm17, %zmm18 #75.38 + 233 | 0.50 | | | | | 0.50 | | || | | vfmadd213pd %zmm24, %zmm17, %zmm24{%k1} #75.38 + 234 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd213pd %zmm24, %zmm18, %zmm24{%k1} #75.38 + 235 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm13, %zmm24, %zmm19 #76.38 + 236 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm10, %zmm24, %zmm21 #77.54 + 237 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm19, %zmm24, %zmm22 #76.44 + 238 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm22, %zmm24, %zmm20 #76.50 + 239 | 0.00 | | | | | 1.00 | | || | | vfmsub213pd %zmm5, %zmm22, %zmm24 #77.54 + 240 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm21, %zmm20, %zmm23 #77.61 + 241 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm24, %zmm23, %zmm28 #77.67 + 242 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm26, %zmm28, %zmm9{%k3} #78.17 + 243 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm27, %zmm28, %zmm8{%k3} #79.17 + 244 | 0.00 | | | | | 1.00 | | || 4.0 | 4.0 | vfmadd231pd %zmm29, %zmm28, %zmm11{%k3} #80.17 + 245 | 0.00 | 0.00 | | | | 0.00 | 1.00 | || | | cmpq %rbx, %r13 #67.9 + 246 | | | | | | | | || | | * jb ..B1.18 # Prob 82% #67.9 + + 20.5 6.00 13.0 2.50 13.0 2.50 20.5 4.00 70.0 4 + + +Loop-Carried Dependencies Analysis Report +----------------------------------------- + 215 | 1.0 | addq $8, %r13 #67.9| [215] + 216 | 1.0 | vpaddd %ymm16, %ymm3, %ymm3 #67.9| [216] + 244 | 4.0 | vfmadd231pd %zmm29, %zmm28, %zmm11{%k3} #80.17| [244] + 243 | 4.0 | vfmadd231pd %zmm27, %zmm28, %zmm8{%k3} #79.17| [243] + 242 | 4.0 | vfmadd231pd %zmm26, %zmm28, %zmm9{%k3} #78.17| [242] + diff --git a/arch_analysis/osaca_output_force_soa.txt b/arch_analysis/osaca_force_aos_lt1200.txt similarity index 100% rename from arch_analysis/osaca_output_force_soa.txt rename to arch_analysis/osaca_force_aos_lt1200.txt diff --git a/arch_analysis/osaca_force_aos_lt8.txt b/arch_analysis/osaca_force_aos_lt8.txt new file mode 100644 index 0000000..810dae9 --- /dev/null +++ b/arch_analysis/osaca_force_aos_lt8.txt @@ -0,0 +1,91 @@ +iwia021h@testfront1:~/MD-Bench/asm$ /home/hpc/iwia/iwia021h/.local/bin/osaca --ignore-unknown --arch=CSX force_aos_lt8_markers.s +Open Source Architecture Code Analyzer (OSACA) - 0.3.14 +Analyzed file: force_aos_lt8_markers.s +Architecture: CSX +Timestamp: 2021-04-29 15:49:27 + + + 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 | +------------------------------------------------------------------------------------------------- + 358 | | | | | | | | || | | # LOE rax rdx rcx rbp rsi rdi r8 r9 r10 r11d r14d xmm6 xmm7 xmm12 ymm15 ymm16 zmm5 zmm8 zmm9 zmm10 zmm11 zmm13 zmm14 + 359 | | | | | | | | || | | ..B1.33: # Preds ..B1.32 + 360 | | | | | | | | || | | # Execution count [2.50e+01] + 361 | | 1.00 | | | | | | || 3.0 | | imulq %r8, %rcx #56.43 + 362 | | | | | | 1.00 | | || | 3.0 | vbroadcastsd %xmm6, %zmm4 #58.23 + 363 | | | | | | | | || | | X subl %r14d, %r11d #67.9 + 364 | 0.00 | 0.00 | | | | 0.00 | 1.00 | || 1.0 | | addq %r10, %rcx #37.5 + 365 | | | | | | | | || | | X vpbroadcastd %r11d, %ymm0 #67.9 + 366 | | | | | | 1.00 | | || | | vpcmpgtd %ymm15, %ymm0, %k3 #67.9 + 367 | 0.00 | 0.00 | | | | 0.00 | 1.00 | || | | movslq %r14d, %r14 #67.9 + 368 | 1.00 | | | | | | | || | | kmovw %k3, %ebx #67.9 + 369 | 0.00 | 1.00 | 0.50 0.50 | 0.50 0.50 | | 0.00 | | || 0.0 | | vmovdqu32 (%rcx,%r14,4), %ymm1{%k3}{z} #68.21 + 370 | 0.00 | 1.00 | | | | 0.00 | | || 1.0 | | vpaddd %ymm1, %ymm1, %ymm2 #69.36 + 371 | 0.00 | 1.00 | | | | 0.00 | | || 1.0 | | vpaddd %ymm2, %ymm1, %ymm0 #69.36 + 372 | | | | | | | | || | | # LOE rax rdx rbp rsi rdi r8 r9 r10 ebx xmm7 xmm12 ymm0 ymm15 ymm16 zmm4 zmm5 zmm8 zmm9 zmm10 zmm11 zmm13 zmm14 k3 + 373 | | | | | | | | || | | ..B1.36: # Preds ..B1.33 + 374 | | | | | | | | || | | # Execution count [1.25e+01] + 375 | 1.00 | | | | | | | || | | kmovw %k3, %k1 #69.36 + 376 | 1.00 | | | | | | | || | | kmovw %k3, %k2 #69.36 + 377 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm1, %zmm1, %zmm1 #69.36 + 378 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm2, %zmm2, %zmm2 #69.36 + 379 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm3, %zmm3, %zmm3 #69.36 + 380 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd 16(%rdi,%ymm0,8), %zmm1{%k1} #69.36 + 381 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || 4.0 | | vgatherdpd 8(%rdi,%ymm0,8), %zmm2{%k2} #69.36 + 382 | 1.50 | 0.00 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 1.00 | || | | vgatherdpd (%rdi,%ymm0,8), %zmm3{%k3} #69.36 + 383 | | | | | | | | || | | # LOE rax rdx rbp rsi rdi r8 r9 r10 ebx xmm7 xmm12 ymm15 ymm16 zmm1 zmm2 zmm3 zmm4 zmm5 zmm8 zmm9 zmm10 zmm11 zmm13 zmm14 + 384 | | | | | | | | || | | ..B1.37: # Preds ..B1.36 + 385 | | | | | | | | || | | # Execution count [2.50e+01] + 386 | | | | | | 1.00 | | || | | vbroadcastsd %xmm7, %zmm7 #59.23 + 387 | | | | | | 1.00 | | || | | vbroadcastsd %xmm12, %zmm12 #60.23 + 388 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm1, %zmm12, %zmm23 #71.36 + 389 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubpd %zmm2, %zmm7, %zmm21 #70.36 + 390 | 0.50 | | | | | 0.50 | | || | 4.0 | vsubpd %zmm3, %zmm4, %zmm20 #69.36 + 391 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm21, %zmm21, %zmm19 #72.49 + 392 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vfmadd231pd %zmm20, %zmm20, %zmm19 #72.49 + 393 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vfmadd231pd %zmm23, %zmm23, %zmm19 #72.63 + 394 | 2.50 | | | | | 0.50 | | || 8.0 | 8.0 | vrcp14pd %zmm19, %zmm18 #75.38 + 395 | | | | | | 1.00 | | || | | vcmppd $1, %zmm14, %zmm19, %k2 #74.22 + 396 | | | | | | 1.00 | | || | | vfpclasspd $30, %zmm18, %k0 #75.38 + 397 | 1.00 | | | | | | | || | | kmovw %k2, %ecx #74.22 + 398 | 1.00 | | | | | | | || | | knotw %k0, %k1 #75.38 + 399 | | | | | | | | || | | * vmovaps %zmm19, %zmm0 #75.38 + 400 | 0.00 | 0.00 | | | | 0.00 | 1.00 | || | | andl %ecx, %ebx #74.22 + 401 | 0.50 | | 0.50 0.50 | 0.50 0.50 | | 0.50 | | || 4.0 | | vfnmadd213pd .L_2il0floatpacket.9(%rip){1to8}, %zmm18, %zmm0 #75.38 + 402 | 1.00 | | | | | | | || | | kmovw %ebx, %k3 #78.17 + 403 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm0, %zmm0, %zmm1 #75.38 + 404 | 0.50 | | | | | 0.50 | | || | 4.0 | vfmadd213pd %zmm18, %zmm0, %zmm18{%k1} #75.38 + 405 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vfmadd213pd %zmm18, %zmm1, %zmm18{%k1} #75.38 + 406 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm13, %zmm18, %zmm2 #76.38 + 407 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm10, %zmm18, %zmm4 #77.54 + 408 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vmulpd %zmm2, %zmm18, %zmm6 #76.44 + 409 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm6, %zmm18, %zmm3 #76.50 + 410 | 0.50 | | | | | 0.50 | | || | | vfmsub213pd %zmm5, %zmm6, %zmm18 #77.54 + 411 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm4, %zmm3, %zmm17 #77.61 + 412 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm18, %zmm17, %zmm22 #77.67 + 413 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm20, %zmm22, %zmm9{%k3} #78.17 + 414 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm21, %zmm22, %zmm8{%k3} #79.17 + 415 | 0.00 | | | | | 1.00 | | || 4.0 | | vfmadd231pd %zmm23, %zmm22, %zmm11{%k3} #80.17 + + 22.0 5.00 13.0 2.50 13.0 2.50 22.0 5.00 70.0 35.0 + + +Loop-Carried Dependencies Analysis Report +----------------------------------------- + 363 | 0.0 | subl %r14d, %r11d #67.9| [363] + 367 | 1.0 | movslq %r14d, %r14 #67.9| [367] + 386 | 3.0 | vbroadcastsd %xmm7, %zmm7 #59.23| [386] + 387 | 3.0 | vbroadcastsd %xmm12, %zmm12 #60.23| [387] + 415 | 4.0 | vfmadd231pd %zmm23, %zmm22, %zmm11{%k3} #80.17| [415] + 414 | 4.0 | vfmadd231pd %zmm21, %zmm22, %zmm8{%k3} #79.17| [414] + 413 | 4.0 | vfmadd231pd %zmm20, %zmm22, %zmm9{%k3} #78.17| [413] + 397 | 28.0 | kmovw %k2, %ecx #74.22| [361, 364, 369, 371, 382, 390, 392, 393, 395, 397] + 408 | 35.0 | vmulpd %zmm2, %zmm18, %zmm6 #76.44| [362, 390, 392, 393, 394, 404, 405, 408] + diff --git a/arch_analysis/osaca_force_soa_geq1200.txt b/arch_analysis/osaca_force_soa_geq1200.txt new file mode 100644 index 0000000..a98d11b --- /dev/null +++ b/arch_analysis/osaca_force_soa_geq1200.txt @@ -0,0 +1,71 @@ +iwia021h@testfront1:~/MD-Bench/asm$ /home/hpc/iwia/iwia021h/.local/bin/osaca --ignore-unknown --arch=CSX force_soa_geq1200_markers.s +Open Source Architecture Code Analyzer (OSACA) - 0.3.14 +Analyzed file: force_soa_geq1200_markers.s +Architecture: CSX +Timestamp: 2021-04-29 15:54:23 + + + 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 | +------------------------------------------------------------------------------------------------- + 189 | | | | | | | | || | | # LOE rax rdx rcx rbp rsi rdi r8 r10 r11 r12 r14 r15 ebx r9d r13d xmm8 xmm9 xmm10 ymm3 ymm4 ymm17 ymm18 zmm2 zmm5 zmm6 zmm7 zmm11 zmm12 zmm13 zmm14 zmm15 zmm16 zmm19 + 190 | | | | | | | | || | | ..B1.18: # Preds ..B1.18 ..B1.17 + 191 | | | | | | | | || | | # Execution count [2.50e+01] + 192 | | | | | | 1.00 | | || | | vpcmpgtd %ymm4, %ymm3, %k5 #67.9 + 193 | 0.00 | 1.00 | | | | 0.00 | | || | | vpaddd %ymm18, %ymm4, %ymm4 #67.9 + 194 | 0.00 | 1.00 | 0.50 0.50 | 0.50 0.50 | | 0.00 | | || 4.0 | | vmovdqu32 (%rcx,%r15,4), %ymm20{%k5}{z} #68.21 + 195 | | | | | | | | || | | * vmovaps %zmm19, %zmm22 #70.36 + 196 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | addq $8, %r15 #67.9 + 197 | 1.00 | | | | | | | || | | kmovw %k5, %k2 #70.36 + 198 | | | | | | | | || | | * vmovaps %zmm19, %zmm21 #69.36 + 199 | 1.00 | | | | | | | || | | kmovw %k5, %k1 #69.36 + 200 | | | | | | | | || | | * vmovaps %zmm19, %zmm23 #71.36 + 201 | 1.00 | | | | | | | || | | kmovw %k5, %k3 #71.36 + 202 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd (%rsi,%ymm20,8), %zmm23{%k3} #71.36 + 203 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || 4.0 | | vgatherdpd (%rax,%ymm20,8), %zmm22{%k2} #70.36 + 204 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd (%rdx,%ymm20,8), %zmm21{%k1} #69.36 + 205 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubpd %zmm22, %zmm5, %zmm0 #70.36 + 206 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm21, %zmm2, %zmm1 #69.36 + 207 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm23, %zmm6, %zmm21 #71.36 + 208 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm0, %zmm0, %zmm20 #72.49 + 209 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm1, %zmm1, %zmm20 #72.49 + 210 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm21, %zmm21, %zmm20 #72.63 + 211 | 2.50 | | | | | 0.50 | | || 8.0 | | vrcp14pd %zmm20, %zmm31 #75.38 + 212 | | | | | | 1.00 | | || | | vcmppd $1, %zmm16, %zmm20, %k6{%k5} #74.22 + 213 | | | | | | 1.00 | | || | | vfpclasspd $30, %zmm31, %k0 #75.38 + 214 | | | | | | | | || | | * vmovaps %zmm20, %zmm24 #75.38 + 215 | 0.50 | | 0.50 0.50 | 0.50 0.50 | | 0.50 | | || 4.0 | | vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm31, %zmm24 #75.38 + 216 | 1.00 | | | | | | | || | | knotw %k0, %k4 #75.38 + 217 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm24, %zmm24, %zmm25 #75.38 + 218 | 0.50 | | | | | 0.50 | | || | | vfmadd213pd %zmm31, %zmm24, %zmm31{%k4} #75.38 + 219 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd213pd %zmm31, %zmm25, %zmm31{%k4} #75.38 + 220 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm15, %zmm31, %zmm26 #76.38 + 221 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm14, %zmm31, %zmm28 #77.54 + 222 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm26, %zmm31, %zmm29 #76.44 + 223 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm29, %zmm31, %zmm27 #76.50 + 224 | 0.00 | | | | | 1.00 | | || | | vfmsub213pd %zmm7, %zmm29, %zmm31 #77.54 + 225 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm28, %zmm27, %zmm30 #77.61 + 226 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm31, %zmm30, %zmm24 #77.67 + 227 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm1, %zmm24, %zmm13{%k6} #78.17 + 228 | 0.00 | | | | | 1.00 | | || | 4.0 | vfmadd231pd %zmm0, %zmm24, %zmm12{%k6} #79.17 + 229 | 0.00 | | | | | 1.00 | | || 4.0 | | vfmadd231pd %zmm21, %zmm24, %zmm11{%k6} #80.17 + 230 | 0.00 | 0.17 | | | | 0.00 | 0.83 | || | | cmpq %r14, %r15 #67.9 + 231 | | | | | | | | || | | * jb ..B1.18 # Prob 82% #67.9 + + 18.0 4.17 13.0 2.50 13.0 2.50 18.0 2.83 68.0 4 + + +Loop-Carried Dependencies Analysis Report +----------------------------------------- + 193 | 1.0 | vpaddd %ymm18, %ymm4, %ymm4 #67.9| [193] + 196 | 1.0 | addq $8, %r15 #67.9| [196] + 228 | 4.0 | vfmadd231pd %zmm0, %zmm24, %zmm12{%k6} #79.17| [228] + 227 | 4.0 | vfmadd231pd %zmm1, %zmm24, %zmm13{%k6} #78.17| [227] + 229 | 4.0 | vfmadd231pd %zmm21, %zmm24, %zmm11{%k6} #80.17| [229] diff --git a/arch_analysis/osaca_force_soa_lt1200.txt b/arch_analysis/osaca_force_soa_lt1200.txt new file mode 100644 index 0000000..ded0878 --- /dev/null +++ b/arch_analysis/osaca_force_soa_lt1200.txt @@ -0,0 +1,69 @@ +iwia021h@testfront1:~/MD-Bench/asm$ /home/hpc/iwia/iwia021h/.local/bin/osaca --ignore-unknown --arch=CSX force_soa_lt1200_markers.s +Open Source Architecture Code Analyzer (OSACA) - 0.3.14 +Analyzed file: force_soa_lt1200_markers.s +Architecture: CSX +Timestamp: 2021-04-29 15:39:58 + + + 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 | +------------------------------------------------------------------------------------------------- + 253 | | | | | | | | || | | # LOE rax rdx rcx rbp rsi rdi r8 r10 r11 r12 r14 ebx r9d r13d xmm8 xmm9 xmm10 ymm17 ymm18 zmm0 zmm1 zmm2 zmm7 zmm11 zmm12 zmm13 zmm14 zmm15 zmm16 zmm19 + 254 | | | | | | | | || | | ..B1.22: # Preds ..B1.22 ..B1.21 + 255 | | | | | | | | || | | # Execution count [2.50e+01] + 256 | | | | | | | | || | | X vpcmpeqb %xmm0, %xmm0, %k2 #70.36 + 257 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | addl $8, %r9d #67.9 + 258 | | | | | | | | || | | X vpcmpeqb %xmm0, %xmm0, %k1 #69.36 + 259 | | | | | | | | || | | X vpcmpeqb %xmm0, %xmm0, %k3 #71.36 + 260 | | | 0.50 0.50 | 0.50 0.50 | | | | || 4.0 | | vmovdqu (%rcx,%r14,4), %ymm3 #68.21 + 261 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | addq $8, %r14 #67.9 + 262 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm5, %zmm5, %zmm5 #70.36 + 263 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm4, %zmm4, %zmm4 #69.36 + 264 | 0.50 | | | | | 0.50 | | || | | vpxord %zmm6, %zmm6, %zmm6 #71.36 + 265 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || 4.0 | | vgatherdpd (%rax,%ymm3,8), %zmm5{%k2} #70.36 + 266 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd (%rdx,%ymm3,8), %zmm4{%k1} #69.36 + 267 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd (%rsi,%ymm3,8), %zmm6{%k3} #71.36 + 268 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubpd %zmm5, %zmm1, %zmm29 #70.36 + 269 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm4, %zmm0, %zmm28 #69.36 + 270 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm6, %zmm2, %zmm31 #71.36 + 271 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm29, %zmm29, %zmm20 #72.49 + 272 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm28, %zmm28, %zmm20 #72.49 + 273 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd231pd %zmm31, %zmm31, %zmm20 #72.63 + 274 | 2.50 | | | | | 0.50 | | || 8.0 | | vrcp14pd %zmm20, %zmm27 #75.38 + 275 | | | | | | 1.00 | | || | | vcmppd $1, %zmm16, %zmm20, %k5 #74.22 + 276 | | | | | | 1.00 | | || | | vfpclasspd $30, %zmm27, %k0 #75.38 + 277 | 0.50 | | 0.50 0.50 | 0.50 0.50 | | 0.50 | | || 4.0 | | vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm27, %zmm20 #75.38 + 278 | 1.00 | | | | | | | || | | knotw %k0, %k4 #75.38 + 279 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm20, %zmm20, %zmm21 #75.38 + 280 | 0.50 | | | | | 0.50 | | || | | vfmadd213pd %zmm27, %zmm20, %zmm27{%k4} #75.38 + 281 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd213pd %zmm27, %zmm21, %zmm27{%k4} #75.38 + 282 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm15, %zmm27, %zmm22 #76.38 + 283 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm14, %zmm27, %zmm24 #77.54 + 284 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm22, %zmm27, %zmm25 #76.44 + 285 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm25, %zmm27, %zmm23 #76.50 + 286 | 0.50 | | | | | 0.50 | | || | | vfmsub213pd %zmm7, %zmm25, %zmm27 #77.54 + 287 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm24, %zmm23, %zmm26 #77.61 + 288 | 0.00 | | | | | 1.00 | | || 4.0 | | vmulpd %zmm27, %zmm26, %zmm30 #77.67 + 289 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm28, %zmm30, %zmm13{%k5} #78.17 + 290 | 0.00 | | | | | 1.00 | | || | 4.0 | vfmadd231pd %zmm29, %zmm30, %zmm12{%k5} #79.17 + 291 | 0.00 | | | | | 1.00 | | || 4.0 | | vfmadd231pd %zmm31, %zmm30, %zmm11{%k5} #80.17 + 292 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || | | cmpl %ebx, %r9d #67.9 + 293 | | | | | | | | || | | * jb ..B1.22 # Prob 82% #67.9 + + 17.5 3.00 13.0 2.50 13.0 2.50 17.5 3.00 68.0 4 + + +Loop-Carried Dependencies Analysis Report +----------------------------------------- + 257 | 1.0 | addl $8, %r9d #67.9| [257] + 261 | 1.0 | addq $8, %r14 #67.9| [261] + 290 | 4.0 | vfmadd231pd %zmm29, %zmm30, %zmm12{%k5} #79.17| [290] + 289 | 4.0 | vfmadd231pd %zmm28, %zmm30, %zmm13{%k5} #78.17| [289] + 291 | 4.0 | vfmadd231pd %zmm31, %zmm30, %zmm11{%k5} #80.17| [291] diff --git a/arch_analysis/osaca_force_soa_lt8.txt b/arch_analysis/osaca_force_soa_lt8.txt new file mode 100644 index 0000000..bf328fa --- /dev/null +++ b/arch_analysis/osaca_force_soa_lt8.txt @@ -0,0 +1,79 @@ +iwia021h@testfront1:~/MD-Bench/asm$ /home/hpc/iwia/iwia021h/.local/bin/osaca --ignore-unknown --arch=CSX force_soa_lt8_markers.s +Open Source Architecture Code Analyzer (OSACA) - 0.3.14 +Analyzed file: force_soa_lt8_markers.s +Architecture: CSX +Timestamp: 2021-04-29 15:52:48 + + + 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 | 2 - 2D | 3 - 3D | 4 | 5 | 6 | 7 || CP | LCD | +------------------------------------------------------------------------------------------------- + 300 | | | | | | | | || | | # LOE rax rdx rbp rsi rdi r8 r10 r11 r12 ebx r13d xmm8 xmm9 xmm10 ymm17 ymm18 zmm7 zmm11 zmm12 zmm13 zmm14 zmm15 zmm16 zmm19 + 301 | | | | | | | | || | | ..B1.25: # Preds ..B1.24 + 302 | | | | | | | | || | | # Execution count [2.50e+01] + 303 | | 1.00 | | | | | | || 3.0 | | imulq %r12, %r8 #56.43 + 304 | | | | | | 1.00 | | || | | vbroadcastsd %xmm9, %zmm9 #59.23 + 305 | | | | | | 1.00 | | || | 3.0 | vbroadcastsd %xmm8, %zmm2 #58.23 + 306 | | | | | | 1.00 | | || | | vbroadcastsd %xmm10, %zmm10 #60.23 + 307 | | | | | | | | || | | X subl %ebx, %r13d #67.9 + 308 | 0.00 | 0.50 | | | | 0.00 | 0.50 | || 1.0 | | addq %r11, %r8 #37.5 + 309 | | | | | | | | || | | X vpbroadcastd %r13d, %ymm0 #67.9 + 310 | | | | | | 1.00 | | || | | vpcmpgtd %ymm17, %ymm0, %k5 #67.9 + 311 | 0.00 | 0.16 | | | | 0.00 | 0.84 | || | | movslq %ebx, %rbx #67.9 + 312 | | | | | | | | || | | * vmovaps %zmm19, %zmm4 #70.36 + 313 | 1.00 | | | | | | | || | | kmovw %k5, %k2 #70.36 + 314 | | | | | | | | || | | * vmovaps %zmm19, %zmm3 #69.36 + 315 | 0.00 | 1.00 | 0.50 0.50 | 0.50 0.50 | | 0.00 | | || 0.0 | | vmovdqu32 (%r8,%rbx,4), %ymm1{%k5}{z} #68.21 + 316 | 1.00 | | | | | | | || | | kmovw %k5, %k1 #69.36 + 317 | | | | | | | | || | | * vmovaps %zmm19, %zmm5 #71.36 + 318 | 1.00 | | | | | | | || | | kmovw %k5, %k3 #71.36 + 319 | 1.50 | 0.50 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.50 | || | | vgatherdpd (%rsi,%ymm1,8), %zmm5{%k3} #71.36 + 320 | 1.50 | 0.34 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 0.66 | || 4.0 | | vgatherdpd (%rax,%ymm1,8), %zmm4{%k2} #70.36 + 321 | 1.50 | 0.00 | 4.00 0.50 | 4.00 0.50 | | 0.50 | 1.00 | || | | vgatherdpd (%rdx,%ymm1,8), %zmm3{%k1} #69.36 + 322 | 0.50 | | | | | 0.50 | | || | | vsubpd %zmm5, %zmm10, %zmm30 #71.36 + 323 | 0.50 | | | | | 0.50 | | || 4.0 | | vsubpd %zmm4, %zmm9, %zmm28 #70.36 + 324 | 0.50 | | | | | 0.50 | | || | 4.0 | vsubpd %zmm3, %zmm2, %zmm27 #69.36 + 325 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm28, %zmm28, %zmm26 #72.49 + 326 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vfmadd231pd %zmm27, %zmm27, %zmm26 #72.49 + 327 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vfmadd231pd %zmm30, %zmm30, %zmm26 #72.63 + 328 | 2.50 | | | | | 0.50 | | || 8.0 | 8.0 | vrcp14pd %zmm26, %zmm25 #75.38 + 329 | | | | | | 1.00 | | || | | vcmppd $1, %zmm16, %zmm26, %k6{%k5} #74.22 + 330 | | | | | | 1.00 | | || | | vfpclasspd $30, %zmm25, %k0 #75.38 + 331 | | | | | | | | || | | * vmovaps %zmm26, %zmm6 #75.38 + 332 | 0.50 | | 0.50 0.50 | 0.50 0.50 | | 0.50 | | || 4.0 | 4.0 | vfnmadd213pd .L_2il0floatpacket.5(%rip){1to8}, %zmm25, %zmm6 #75.38 + 333 | 1.00 | | | | | | | || | | knotw %k0, %k4 #75.38 + 334 | 0.50 | | | | | 0.50 | | || 4.0 | 4.0 | vmulpd %zmm6, %zmm6, %zmm8 #75.38 + 335 | 0.50 | | | | | 0.50 | | || | | vfmadd213pd %zmm25, %zmm6, %zmm25{%k4} #75.38 + 336 | 0.50 | | | | | 0.50 | | || 4.0 | | vfmadd213pd %zmm25, %zmm8, %zmm25{%k4} #75.38 + 337 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm15, %zmm25, %zmm20 #76.38 + 338 | 0.50 | | | | | 0.50 | | || | | vmulpd %zmm14, %zmm25, %zmm22 #77.54 + 339 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm20, %zmm25, %zmm23 #76.44 + 340 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm23, %zmm25, %zmm21 #76.50 + 341 | 0.50 | | | | | 0.50 | | || | | vfmsub213pd %zmm7, %zmm23, %zmm25 #77.54 + 342 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm22, %zmm21, %zmm24 #77.61 + 343 | 0.50 | | | | | 0.50 | | || 4.0 | | vmulpd %zmm25, %zmm24, %zmm29 #77.67 + 344 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm27, %zmm29, %zmm13{%k6} #78.17 + 345 | 0.00 | | | | | 1.00 | | || | | vfmadd231pd %zmm28, %zmm29, %zmm12{%k6} #79.17 + 346 | 0.00 | | | | | 1.00 | | || 4.0 | | vfmadd231pd %zmm30, %zmm29, %zmm11{%k6} #80.17 + + 19.5 3.50 13.0 2.50 13.0 2.50 19.5 3.50 68.0 31.0 + + +Loop-Carried Dependencies Analysis Report +----------------------------------------- + 308 | 4.0 | addq %r11, %r8 #37.5| [303, 308] + 304 | 3.0 | vbroadcastsd %xmm9, %zmm9 #59.23| [304] + 306 | 3.0 | vbroadcastsd %xmm10, %zmm10 #60.23| [306] + 307 | 0.0 | subl %ebx, %r13d #67.9| [307] + 311 | 1.0 | movslq %ebx, %rbx #67.9| [311] + 346 | 4.0 | vfmadd231pd %zmm30, %zmm29, %zmm11{%k6} #80.17| [346] + 345 | 4.0 | vfmadd231pd %zmm28, %zmm29, %zmm12{%k6} #79.17| [345] + 344 | 4.0 | vfmadd231pd %zmm27, %zmm29, %zmm13{%k6} #78.17| [344] + 334 | 31.0 | vmulpd %zmm6, %zmm6, %zmm8 #75.38| [305, 324, 326, 327, 328, 332, 334] diff --git a/scripts/results_aos_medusa.txt b/scripts/results_aos_medusa.txt new file mode 100644 index 0000000..884af93 --- /dev/null +++ b/scripts/results_aos_medusa.txt @@ -0,0 +1,450 @@ +200,4x4x2,8,256,21.5040,6.1440,9.2160,0.0012,41.1057,80.3051,11.4722 +200,4x4x4,8,512,43.0080,12.2880,18.4320,0.0025,40.3647,81.7793,11.6828 +200,4x4x8,8,1024,86.0160,24.5760,36.8640,0.0051,39.8752,82.7833,11.8262 +200,4x4x16,8,2048,172.0320,49.1520,73.7280,0.0101,40.6017,81.3020,11.6146 +200,4x4x32,8,4096,344.0640,98.3040,147.4560,0.0204,40.2231,82.0673,11.7239 +200,4x4x64,8,8192,688.1280,196.6080,294.9120,0.0472,34.6834,95.1752,13.5965 +200,4x8x2,8,512,43.0080,12.2880,18.4320,0.0025,40.4194,81.6686,11.6669 +200,4x8x4,8,1024,86.0160,24.5760,36.8640,0.0052,39.3566,83.8740,11.9820 +200,4x8x8,8,2048,172.0320,49.1520,73.7280,0.0102,39.9745,82.5777,11.7968 +200,4x8x16,8,4096,344.0640,98.3040,147.4560,0.0204,40.1524,82.2118,11.7445 +200,4x8x32,8,8192,688.1280,196.6080,294.9120,0.0466,35.1455,93.9238,13.4177 +200,4x8x64,8,16384,1376.2560,393.2160,589.8240,0.0929,35.2833,93.5569,13.3653 +200,4x16x2,8,1024,86.0160,24.5760,36.8640,0.0052,39.5220,83.5232,11.9319 +200,4x16x4,8,2048,172.0320,49.1520,73.7280,0.0102,40.0184,82.4871,11.7839 +200,4x16x8,8,4096,344.0640,98.3040,147.4560,0.0207,39.5628,83.4369,11.9196 +200,4x16x16,8,8192,688.1280,196.6080,294.9120,0.0468,35.0227,94.2531,13.4647 +200,4x16x32,8,16384,1376.2560,393.2160,589.8240,0.0952,34.4175,95.9105,13.7015 +200,4x16x64,8,32768,2752.5120,786.4320,1179.6480,0.1878,34.8933,94.6026,13.5147 +200,4x32x2,8,2048,172.0320,49.1520,73.7280,0.0102,40.0417,82.4391,11.7770 +200,4x32x4,8,4096,344.0640,98.3040,147.4560,0.0205,39.8714,82.7911,11.8273 +200,4x32x8,8,8192,688.1280,196.6080,294.9120,0.0458,35.8069,92.1889,13.1698 +200,4x32x16,8,16384,1376.2560,393.2160,589.8240,0.0955,34.3126,96.2037,13.7434 +200,4x32x32,8,32768,2752.5120,786.4320,1179.6480,0.1895,34.5920,95.4266,13.6324 +200,4x32x64,8,65536,5505.0240,1572.8640,2359.2960,0.3960,33.1002,99.7276,14.2468 +200,4x64x2,8,4096,344.0640,98.3040,147.4560,0.0203,40.4125,81.6827,11.6690 +200,4x64x4,8,8192,688.1280,196.6080,294.9120,0.0456,35.9633,91.7881,13.1126 +200,4x64x8,8,16384,1376.2560,393.2160,589.8240,0.0934,35.0939,94.0620,13.4374 +200,4x64x16,8,32768,2752.5120,786.4320,1179.6480,0.1896,34.5699,95.4876,13.6411 +200,4x64x32,8,65536,5505.0240,1572.8640,2359.2960,0.3912,33.5037,98.5264,14.0752 +200,4x64x64,8,131072,11010.0480,3145.7280,4718.5920,1.1277,23.2467,141.9985,20.2855 +200,8x4x2,8,512,43.0080,12.2880,18.4320,0.0026,40.0831,82.3538,11.7648 +200,8x4x4,8,1024,86.0160,24.5760,36.8640,0.0052,39.7363,83.0727,11.8675 +200,8x4x8,8,2048,172.0320,49.1520,73.7280,0.0103,39.8957,82.7408,11.8201 +200,8x4x16,8,4096,344.0640,98.3040,147.4560,0.0209,39.2829,84.0314,12.0045 +200,8x4x32,8,8192,688.1280,196.6080,294.9120,0.0458,35.7476,92.3419,13.1917 +200,8x4x64,8,16384,1376.2560,393.2160,589.8240,0.0946,34.6359,95.3057,13.6151 +200,8x8x2,8,1024,86.0160,24.5760,36.8640,0.0051,40.0148,82.4944,11.7849 +200,8x8x4,8,2048,172.0320,49.1520,73.7280,0.0103,39.6144,83.3284,11.9041 +200,8x8x8,8,4096,344.0640,98.3040,147.4560,0.0205,39.8786,82.7763,11.8252 +200,8x8x16,8,8192,688.1280,196.6080,294.9120,0.0464,35.3339,93.4229,13.3461 +200,8x8x32,8,16384,1376.2560,393.2160,589.8240,0.0954,34.3429,96.1188,13.7313 +200,8x8x64,8,32768,2752.5120,786.4320,1179.6480,0.1857,35.2944,93.5275,13.3611 +200,8x16x2,8,2048,172.0320,49.1520,73.7280,0.0103,39.6254,83.3052,11.9007 +200,8x16x4,8,4096,344.0640,98.3040,147.4560,0.0210,39.0435,84.5466,12.0781 +200,8x16x8,8,8192,688.1280,196.6080,294.9120,0.0464,35.3417,93.4023,13.3432 +200,8x16x16,8,16384,1376.2560,393.2160,589.8240,0.0952,34.4276,95.8824,13.6975 +200,8x16x32,8,32768,2752.5120,786.4320,1179.6480,0.1901,34.4669,95.7730,13.6819 +200,8x16x64,8,65536,5505.0240,1572.8640,2359.2960,0.3949,33.1919,99.4520,14.2074 +200,8x32x2,8,4096,344.0640,98.3040,147.4560,0.0207,39.5242,83.5184,11.9312 +200,8x32x4,8,8192,688.1280,196.6080,294.9120,0.0453,36.1420,91.3341,13.0477 +200,8x32x8,8,16384,1376.2560,393.2160,589.8240,0.0943,34.7606,94.9638,13.5663 +200,8x32x16,8,32768,2752.5120,786.4320,1179.6480,0.1897,34.5562,95.5256,13.6465 +200,8x32x32,8,65536,5505.0240,1572.8640,2359.2960,0.3924,33.4054,98.8165,14.1166 +200,8x32x64,8,131072,11010.0480,3145.7280,4718.5920,1.1113,23.5885,139.9413,19.9916 +200,8x64x2,8,8192,688.1280,196.6080,294.9120,0.0464,35.3179,93.4654,13.3522 +200,8x64x4,8,16384,1376.2560,393.2160,589.8240,0.0954,34.3379,96.1328,13.7333 +200,8x64x8,8,32768,2752.5120,786.4320,1179.6480,0.1836,35.6978,92.4708,13.2101 +200,8x64x16,8,65536,5505.0240,1572.8640,2359.2960,0.3942,33.2522,99.2717,14.1817 +200,8x64x32,8,131072,11010.0480,3145.7280,4718.5920,1.1300,23.1979,142.2975,20.3282 +200,8x64x64,8,262144,22020.0960,6291.4560,9437.1840,2.7875,18.8084,175.5068,25.0724 +200,16x4x2,8,1024,86.0160,24.5760,36.8640,0.0051,39.8587,82.8175,11.8311 +200,16x4x4,8,2048,172.0320,49.1520,73.7280,0.0102,40.2620,81.9879,11.7126 +200,16x4x8,8,4096,344.0640,98.3040,147.4560,0.0205,39.9633,82.6008,11.8001 +200,16x4x16,8,8192,688.1280,196.6080,294.9120,0.0467,35.0947,94.0599,13.4371 +200,16x4x32,8,16384,1376.2560,393.2160,589.8240,0.0951,34.4516,95.8156,13.6879 +200,16x4x64,8,32768,2752.5120,786.4320,1179.6480,0.1862,35.1990,93.7812,13.3973 +200,16x8x2,8,2048,172.0320,49.1520,73.7280,0.0103,39.7484,83.0474,11.8639 +200,16x8x4,8,4096,344.0640,98.3040,147.4560,0.0208,39.2926,84.0107,12.0015 +200,16x8x8,8,8192,688.1280,196.6080,294.9120,0.0457,35.8223,92.1492,13.1642 +200,16x8x16,8,16384,1376.2560,393.2160,589.8240,0.0955,34.3243,96.1708,13.7387 +200,16x8x32,8,32768,2752.5120,786.4320,1179.6480,0.1852,35.3809,93.2990,13.3284 +200,16x8x64,8,65536,5505.0240,1572.8640,2359.2960,0.3926,33.3876,98.8690,14.1241 +200,16x16x2,8,4096,344.0640,98.3040,147.4560,0.0206,39.8296,82.8780,11.8397 +200,16x16x4,8,8192,688.1280,196.6080,294.9120,0.0465,35.2205,93.7237,13.3891 +200,16x16x8,8,16384,1376.2560,393.2160,589.8240,0.0950,34.4971,95.6893,13.6699 +200,16x16x16,8,32768,2752.5120,786.4320,1179.6480,0.1854,35.3446,93.3949,13.3421 +200,16x16x32,8,65536,5505.0240,1572.8640,2359.2960,0.3933,33.3269,99.0492,14.1499 +200,16x16x64,8,131072,11010.0480,3145.7280,4718.5920,1.1221,23.3617,141.2995,20.1856 +200,16x32x2,8,8192,688.1280,196.6080,294.9120,0.0465,35.2689,93.5953,13.3708 +200,16x32x4,8,16384,1376.2560,393.2160,589.8240,0.0933,35.1150,94.0053,13.4293 +200,16x32x8,8,32768,2752.5120,786.4320,1179.6480,0.1890,34.6767,95.1937,13.5991 +200,16x32x16,8,65536,5505.0240,1572.8640,2359.2960,0.3917,33.4612,98.6515,14.0931 +200,16x32x32,8,131072,11010.0480,3145.7280,4718.5920,1.1154,23.5026,140.4528,20.0647 +200,16x32x64,8,262144,22020.0960,6291.4560,9437.1840,2.8702,18.2666,180.7123,25.8160 +200,16x64x2,8,16384,1376.2560,393.2160,589.8240,0.0935,35.0393,94.2084,13.4583 +200,16x64x4,8,32768,2752.5120,786.4320,1179.6480,0.1859,35.2627,93.6118,13.3731 +200,16x64x8,8,65536,5505.0240,1572.8640,2359.2960,0.3860,33.9565,97.2126,13.8875 +200,16x64x16,8,131072,11010.0480,3145.7280,4718.5920,1.1278,23.2434,142.0187,20.2884 +200,16x64x32,8,262144,22020.0960,6291.4560,9437.1840,2.7969,18.7451,176.0992,25.1570 +200,16x64x64,8,524288,44040.1920,12582.9120,18874.3680,6.0921,17.2122,191.7829,27.3976 +200,32x4x2,8,2048,172.0320,49.1520,73.7280,0.0104,39.5116,83.5452,11.9350 +200,32x4x4,8,4096,344.0640,98.3040,147.4560,0.0210,39.0648,84.5007,12.0715 +200,32x4x8,8,8192,688.1280,196.6080,294.9120,0.0466,35.1938,93.7948,13.3993 +200,32x4x16,8,16384,1376.2560,393.2160,589.8240,0.0943,34.7486,94.9965,13.5709 +200,32x4x32,8,32768,2752.5120,786.4320,1179.6480,0.1895,34.5862,95.4426,13.6347 +200,32x4x64,8,65536,5505.0240,1572.8640,2359.2960,0.3987,32.8783,100.4005,14.3429 +200,32x8x2,8,4096,344.0640,98.3040,147.4560,0.0205,39.8861,82.7606,11.8229 +200,32x8x4,8,8192,688.1280,196.6080,294.9120,0.0461,35.5303,92.9066,13.2724 +200,32x8x8,8,16384,1376.2560,393.2160,589.8240,0.0945,34.6607,95.2374,13.6053 +200,32x8x16,8,32768,2752.5120,786.4320,1179.6480,0.1869,35.0584,94.1573,13.4510 +200,32x8x32,8,65536,5505.0240,1572.8640,2359.2960,0.3925,33.3962,98.8436,14.1205 +200,32x8x64,8,131072,11010.0480,3145.7280,4718.5920,1.1238,23.3268,141.5113,20.2159 +200,32x16x2,8,8192,688.1280,196.6080,294.9120,0.0457,35.8343,92.1184,13.1598 +200,32x16x4,8,16384,1376.2560,393.2160,589.8240,0.0964,33.9864,97.1271,13.8753 +200,32x16x8,8,32768,2752.5120,786.4320,1179.6480,0.1880,34.8516,94.7160,13.5309 +200,32x16x16,8,65536,5505.0240,1572.8640,2359.2960,0.3958,33.1143,99.6850,14.2407 +200,32x16x32,8,131072,11010.0480,3145.7280,4718.5920,1.1231,23.3408,141.4262,20.2037 +200,32x16x64,8,262144,22020.0960,6291.4560,9437.1840,2.8733,18.2471,180.9059,25.8437 +200,32x32x2,8,16384,1376.2560,393.2160,589.8240,0.0956,34.2772,96.3030,13.7576 +200,32x32x4,8,32768,2752.5120,786.4320,1179.6480,0.1897,34.5447,95.5574,13.6511 +200,32x32x8,8,65536,5505.0240,1572.8640,2359.2960,0.3997,32.7961,100.6523,14.3789 +200,32x32x16,8,131072,11010.0480,3145.7280,4718.5920,1.1139,23.5333,140.2696,20.0385 +200,32x32x32,8,262144,22020.0960,6291.4560,9437.1840,2.8750,18.2358,181.0173,25.8596 +200,32x32x64,8,524288,44040.1920,12582.9120,18874.3680,6.0705,17.2733,191.1044,27.3006 +200,32x64x2,8,32768,2752.5120,786.4320,1179.6480,0.1856,35.3144,93.4747,13.3535 +200,32x64x4,8,65536,5505.0240,1572.8640,2359.2960,0.3870,33.8709,97.4582,13.9226 +200,32x64x8,8,131072,11010.0480,3145.7280,4718.5920,1.1255,23.2919,141.7230,20.2461 +200,32x64x16,8,262144,22020.0960,6291.4560,9437.1840,2.8226,18.5745,177.7170,25.3881 +200,32x64x32,8,524288,44040.1920,12582.9120,18874.3680,6.1089,17.1648,192.3122,27.4732 +200,32x64x64,8,1048576,88080.3840,25165.8240,37748.7360,12.4440,16.8527,195.8737,27.9820 +200,64x4x2,8,4096,344.0640,98.3040,147.4560,0.0206,39.8061,82.9270,11.8467 +200,64x4x4,8,8192,688.1280,196.6080,294.9120,0.0468,35.0209,94.2580,13.4654 +200,64x4x8,8,16384,1376.2560,393.2160,589.8240,0.0953,34.3759,96.0265,13.7181 +200,64x4x16,8,32768,2752.5120,786.4320,1179.6480,0.1905,34.3953,95.9725,13.7104 +200,64x4x32,8,65536,5505.0240,1572.8640,2359.2960,0.4040,32.4474,101.7340,14.5334 +200,64x4x64,8,131072,11010.0480,3145.7280,4718.5920,1.1196,23.4137,140.9856,20.1408 +200,64x8x2,8,8192,688.1280,196.6080,294.9120,0.0469,34.9211,94.5273,13.5039 +200,64x8x4,8,16384,1376.2560,393.2160,589.8240,0.0931,35.1895,93.8065,13.4009 +200,64x8x8,8,32768,2752.5120,786.4320,1179.6480,0.1876,34.9341,94.4921,13.4989 +200,64x8x16,8,65536,5505.0240,1572.8640,2359.2960,0.4015,32.6446,101.1194,14.4456 +200,64x8x32,8,131072,11010.0480,3145.7280,4718.5920,1.1355,23.0863,142.9852,20.4265 +200,64x8x64,8,262144,22020.0960,6291.4560,9437.1840,2.7960,18.7514,176.0401,25.1486 +200,64x16x2,8,16384,1376.2560,393.2160,589.8240,0.0947,34.6156,95.3617,13.6231 +200,64x16x4,8,32768,2752.5120,786.4320,1179.6480,0.1877,34.9064,94.5672,13.5096 +200,64x16x8,8,65536,5505.0240,1572.8640,2359.2960,0.3966,33.0458,99.8916,14.2702 +200,64x16x16,8,131072,11010.0480,3145.7280,4718.5920,1.1021,23.7865,138.7759,19.8251 +200,64x16x32,8,262144,22020.0960,6291.4560,9437.1840,2.7874,18.8091,175.5005,25.0715 +200,64x16x64,8,524288,44040.1920,12582.9120,18874.3680,6.1138,17.1511,192.4663,27.4952 +200,64x32x2,8,32768,2752.5120,786.4320,1179.6480,0.1897,34.5455,95.5553,13.6508 +200,64x32x4,8,65536,5505.0240,1572.8640,2359.2960,0.3956,33.1363,99.6189,14.2313 +200,64x32x8,8,131072,11010.0480,3145.7280,4718.5920,1.1204,23.3981,141.0800,20.1543 +200,64x32x16,8,262144,22020.0960,6291.4560,9437.1840,2.8010,18.7181,176.3538,25.1934 +200,64x32x32,8,524288,44040.1920,12582.9120,18874.3680,6.1574,17.0296,193.8395,27.6914 +200,64x32x64,8,1048576,88080.3840,25165.8240,37748.7360,12.3240,17.0169,193.9841,27.7120 +200,64x64x2,8,65536,5505.0240,1572.8640,2359.2960,0.3888,33.7099,97.9237,13.9891 +200,64x64x4,8,131072,11010.0480,3145.7280,4718.5920,1.1338,23.1208,142.7720,20.3960 +200,64x64x8,8,262144,22020.0960,6291.4560,9437.1840,2.8212,18.5837,177.6291,25.3756 +200,64x64x16,8,524288,44040.1920,12582.9120,18874.3680,6.1008,17.1875,192.0577,27.4368 +200,64x64x32,8,1048576,88080.3840,25165.8240,37748.7360,12.4366,16.8628,195.7566,27.9652 +200,64x64x64,8,2097152,176160.7680,50331.6480,75497.4720,25.4410,16.4864,200.2254,-61.7980 +200,4x4x2,16,512,59.3920,12.2880,34.8160,0.0041,24.7324,133.4689,8.8979 +200,4x4x4,16,1024,118.7840,24.5760,69.6320,0.0083,24.6887,133.7047,8.9136 +200,4x4x8,16,2048,237.5680,49.1520,139.2640,0.0163,25.0903,131.5646,8.7710 +200,4x4x16,16,4096,475.1360,98.3040,278.5280,0.0329,24.8829,132.6616,8.8441 +200,4x4x32,16,8192,950.2720,196.6080,557.0560,0.0680,24.0966,136.9905,9.1327 +200,4x4x64,16,16384,1900.5440,393.2160,1114.1120,0.1371,23.8973,138.1328,9.2089 +200,4x8x2,16,1024,118.7840,24.5760,69.6320,0.0082,25.0360,131.8501,8.7900 +200,4x8x4,16,2048,237.5680,49.1520,139.2640,0.0164,24.9590,132.2571,8.8171 +200,4x8x8,16,4096,475.1360,98.3040,278.5280,0.0335,24.4561,134.9764,8.9984 +200,4x8x16,16,8192,950.2720,196.6080,557.0560,0.0685,23.9268,137.9623,9.1975 +200,4x8x32,16,16384,1900.5440,393.2160,1114.1120,0.1375,23.8339,138.5001,9.2333 +200,4x8x64,16,32768,3801.0880,786.4320,2228.2240,0.2740,23.9222,137.9890,9.1993 +200,4x16x2,16,2048,237.5680,49.1520,139.2640,0.0165,24.8840,132.6557,8.8437 +200,4x16x4,16,4096,475.1360,98.3040,278.5280,0.0331,24.7245,133.5111,8.9007 +200,4x16x8,16,8192,950.2720,196.6080,557.0560,0.0681,24.0635,137.1784,9.1452 +200,4x16x16,16,16384,1900.5440,393.2160,1114.1120,0.1379,23.7594,138.9344,9.2623 +200,4x16x32,16,32768,3801.0880,786.4320,2228.2240,0.2743,23.8917,138.1649,9.2110 +200,4x16x64,16,65536,7602.1760,1572.8640,4456.4480,0.5828,22.4908,146.7711,9.7847 +200,4x32x2,16,4096,475.1360,98.3040,278.5280,0.0332,24.6499,133.9152,8.9277 +200,4x32x4,16,8192,950.2720,196.6080,557.0560,0.0691,23.7219,139.1539,9.2769 +200,4x32x8,16,16384,1900.5440,393.2160,1114.1120,0.1368,23.9567,137.7903,9.1860 +200,4x32x16,16,32768,3801.0880,786.4320,2228.2240,0.2735,23.9648,137.7438,9.1829 +200,4x32x32,16,65536,7602.1760,1572.8640,4456.4480,0.5886,22.2698,148.2277,9.8818 +200,4x32x64,16,131072,15204.3520,3145.7280,8912.8960,1.4720,17.8088,185.3577,12.3572 +200,4x64x2,16,8192,950.2720,196.6080,557.0560,0.0682,24.0084,137.4936,9.1662 +200,4x64x4,16,16384,1900.5440,393.2160,1114.1120,0.1372,23.8862,138.1971,9.2131 +200,4x64x8,16,32768,3801.0880,786.4320,2228.2240,0.2742,23.9051,138.0878,9.2059 +200,4x64x16,16,65536,7602.1760,1572.8640,4456.4480,0.5849,22.4077,147.3151,9.8210 +200,4x64x32,16,131072,15204.3520,3145.7280,8912.8960,1.4458,18.1316,182.0577,12.1372 +200,4x64x64,16,262144,30408.7040,6291.4560,17825.7920,3.1137,16.8378,196.0465,13.0698 +200,8x4x2,16,1024,118.7840,24.5760,69.6320,0.0083,24.7704,133.2639,8.8843 +200,8x4x4,16,2048,237.5680,49.1520,139.2640,0.0164,24.9790,132.1512,8.8101 +200,8x4x8,16,4096,475.1360,98.3040,278.5280,0.0327,25.0873,131.5805,8.7720 +200,8x4x16,16,8192,950.2720,196.6080,557.0560,0.0683,23.9916,137.5897,9.1726 +200,8x4x32,16,16384,1900.5440,393.2160,1114.1120,0.1374,23.8546,138.3798,9.2253 +200,8x4x64,16,32768,3801.0880,786.4320,2228.2240,0.2742,23.8990,138.1229,9.2082 +200,8x8x2,16,2048,237.5680,49.1520,139.2640,0.0163,25.1862,131.0636,8.7376 +200,8x8x4,16,4096,475.1360,98.3040,278.5280,0.0333,24.6350,133.9965,8.9331 +200,8x8x8,16,8192,950.2720,196.6080,557.0560,0.0681,24.0493,137.2596,9.1506 +200,8x8x16,16,16384,1900.5440,393.2160,1114.1120,0.1373,23.8580,138.3605,9.2240 +200,8x8x32,16,32768,3801.0880,786.4320,2228.2240,0.2736,23.9502,137.8279,9.1885 +200,8x8x64,16,65536,7602.1760,1572.8640,4456.4480,0.5870,22.3294,147.8318,9.8555 +200,8x16x2,16,4096,475.1360,98.3040,278.5280,0.0331,24.7333,133.4638,8.8976 +200,8x16x4,16,8192,950.2720,196.6080,557.0560,0.0686,23.8895,138.1779,9.2119 +200,8x16x8,16,16384,1900.5440,393.2160,1114.1120,0.1371,23.8939,138.1526,9.2102 +200,8x16x16,16,32768,3801.0880,786.4320,2228.2240,0.2742,23.9045,138.0909,9.2061 +200,8x16x32,16,65536,7602.1760,1572.8640,4456.4480,0.5851,22.4035,147.3428,9.8229 +200,8x16x64,16,131072,15204.3520,3145.7280,8912.8960,1.4449,18.1431,181.9423,12.1295 +200,8x32x2,16,8192,950.2720,196.6080,557.0560,0.0685,23.9332,137.9258,9.1951 +200,8x32x4,16,16384,1900.5440,393.2160,1114.1120,0.1354,24.1941,136.4383,9.0959 +200,8x32x8,16,32768,3801.0880,786.4320,2228.2240,0.2742,23.9018,138.1068,9.2071 +200,8x32x16,16,65536,7602.1760,1572.8640,4456.4480,0.5858,22.3747,147.5327,9.8355 +200,8x32x32,16,131072,15204.3520,3145.7280,8912.8960,1.4728,17.7993,185.4566,12.3638 +200,8x32x64,16,262144,30408.7040,6291.4560,17825.7920,3.1009,16.9075,195.2388,13.0159 +200,8x64x2,16,16384,1900.5440,393.2160,1114.1120,0.1362,24.0517,137.2460,9.1497 +200,8x64x4,16,32768,3801.0880,786.4320,2228.2240,0.2729,24.0178,137.4398,9.1627 +200,8x64x8,16,65536,7602.1760,1572.8640,4456.4480,0.5883,22.2787,148.1687,9.8779 +200,8x64x16,16,131072,15204.3520,3145.7280,8912.8960,1.4518,18.0563,182.8169,12.1878 +200,8x64x32,16,262144,30408.7040,6291.4560,17825.7920,3.1235,16.7852,196.6615,13.1108 +200,8x64x64,16,524288,60817.4080,12582.9120,35651.5840,6.4154,16.3447,201.9617,13.4641 +200,16x4x2,16,2048,237.5680,49.1520,139.2640,0.0164,25.0188,131.9407,8.7960 +200,16x4x4,16,4096,475.1360,98.3040,278.5280,0.0327,25.0635,131.7055,8.7804 +200,16x4x8,16,8192,950.2720,196.6080,557.0560,0.0681,24.0625,137.1844,9.1456 +200,16x4x16,16,16384,1900.5440,393.2160,1114.1120,0.1353,24.2172,136.3079,9.0872 +200,16x4x32,16,32768,3801.0880,786.4320,2228.2240,0.2736,23.9531,137.8109,9.1874 +200,16x4x64,16,65536,7602.1760,1572.8640,4456.4480,0.5894,22.2374,148.4434,9.8962 +200,16x8x2,16,4096,475.1360,98.3040,278.5280,0.0331,24.7414,133.4200,8.8947 +200,16x8x4,16,8192,950.2720,196.6080,557.0560,0.0681,24.0635,137.1789,9.1453 +200,16x8x8,16,16384,1900.5440,393.2160,1114.1120,0.1377,23.7946,138.7287,9.2486 +200,16x8x16,16,32768,3801.0880,786.4320,2228.2240,0.2731,23.9998,137.5431,9.1695 +200,16x8x32,16,65536,7602.1760,1572.8640,4456.4480,0.5872,22.3223,147.8793,9.8586 +200,16x8x64,16,131072,15204.3520,3145.7280,8912.8960,1.4703,17.8294,185.1437,12.3429 +200,16x16x2,16,8192,950.2720,196.6080,557.0560,0.0687,23.8416,138.4552,9.2303 +200,16x16x4,16,16384,1900.5440,393.2160,1114.1120,0.1375,23.8375,138.4791,9.2319 +200,16x16x8,16,32768,3801.0880,786.4320,2228.2240,0.2727,24.0302,137.3686,9.1579 +200,16x16x16,16,65536,7602.1760,1572.8640,4456.4480,0.5883,22.2792,148.1652,9.8777 +200,16x16x32,16,131072,15204.3520,3145.7280,8912.8960,1.4533,18.0375,183.0080,12.2005 +200,16x16x64,16,262144,30408.7040,6291.4560,17825.7920,3.1294,16.7536,197.0325,13.1355 +200,16x32x2,16,16384,1900.5440,393.2160,1114.1120,0.1378,23.7792,138.8186,9.2546 +200,16x32x4,16,32768,3801.0880,786.4320,2228.2240,0.2724,24.0554,137.2249,9.1483 +200,16x32x8,16,65536,7602.1760,1572.8640,4456.4480,0.5840,22.4451,147.0702,9.8047 +200,16x32x16,16,131072,15204.3520,3145.7280,8912.8960,1.4553,18.0128,183.2583,12.2172 +200,16x32x32,16,262144,30408.7040,6291.4560,17825.7920,3.1316,16.7421,197.1674,13.1445 +200,16x32x64,16,524288,60817.4080,12582.9120,35651.5840,6.5036,16.1231,204.7372,13.6491 +200,16x64x2,16,32768,3801.0880,786.4320,2228.2240,0.2731,23.9947,137.5723,9.1715 +200,16x64x4,16,65536,7602.1760,1572.8640,4456.4480,0.5852,22.3992,147.3712,9.8247 +200,16x64x8,16,131072,15204.3520,3145.7280,8912.8960,1.4516,18.0592,182.7882,12.1859 +200,16x64x16,16,262144,30408.7040,6291.4560,17825.7920,3.1097,16.8599,195.7903,13.0527 +200,16x64x32,16,524288,60817.4080,12582.9120,35651.5840,6.5056,16.1181,204.8003,13.6534 +200,16x64x64,16,1048576,121634.8160,25165.8240,71303.1680,13.1053,16.0023,206.2823,-37.6428 +200,32x4x2,16,4096,475.1360,98.3040,278.5280,0.0328,24.9512,132.2984,8.8199 +200,32x4x4,16,8192,950.2720,196.6080,557.0560,0.0682,24.0216,137.4177,9.1612 +200,32x4x8,16,16384,1900.5440,393.2160,1114.1120,0.1377,23.7965,138.7181,9.2479 +200,32x4x16,16,32768,3801.0880,786.4320,2228.2240,0.2730,24.0046,137.5155,9.1677 +200,32x4x32,16,65536,7602.1760,1572.8640,4456.4480,0.5829,22.4881,146.7890,9.7859 +200,32x4x64,16,131072,15204.3520,3145.7280,8912.8960,1.4484,18.0992,182.3833,12.1589 +200,32x8x2,16,8192,950.2720,196.6080,557.0560,0.0677,24.1845,136.4923,9.0995 +200,32x8x4,16,16384,1900.5440,393.2160,1114.1120,0.1374,23.8416,138.4555,9.2304 +200,32x8x8,16,32768,3801.0880,786.4320,2228.2240,0.2738,23.9371,137.9030,9.1935 +200,32x8x16,16,65536,7602.1760,1572.8640,4456.4480,0.5882,22.2849,148.1270,9.8751 +200,32x8x32,16,131072,15204.3520,3145.7280,8912.8960,1.4562,18.0018,183.3708,12.2247 +200,32x8x64,16,262144,30408.7040,6291.4560,17825.7920,3.0955,16.9373,194.8949,12.9930 +200,32x16x2,16,16384,1900.5440,393.2160,1114.1120,0.1377,23.7916,138.7464,9.2498 +200,32x16x4,16,32768,3801.0880,786.4320,2228.2240,0.2742,23.8984,138.1263,9.2084 +200,32x16x8,16,65536,7602.1760,1572.8640,4456.4480,0.5860,22.3662,147.5890,9.8393 +200,32x16x16,16,131072,15204.3520,3145.7280,8912.8960,1.4521,18.0527,182.8531,12.1902 +200,32x16x32,16,262144,30408.7040,6291.4560,17825.7920,3.1149,16.8315,196.1201,13.0747 +200,32x16x64,16,524288,60817.4080,12582.9120,35651.5840,6.4845,16.1705,204.1378,13.6092 +200,32x32x2,16,32768,3801.0880,786.4320,2228.2240,0.2740,23.9190,138.0077,9.2005 +200,32x32x4,16,65536,7602.1760,1572.8640,4456.4480,0.5801,22.5958,146.0891,9.7393 +200,32x32x8,16,131072,15204.3520,3145.7280,8912.8960,1.4427,18.1702,181.6708,12.1114 +200,32x32x16,16,262144,30408.7040,6291.4560,17825.7920,3.1059,16.8805,195.5508,13.0367 +200,32x32x32,16,524288,60817.4080,12582.9120,35651.5840,6.5648,15.9727,206.6647,13.7776 +200,32x32x64,16,1048576,121634.8160,25165.8240,71303.1680,13.4465,15.5962,211.6535,-38.6229 +200,32x64x2,16,65536,7602.1760,1572.8640,4456.4480,0.5794,22.6212,145.9248,9.7283 +200,32x64x4,16,131072,15204.3520,3145.7280,8912.8960,1.4597,17.9582,183.8159,12.2544 +200,32x64x8,16,262144,30408.7040,6291.4560,17825.7920,3.1126,16.8442,195.9724,13.0648 +200,32x64x16,16,524288,60817.4080,12582.9120,35651.5840,6.5076,16.1131,204.8649,13.6577 +200,32x64x32,16,1048576,121634.8160,25165.8240,71303.1680,13.2052,15.8813,207.8550,-37.9298 +200,32x64x64,16,2097152,243269.6320,50331.6480,142606.3360,26.5533,15.7958,208.9801,43.9034 +200,64x4x2,16,8192,950.2720,196.6080,557.0560,0.0676,24.2458,136.1475,9.0765 +200,64x4x4,16,16384,1900.5440,393.2160,1114.1120,0.1387,23.6314,139.6870,9.3125 +200,64x4x8,16,32768,3801.0880,786.4320,2228.2240,0.2728,24.0216,137.4180,9.1612 +200,64x4x16,16,65536,7602.1760,1572.8640,4456.4480,0.5876,22.3071,147.9798,9.8653 +200,64x4x32,16,131072,15204.3520,3145.7280,8912.8960,1.4662,17.8796,184.6236,12.3082 +200,64x4x64,16,262144,30408.7040,6291.4560,17825.7920,3.1136,16.8386,196.0381,13.0692 +200,64x8x2,16,16384,1900.5440,393.2160,1114.1120,0.1372,23.8911,138.1686,9.2112 +200,64x8x4,16,32768,3801.0880,786.4320,2228.2240,0.2738,23.9316,137.9348,9.1957 +200,64x8x8,16,65536,7602.1760,1572.8640,4456.4480,0.5872,22.3233,147.8722,9.8581 +200,64x8x16,16,131072,15204.3520,3145.7280,8912.8960,1.4458,18.1310,182.0638,12.1376 +200,64x8x32,16,262144,30408.7040,6291.4560,17825.7920,3.1368,16.7141,197.4976,13.1665 +200,64x8x64,16,524288,60817.4080,12582.9120,35651.5840,6.4162,16.3427,201.9857,13.4657 +200,64x16x2,16,32768,3801.0880,786.4320,2228.2240,0.2740,23.9176,138.0158,9.2011 +200,64x16x4,16,65536,7602.1760,1572.8640,4456.4480,0.5800,22.5988,146.0695,9.7380 +200,64x16x8,16,131072,15204.3520,3145.7280,8912.8960,1.4595,17.9611,183.7857,12.2524 +200,64x16x16,16,262144,30408.7040,6291.4560,17825.7920,3.0984,16.9211,195.0822,13.0055 +200,64x16x32,16,524288,60817.4080,12582.9120,35651.5840,6.4903,16.1561,204.3191,13.6213 +200,64x16x64,16,1048576,121634.8160,25165.8240,71303.1680,13.1687,15.9252,207.2811,-37.8250 +200,64x32x2,16,65536,7602.1760,1572.8640,4456.4480,0.5855,22.3859,147.4589,9.8306 +200,64x32x4,16,131072,15204.3520,3145.7280,8912.8960,1.4746,17.7769,185.6908,12.3794 +200,64x32x8,16,262144,30408.7040,6291.4560,17825.7920,3.1073,16.8730,195.6382,13.0425 +200,64x32x16,16,524288,60817.4080,12582.9120,35651.5840,6.4985,16.1356,204.5791,13.6386 +200,64x32x32,16,1048576,121634.8160,25165.8240,71303.1680,13.3353,15.7263,209.9025,-38.3034 +200,64x32x64,16,2097152,243269.6320,50331.6480,142606.3360,26.9030,15.5905,211.7316,44.4814 +200,64x64x2,16,131072,15204.3520,3145.7280,8912.8960,1.4540,18.0290,183.0936,12.2062 +200,64x64x4,16,262144,30408.7040,6291.4560,17825.7920,3.1314,16.7431,197.1556,13.1437 +200,64x64x8,16,524288,60817.4080,12582.9120,35651.5840,6.4141,16.3480,201.9211,13.4614 +200,64x64x16,16,1048576,121634.8160,25165.8240,71303.1680,13.2231,15.8597,208.1375,-37.9813 +200,64x64x32,16,2097152,243269.6320,50331.6480,142606.3360,26.2168,15.9985,206.3317,43.3470 +200,64x64x64,16,4194304,486539.2640,100663.2960,285212.6720,53.6958,15.6225,211.2984,-586.9401 +200,4x4x2,32,1024,184.3200,24.5760,135.1680,0.0134,15.2346,216.6777,6.9896 +200,4x4x4,32,2048,368.6400,49.1520,270.3360,0.0266,15.4085,214.2323,6.9107 +200,4x4x8,32,4096,737.2800,98.3040,540.6720,0.0545,15.0233,219.7251,7.0879 +200,4x4x16,32,8192,1474.5600,196.6080,1081.3440,0.1093,14.9944,220.1483,7.1016 +200,4x4x32,32,16384,2949.1200,393.2160,2162.6880,0.2193,14.9437,220.8951,7.1256 +200,4x4x64,32,32768,5898.2400,786.4320,4325.3760,0.4379,14.9647,220.5860,7.1157 +200,4x8x2,32,2048,368.6400,49.1520,270.3360,0.0267,15.3207,215.4599,6.9503 +200,4x8x4,32,4096,737.2800,98.3040,540.6720,0.0546,15.0008,220.0543,7.0985 +200,4x8x8,32,8192,1474.5600,196.6080,1081.3440,0.1094,14.9822,220.3278,7.1073 +200,4x8x16,32,16384,2949.1200,393.2160,2162.6880,0.2191,14.9583,220.6805,7.1187 +200,4x8x32,32,32768,5898.2400,786.4320,4325.3760,0.4374,14.9848,220.2903,7.1061 +200,4x8x64,32,65536,11796.4800,1572.8640,8650.7520,0.9374,13.9828,236.0765,7.6154 +200,4x16x2,32,4096,737.2800,98.3040,540.6720,0.0541,15.1494,217.8961,7.0289 +200,4x16x4,32,8192,1474.5600,196.6080,1081.3440,0.1089,15.0502,219.3323,7.0752 +200,4x16x8,32,16384,2949.1200,393.2160,2162.6880,0.2189,14.9698,220.5113,7.1133 +200,4x16x16,32,32768,5898.2400,786.4320,4325.3760,0.4385,14.9443,220.8864,7.1254 +200,4x16x32,32,65536,11796.4800,1572.8640,8650.7520,0.9337,14.0372,235.1611,7.5858 +200,4x16x64,32,131072,23592.9600,3145.7280,17301.5040,2.0220,12.9647,254.6154,8.2134 +200,4x32x2,32,8192,1474.5600,196.6080,1081.3440,0.1087,15.0688,219.0623,7.0665 +200,4x32x4,32,16384,2949.1200,393.2160,2162.6880,0.2187,14.9847,220.2915,7.1062 +200,4x32x8,32,32768,5898.2400,786.4320,4325.3760,0.4346,15.0800,218.8995,7.0613 +200,4x32x16,32,65536,11796.4800,1572.8640,8650.7520,0.9384,13.9682,236.3232,7.6233 +200,4x32x32,32,131072,23592.9600,3145.7280,17301.5040,2.0175,12.9935,254.0510,8.1952 +200,4x32x64,32,262144,47185.9200,6291.4560,34603.0080,4.1609,12.6004,261.9751,8.4508 +200,4x64x2,32,16384,2949.1200,393.2160,2162.6880,0.2187,14.9811,220.3445,7.1079 +200,4x64x4,32,32768,5898.2400,786.4320,4325.3760,0.4385,14.9470,220.8474,7.1241 +200,4x64x8,32,65536,11796.4800,1572.8640,8650.7520,0.9425,13.9075,237.3533,7.6566 +200,4x64x16,32,131072,23592.9600,3145.7280,17301.5040,2.0193,12.9817,254.2807,8.2026 +200,4x64x32,32,262144,47185.9200,6291.4560,34603.0080,4.1060,12.7687,258.5221,8.3394 +200,4x64x64,32,524288,94371.8400,12582.9120,69206.0160,8.5023,12.3329,267.6588,-26.8734 +200,8x4x2,32,2048,368.6400,49.1520,270.3360,0.0269,15.2501,216.4575,6.9825 +200,8x4x4,32,4096,737.2800,98.3040,540.6720,0.0546,15.0017,220.0414,7.0981 +200,8x4x8,32,8192,1474.5600,196.6080,1081.3440,0.1090,15.0299,219.6287,7.0848 +200,8x4x16,32,16384,2949.1200,393.2160,2162.6880,0.2186,14.9877,220.2466,7.1047 +200,8x4x32,32,32768,5898.2400,786.4320,4325.3760,0.4382,14.9568,220.7025,7.1194 +200,8x4x64,32,65536,11796.4800,1572.8640,8650.7520,0.9368,13.9922,235.9171,7.6102 +200,8x8x2,32,4096,737.2800,98.3040,540.6720,0.0542,15.1196,218.3266,7.0428 +200,8x8x4,32,8192,1474.5600,196.6080,1081.3440,0.1092,15.0007,220.0570,7.0986 +200,8x8x8,32,16384,2949.1200,393.2160,2162.6880,0.2159,15.1799,217.4583,7.0148 +200,8x8x16,32,32768,5898.2400,786.4320,4325.3760,0.4374,14.9815,220.3387,7.1077 +200,8x8x32,32,65536,11796.4800,1572.8640,8650.7520,0.9386,13.9650,236.3773,7.6251 +200,8x8x64,32,131072,23592.9600,3145.7280,17301.5040,2.0236,12.9544,254.8161,8.2199 +200,8x16x2,32,8192,1474.5600,196.6080,1081.3440,0.1093,14.9932,220.1666,7.1021 +200,8x16x4,32,16384,2949.1200,393.2160,2162.6880,0.2187,14.9802,220.3572,7.1083 +200,8x16x8,32,32768,5898.2400,786.4320,4325.3760,0.4388,14.9344,221.0333,7.1301 +200,8x16x16,32,65536,11796.4800,1572.8640,8650.7520,0.9327,14.0529,234.8988,7.5774 +200,8x16x32,32,131072,23592.9600,3145.7280,17301.5040,2.0367,12.8711,256.4670,8.2731 +200,8x16x64,32,262144,47185.9200,6291.4560,34603.0080,4.1018,12.7819,258.2559,8.3308 +200,8x32x2,32,16384,2949.1200,393.2160,2162.6880,0.2188,14.9790,220.3750,7.1089 +200,8x32x4,32,32768,5898.2400,786.4320,4325.3760,0.4386,14.9426,220.9122,7.1262 +200,8x32x8,32,65536,11796.4800,1572.8640,8650.7520,0.9360,14.0039,235.7196,7.6039 +200,8x32x16,32,131072,23592.9600,3145.7280,17301.5040,2.0310,12.9071,255.7514,8.2500 +200,8x32x32,32,262144,47185.9200,6291.4560,34603.0080,4.1461,12.6452,261.0469,8.4209 +200,8x32x64,32,524288,94371.8400,12582.9120,69206.0160,8.3325,12.5842,262.3128,-26.3366 +200,8x64x2,32,32768,5898.2400,786.4320,4325.3760,0.4385,14.9469,220.8478,7.1241 +200,8x64x4,32,65536,11796.4800,1572.8640,8650.7520,0.9403,13.9390,236.8176,7.6393 +200,8x64x8,32,131072,23592.9600,3145.7280,17301.5040,2.0259,12.9397,255.1062,8.2292 +200,8x64x16,32,262144,47185.9200,6291.4560,34603.0080,4.1068,12.7662,258.5733,8.3411 +200,8x64x32,32,524288,94371.8400,12582.9120,69206.0160,8.4559,12.4005,266.1989,-26.7268 +200,8x64x64,32,1048576,188743.6800,25165.8240,138412.0320,17.0485,12.3011,268.3504,-26.9428 +200,16x4x2,32,4096,737.2800,98.3040,540.6720,0.0545,15.0353,219.5506,7.0823 +200,16x4x4,32,8192,1474.5600,196.6080,1081.3440,0.1083,15.1228,218.2803,7.0413 +200,16x4x8,32,16384,2949.1200,393.2160,2162.6880,0.2193,14.9435,220.8982,7.1257 +200,16x4x16,32,32768,5898.2400,786.4320,4325.3760,0.4371,14.9928,220.1717,7.1023 +200,16x4x32,32,65536,11796.4800,1572.8640,8650.7520,0.9377,13.9786,236.1473,7.6177 +200,16x4x64,32,131072,23592.9600,3145.7280,17301.5040,2.0308,12.9084,255.7246,8.2492 +200,16x8x2,32,8192,1474.5600,196.6080,1081.3440,0.1092,14.9993,220.0768,7.0993 +200,16x8x4,32,16384,2949.1200,393.2160,2162.6880,0.2156,15.2008,217.1597,7.0052 +200,16x8x8,32,32768,5898.2400,786.4320,4325.3760,0.4348,15.0713,219.0254,7.0653 +200,16x8x16,32,65536,11796.4800,1572.8640,8650.7520,0.9381,13.9724,236.2512,7.6210 +200,16x8x32,32,131072,23592.9600,3145.7280,17301.5040,2.0138,13.0174,253.5827,8.1801 +200,16x8x64,32,262144,47185.9200,6291.4560,34603.0080,4.1049,12.7722,258.4526,8.3372 +200,16x16x2,32,16384,2949.1200,393.2160,2162.6880,0.2196,14.9241,221.1865,7.1350 +200,16x16x4,32,32768,5898.2400,786.4320,4325.3760,0.4374,14.9833,220.3117,7.1068 +200,16x16x8,32,65536,11796.4800,1572.8640,8650.7520,0.9391,13.9572,236.5088,7.6293 +200,16x16x16,32,131072,23592.9600,3145.7280,17301.5040,2.0364,12.8726,256.4356,8.2721 +200,16x16x32,32,262144,47185.9200,6291.4560,34603.0080,4.1083,12.7618,258.6626,8.3440 +200,16x16x64,32,524288,94371.8400,12582.9120,69206.0160,8.5071,12.3259,267.8100,-26.8886 +200,16x32x2,32,32768,5898.2400,786.4320,4325.3760,0.4374,14.9829,220.3184,7.1070 +200,16x32x4,32,65536,11796.4800,1572.8640,8650.7520,0.9337,14.0376,235.1549,7.5856 +200,16x32x8,32,131072,23592.9600,3145.7280,17301.5040,2.0285,12.9228,255.4397,8.2400 +200,16x32x16,32,262144,47185.9200,6291.4560,34603.0080,4.1517,12.6282,261.3994,8.4322 +200,16x32x32,32,524288,94371.8400,12582.9120,69206.0160,8.3354,12.5797,262.4065,-26.3460 +200,16x32x64,32,1048576,188743.6800,25165.8240,138412.0320,17.1852,12.2033,270.5016,-27.1588 +200,16x64x2,32,65536,11796.4800,1572.8640,8650.7520,0.9372,13.9857,236.0275,7.6138 +200,16x64x4,32,131072,23592.9600,3145.7280,17301.5040,2.0181,12.9897,254.1243,8.1976 +200,16x64x8,32,262144,47185.9200,6291.4560,34603.0080,4.1102,12.7557,258.7871,8.3480 +200,16x64x16,32,524288,94371.8400,12582.9120,69206.0160,8.5143,12.3155,268.0368,-26.9113 +200,16x64x32,32,1048576,188743.6800,25165.8240,138412.0320,16.7462,12.5231,263.5925,-26.4651 +200,16x64x64,32,2097152,377487.3600,50331.6480,276824.0640,34.3474,12.2114,270.3206,965.4307 +200,32x4x2,32,8192,1474.5600,196.6080,1081.3440,0.1091,15.0122,219.8883,7.0932 +200,32x4x4,32,16384,2949.1200,393.2160,2162.6880,0.2191,14.9554,220.7223,7.1201 +200,32x4x8,32,32768,5898.2400,786.4320,4325.3760,0.4372,14.9912,220.1951,7.1031 +200,32x4x16,32,65536,11796.4800,1572.8640,8650.7520,0.9347,14.0224,235.4083,7.5938 +200,32x4x32,32,131072,23592.9600,3145.7280,17301.5040,2.0181,12.9898,254.1230,8.1975 +200,32x4x64,32,262144,47185.9200,6291.4560,34603.0080,4.0964,12.7986,257.9188,8.3200 +200,32x8x2,32,16384,2949.1200,393.2160,2162.6880,0.2191,14.9549,220.7300,7.1203 +200,32x8x4,32,32768,5898.2400,786.4320,4325.3760,0.4380,14.9628,220.6131,7.1166 +200,32x8x8,32,65536,11796.4800,1572.8640,8650.7520,0.9370,13.9889,235.9727,7.6120 +200,32x8x16,32,131072,23592.9600,3145.7280,17301.5040,2.0005,13.1036,251.9156,8.1263 +200,32x8x32,32,262144,47185.9200,6291.4560,34603.0080,4.1569,12.6125,261.7241,8.4427 +200,32x8x64,32,524288,94371.8400,12582.9120,69206.0160,8.4536,12.4039,266.1250,-26.7194 +200,32x16x2,32,32768,5898.2400,786.4320,4325.3760,0.4376,14.9762,220.4158,7.1102 +200,32x16x4,32,65536,11796.4800,1572.8640,8650.7520,0.9325,14.0565,234.8381,7.5754 +200,32x16x8,32,131072,23592.9600,3145.7280,17301.5040,2.0189,12.9848,254.2212,8.2007 +200,32x16x16,32,262144,47185.9200,6291.4560,34603.0080,4.1342,12.6818,260.2952,8.3966 +200,32x16x32,32,524288,94371.8400,12582.9120,69206.0160,8.4425,12.4201,265.7779,-26.6845 +200,32x16x64,32,1048576,188743.6800,25165.8240,138412.0320,16.8367,12.4558,265.0161,-26.6080 +200,32x32x2,32,65536,11796.4800,1572.8640,8650.7520,0.9372,13.9857,236.0276,7.6138 +200,32x32x4,32,131072,23592.9600,3145.7280,17301.5040,2.0228,12.9595,254.7174,8.2167 +200,32x32x8,32,262144,47185.9200,6291.4560,34603.0080,4.1124,12.7491,258.9207,8.3523 +200,32x32x16,32,524288,94371.8400,12582.9120,69206.0160,8.5060,12.3275,267.7762,-26.8852 +200,32x32x32,32,1048576,188743.6800,25165.8240,138412.0320,17.1890,12.2005,270.5622,-27.1649 +200,32x32x64,32,2097152,377487.3600,50331.6480,276824.0640,33.5418,12.5047,263.9803,942.7868 +200,32x64x2,32,131072,23592.9600,3145.7280,17301.5040,2.1203,12.3637,266.9921,8.6126 +200,32x64x4,32,262144,47185.9200,6291.4560,34603.0080,4.1809,12.5402,263.2341,8.4914 +200,32x64x8,32,524288,94371.8400,12582.9120,69206.0160,8.3133,12.6132,261.7105,-26.2762 +200,32x64x16,32,1048576,188743.6800,25165.8240,138412.0320,16.6965,12.5605,262.8088,-26.3864 +200,32x64x32,32,2097152,377487.3600,50331.6480,276824.0640,33.7448,12.4295,265.5785,948.4946 +200,32x64x64,32,4194304,754974.7200,100663.2960,553648.1280,68.5976,12.2287,269.9385,964.0660 +200,64x4x2,32,16384,2949.1200,393.2160,2162.6880,0.2194,14.9371,220.9935,7.1288 +200,64x4x4,32,32768,5898.2400,786.4320,4325.3760,0.4381,14.9604,220.6498,7.1177 +200,64x4x8,32,65536,11796.4800,1572.8640,8650.7520,0.9245,14.1782,232.8227,7.5104 +200,64x4x16,32,131072,23592.9600,3145.7280,17301.5040,2.0184,12.9880,254.1572,8.1986 +200,64x4x32,32,262144,47185.9200,6291.4560,34603.0080,4.1707,12.5708,262.5927,8.4707 +200,64x4x64,32,524288,94371.8400,12582.9120,69206.0160,8.2933,12.6437,261.0782,-26.2127 +200,64x8x2,32,32768,5898.2400,786.4320,4325.3760,0.4371,14.9927,220.1744,7.1024 +200,64x8x4,32,65536,11796.4800,1572.8640,8650.7520,0.9394,13.9534,236.5739,7.6314 +200,64x8x8,32,131072,23592.9600,3145.7280,17301.5040,2.0204,12.9749,254.4147,8.2069 +200,64x8x16,32,262144,47185.9200,6291.4560,34603.0080,4.1678,12.5794,262.4123,8.4649 +200,64x8x32,32,524288,94371.8400,12582.9120,69206.0160,8.3336,12.5825,262.3480,-26.3402 +200,64x8x64,32,1048576,188743.6800,25165.8240,138412.0320,17.0020,12.3347,267.6182,-26.8693 +200,64x16x2,32,65536,11796.4800,1572.8640,8650.7520,0.9336,14.0390,235.1313,7.5849 +200,64x16x4,32,131072,23592.9600,3145.7280,17301.5040,2.0218,12.9657,254.5951,8.2127 +200,64x16x8,32,262144,47185.9200,6291.4560,34603.0080,4.1207,12.7233,259.4454,8.3692 +200,64x16x16,32,524288,94371.8400,12582.9120,69206.0160,8.3560,12.5488,263.0527,-26.4109 +200,64x16x32,32,1048576,188743.6800,25165.8240,138412.0320,16.7676,12.5072,263.9284,-26.4988 +200,64x16x64,32,2097152,377487.3600,50331.6480,276824.0640,33.4795,12.5280,263.4900,941.0357 +200,64x32x2,32,131072,23592.9600,3145.7280,17301.5040,2.0220,12.9643,254.6225,8.2136 +200,64x32x4,32,262144,47185.9200,6291.4560,34603.0080,4.0872,12.8275,257.3383,8.3012 +200,64x32x8,32,524288,94371.8400,12582.9120,69206.0160,8.4447,12.4169,265.8471,-26.6915 +200,64x32x16,32,1048576,188743.6800,25165.8240,138412.0320,17.0434,12.3048,268.2701,-26.9347 +200,64x32x32,32,2097152,377487.3600,50331.6480,276824.0640,33.4924,12.5231,263.5920,941.3999 +200,64x32x64,32,4194304,754974.7200,100663.2960,553648.1280,68.4806,12.2496,269.4779,962.4209 +200,64x64x2,32,262144,47185.9200,6291.4560,34603.0080,4.1498,12.6341,261.2772,8.4283 +200,64x64x4,32,524288,94371.8400,12582.9120,69206.0160,8.4875,12.3543,267.1943,-26.8267 +200,64x64x8,32,1048576,188743.6800,25165.8240,138412.0320,16.7591,12.5135,263.7955,-26.4855 +200,64x64x16,32,2097152,377487.3600,50331.6480,276824.0640,33.6675,12.4580,264.9700,946.3215 +200,64x64x32,32,4194304,754974.7200,100663.2960,553648.1280,68.4488,12.2553,269.3528,961.9742 +200,64x64x64,32,8388608,1509949.4400,201326.5920,1107296.2560,136.3839,12.3015,268.3420,958.3643 diff --git a/scripts/results_aos_skylakesp2.txt b/scripts/results_aos_skylakesp2.txt new file mode 100644 index 0000000..61a646a --- /dev/null +++ b/scripts/results_aos_skylakesp2.txt @@ -0,0 +1,450 @@ +200,4x4x2,8,256,21.5040,6.1440,9.2160,0.0017,30.3465,108.7769,15.5396 +200,4x4x4,8,512,43.0080,12.2880,18.4320,0.0035,29.4117,112.2341,16.0334 +200,4x4x8,8,1024,86.0160,24.5760,36.8640,0.0068,29.9117,110.3582,15.7655 +200,4x4x16,8,2048,172.0320,49.1520,73.7280,0.0140,29.2747,112.7597,16.1085 +200,4x4x32,8,4096,344.0640,98.3040,147.4560,0.0277,29.6271,111.4183,15.9169 +200,4x4x64,8,8192,688.1280,196.6080,294.9120,0.0588,27.8858,118.3758,16.9108 +200,4x8x2,8,512,43.0080,12.2880,18.4320,0.0035,29.2900,112.7006,16.1001 +200,4x8x4,8,1024,86.0160,24.5760,36.8640,0.0071,28.8960,114.2372,16.3196 +200,4x8x8,8,2048,172.0320,49.1520,73.7280,0.0138,29.7567,110.9330,15.8476 +200,4x8x16,8,4096,344.0640,98.3040,147.4560,0.0283,28.9645,113.9670,16.2810 +200,4x8x32,8,8192,688.1280,196.6080,294.9120,0.0589,27.8278,118.6226,16.9461 +200,4x8x64,8,16384,1376.2560,393.2160,589.8240,0.1161,28.2126,117.0045,16.7149 +200,4x16x2,8,1024,86.0160,24.5760,36.8640,0.0070,29.1692,113.1674,16.1668 +200,4x16x4,8,2048,172.0320,49.1520,73.7280,0.0138,29.7129,111.0967,15.8710 +200,4x16x8,8,4096,344.0640,98.3040,147.4560,0.0281,29.1939,113.0715,16.1531 +200,4x16x16,8,8192,688.1280,196.6080,294.9120,0.0575,28.5109,115.7801,16.5400 +200,4x16x32,8,16384,1376.2560,393.2160,589.8240,0.1183,27.7097,119.1278,17.0183 +200,4x16x64,8,32768,2752.5120,786.4320,1179.6480,0.2349,27.9053,118.2930,16.8990 +200,4x32x2,8,2048,172.0320,49.1520,73.7280,0.0143,28.6695,115.1397,16.4485 +200,4x32x4,8,4096,344.0640,98.3040,147.4560,0.0284,28.8051,114.5978,16.3711 +200,4x32x8,8,8192,688.1280,196.6080,294.9120,0.0586,27.9695,118.0216,16.8602 +200,4x32x16,8,16384,1376.2560,393.2160,589.8240,0.1180,27.7722,118.8600,16.9800 +200,4x32x32,8,32768,2752.5120,786.4320,1179.6480,0.2282,28.7202,114.9367,16.4195 +200,4x32x64,8,65536,5505.0240,1572.8640,2359.2960,0.5880,22.2904,148.0906,21.1558 +200,4x64x2,8,4096,344.0640,98.3040,147.4560,0.0281,29.1687,113.1693,16.1670 +200,4x64x4,8,8192,688.1280,196.6080,294.9120,0.0587,27.9318,118.1807,16.8830 +200,4x64x8,8,16384,1376.2560,393.2160,589.8240,0.1181,27.7405,118.9959,16.9994 +200,4x64x16,8,32768,2752.5120,786.4320,1179.6480,0.2362,27.7451,118.9758,16.9965 +200,4x64x32,8,65536,5505.0240,1572.8640,2359.2960,0.5785,22.6560,145.7012,20.8145 +200,4x64x64,8,131072,11010.0480,3145.7280,4718.5920,1.4375,18.2361,181.0141,25.8592 +200,8x4x2,8,512,43.0080,12.2880,18.4320,0.0035,29.3622,112.4235,16.0605 +200,8x4x4,8,1024,86.0160,24.5760,36.8640,0.0068,29.9101,110.3639,15.7663 +200,8x4x8,8,2048,172.0320,49.1520,73.7280,0.0141,29.0417,113.6642,16.2377 +200,8x4x16,8,4096,344.0640,98.3040,147.4560,0.0281,29.1617,113.1963,16.1709 +200,8x4x32,8,8192,688.1280,196.6080,294.9120,0.0585,28.0111,117.8460,16.8351 +200,8x4x64,8,16384,1376.2560,393.2160,589.8240,0.1183,27.7088,119.1318,17.0188 +200,8x8x2,8,1024,86.0160,24.5760,36.8640,0.0069,29.8459,110.6015,15.8002 +200,8x8x4,8,2048,172.0320,49.1520,73.7280,0.0139,29.4463,112.1024,16.0146 +200,8x8x8,8,4096,344.0640,98.3040,147.4560,0.0277,29.5525,111.6996,15.9571 +200,8x8x16,8,8192,688.1280,196.6080,294.9120,0.0579,28.3017,116.6362,16.6623 +200,8x8x32,8,16384,1376.2560,393.2160,589.8240,0.1145,28.6203,115.3378,16.4768 +200,8x8x64,8,32768,2752.5120,786.4320,1179.6480,0.2280,28.7474,114.8278,16.4040 +200,8x16x2,8,2048,172.0320,49.1520,73.7280,0.0140,29.3212,112.5807,16.0830 +200,8x16x4,8,4096,344.0640,98.3040,147.4560,0.0277,29.5887,111.5627,15.9375 +200,8x16x8,8,8192,688.1280,196.6080,294.9120,0.0572,28.6587,115.1831,16.4547 +200,8x16x16,8,16384,1376.2560,393.2160,589.8240,0.1178,27.8274,118.6242,16.9463 +200,8x16x32,8,32768,2752.5120,786.4320,1179.6480,0.2344,27.9549,118.0829,16.8690 +200,8x16x64,8,65536,5505.0240,1572.8640,2359.2960,0.5755,22.7750,144.9394,20.7056 +200,8x32x2,8,4096,344.0640,98.3040,147.4560,0.0283,28.9347,114.0844,16.2978 +200,8x32x4,8,8192,688.1280,196.6080,294.9120,0.0586,27.9741,118.0018,16.8574 +200,8x32x8,8,16384,1376.2560,393.2160,589.8240,0.1156,28.3512,116.4326,16.6332 +200,8x32x16,8,32768,2752.5120,786.4320,1179.6480,0.2286,28.6691,115.1416,16.4488 +200,8x32x32,8,65536,5505.0240,1572.8640,2359.2960,0.5765,22.7365,145.1848,20.7407 +200,8x32x64,8,131072,11010.0480,3145.7280,4718.5920,1.4350,18.2676,180.7024,25.8146 +200,8x64x2,8,8192,688.1280,196.6080,294.9120,0.0584,28.0706,117.5963,16.7995 +200,8x64x4,8,16384,1376.2560,393.2160,589.8240,0.1148,28.5532,115.6087,16.5155 +200,8x64x8,8,32768,2752.5120,786.4320,1179.6480,0.2361,27.7596,118.9138,16.9877 +200,8x64x16,8,65536,5505.0240,1572.8640,2359.2960,0.5871,22.3246,147.8639,21.1234 +200,8x64x32,8,131072,11010.0480,3145.7280,4718.5920,1.4440,18.1544,181.8290,25.9756 +200,8x64x64,8,262144,22020.0960,6291.4560,9437.1840,3.0284,17.3122,190.6752,27.2393 +200,16x4x2,8,1024,86.0160,24.5760,36.8640,0.0070,29.1585,113.2087,16.1727 +200,16x4x4,8,2048,172.0320,49.1520,73.7280,0.0138,29.6911,111.1780,15.8826 +200,16x4x8,8,4096,344.0640,98.3040,147.4560,0.0283,28.9797,113.9074,16.2725 +200,16x4x16,8,8192,688.1280,196.6080,294.9120,0.0587,27.9252,118.2088,16.8870 +200,16x4x32,8,16384,1376.2560,393.2160,589.8240,0.1183,27.7026,119.1586,17.0227 +200,16x4x64,8,32768,2752.5120,786.4320,1179.6480,0.2341,27.9895,117.9373,16.8482 +200,16x8x2,8,2048,172.0320,49.1520,73.7280,0.0142,28.7942,114.6411,16.3773 +200,16x8x4,8,4096,344.0640,98.3040,147.4560,0.0283,28.9327,114.0924,16.2989 +200,16x8x8,8,8192,688.1280,196.6080,294.9120,0.0570,28.7438,114.8422,16.4060 +200,16x8x16,8,16384,1376.2560,393.2160,589.8240,0.1146,28.5861,115.4759,16.4966 +200,16x8x32,8,32768,2752.5120,786.4320,1179.6480,0.2326,28.1699,117.1817,16.7402 +200,16x8x64,8,65536,5505.0240,1572.8640,2359.2960,0.5820,22.5202,146.5794,20.9399 +200,16x16x2,8,4096,344.0640,98.3040,147.4560,0.0286,28.6319,115.2912,16.4702 +200,16x16x4,8,8192,688.1280,196.6080,294.9120,0.0577,28.4037,116.2174,16.6025 +200,16x16x8,8,16384,1376.2560,393.2160,589.8240,0.1157,28.3232,116.5474,16.6496 +200,16x16x16,8,32768,2752.5120,786.4320,1179.6480,0.2272,28.8476,114.4289,16.3470 +200,16x16x32,8,65536,5505.0240,1572.8640,2359.2960,0.5853,22.3948,147.4001,21.0572 +200,16x16x64,8,131072,11010.0480,3145.7280,4718.5920,1.4359,18.2569,180.8082,25.8297 +200,16x32x2,8,8192,688.1280,196.6080,294.9120,0.0592,27.6563,119.3580,17.0511 +200,16x32x4,8,16384,1376.2560,393.2160,589.8240,0.1175,27.8953,118.3353,16.9050 +200,16x32x8,8,32768,2752.5120,786.4320,1179.6480,0.2339,28.0208,117.8051,16.8293 +200,16x32x16,8,65536,5505.0240,1572.8640,2359.2960,0.5877,22.3036,148.0030,21.1433 +200,16x32x32,8,131072,11010.0480,3145.7280,4718.5920,1.4163,18.5085,178.3503,25.4786 +200,16x32x64,8,262144,22020.0960,6291.4560,9437.1840,3.0250,17.3321,190.4557,27.2080 +200,16x64x2,8,16384,1376.2560,393.2160,589.8240,0.1184,27.6850,119.2343,17.0335 +200,16x64x4,8,32768,2752.5120,786.4320,1179.6480,0.2318,28.2692,116.7704,16.6815 +200,16x64x8,8,65536,5505.0240,1572.8640,2359.2960,0.5828,22.4888,146.7843,20.9692 +200,16x64x16,8,131072,11010.0480,3145.7280,4718.5920,1.4080,18.6177,177.3041,25.3292 +200,16x64x32,8,262144,22020.0960,6291.4560,9437.1840,3.0668,17.0956,193.0906,27.5844 +200,16x64x64,8,524288,44040.1920,12582.9120,18874.3680,6.2702,16.7233,197.3894,28.1985 +200,32x4x2,8,2048,172.0320,49.1520,73.7280,0.0138,29.7469,110.9697,15.8528 +200,32x4x4,8,4096,344.0640,98.3040,147.4560,0.0280,29.2260,112.9475,16.1354 +200,32x4x8,8,8192,688.1280,196.6080,294.9120,0.0592,27.6594,119.3447,17.0492 +200,32x4x16,8,16384,1376.2560,393.2160,589.8240,0.1176,27.8590,118.4893,16.9270 +200,32x4x32,8,32768,2752.5120,786.4320,1179.6480,0.2335,28.0716,117.5922,16.7989 +200,32x4x64,8,65536,5505.0240,1572.8640,2359.2960,0.5712,22.9486,143.8433,20.5490 +200,32x8x2,8,4096,344.0640,98.3040,147.4560,0.0278,29.4205,112.2006,16.0287 +200,32x8x4,8,8192,688.1280,196.6080,294.9120,0.0582,28.1302,117.3473,16.7639 +200,32x8x8,8,16384,1376.2560,393.2160,589.8240,0.1179,27.8007,118.7378,16.9625 +200,32x8x16,8,32768,2752.5120,786.4320,1179.6480,0.2297,28.5347,115.6839,16.5263 +200,32x8x32,8,65536,5505.0240,1572.8640,2359.2960,0.5933,22.0925,149.4173,21.3453 +200,32x8x64,8,131072,11010.0480,3145.7280,4718.5920,1.4077,18.6223,177.2608,25.3230 +200,32x16x2,8,8192,688.1280,196.6080,294.9120,0.0584,28.0354,117.7439,16.8206 +200,32x16x4,8,16384,1376.2560,393.2160,589.8240,0.1151,28.4770,115.9181,16.5597 +200,32x16x8,8,32768,2752.5120,786.4320,1179.6480,0.2362,27.7498,118.9559,16.9937 +200,32x16x16,8,65536,5505.0240,1572.8640,2359.2960,0.5820,22.5213,146.5721,20.9389 +200,32x16x32,8,131072,11010.0480,3145.7280,4718.5920,1.4174,18.4944,178.4868,25.4981 +200,32x16x64,8,262144,22020.0960,6291.4560,9437.1840,3.0733,17.0595,193.4992,27.6427 +200,32x32x2,8,16384,1376.2560,393.2160,589.8240,0.1152,28.4535,116.0140,16.5734 +200,32x32x4,8,32768,2752.5120,786.4320,1179.6480,0.2266,28.9244,114.1250,16.3036 +200,32x32x8,8,65536,5505.0240,1572.8640,2359.2960,0.5804,22.5825,146.1755,20.8822 +200,32x32x16,8,131072,11010.0480,3145.7280,4718.5920,1.4367,18.2460,180.9162,25.8452 +200,32x32x32,8,262144,22020.0960,6291.4560,9437.1840,3.0375,17.2607,191.2436,27.3205 +200,32x32x64,8,524288,44040.1920,12582.9120,18874.3680,6.2335,16.8215,196.2366,28.0338 +200,32x64x2,8,32768,2752.5120,786.4320,1179.6480,0.2302,28.4738,115.9312,16.5616 +200,32x64x4,8,65536,5505.0240,1572.8640,2359.2960,0.5861,22.3652,147.5953,21.0850 +200,32x64x8,8,131072,11010.0480,3145.7280,4718.5920,1.4180,18.4875,178.5533,25.5076 +200,32x64x16,8,262144,22020.0960,6291.4560,9437.1840,3.0346,17.2770,191.0631,27.2947 +200,32x64x32,8,524288,44040.1920,12582.9120,18874.3680,6.3025,16.6376,198.4062,28.3437 +200,32x64x64,8,1048576,88080.3840,25165.8240,37748.7360,12.7814,16.4079,201.1838,28.7405 +200,64x4x2,8,4096,344.0640,98.3040,147.4560,0.0283,28.9709,113.9419,16.2774 +200,64x4x4,8,8192,688.1280,196.6080,294.9120,0.0582,28.1578,117.2320,16.7474 +200,64x4x8,8,16384,1376.2560,393.2160,589.8240,0.1183,27.7027,119.1582,17.0226 +200,64x4x16,8,32768,2752.5120,786.4320,1179.6480,0.2278,28.7749,114.7179,16.3883 +200,64x4x32,8,65536,5505.0240,1572.8640,2359.2960,0.5870,22.3280,147.8415,21.1202 +200,64x4x64,8,131072,11010.0480,3145.7280,4718.5920,1.4253,18.3927,179.4738,25.6391 +200,64x8x2,8,8192,688.1280,196.6080,294.9120,0.0583,28.1031,117.4602,16.7800 +200,64x8x4,8,16384,1376.2560,393.2160,589.8240,0.1160,28.2362,116.9066,16.7009 +200,64x8x8,8,32768,2752.5120,786.4320,1179.6480,0.2346,27.9345,118.1694,16.8813 +200,64x8x16,8,65536,5505.0240,1572.8640,2359.2960,0.5759,22.7579,145.0484,20.7212 +200,64x8x32,8,131072,11010.0480,3145.7280,4718.5920,1.4412,18.1889,181.4842,25.9263 +200,64x8x64,8,262144,22020.0960,6291.4560,9437.1840,3.0304,17.3007,190.8014,27.2573 +200,64x16x2,8,16384,1376.2560,393.2160,589.8240,0.1152,28.4352,116.0884,16.5841 +200,64x16x4,8,32768,2752.5120,786.4320,1179.6480,0.2329,28.1400,117.3061,16.7580 +200,64x16x8,8,65536,5505.0240,1572.8640,2359.2960,0.5882,22.2847,148.1284,21.1612 +200,64x16x16,8,131072,11010.0480,3145.7280,4718.5920,1.4200,18.4609,178.8099,25.5443 +200,64x16x32,8,262144,22020.0960,6291.4560,9437.1840,3.0645,17.1084,192.9467,27.5638 +200,64x16x64,8,524288,44040.1920,12582.9120,18874.3680,6.2823,16.6910,197.7714,28.2531 +200,64x32x2,8,32768,2752.5120,786.4320,1179.6480,0.2325,28.1827,117.1285,16.7326 +200,64x32x4,8,65536,5505.0240,1572.8640,2359.2960,0.5814,22.5459,146.4124,20.9161 +200,64x32x8,8,131072,11010.0480,3145.7280,4718.5920,1.4327,18.2977,180.4052,25.7722 +200,64x32x16,8,262144,22020.0960,6291.4560,9437.1840,3.0435,17.2262,191.6265,27.3752 +200,64x32x32,8,524288,44040.1920,12582.9120,18874.3680,6.2562,16.7606,196.9494,28.1356 +200,64x32x64,8,1048576,88080.3840,25165.8240,37748.7360,12.8218,16.3562,201.8198,28.8314 +200,64x64x2,8,65536,5505.0240,1572.8640,2359.2960,0.5803,22.5887,146.1352,20.8765 +200,64x64x4,8,131072,11010.0480,3145.7280,4718.5920,1.4161,18.5111,178.3255,25.4751 +200,64x64x8,8,262144,22020.0960,6291.4560,9437.1840,3.0288,17.3098,190.7007,27.2430 +200,64x64x16,8,524288,44040.1920,12582.9120,18874.3680,6.2470,16.7853,196.6601,28.0943 +200,64x64x32,8,1048576,88080.3840,25165.8240,37748.7360,12.7711,16.4211,201.0219,28.7174 +200,64x64x64,8,2097152,176160.7680,50331.6480,75497.4720,25.5759,16.3994,201.2874,-62.1257 +200,4x4x2,16,512,59.3920,12.2880,34.8160,0.0056,18.4446,178.9684,11.9312 +200,4x4x4,16,1024,118.7840,24.5760,69.6320,0.0112,18.2150,181.2240,12.0816 +200,4x4x8,16,2048,237.5680,49.1520,139.2640,0.0224,18.3113,180.2714,12.0181 +200,4x4x16,16,4096,475.1360,98.3040,278.5280,0.0447,18.3455,179.9354,11.9957 +200,4x4x32,16,8192,950.2720,196.6080,557.0560,0.0905,18.1055,182.3198,12.1547 +200,4x4x64,16,16384,1900.5440,393.2160,1114.1120,0.1819,18.0138,183.2489,12.2166 +200,4x8x2,16,1024,118.7840,24.5760,69.6320,0.0111,18.4483,178.9328,11.9289 +200,4x8x4,16,2048,237.5680,49.1520,139.2640,0.0222,18.4121,179.2842,11.9523 +200,4x8x8,16,4096,475.1360,98.3040,278.5280,0.0452,18.1169,182.2060,12.1471 +200,4x8x16,16,8192,950.2720,196.6080,557.0560,0.0921,17.7870,185.5850,12.3723 +200,4x8x32,16,16384,1900.5440,393.2160,1114.1120,0.1818,18.0274,183.1101,12.2073 +200,4x8x64,16,32768,3801.0880,786.4320,2228.2240,0.3687,17.7742,185.7186,12.3812 +200,4x16x2,16,2048,237.5680,49.1520,139.2640,0.0224,18.3173,180.2120,12.0141 +200,4x16x4,16,4096,475.1360,98.3040,278.5280,0.0459,17.8317,185.1201,12.3413 +200,4x16x8,16,8192,950.2720,196.6080,557.0560,0.0907,18.0668,182.7105,12.1807 +200,4x16x16,16,16384,1900.5440,393.2160,1114.1120,0.1836,17.8502,184.9274,12.3285 +200,4x16x32,16,32768,3801.0880,786.4320,2228.2240,0.3632,18.0417,182.9653,12.1977 +200,4x16x64,16,65536,7602.1760,1572.8640,4456.4480,0.8405,15.5939,211.6859,14.1124 +200,4x32x2,16,4096,475.1360,98.3040,278.5280,0.0453,18.1000,182.3761,12.1584 +200,4x32x4,16,8192,950.2720,196.6080,557.0560,0.0906,18.0813,182.5645,12.1710 +200,4x32x8,16,16384,1900.5440,393.2160,1114.1120,0.1839,17.8212,185.2292,12.3486 +200,4x32x16,16,32768,3801.0880,786.4320,2228.2240,0.3639,18.0100,183.2872,12.2191 +200,4x32x32,16,65536,7602.1760,1572.8640,4456.4480,0.8393,15.6170,211.3718,14.0915 +200,4x32x64,16,131072,15204.3520,3145.7280,8912.8960,1.7298,15.1546,217.8222,14.5215 +200,4x64x2,16,8192,950.2720,196.6080,557.0560,0.0914,17.9284,184.1209,12.2747 +200,4x64x4,16,16384,1900.5440,393.2160,1114.1120,0.1847,17.7401,186.0756,12.4050 +200,4x64x8,16,32768,3801.0880,786.4320,2228.2240,0.3655,17.9308,184.0962,12.2731 +200,4x64x16,16,65536,7602.1760,1572.8640,4456.4480,0.8365,15.6689,210.6717,14.0448 +200,4x64x32,16,131072,15204.3520,3145.7280,8912.8960,1.7282,15.1685,217.6226,14.5082 +200,4x64x64,16,262144,30408.7040,6291.4560,17825.7920,3.4849,15.0444,219.4168,14.6278 +200,8x4x2,16,1024,118.7840,24.5760,69.6320,0.0111,18.4278,179.1319,11.9421 +200,8x4x4,16,2048,237.5680,49.1520,139.2640,0.0226,18.1638,181.7354,12.1157 +200,8x4x8,16,4096,475.1360,98.3040,278.5280,0.0453,18.0726,182.6524,12.1768 +200,8x4x16,16,8192,950.2720,196.6080,557.0560,0.0920,17.8152,185.2914,12.3528 +200,8x4x32,16,16384,1900.5440,393.2160,1114.1120,0.1823,17.9748,183.6461,12.2431 +200,8x4x64,16,32768,3801.0880,786.4320,2228.2240,0.3658,17.9157,184.2522,12.2835 +200,8x8x2,16,2048,237.5680,49.1520,139.2640,0.0222,18.4192,179.2152,11.9477 +200,8x8x4,16,4096,475.1360,98.3040,278.5280,0.0444,18.4360,179.0522,11.9368 +200,8x8x8,16,8192,950.2720,196.6080,557.0560,0.0916,17.8863,184.5548,12.3037 +200,8x8x16,16,16384,1900.5440,393.2160,1114.1120,0.1839,17.8220,185.2203,12.3480 +200,8x8x32,16,32768,3801.0880,786.4320,2228.2240,0.3664,17.8863,184.5542,12.3036 +200,8x8x64,16,65536,7602.1760,1572.8640,4456.4480,0.8380,15.6408,211.0501,14.0700 +200,8x16x2,16,4096,475.1360,98.3040,278.5280,0.0453,18.0660,182.7192,12.1813 +200,8x16x4,16,8192,950.2720,196.6080,557.0560,0.0919,17.8192,185.2493,12.3500 +200,8x16x8,16,16384,1900.5440,393.2160,1114.1120,0.1840,17.8059,185.3877,12.3592 +200,8x16x16,16,32768,3801.0880,786.4320,2228.2240,0.3670,17.8573,184.8539,12.3236 +200,8x16x32,16,65536,7602.1760,1572.8640,4456.4480,0.8359,15.6812,210.5074,14.0338 +200,8x16x64,16,131072,15204.3520,3145.7280,8912.8960,1.7319,15.1360,218.0891,14.5393 +200,8x32x2,16,8192,950.2720,196.6080,557.0560,0.0904,18.1311,182.0625,12.1375 +200,8x32x4,16,16384,1900.5440,393.2160,1114.1120,0.1824,17.9638,183.7583,12.2506 +200,8x32x8,16,32768,3801.0880,786.4320,2228.2240,0.3648,17.9625,183.7718,12.2515 +200,8x32x16,16,65536,7602.1760,1572.8640,4456.4480,0.8361,15.6759,210.5784,14.0386 +200,8x32x32,16,131072,15204.3520,3145.7280,8912.8960,1.7322,15.1336,218.1245,14.5416 +200,8x32x64,16,262144,30408.7040,6291.4560,17825.7920,3.4793,15.0688,219.0625,14.6042 +200,8x64x2,16,16384,1900.5440,393.2160,1114.1120,0.1843,17.7795,185.6637,12.3776 +200,8x64x4,16,32768,3801.0880,786.4320,2228.2240,0.3625,18.0764,182.6137,12.1742 +200,8x64x8,16,65536,7602.1760,1572.8640,4456.4480,0.8262,15.8645,208.0749,13.8717 +200,8x64x16,16,131072,15204.3520,3145.7280,8912.8960,1.7275,15.1748,217.5316,14.5021 +200,8x64x32,16,262144,30408.7040,6291.4560,17825.7920,3.4846,15.0457,219.3977,14.6265 +200,8x64x64,16,524288,60817.4080,12582.9120,35651.5840,7.0206,14.9356,221.0153,14.7344 +200,16x4x2,16,2048,237.5680,49.1520,139.2640,0.0226,18.1117,182.2579,12.1505 +200,16x4x4,16,4096,475.1360,98.3040,278.5280,0.0449,18.2408,180.9682,12.0645 +200,16x4x8,16,8192,950.2720,196.6080,557.0560,0.0919,17.8350,185.0856,12.3390 +200,16x4x16,16,16384,1900.5440,393.2160,1114.1120,0.1816,18.0462,182.9196,12.1946 +200,16x4x32,16,32768,3801.0880,786.4320,2228.2240,0.3678,17.8165,185.2778,12.3519 +200,16x4x64,16,65536,7602.1760,1572.8640,4456.4480,0.8404,15.5960,211.6567,14.1104 +200,16x8x2,16,4096,475.1360,98.3040,278.5280,0.0450,18.2228,181.1466,12.0764 +200,16x8x4,16,8192,950.2720,196.6080,557.0560,0.0908,18.0431,182.9508,12.1967 +200,16x8x8,16,16384,1900.5440,393.2160,1114.1120,0.1820,18.0031,183.3572,12.2238 +200,16x8x16,16,32768,3801.0880,786.4320,2228.2240,0.3693,17.7458,186.0162,12.4011 +200,16x8x32,16,65536,7602.1760,1572.8640,4456.4480,0.8347,15.7034,210.2096,14.0140 +200,16x8x64,16,131072,15204.3520,3145.7280,8912.8960,1.7291,15.1608,217.7328,14.5155 +200,16x16x2,16,8192,950.2720,196.6080,557.0560,0.0909,18.0184,183.2018,12.2135 +200,16x16x4,16,16384,1900.5440,393.2160,1114.1120,0.1824,17.9630,183.7665,12.2511 +200,16x16x8,16,32768,3801.0880,786.4320,2228.2240,0.3699,17.7162,186.3271,12.4218 +200,16x16x16,16,65536,7602.1760,1572.8640,4456.4480,0.8338,15.7207,209.9783,13.9986 +200,16x16x32,16,131072,15204.3520,3145.7280,8912.8960,1.7287,15.1644,217.6807,14.5120 +200,16x16x64,16,262144,30408.7040,6291.4560,17825.7920,3.4878,15.0321,219.5966,14.6398 +200,16x32x2,16,16384,1900.5440,393.2160,1114.1120,0.1840,17.8096,185.3495,12.3566 +200,16x32x4,16,32768,3801.0880,786.4320,2228.2240,0.3640,18.0034,183.3538,12.2236 +200,16x32x8,16,65536,7602.1760,1572.8640,4456.4480,0.8352,15.6942,210.3329,14.0222 +200,16x32x16,16,131072,15204.3520,3145.7280,8912.8960,1.7275,15.1744,217.5369,14.5025 +200,16x32x32,16,262144,30408.7040,6291.4560,17825.7920,3.4834,15.0510,219.3216,14.6214 +200,16x32x64,16,524288,60817.4080,12582.9120,35651.5840,7.0276,14.9209,221.2334,14.7489 +200,16x64x2,16,32768,3801.0880,786.4320,2228.2240,0.3636,18.0229,183.1558,12.2104 +200,16x64x4,16,65536,7602.1760,1572.8640,4456.4480,0.8278,15.8337,208.4795,13.8986 +200,16x64x8,16,131072,15204.3520,3145.7280,8912.8960,1.7258,15.1897,217.3186,14.4879 +200,16x64x16,16,262144,30408.7040,6291.4560,17825.7920,3.4981,14.9878,220.2464,14.6831 +200,16x64x32,16,524288,60817.4080,12582.9120,35651.5840,7.0395,14.8955,221.6102,14.7740 +200,16x64x64,16,1048576,121634.8160,25165.8240,71303.1680,14.1277,14.8442,222.3762,-40.5796 +200,32x4x2,16,4096,475.1360,98.3040,278.5280,0.0454,18.0286,183.0981,12.2065 +200,32x4x4,16,8192,950.2720,196.6080,557.0560,0.0921,17.7984,185.4660,12.3644 +200,32x4x8,16,16384,1900.5440,393.2160,1114.1120,0.1820,18.0071,183.3167,12.2211 +200,32x4x16,16,32768,3801.0880,786.4320,2228.2240,0.3688,17.7722,185.7397,12.3826 +200,32x4x32,16,65536,7602.1760,1572.8640,4456.4480,0.8394,15.6154,211.3937,14.0929 +200,32x4x64,16,131072,15204.3520,3145.7280,8912.8960,1.7272,15.1777,217.4896,14.4993 +200,32x8x2,16,8192,950.2720,196.6080,557.0560,0.0922,17.7751,185.7089,12.3806 +200,32x8x4,16,16384,1900.5440,393.2160,1114.1120,0.1847,17.7401,186.0755,12.4050 +200,32x8x8,16,32768,3801.0880,786.4320,2228.2240,0.3650,17.9548,183.8507,12.2567 +200,32x8x16,16,65536,7602.1760,1572.8640,4456.4480,0.8342,15.7128,210.0837,14.0056 +200,32x8x32,16,131072,15204.3520,3145.7280,8912.8960,1.7343,15.1151,218.3913,14.5594 +200,32x8x64,16,262144,30408.7040,6291.4560,17825.7920,3.4881,15.0309,219.6142,14.6409 +200,32x16x2,16,16384,1900.5440,393.2160,1114.1120,0.1842,17.7899,185.5548,12.3703 +200,32x16x4,16,32768,3801.0880,786.4320,2228.2240,0.3635,18.0279,183.1051,12.2070 +200,32x16x8,16,65536,7602.1760,1572.8640,4456.4480,0.8402,15.5994,211.6101,14.1073 +200,32x16x16,16,131072,15204.3520,3145.7280,8912.8960,1.7321,15.1345,218.1105,14.5407 +200,32x16x32,16,262144,30408.7040,6291.4560,17825.7920,3.4956,14.9983,220.0914,14.6728 +200,32x16x64,16,524288,60817.4080,12582.9120,35651.5840,7.0035,14.9722,220.4748,14.6983 +200,32x32x2,16,32768,3801.0880,786.4320,2228.2240,0.3676,17.8286,185.1519,12.3435 +200,32x32x4,16,65536,7602.1760,1572.8640,4456.4480,0.8358,15.6819,210.4980,14.0332 +200,32x32x8,16,131072,15204.3520,3145.7280,8912.8960,1.7292,15.1599,217.7456,14.5164 +200,32x32x16,16,262144,30408.7040,6291.4560,17825.7920,3.4836,15.0501,219.3342,14.6223 +200,32x32x32,16,524288,60817.4080,12582.9120,35651.5840,7.0147,14.9483,220.8277,14.7218 +200,32x32x64,16,1048576,121634.8160,25165.8240,71303.1680,14.1095,14.8634,222.0885,-40.5271 +200,32x64x2,16,65536,7602.1760,1572.8640,4456.4480,0.8323,15.7487,209.6045,13.9736 +200,32x64x4,16,131072,15204.3520,3145.7280,8912.8960,1.7337,15.1204,218.3147,14.5543 +200,32x64x8,16,262144,30408.7040,6291.4560,17825.7920,3.4854,15.0424,219.4469,14.6298 +200,32x64x16,16,524288,60817.4080,12582.9120,35651.5840,6.9997,14.9803,220.3564,14.6904 +200,32x64x32,16,1048576,121634.8160,25165.8240,71303.1680,14.1000,14.8734,221.9396,-40.4999 +200,32x64x64,16,2097152,243269.6320,50331.6480,142606.3360,28.5006,14.7165,224.3054,47.1230 +200,64x4x2,16,8192,950.2720,196.6080,557.0560,0.0928,17.6461,187.0664,12.4711 +200,64x4x4,16,16384,1900.5440,393.2160,1114.1120,0.1819,18.0106,183.2808,12.2187 +200,64x4x8,16,32768,3801.0880,786.4320,2228.2240,0.3692,17.7502,185.9693,12.3980 +200,64x4x16,16,65536,7602.1760,1572.8640,4456.4480,0.8337,15.7213,209.9699,13.9980 +200,64x4x32,16,131072,15204.3520,3145.7280,8912.8960,1.7324,15.1317,218.1512,14.5434 +200,64x4x64,16,262144,30408.7040,6291.4560,17825.7920,3.4837,15.0497,219.3394,14.6226 +200,64x8x2,16,16384,1900.5440,393.2160,1114.1120,0.1839,17.8183,185.2592,12.3506 +200,64x8x4,16,32768,3801.0880,786.4320,2228.2240,0.3694,17.7413,186.0627,12.4042 +200,64x8x8,16,65536,7602.1760,1572.8640,4456.4480,0.8317,15.7603,209.4500,13.9633 +200,64x8x16,16,131072,15204.3520,3145.7280,8912.8960,1.7289,15.1629,217.7025,14.5135 +200,64x8x32,16,262144,30408.7040,6291.4560,17825.7920,3.4803,15.0645,219.1241,14.6083 +200,64x8x64,16,524288,60817.4080,12582.9120,35651.5840,7.0112,14.9557,220.7180,14.7145 +200,64x16x2,16,32768,3801.0880,786.4320,2228.2240,0.3702,17.7021,186.4753,12.4317 +200,64x16x4,16,65536,7602.1760,1572.8640,4456.4480,0.8310,15.7727,209.2857,13.9524 +200,64x16x8,16,131072,15204.3520,3145.7280,8912.8960,1.7311,15.1428,217.9918,14.5328 +200,64x16x16,16,262144,30408.7040,6291.4560,17825.7920,3.4783,15.0730,219.0016,14.6001 +200,64x16x32,16,524288,60817.4080,12582.9120,35651.5840,7.1692,14.6261,225.6924,15.0462 +200,64x16x64,16,1048576,121634.8160,25165.8240,71303.1680,14.0752,14.8996,221.5499,-40.4288 +200,64x32x2,16,65536,7602.1760,1572.8640,4456.4480,0.8301,15.7907,209.0467,13.9364 +200,64x32x4,16,131072,15204.3520,3145.7280,8912.8960,1.7349,15.1099,218.4658,14.5644 +200,64x32x8,16,262144,30408.7040,6291.4560,17825.7920,3.4954,14.9994,220.0760,14.6717 +200,64x32x16,16,524288,60817.4080,12582.9120,35651.5840,7.0085,14.9614,220.6340,14.7089 +200,64x32x32,16,1048576,121634.8160,25165.8240,71303.1680,14.0931,14.8807,221.8305,-40.4800 +200,64x32x64,16,2097152,243269.6320,50331.6480,142606.3360,28.3617,14.7886,223.2118,46.8932 +200,64x64x2,16,131072,15204.3520,3145.7280,8912.8960,1.7273,15.1768,217.5037,14.5002 +200,64x64x4,16,262144,30408.7040,6291.4560,17825.7920,3.4938,15.0061,219.9772,14.6651 +200,64x64x8,16,524288,60817.4080,12582.9120,35651.5840,7.0357,14.9037,221.4885,14.7659 +200,64x64x16,16,1048576,121634.8160,25165.8240,71303.1680,14.1410,14.8303,222.5848,-40.6177 +200,64x64x32,16,2097152,243269.6320,50331.6480,142606.3360,28.4706,14.7320,224.0696,47.0734 +200,64x64x64,16,4194304,486539.2640,100663.2960,285212.6720,56.5696,14.8288,222.6070,-618.3528 +200,4x4x2,32,1024,184.3200,24.5760,135.1680,0.0184,11.1141,297.0107,9.5810 +200,4x4x4,32,2048,368.6400,49.1520,270.3360,0.0363,11.2779,292.6971,9.4418 +200,4x4x8,32,4096,737.2800,98.3040,540.6720,0.0742,11.0449,298.8711,9.6410 +200,4x4x16,32,8192,1474.5600,196.6080,1081.3440,0.1481,11.0605,298.4503,9.6274 +200,4x4x32,32,16384,2949.1200,393.2160,2162.6880,0.2949,11.1106,297.1028,9.5840 +200,4x4x64,32,32768,5898.2400,786.4320,4325.3760,0.5983,10.9532,301.3734,9.7217 +200,4x8x2,32,2048,368.6400,49.1520,270.3360,0.0368,11.1204,296.8413,9.5755 +200,4x8x4,32,4096,737.2800,98.3040,540.6720,0.0742,11.0352,299.1326,9.6494 +200,4x8x8,32,8192,1474.5600,196.6080,1081.3440,0.1483,11.0465,298.8270,9.6396 +200,4x8x16,32,16384,2949.1200,393.2160,2162.6880,0.2961,11.0655,298.3154,9.6231 +200,4x8x32,32,32768,5898.2400,786.4320,4325.3760,0.5986,10.9475,301.5306,9.7268 +200,4x8x64,32,65536,11796.4800,1572.8640,8650.7520,1.2720,10.3045,320.3467,10.3338 +200,4x16x2,32,4096,737.2800,98.3040,540.6720,0.0743,11.0186,299.5856,9.6641 +200,4x16x4,32,8192,1474.5600,196.6080,1081.3440,0.1484,11.0422,298.9442,9.6434 +200,4x16x8,32,16384,2949.1200,393.2160,2162.6880,0.2966,11.0488,298.7648,9.6376 +200,4x16x16,32,32768,5898.2400,786.4320,4325.3760,0.5989,10.9436,301.6379,9.7303 +200,4x16x32,32,65536,11796.4800,1572.8640,8650.7520,1.2770,10.2640,321.6110,10.3745 +200,4x16x64,32,131072,23592.9600,3145.7280,17301.5040,2.6173,10.0157,329.5828,10.6317 +200,4x32x2,32,8192,1474.5600,196.6080,1081.3440,0.1488,11.0087,299.8546,9.6727 +200,4x32x4,32,16384,2949.1200,393.2160,2162.6880,0.2971,11.0310,299.2466,9.6531 +200,4x32x8,32,32768,5898.2400,786.4320,4325.3760,0.5925,11.0611,298.4334,9.6269 +200,4x32x16,32,65536,11796.4800,1572.8640,8650.7520,1.2776,10.2593,321.7576,10.3793 +200,4x32x32,32,131072,23592.9600,3145.7280,17301.5040,2.6138,10.0294,329.1324,10.6172 +200,4x32x64,32,262144,47185.9200,6291.4560,34603.0080,5.2766,9.9362,332.2209,10.7168 +200,4x64x2,32,16384,2949.1200,393.2160,2162.6880,0.2965,11.0517,298.6869,9.6351 +200,4x64x4,32,32768,5898.2400,786.4320,4325.3760,0.5938,11.0371,299.0820,9.6478 +200,4x64x8,32,65536,11796.4800,1572.8640,8650.7520,1.2778,10.2578,321.8033,10.3808 +200,4x64x16,32,131072,23592.9600,3145.7280,17301.5040,2.6155,10.0229,329.3472,10.6241 +200,4x64x32,32,262144,47185.9200,6291.4560,34603.0080,5.2779,9.9336,332.3065,10.7196 +200,4x64x64,32,524288,94371.8400,12582.9120,69206.0160,10.6334,9.8612,334.7478,-33.6092 +200,8x4x2,32,2048,368.6400,49.1520,270.3360,0.0367,11.1554,295.9115,9.5455 +200,8x4x4,32,4096,737.2800,98.3040,540.6720,0.0740,11.0655,298.3153,9.6231 +200,8x4x8,32,8192,1474.5600,196.6080,1081.3440,0.1486,11.0227,299.4742,9.6605 +200,8x4x16,32,16384,2949.1200,393.2160,2162.6880,0.2971,11.0293,299.2935,9.6546 +200,8x4x32,32,32768,5898.2400,786.4320,4325.3760,0.6002,10.9192,302.3105,9.7520 +200,8x4x64,32,65536,11796.4800,1572.8640,8650.7520,1.2766,10.2675,321.4994,10.3709 +200,8x8x2,32,4096,737.2800,98.3040,540.6720,0.0741,11.0621,298.4065,9.6260 +200,8x8x4,32,8192,1474.5600,196.6080,1081.3440,0.1473,11.1195,296.8666,9.5763 +200,8x8x8,32,16384,2949.1200,393.2160,2162.6880,0.2977,11.0065,299.9133,9.6746 +200,8x8x16,32,32768,5898.2400,786.4320,4325.3760,0.5911,11.0872,297.7294,9.6042 +200,8x8x32,32,65536,11796.4800,1572.8640,8650.7520,1.2751,10.2790,321.1408,10.3594 +200,8x8x64,32,131072,23592.9600,3145.7280,17301.5040,2.6235,9.9923,330.3550,10.6566 +200,8x16x2,32,8192,1474.5600,196.6080,1081.3440,0.1479,11.0789,297.9548,9.6114 +200,8x16x4,32,16384,2949.1200,393.2160,2162.6880,0.2968,11.0408,298.9830,9.6446 +200,8x16x8,32,32768,5898.2400,786.4320,4325.3760,0.5965,10.9874,300.4339,9.6914 +200,8x16x16,32,65536,11796.4800,1572.8640,8650.7520,1.2750,10.2803,321.0997,10.3581 +200,8x16x32,32,131072,23592.9600,3145.7280,17301.5040,2.6219,9.9984,330.1535,10.6501 +200,8x16x64,32,262144,47185.9200,6291.4560,34603.0080,5.2861,9.9183,332.8200,10.7361 +200,8x32x2,32,16384,2949.1200,393.2160,2162.6880,0.2988,10.9680,300.9674,9.7086 +200,8x32x4,32,32768,5898.2400,786.4320,4325.3760,0.6009,10.9058,302.6840,9.7640 +200,8x32x8,32,65536,11796.4800,1572.8640,8650.7520,1.2771,10.2631,321.6368,10.3754 +200,8x32x16,32,131072,23592.9600,3145.7280,17301.5040,2.6137,10.0297,329.1236,10.6169 +200,8x32x32,32,262144,47185.9200,6291.4560,34603.0080,5.2858,9.9188,332.8016,10.7355 +200,8x32x64,32,524288,94371.8400,12582.9120,69206.0160,10.6487,9.8470,335.2298,-33.6576 +200,8x64x2,32,32768,5898.2400,786.4320,4325.3760,0.5968,10.9820,300.5841,9.6963 +200,8x64x4,32,65536,11796.4800,1572.8640,8650.7520,1.2759,10.2733,321.3197,10.3652 +200,8x64x8,32,131072,23592.9600,3145.7280,17301.5040,2.6176,10.0147,329.6169,10.6328 +200,8x64x16,32,262144,47185.9200,6291.4560,34603.0080,5.2745,9.9401,332.0889,10.7125 +200,8x64x32,32,524288,94371.8400,12582.9120,69206.0160,10.6213,9.8724,334.3654,-33.5708 +200,8x64x64,32,1048576,188743.6800,25165.8240,138412.0320,21.3695,9.8138,336.3646,-33.7715 +200,16x4x2,32,4096,737.2800,98.3040,540.6720,0.0735,11.1455,296.1731,9.5540 +200,16x4x4,32,8192,1474.5600,196.6080,1081.3440,0.1485,11.0346,299.1487,9.6500 +200,16x4x8,32,16384,2949.1200,393.2160,2162.6880,0.2974,11.0192,299.5679,9.6635 +200,16x4x16,32,32768,5898.2400,786.4320,4325.3760,0.5902,11.1047,297.2608,9.5891 +200,16x4x32,32,65536,11796.4800,1572.8640,8650.7520,1.2747,10.2823,321.0372,10.3560 +200,16x4x64,32,131072,23592.9600,3145.7280,17301.5040,2.6211,10.0014,330.0542,10.6469 +200,16x8x2,32,8192,1474.5600,196.6080,1081.3440,0.1464,11.1916,294.9529,9.5146 +200,16x8x4,32,16384,2949.1200,393.2160,2162.6880,0.2968,11.0406,298.9861,9.6447 +200,16x8x8,32,32768,5898.2400,786.4320,4325.3760,0.5997,10.9280,302.0694,9.7442 +200,16x8x16,32,65536,11796.4800,1572.8640,8650.7520,1.2737,10.2908,320.7705,10.3474 +200,16x8x32,32,131072,23592.9600,3145.7280,17301.5040,2.6176,10.0146,329.6179,10.6328 +200,16x8x64,32,262144,47185.9200,6291.4560,34603.0080,5.2740,9.9410,332.0605,10.7116 +200,16x16x2,32,16384,2949.1200,393.2160,2162.6880,0.2980,10.9960,300.1990,9.6838 +200,16x16x4,32,32768,5898.2400,786.4320,4325.3760,0.5998,10.9255,302.1364,9.7463 +200,16x16x8,32,65536,11796.4800,1572.8640,8650.7520,1.2795,10.2436,322.2487,10.3951 +200,16x16x16,32,131072,23592.9600,3145.7280,17301.5040,2.6165,10.0187,329.4831,10.6285 +200,16x16x32,32,262144,47185.9200,6291.4560,34603.0080,5.2867,9.9172,332.8567,10.7373 +200,16x16x64,32,524288,94371.8400,12582.9120,69206.0160,10.6383,9.8566,334.9024,-33.6247 +200,16x32x2,32,32768,5898.2400,786.4320,4325.3760,0.5986,10.9484,301.5060,9.7260 +200,16x32x4,32,65536,11796.4800,1572.8640,8650.7520,1.2760,10.2722,321.3535,10.3662 +200,16x32x8,32,131072,23592.9600,3145.7280,17301.5040,2.6148,10.0254,329.2634,10.6214 +200,16x32x16,32,262144,47185.9200,6291.4560,34603.0080,5.2901,9.9108,333.0721,10.7443 +200,16x32x32,32,524288,94371.8400,12582.9120,69206.0160,10.6227,9.8711,334.4096,-33.5753 +200,16x32x64,32,1048576,188743.6800,25165.8240,138412.0320,21.3623,9.8171,336.2509,-33.7601 +200,16x64x2,32,65536,11796.4800,1572.8640,8650.7520,1.2790,10.2483,322.1007,10.3903 +200,16x64x4,32,131072,23592.9600,3145.7280,17301.5040,2.6180,10.0131,329.6669,10.6344 +200,16x64x8,32,262144,47185.9200,6291.4560,34603.0080,5.2855,9.9195,332.7805,10.7349 +200,16x64x16,32,524288,94371.8400,12582.9120,69206.0160,10.6399,9.8552,334.9509,-33.6296 +200,16x64x32,32,1048576,188743.6800,25165.8240,138412.0320,21.3698,9.8136,336.3697,-33.7721 +200,16x64x64,32,2097152,377487.3600,50331.6480,276824.0640,43.1537,9.7195,339.6280,1212.9573 +200,32x4x2,32,8192,1474.5600,196.6080,1081.3440,0.1487,11.0146,299.6924,9.6675 +200,32x4x4,32,16384,2949.1200,393.2160,2162.6880,0.2971,11.0283,299.3212,9.6555 +200,32x4x8,32,32768,5898.2400,786.4320,4325.3760,0.6031,10.8658,303.7984,9.7999 +200,32x4x16,32,65536,11796.4800,1572.8640,8650.7520,1.2738,10.2897,320.8047,10.3485 +200,32x4x32,32,131072,23592.9600,3145.7280,17301.5040,2.6164,10.0192,329.4670,10.6280 +200,32x4x64,32,262144,47185.9200,6291.4560,34603.0080,5.2957,9.9002,333.4274,10.7557 +200,32x8x2,32,16384,2949.1200,393.2160,2162.6880,0.2961,11.0654,298.3166,9.6231 +200,32x8x4,32,32768,5898.2400,786.4320,4325.3760,0.5972,10.9736,300.8139,9.7037 +200,32x8x8,32,65536,11796.4800,1572.8640,8650.7520,1.2758,10.2741,321.2934,10.3643 +200,32x8x16,32,131072,23592.9600,3145.7280,17301.5040,2.6237,9.9914,330.3840,10.6575 +200,32x8x32,32,262144,47185.9200,6291.4560,34603.0080,5.2833,9.9235,332.6437,10.7304 +200,32x8x64,32,524288,94371.8400,12582.9120,69206.0160,10.6768,9.8211,336.1128,-33.7463 +200,32x16x2,32,32768,5898.2400,786.4320,4325.3760,0.6002,10.9182,302.3380,9.7528 +200,32x16x4,32,65536,11796.4800,1572.8640,8650.7520,1.2746,10.2830,321.0152,10.3553 +200,32x16x8,32,131072,23592.9600,3145.7280,17301.5040,2.6157,10.0219,329.3779,10.6251 +200,32x16x16,32,262144,47185.9200,6291.4560,34603.0080,5.2852,9.9200,332.7618,10.7343 +200,32x16x32,32,524288,94371.8400,12582.9120,69206.0160,10.6337,9.8609,334.7568,-33.6101 +200,32x16x64,32,1048576,188743.6800,25165.8240,138412.0320,21.3454,9.8248,335.9852,-33.7335 +200,32x32x2,32,65536,11796.4800,1572.8640,8650.7520,1.2752,10.2788,321.1461,10.3596 +200,32x32x4,32,131072,23592.9600,3145.7280,17301.5040,2.6087,10.0488,328.4974,10.5967 +200,32x32x8,32,262144,47185.9200,6291.4560,34603.0080,5.2916,9.9080,333.1646,10.7472 +200,32x32x16,32,524288,94371.8400,12582.9120,69206.0160,10.6600,9.8365,335.5854,-33.6933 +200,32x32x32,32,1048576,188743.6800,25165.8240,138412.0320,21.2981,9.8467,335.2408,-33.6587 +200,32x32x64,32,2097152,377487.3600,50331.6480,276824.0640,44.2297,9.4830,348.0965,1243.2018 +200,32x64x2,32,131072,23592.9600,3145.7280,17301.5040,2.6099,10.0444,328.6422,10.6014 +200,32x64x4,32,262144,47185.9200,6291.4560,34603.0080,5.2859,9.9185,332.8113,10.7358 +200,32x64x8,32,524288,94371.8400,12582.9120,69206.0160,10.6227,9.8711,334.4097,-33.5753 +200,32x64x16,32,1048576,188743.6800,25165.8240,138412.0320,21.3381,9.8282,335.8697,-33.7219 +200,32x64x32,32,2097152,377487.3600,50331.6480,276824.0640,43.4748,9.6477,342.1553,1221.9831 +200,32x64x64,32,4194304,754974.7200,100663.2960,553648.1280,85.5724,9.8029,336.7359,1202.6281 +200,64x4x2,32,16384,2949.1200,393.2160,2162.6880,0.2976,11.0103,299.8114,9.6713 +200,64x4x4,32,32768,5898.2400,786.4320,4325.3760,0.5956,11.0036,299.9923,9.6772 +200,64x4x8,32,65536,11796.4800,1572.8640,8650.7520,1.2751,10.2796,321.1224,10.3588 +200,64x4x16,32,131072,23592.9600,3145.7280,17301.5040,2.6173,10.0158,329.5782,10.6316 +200,64x4x32,32,262144,47185.9200,6291.4560,34603.0080,5.2761,9.9371,332.1908,10.7158 +200,64x4x64,32,524288,94371.8400,12582.9120,69206.0160,10.6702,9.8271,335.9071,-33.7256 +200,64x8x2,32,32768,5898.2400,786.4320,4325.3760,0.5979,10.9603,301.1766,9.7154 +200,64x8x4,32,65536,11796.4800,1572.8640,8650.7520,1.2730,10.2965,320.5931,10.3417 +200,64x8x8,32,131072,23592.9600,3145.7280,17301.5040,2.6162,10.0199,329.4430,10.6272 +200,64x8x16,32,262144,47185.9200,6291.4560,34603.0080,5.2847,9.9208,332.7343,10.7334 +200,64x8x32,32,524288,94371.8400,12582.9120,69206.0160,10.6461,9.8494,335.1478,-33.6494 +200,64x8x64,32,1048576,188743.6800,25165.8240,138412.0320,21.2812,9.8545,334.9748,-33.6320 +200,64x16x2,32,65536,11796.4800,1572.8640,8650.7520,1.2672,10.3434,319.1396,10.2948 +200,64x16x4,32,131072,23592.9600,3145.7280,17301.5040,2.6178,10.0139,329.6408,10.6336 +200,64x16x8,32,262144,47185.9200,6291.4560,34603.0080,5.2912,9.9087,333.1431,10.7466 +200,64x16x16,32,524288,94371.8400,12582.9120,69206.0160,10.6585,9.8379,335.5386,-33.6886 +200,64x16x32,32,1048576,188743.6800,25165.8240,138412.0320,21.3308,9.8316,335.7558,-33.7104 +200,64x16x64,32,2097152,377487.3600,50331.6480,276824.0640,42.6895,9.8252,335.9745,1199.9088 +200,64x32x2,32,131072,23592.9600,3145.7280,17301.5040,2.6194,10.0078,329.8425,10.6401 +200,64x32x4,32,262144,47185.9200,6291.4560,34603.0080,5.2909,9.9093,333.1209,10.7458 +200,64x32x8,32,524288,94371.8400,12582.9120,69206.0160,10.6534,9.8426,335.3774,-33.6724 +200,64x32x16,32,1048576,188743.6800,25165.8240,138412.0320,21.3611,9.8176,336.2327,-33.7583 +200,64x32x32,32,2097152,377487.3600,50331.6480,276824.0640,43.1672,9.7164,339.7341,1213.3361 +200,64x32x64,32,4194304,754974.7200,100663.2960,553648.1280,86.3298,9.7169,339.7161,1213.2719 +200,64x64x2,32,262144,47185.9200,6291.4560,34603.0080,5.2673,9.9537,331.6370,10.6980 +200,64x64x4,32,524288,94371.8400,12582.9120,69206.0160,10.6459,9.8496,335.1422,-33.6488 +200,64x64x8,32,1048576,188743.6800,25165.8240,138412.0320,21.2973,9.8471,335.2271,-33.6573 +200,64x64x16,32,2097152,377487.3600,50331.6480,276824.0640,42.8531,9.7876,337.2623,1204.5083 +200,64x64x32,32,4194304,754974.7200,100663.2960,553648.1280,85.7954,9.7775,337.6135,1205.7624 +200,64x64x64,32,8388608,1509949.4400,201326.5920,1107296.2560,175.9705,9.5341,346.2307,1236.5383 diff --git a/scripts/results_soa_skylakesp2.txt b/scripts/results_soa_skylakesp2.txt new file mode 100644 index 0000000..98c4350 --- /dev/null +++ b/scripts/results_soa_skylakesp2.txt @@ -0,0 +1,450 @@ +200,4x4x2,8,256,21.5040,6.1440,9.2160,0.0016,31.1175,106.0818,15.1545 +200,4x4x4,8,512,43.0080,12.2880,18.4320,0.0035,29.3957,112.2953,16.0422 +200,4x4x8,8,1024,86.0160,24.5760,36.8640,0.0070,29.1148,113.3787,16.1970 +200,4x4x16,8,2048,172.0320,49.1520,73.7280,0.0143,28.6699,115.1380,16.4483 +200,4x4x32,8,4096,344.0640,98.3040,147.4560,0.0279,29.3329,112.5357,16.0765 +200,4x4x64,8,8192,688.1280,196.6080,294.9120,0.0589,27.8187,118.6611,16.9516 +200,4x8x2,8,512,43.0080,12.2880,18.4320,0.0034,30.1387,109.5268,15.6467 +200,4x8x4,8,1024,86.0160,24.5760,36.8640,0.0070,29.1126,113.3874,16.1982 +200,4x8x8,8,2048,172.0320,49.1520,73.7280,0.0138,29.7694,110.8857,15.8408 +200,4x8x16,8,4096,344.0640,98.3040,147.4560,0.0283,28.9748,113.9266,16.2752 +200,4x8x32,8,8192,688.1280,196.6080,294.9120,0.0567,28.9172,114.1536,16.3077 +200,4x8x64,8,16384,1376.2560,393.2160,589.8240,0.1181,27.7523,118.9452,16.9922 +200,4x16x2,8,1024,86.0160,24.5760,36.8640,0.0070,29.3553,112.4497,16.0642 +200,4x16x4,8,2048,172.0320,49.1520,73.7280,0.0141,29.0617,113.5858,16.2265 +200,4x16x8,8,4096,344.0640,98.3040,147.4560,0.0283,28.9315,114.0972,16.2996 +200,4x16x16,8,8192,688.1280,196.6080,294.9120,0.0581,28.1803,117.1387,16.7341 +200,4x16x32,8,16384,1376.2560,393.2160,589.8240,0.1182,27.7240,119.0667,17.0095 +200,4x16x64,8,32768,2752.5120,786.4320,1179.6480,0.2292,28.5891,115.4635,16.4948 +200,4x32x2,8,2048,172.0320,49.1520,73.7280,0.0138,29.5889,111.5622,15.9375 +200,4x32x4,8,4096,344.0640,98.3040,147.4560,0.0277,29.6082,111.4894,15.9271 +200,4x32x8,8,8192,688.1280,196.6080,294.9120,0.0573,28.6036,115.4052,16.4865 +200,4x32x16,8,16384,1376.2560,393.2160,589.8240,0.1180,27.7805,118.8243,16.9749 +200,4x32x32,8,32768,2752.5120,786.4320,1179.6480,0.2315,28.3076,116.6117,16.6588 +200,4x32x64,8,65536,5505.0240,1572.8640,2359.2960,0.5896,22.2305,148.4894,21.2128 +200,4x64x2,8,4096,344.0640,98.3040,147.4560,0.0275,29.8382,110.6301,15.8043 +200,4x64x4,8,8192,688.1280,196.6080,294.9120,0.0590,27.7490,118.9591,16.9942 +200,4x64x8,8,16384,1376.2560,393.2160,589.8240,0.1172,27.9699,118.0198,16.8600 +200,4x64x16,8,32768,2752.5120,786.4320,1179.6480,0.2337,28.0471,117.6948,16.8135 +200,4x64x32,8,65536,5505.0240,1572.8640,2359.2960,0.5894,22.2368,148.4475,21.2068 +200,4x64x64,8,131072,11010.0480,3145.7280,4718.5920,1.4231,18.4202,179.2050,25.6007 +200,8x4x2,8,512,43.0080,12.2880,18.4320,0.0034,30.1707,109.4109,15.6301 +200,8x4x4,8,1024,86.0160,24.5760,36.8640,0.0070,29.1336,113.3055,16.1865 +200,8x4x8,8,2048,172.0320,49.1520,73.7280,0.0141,29.0357,113.6876,16.2411 +200,8x4x16,8,4096,344.0640,98.3040,147.4560,0.0283,28.9620,113.9771,16.2824 +200,8x4x32,8,8192,688.1280,196.6080,294.9120,0.0589,27.7938,118.7673,16.9668 +200,8x4x64,8,16384,1376.2560,393.2160,589.8240,0.1177,27.8454,118.5474,16.9353 +200,8x8x2,8,1024,86.0160,24.5760,36.8640,0.0071,28.7228,114.9259,16.4180 +200,8x8x4,8,2048,172.0320,49.1520,73.7280,0.0143,28.6016,115.4133,16.4876 +200,8x8x8,8,4096,344.0640,98.3040,147.4560,0.0277,29.5796,111.5972,15.9425 +200,8x8x16,8,8192,688.1280,196.6080,294.9120,0.0588,27.8794,118.4030,16.9147 +200,8x8x32,8,16384,1376.2560,393.2160,589.8240,0.1171,27.9865,117.9497,16.8500 +200,8x8x64,8,32768,2752.5120,786.4320,1179.6480,0.2282,28.7237,114.9226,16.4175 +200,8x16x2,8,2048,172.0320,49.1520,73.7280,0.0142,28.7967,114.6314,16.3759 +200,8x16x4,8,4096,344.0640,98.3040,147.4560,0.0283,28.9346,114.0847,16.2978 +200,8x16x8,8,8192,688.1280,196.6080,294.9120,0.0570,28.7606,114.7752,16.3965 +200,8x16x16,8,16384,1376.2560,393.2160,589.8240,0.1179,27.7814,118.8205,16.9744 +200,8x16x32,8,32768,2752.5120,786.4320,1179.6480,0.2265,28.9373,114.0741,16.2963 +200,8x16x64,8,65536,5505.0240,1572.8640,2359.2960,0.5811,22.5540,146.3601,20.9086 +200,8x32x2,8,4096,344.0640,98.3040,147.4560,0.0286,28.6660,115.1539,16.4506 +200,8x32x4,8,8192,688.1280,196.6080,294.9120,0.0586,27.9693,118.0222,16.8603 +200,8x32x8,8,16384,1376.2560,393.2160,589.8240,0.1156,28.3397,116.4796,16.6399 +200,8x32x16,8,32768,2752.5120,786.4320,1179.6480,0.2275,28.8080,114.5864,16.3695 +200,8x32x32,8,65536,5505.0240,1572.8640,2359.2960,0.5878,22.2982,148.0390,21.1484 +200,8x32x64,8,131072,11010.0480,3145.7280,4718.5920,1.4210,18.4483,178.9322,25.5617 +200,8x64x2,8,8192,688.1280,196.6080,294.9120,0.0587,27.9060,118.2900,16.8986 +200,8x64x4,8,16384,1376.2560,393.2160,589.8240,0.1172,27.9557,118.0798,16.8685 +200,8x64x8,8,32768,2752.5120,786.4320,1179.6480,0.2330,28.1226,117.3790,16.7684 +200,8x64x16,8,65536,5505.0240,1572.8640,2359.2960,0.5877,22.3042,147.9991,21.1427 +200,8x64x32,8,131072,11010.0480,3145.7280,4718.5920,1.4194,18.4681,178.7404,25.5343 +200,8x64x64,8,262144,22020.0960,6291.4560,9437.1840,3.0295,17.3061,190.7417,27.2488 +200,16x4x2,8,1024,86.0160,24.5760,36.8640,0.0072,28.5625,115.5712,16.5102 +200,16x4x4,8,2048,172.0320,49.1520,73.7280,0.0139,29.4813,111.9692,15.9956 +200,16x4x8,8,4096,344.0640,98.3040,147.4560,0.0281,29.1991,113.0515,16.1502 +200,16x4x16,8,8192,688.1280,196.6080,294.9120,0.0571,28.7037,115.0028,16.4290 +200,16x4x32,8,16384,1376.2560,393.2160,589.8240,0.1143,28.6746,115.1193,16.4456 +200,16x4x64,8,32768,2752.5120,786.4320,1179.6480,0.2279,28.7624,114.7679,16.3954 +200,16x8x2,8,2048,172.0320,49.1520,73.7280,0.0142,28.8441,114.4430,16.3490 +200,16x8x4,8,4096,344.0640,98.3040,147.4560,0.0284,28.8597,114.3809,16.3401 +200,16x8x8,8,8192,688.1280,196.6080,294.9120,0.0571,28.6922,115.0488,16.4355 +200,16x8x16,8,16384,1376.2560,393.2160,589.8240,0.1139,28.7644,114.7598,16.3943 +200,16x8x32,8,32768,2752.5120,786.4320,1179.6480,0.2279,28.7548,114.7984,16.3998 +200,16x8x64,8,65536,5505.0240,1572.8640,2359.2960,0.5880,22.2899,148.0941,21.1563 +200,16x16x2,8,4096,344.0640,98.3040,147.4560,0.0285,28.7502,114.8167,16.4024 +200,16x16x4,8,8192,688.1280,196.6080,294.9120,0.0571,28.7103,114.9760,16.4251 +200,16x16x8,8,16384,1376.2560,393.2160,589.8240,0.1174,27.9047,118.2953,16.8993 +200,16x16x16,8,32768,2752.5120,786.4320,1179.6480,0.2328,28.1544,117.2462,16.7495 +200,16x16x32,8,65536,5505.0240,1572.8640,2359.2960,0.5841,22.4409,147.0975,21.0139 +200,16x16x64,8,131072,11010.0480,3145.7280,4718.5920,1.4255,18.3902,179.4976,25.6425 +200,16x32x2,8,8192,688.1280,196.6080,294.9120,0.0588,27.8632,118.4715,16.9245 +200,16x32x4,8,16384,1376.2560,393.2160,589.8240,0.1147,28.5722,115.5317,16.5045 +200,16x32x8,8,32768,2752.5120,786.4320,1179.6480,0.2358,27.7892,118.7872,16.9696 +200,16x32x16,8,65536,5505.0240,1572.8640,2359.2960,0.5700,22.9961,143.5462,20.5066 +200,16x32x32,8,131072,11010.0480,3145.7280,4718.5920,1.4499,18.0804,182.5737,26.0820 +200,16x32x64,8,262144,22020.0960,6291.4560,9437.1840,3.0517,17.1800,192.1420,27.4489 +200,16x64x2,8,16384,1376.2560,393.2160,589.8240,0.1171,27.9769,117.9904,16.8558 +200,16x64x4,8,32768,2752.5120,786.4320,1179.6480,0.2327,28.1641,117.2060,16.7437 +200,16x64x8,8,65536,5505.0240,1572.8640,2359.2960,0.5765,22.7359,145.1890,20.7413 +200,16x64x16,8,131072,11010.0480,3145.7280,4718.5920,1.4113,18.5747,177.7145,25.3878 +200,16x64x32,8,262144,22020.0960,6291.4560,9437.1840,3.1046,16.8873,195.4718,27.9245 +200,16x64x64,8,524288,44040.1920,12582.9120,18874.3680,6.3321,16.5596,199.3400,28.4771 +200,32x4x2,8,2048,172.0320,49.1520,73.7280,0.0140,29.3028,112.6513,16.0930 +200,32x4x4,8,4096,344.0640,98.3040,147.4560,0.0279,29.4024,112.2697,16.0385 +200,32x4x8,8,8192,688.1280,196.6080,294.9120,0.0571,28.7071,114.9890,16.4270 +200,32x4x16,8,16384,1376.2560,393.2160,589.8240,0.1176,27.8618,118.4778,16.9254 +200,32x4x32,8,32768,2752.5120,786.4320,1179.6480,0.2354,27.8446,118.5509,16.9358 +200,32x4x64,8,65536,5505.0240,1572.8640,2359.2960,0.5903,22.2057,148.6558,21.2365 +200,32x8x2,8,4096,344.0640,98.3040,147.4560,0.0275,29.7629,110.9100,15.8443 +200,32x8x4,8,8192,688.1280,196.6080,294.9120,0.0588,27.8758,118.4181,16.9169 +200,32x8x8,8,16384,1376.2560,393.2160,589.8240,0.1173,27.9366,118.1605,16.8801 +200,32x8x16,8,32768,2752.5120,786.4320,1179.6480,0.2267,28.9068,114.1947,16.3135 +200,32x8x32,8,65536,5505.0240,1572.8640,2359.2960,0.5834,22.4680,146.9204,20.9886 +200,32x8x64,8,131072,11010.0480,3145.7280,4718.5920,1.4399,18.2055,181.3185,25.9026 +200,32x16x2,8,8192,688.1280,196.6080,294.9120,0.0594,27.5914,119.6387,17.0912 +200,32x16x4,8,16384,1376.2560,393.2160,589.8240,0.1171,27.9773,117.9887,16.8555 +200,32x16x8,8,32768,2752.5120,786.4320,1179.6480,0.2352,27.8634,118.4709,16.9244 +200,32x16x16,8,65536,5505.0240,1572.8640,2359.2960,0.5805,22.5780,146.2041,20.8863 +200,32x16x32,8,131072,11010.0480,3145.7280,4718.5920,1.4311,18.3173,180.2122,25.7446 +200,32x16x64,8,262144,22020.0960,6291.4560,9437.1840,3.0673,17.0929,193.1212,27.5887 +200,32x32x2,8,16384,1376.2560,393.2160,589.8240,0.1147,28.5593,115.5841,16.5120 +200,32x32x4,8,32768,2752.5120,786.4320,1179.6480,0.2338,28.0300,117.7668,16.8238 +200,32x32x8,8,65536,5505.0240,1572.8640,2359.2960,0.5872,22.3231,147.8738,21.1248 +200,32x32x16,8,131072,11010.0480,3145.7280,4718.5920,1.4118,18.5683,177.7761,25.3966 +200,32x32x32,8,262144,22020.0960,6291.4560,9437.1840,3.0614,17.1258,192.7496,27.5357 +200,32x32x64,8,524288,44040.1920,12582.9120,18874.3680,6.3631,16.4789,200.3168,28.6167 +200,32x64x2,8,32768,2752.5120,786.4320,1179.6480,0.2330,28.1262,117.3640,16.7663 +200,32x64x4,8,65536,5505.0240,1572.8640,2359.2960,0.5818,22.5288,146.5236,20.9319 +200,32x64x8,8,131072,11010.0480,3145.7280,4718.5920,1.4092,18.6030,177.4448,25.3493 +200,32x64x16,8,262144,22020.0960,6291.4560,9437.1840,3.0520,17.1785,192.1593,27.4513 +200,32x64x32,8,524288,44040.1920,12582.9120,18874.3680,6.3449,16.5264,199.7414,28.5345 +200,32x64x64,8,1048576,88080.3840,25165.8240,37748.7360,12.8872,16.2732,202.8493,28.9785 +200,64x4x2,8,4096,344.0640,98.3040,147.4560,0.0278,29.4982,111.9052,15.9865 +200,64x4x4,8,8192,688.1280,196.6080,294.9120,0.0573,28.5718,115.5334,16.5048 +200,64x4x8,8,16384,1376.2560,393.2160,589.8240,0.1152,28.4428,116.0573,16.5796 +200,64x4x16,8,32768,2752.5120,786.4320,1179.6480,0.2336,28.0505,117.6807,16.8115 +200,64x4x32,8,65536,5505.0240,1572.8640,2359.2960,0.5798,22.6063,146.0209,20.8601 +200,64x4x64,8,131072,11010.0480,3145.7280,4718.5920,1.4209,18.4488,178.9273,25.5610 +200,64x8x2,8,8192,688.1280,196.6080,294.9120,0.0586,27.9668,118.0326,16.8618 +200,64x8x4,8,16384,1376.2560,393.2160,589.8240,0.1160,28.2470,116.8621,16.6946 +200,64x8x8,8,32768,2752.5120,786.4320,1179.6480,0.2294,28.5742,115.5238,16.5034 +200,64x8x16,8,65536,5505.0240,1572.8640,2359.2960,0.5870,22.3285,147.8382,21.1197 +200,64x8x32,8,131072,11010.0480,3145.7280,4718.5920,1.4191,18.4732,178.6914,25.5273 +200,64x8x64,8,262144,22020.0960,6291.4560,9437.1840,3.0748,17.0510,193.5953,27.6565 +200,64x16x2,8,16384,1376.2560,393.2160,589.8240,0.1159,28.2836,116.7109,16.6730 +200,64x16x4,8,32768,2752.5120,786.4320,1179.6480,0.2332,28.0997,117.4745,16.7821 +200,64x16x8,8,65536,5505.0240,1572.8640,2359.2960,0.5861,22.3650,147.5965,21.0852 +200,64x16x16,8,131072,11010.0480,3145.7280,4718.5920,1.4183,18.4828,178.5985,25.5141 +200,64x16x32,8,262144,22020.0960,6291.4560,9437.1840,3.0343,17.2785,191.0463,27.2923 +200,64x16x64,8,524288,44040.1920,12582.9120,18874.3680,6.3269,16.5733,199.1752,28.4536 +200,64x32x2,8,32768,2752.5120,786.4320,1179.6480,0.2275,28.8109,114.5747,16.3678 +200,64x32x4,8,65536,5505.0240,1572.8640,2359.2960,0.5870,22.3278,147.8425,21.1204 +200,64x32x8,8,131072,11010.0480,3145.7280,4718.5920,1.4124,18.5597,177.8585,25.4084 +200,64x32x16,8,262144,22020.0960,6291.4560,9437.1840,3.0282,17.3134,190.6611,27.2373 +200,64x32x32,8,524288,44040.1920,12582.9120,18874.3680,6.3631,16.4791,200.3148,28.6164 +200,64x32x64,8,1048576,88080.3840,25165.8240,37748.7360,12.7459,16.4536,200.6248,28.6607 +200,64x64x2,8,65536,5505.0240,1572.8640,2359.2960,0.5816,22.5346,146.4856,20.9265 +200,64x64x4,8,131072,11010.0480,3145.7280,4718.5920,1.4185,18.4802,178.6234,25.5176 +200,64x64x8,8,262144,22020.0960,6291.4560,9437.1840,3.0653,17.1039,192.9967,27.5710 +200,64x64x16,8,524288,44040.1920,12582.9120,18874.3680,6.2591,16.7527,197.0425,28.1489 +200,64x64x32,8,1048576,88080.3840,25165.8240,37748.7360,12.7873,16.4002,201.2777,28.7540 +200,64x64x64,8,2097152,176160.7680,50331.6480,75497.4720,25.3414,16.5512,199.4419,-61.5561 +200,4x4x2,16,512,59.3920,12.2880,34.8160,0.0056,18.2960,180.4222,12.0281 +200,4x4x4,16,1024,118.7840,24.5760,69.6320,0.0113,18.0639,182.7398,12.1827 +200,4x4x8,16,2048,237.5680,49.1520,139.2640,0.0232,17.6695,186.8195,12.4546 +200,4x4x16,16,4096,475.1360,98.3040,278.5280,0.0451,18.1703,181.6698,12.1113 +200,4x4x32,16,8192,950.2720,196.6080,557.0560,0.0915,17.9014,184.3990,12.2933 +200,4x4x64,16,16384,1900.5440,393.2160,1114.1120,0.1840,17.8046,185.4010,12.3601 +200,4x8x2,16,1024,118.7840,24.5760,69.6320,0.0112,18.2238,181.1364,12.0758 +200,4x8x4,16,2048,237.5680,49.1520,139.2640,0.0225,18.2084,181.2901,12.0860 +200,4x8x8,16,4096,475.1360,98.3040,278.5280,0.0452,18.1204,182.1706,12.1447 +200,4x8x16,16,8192,950.2720,196.6080,557.0560,0.0908,18.0397,182.9853,12.1990 +200,4x8x32,16,16384,1900.5440,393.2160,1114.1120,0.1838,17.8319,185.1175,12.3412 +200,4x8x64,16,32768,3801.0880,786.4320,2228.2240,0.3640,18.0025,183.3630,12.2242 +200,4x16x2,16,2048,237.5680,49.1520,139.2640,0.0227,18.0239,183.1456,12.2097 +200,4x16x4,16,4096,475.1360,98.3040,278.5280,0.0451,18.1620,181.7526,12.1168 +200,4x16x8,16,8192,950.2720,196.6080,557.0560,0.0923,17.7419,186.0569,12.4038 +200,4x16x16,16,16384,1900.5440,393.2160,1114.1120,0.1816,18.0477,182.9043,12.1936 +200,4x16x32,16,32768,3801.0880,786.4320,2228.2240,0.3646,17.9729,183.6656,12.2444 +200,4x16x64,16,65536,7602.1760,1572.8640,4456.4480,0.8363,15.6732,210.6148,14.0410 +200,4x32x2,16,4096,475.1360,98.3040,278.5280,0.0449,18.2632,180.7461,12.0497 +200,4x32x4,16,8192,950.2720,196.6080,557.0560,0.0921,17.7950,185.5015,12.3668 +200,4x32x8,16,16384,1900.5440,393.2160,1114.1120,0.1838,17.8299,185.1388,12.3426 +200,4x32x16,16,32768,3801.0880,786.4320,2228.2240,0.3655,17.9329,184.0750,12.2717 +200,4x32x32,16,65536,7602.1760,1572.8640,4456.4480,0.8389,15.6246,211.2694,14.0846 +200,4x32x64,16,131072,15204.3520,3145.7280,8912.8960,1.7340,15.1178,218.3526,14.5568 +200,4x64x2,16,8192,950.2720,196.6080,557.0560,0.0907,18.0613,182.7666,12.1844 +200,4x64x4,16,16384,1900.5440,393.2160,1114.1120,0.1839,17.8213,185.2282,12.3485 +200,4x64x8,16,32768,3801.0880,786.4320,2228.2240,0.3693,17.7464,186.0092,12.4006 +200,4x64x16,16,65536,7602.1760,1572.8640,4456.4480,0.8366,15.6679,210.6855,14.0457 +200,4x64x32,16,131072,15204.3520,3145.7280,8912.8960,1.7225,15.2190,216.9000,14.4600 +200,4x64x64,16,262144,30408.7040,6291.4560,17825.7920,3.4820,15.0573,219.2297,14.6153 +200,8x4x2,16,1024,118.7840,24.5760,69.6320,0.0114,18.0138,183.2482,12.2165 +200,8x4x4,16,2048,237.5680,49.1520,139.2640,0.0225,18.2077,181.2973,12.0865 +200,8x4x8,16,4096,475.1360,98.3040,278.5280,0.0454,18.0407,182.9754,12.1984 +200,8x4x16,16,8192,950.2720,196.6080,557.0560,0.0918,17.8433,184.9994,12.3333 +200,8x4x32,16,16384,1900.5440,393.2160,1114.1120,0.1826,17.9495,183.9044,12.2603 +200,8x4x64,16,32768,3801.0880,786.4320,2228.2240,0.3641,18.0005,183.3834,12.2256 +200,8x8x2,16,2048,237.5680,49.1520,139.2640,0.0224,18.3071,180.3121,12.0208 +200,8x8x4,16,4096,475.1360,98.3040,278.5280,0.0453,18.0714,182.6647,12.1776 +200,8x8x8,16,8192,950.2720,196.6080,557.0560,0.0906,18.0807,182.5707,12.1714 +200,8x8x16,16,16384,1900.5440,393.2160,1114.1120,0.1838,17.8322,185.1142,12.3409 +200,8x8x32,16,32768,3801.0880,786.4320,2228.2240,0.3640,18.0066,183.3212,12.2214 +200,8x8x64,16,65536,7602.1760,1572.8640,4456.4480,0.8361,15.6765,210.5705,14.0380 +200,8x16x2,16,4096,475.1360,98.3040,278.5280,0.0445,18.4011,179.3913,11.9594 +200,8x16x4,16,8192,950.2720,196.6080,557.0560,0.0908,18.0523,182.8576,12.1905 +200,8x16x8,16,16384,1900.5440,393.2160,1114.1120,0.1840,17.8071,185.3758,12.3584 +200,8x16x16,16,32768,3801.0880,786.4320,2228.2240,0.3677,17.8222,185.2185,12.3479 +200,8x16x32,16,65536,7602.1760,1572.8640,4456.4480,0.8354,15.6894,210.3971,14.0265 +200,8x16x64,16,131072,15204.3520,3145.7280,8912.8960,1.7307,15.1470,217.9303,14.5287 +200,8x32x2,16,8192,950.2720,196.6080,557.0560,0.0915,17.8982,184.4316,12.2954 +200,8x32x4,16,16384,1900.5440,393.2160,1114.1120,0.1839,17.8177,185.2656,12.3510 +200,8x32x8,16,32768,3801.0880,786.4320,2228.2240,0.3630,18.0547,182.8336,12.1889 +200,8x32x16,16,65536,7602.1760,1572.8640,4456.4480,0.8365,15.6691,210.6693,14.0446 +200,8x32x32,16,131072,15204.3520,3145.7280,8912.8960,1.7251,15.1956,217.2335,14.4822 +200,8x32x64,16,262144,30408.7040,6291.4560,17825.7920,3.4910,15.0184,219.7975,14.6532 +200,8x64x2,16,16384,1900.5440,393.2160,1114.1120,0.1841,17.8028,185.4207,12.3614 +200,8x64x4,16,32768,3801.0880,786.4320,2228.2240,0.3677,17.8242,185.1975,12.3465 +200,8x64x8,16,65536,7602.1760,1572.8640,4456.4480,0.8365,15.6697,210.6616,14.0441 +200,8x64x16,16,131072,15204.3520,3145.7280,8912.8960,1.7215,15.2276,216.7771,14.4518 +200,8x64x32,16,262144,30408.7040,6291.4560,17825.7920,3.4890,15.0267,219.6760,14.6451 +200,8x64x64,16,524288,60817.4080,12582.9120,35651.5840,7.0182,14.9408,220.9380,14.7292 +200,16x4x2,16,2048,237.5680,49.1520,139.2640,0.0225,18.2315,181.0606,12.0707 +200,16x4x4,16,4096,475.1360,98.3040,278.5280,0.0454,18.0499,182.8815,12.1921 +200,16x4x8,16,8192,950.2720,196.6080,557.0560,0.0919,17.8201,185.2398,12.3493 +200,16x4x16,16,16384,1900.5440,393.2160,1114.1120,0.1826,17.9490,183.9098,12.2607 +200,16x4x32,16,32768,3801.0880,786.4320,2228.2240,0.3682,17.8013,185.4364,12.3624 +200,16x4x64,16,65536,7602.1760,1572.8640,4456.4480,0.8284,15.8219,208.6348,13.9090 +200,16x8x2,16,4096,475.1360,98.3040,278.5280,0.0453,18.0897,182.4799,12.1653 +200,16x8x4,16,8192,950.2720,196.6080,557.0560,0.0921,17.7910,185.5429,12.3695 +200,16x8x8,16,16384,1900.5440,393.2160,1114.1120,0.1841,17.7950,185.5011,12.3667 +200,16x8x16,16,32768,3801.0880,786.4320,2228.2240,0.3644,17.9861,183.5306,12.2354 +200,16x8x32,16,65536,7602.1760,1572.8640,4456.4480,0.8360,15.6776,210.5549,14.0370 +200,16x8x64,16,131072,15204.3520,3145.7280,8912.8960,1.7218,15.2250,216.8139,14.4543 +200,16x16x2,16,8192,950.2720,196.6080,557.0560,0.0919,17.8267,185.1722,12.3448 +200,16x16x4,16,16384,1900.5440,393.2160,1114.1120,0.1816,18.0469,182.9119,12.1941 +200,16x16x8,16,32768,3801.0880,786.4320,2228.2240,0.3628,18.0620,182.7598,12.1840 +200,16x16x16,16,65536,7602.1760,1572.8640,4456.4480,0.8371,15.6579,210.8203,14.0547 +200,16x16x32,16,131072,15204.3520,3145.7280,8912.8960,1.7275,15.1749,217.5302,14.5020 +200,16x16x64,16,262144,30408.7040,6291.4560,17825.7920,3.4822,15.0561,219.2462,14.6164 +200,16x32x2,16,16384,1900.5440,393.2160,1114.1120,0.1814,18.0647,182.7321,12.1821 +200,16x32x4,16,32768,3801.0880,786.4320,2228.2240,0.3693,17.7452,186.0226,12.4015 +200,16x32x8,16,65536,7602.1760,1572.8640,4456.4480,0.8312,15.7692,209.3325,13.9555 +200,16x32x16,16,131072,15204.3520,3145.7280,8912.8960,1.7303,15.1499,217.8895,14.5260 +200,16x32x32,16,262144,30408.7040,6291.4560,17825.7920,3.4813,15.0603,219.1857,14.6124 +200,16x32x64,16,524288,60817.4080,12582.9120,35651.5840,7.0206,14.9358,221.0133,14.7342 +200,16x64x2,16,32768,3801.0880,786.4320,2228.2240,0.3677,17.8227,185.2129,12.3475 +200,16x64x4,16,65536,7602.1760,1572.8640,4456.4480,0.8286,15.8193,208.6690,13.9113 +200,16x64x8,16,131072,15204.3520,3145.7280,8912.8960,1.7333,15.1243,218.2585,14.5506 +200,16x64x16,16,262144,30408.7040,6291.4560,17825.7920,3.4808,15.0624,219.1549,14.6103 +200,16x64x32,16,524288,60817.4080,12582.9120,35651.5840,7.0109,14.9565,220.7072,14.7138 +200,16x64x64,16,1048576,121634.8160,25165.8240,71303.1680,14.0846,14.8897,221.6970,-40.4557 +200,32x4x2,16,4096,475.1360,98.3040,278.5280,0.0455,18.0158,183.2281,12.2152 +200,32x4x4,16,8192,950.2720,196.6080,557.0560,0.0910,18.0058,183.3293,12.2220 +200,32x4x8,16,16384,1900.5440,393.2160,1114.1120,0.1824,17.9626,183.7708,12.2514 +200,32x4x16,16,32768,3801.0880,786.4320,2228.2240,0.3649,17.9604,183.7931,12.2529 +200,32x4x32,16,65536,7602.1760,1572.8640,4456.4480,0.8305,15.7818,209.1647,13.9443 +200,32x4x64,16,131072,15204.3520,3145.7280,8912.8960,1.7326,15.1299,218.1779,14.5452 +200,32x8x2,16,8192,950.2720,196.6080,557.0560,0.0914,17.9206,184.2011,12.2801 +200,32x8x4,16,16384,1900.5440,393.2160,1114.1120,0.1817,18.0318,183.0659,12.2044 +200,32x8x8,16,32768,3801.0880,786.4320,2228.2240,0.3631,18.0476,182.9056,12.1937 +200,32x8x16,16,65536,7602.1760,1572.8640,4456.4480,0.8336,15.7244,209.9284,13.9952 +200,32x8x32,16,131072,15204.3520,3145.7280,8912.8960,1.7333,15.1241,218.2616,14.5508 +200,32x8x64,16,262144,30408.7040,6291.4560,17825.7920,3.4862,15.0390,219.4955,14.6330 +200,32x16x2,16,16384,1900.5440,393.2160,1114.1120,0.1817,18.0327,183.0564,12.2038 +200,32x16x4,16,32768,3801.0880,786.4320,2228.2240,0.3708,17.6763,186.7474,12.4498 +200,32x16x8,16,65536,7602.1760,1572.8640,4456.4480,0.8334,15.7281,209.8790,13.9919 +200,32x16x16,16,131072,15204.3520,3145.7280,8912.8960,1.7301,15.1518,217.8613,14.5241 +200,32x16x32,16,262144,30408.7040,6291.4560,17825.7920,3.4846,15.0461,219.3931,14.6262 +200,32x16x64,16,524288,60817.4080,12582.9120,35651.5840,7.0117,14.9548,220.7325,14.7155 +200,32x32x2,16,32768,3801.0880,786.4320,2228.2240,0.3650,17.9532,183.8669,12.2578 +200,32x32x4,16,65536,7602.1760,1572.8640,4456.4480,0.8263,15.8627,208.0976,13.8732 +200,32x32x8,16,131072,15204.3520,3145.7280,8912.8960,1.7333,15.1243,218.2578,14.5505 +200,32x32x16,16,262144,30408.7040,6291.4560,17825.7920,3.4864,15.0382,219.5082,14.6339 +200,32x32x32,16,524288,60817.4080,12582.9120,35651.5840,7.0269,14.9223,221.2125,14.7475 +200,32x32x64,16,1048576,121634.8160,25165.8240,71303.1680,14.0684,14.9068,221.4424,-40.4092 +200,32x64x2,16,65536,7602.1760,1572.8640,4456.4480,0.8343,15.7113,210.1042,14.0069 +200,32x64x4,16,131072,15204.3520,3145.7280,8912.8960,1.7294,15.1578,217.7754,14.5184 +200,32x64x8,16,262144,30408.7040,6291.4560,17825.7920,3.4826,15.0546,219.2679,14.6179 +200,32x64x16,16,524288,60817.4080,12582.9120,35651.5840,7.0182,14.9408,220.9389,14.7293 +200,32x64x32,16,1048576,121634.8160,25165.8240,71303.1680,14.0401,14.9369,220.9959,-40.3277 +200,32x64x64,16,2097152,243269.6320,50331.6480,142606.3360,28.4436,14.7460,223.8568,47.0287 +200,64x4x2,16,8192,950.2720,196.6080,557.0560,0.0907,18.0594,182.7859,12.1857 +200,64x4x4,16,16384,1900.5440,393.2160,1114.1120,0.1821,17.9935,183.4551,12.2303 +200,64x4x8,16,32768,3801.0880,786.4320,2228.2240,0.3673,17.8419,185.0140,12.3343 +200,64x4x16,16,65536,7602.1760,1572.8640,4456.4480,0.8270,15.8488,208.2813,13.8854 +200,64x4x32,16,131072,15204.3520,3145.7280,8912.8960,1.7268,15.1806,217.4484,14.4966 +200,64x4x64,16,262144,30408.7040,6291.4560,17825.7920,3.5042,14.9618,220.6282,14.7085 +200,64x8x2,16,16384,1900.5440,393.2160,1114.1120,0.1841,17.7998,185.4515,12.3634 +200,64x8x4,16,32768,3801.0880,786.4320,2228.2240,0.3677,17.8227,185.2128,12.3475 +200,64x8x8,16,65536,7602.1760,1572.8640,4456.4480,0.8403,15.5980,211.6294,14.1086 +200,64x8x16,16,131072,15204.3520,3145.7280,8912.8960,1.7286,15.1654,217.6671,14.5111 +200,64x8x32,16,262144,30408.7040,6291.4560,17825.7920,3.4831,15.0521,219.3045,14.6203 +200,64x8x64,16,524288,60817.4080,12582.9120,35651.5840,7.0128,14.9524,220.7673,14.7178 +200,64x16x2,16,32768,3801.0880,786.4320,2228.2240,0.3696,17.7295,186.1872,12.4125 +200,64x16x4,16,65536,7602.1760,1572.8640,4456.4480,0.8355,15.6870,210.4292,14.0286 +200,64x16x8,16,131072,15204.3520,3145.7280,8912.8960,1.7271,15.1781,217.4841,14.4989 +200,64x16x16,16,262144,30408.7040,6291.4560,17825.7920,3.4838,15.0493,219.3463,14.6231 +200,64x16x32,16,524288,60817.4080,12582.9120,35651.5840,6.9985,14.9828,220.3193,14.6880 +200,64x16x64,16,1048576,121634.8160,25165.8240,71303.1680,14.1217,14.8505,222.2818,-40.5624 +200,64x32x2,16,65536,7602.1760,1572.8640,4456.4480,0.8328,15.7387,209.7378,13.9825 +200,64x32x4,16,131072,15204.3520,3145.7280,8912.8960,1.7318,15.1367,218.0798,14.5387 +200,64x32x8,16,262144,30408.7040,6291.4560,17825.7920,3.4835,15.0505,219.3286,14.6219 +200,64x32x16,16,524288,60817.4080,12582.9120,35651.5840,7.0249,14.9267,221.1479,14.7432 +200,64x32x32,16,1048576,121634.8160,25165.8240,71303.1680,14.0693,14.9059,221.4558,-40.4116 +200,64x32x64,16,2097152,243269.6320,50331.6480,142606.3360,28.5260,14.7034,224.5056,47.1650 +200,64x64x2,16,131072,15204.3520,3145.7280,8912.8960,1.7298,15.1548,217.8186,14.5212 +200,64x64x4,16,262144,30408.7040,6291.4560,17825.7920,3.4835,15.0508,219.3240,14.6216 +200,64x64x8,16,524288,60817.4080,12582.9120,35651.5840,7.0038,14.9715,220.4853,14.6990 +200,64x64x16,16,1048576,121634.8160,25165.8240,71303.1680,14.0787,14.8960,221.6037,-40.4386 +200,64x64x32,16,2097152,243269.6320,50331.6480,142606.3360,28.2532,14.8454,222.3579,46.7138 +200,64x64x64,16,4194304,486539.2640,100663.2960,285212.6720,56.7032,14.7939,223.1326,-619.8127 +200,4x4x2,32,1024,184.3200,24.5760,135.1680,0.0184,11.1343,296.4700,9.5635 +200,4x4x4,32,2048,368.6400,49.1520,270.3360,0.0367,11.1623,295.7287,9.5396 +200,4x4x8,32,4096,737.2800,98.3040,540.6720,0.0742,11.0459,298.8427,9.6401 +200,4x4x16,32,8192,1474.5600,196.6080,1081.3440,0.1479,11.0768,298.0102,9.6132 +200,4x4x32,32,16384,2949.1200,393.2160,2162.6880,0.2940,11.1459,296.1616,9.5536 +200,4x4x64,32,32768,5898.2400,786.4320,4325.3760,0.5993,10.9363,301.8385,9.7367 +200,4x8x2,32,2048,368.6400,49.1520,270.3360,0.0363,11.2914,292.3454,9.4305 +200,4x8x4,32,4096,737.2800,98.3040,540.6720,0.0743,11.0324,299.2096,9.6519 +200,4x8x8,32,8192,1474.5600,196.6080,1081.3440,0.1485,11.0358,299.1171,9.6489 +200,4x8x16,32,16384,2949.1200,393.2160,2162.6880,0.2969,11.0373,299.0780,9.6477 +200,4x8x32,32,32768,5898.2400,786.4320,4325.3760,0.5939,11.0341,299.1637,9.6504 +200,4x8x64,32,65536,11796.4800,1572.8640,8650.7520,1.2794,10.2451,322.2030,10.3936 +200,4x16x2,32,4096,737.2800,98.3040,540.6720,0.0740,11.0639,298.3586,9.6245 +200,4x16x4,32,8192,1474.5600,196.6080,1081.3440,0.1462,11.2070,294.5475,9.5015 +200,4x16x8,32,16384,2949.1200,393.2160,2162.6880,0.2939,11.1506,296.0374,9.5496 +200,4x16x16,32,32768,5898.2400,786.4320,4325.3760,0.5989,10.9423,301.6720,9.7314 +200,4x16x32,32,65536,11796.4800,1572.8640,8650.7520,1.2748,10.2822,321.0414,10.3562 +200,4x16x64,32,131072,23592.9600,3145.7280,17301.5040,2.6346,9.9501,331.7548,10.7018 +200,4x32x2,32,8192,1474.5600,196.6080,1081.3440,0.1485,11.0330,299.1930,9.6514 +200,4x32x4,32,16384,2949.1200,393.2160,2162.6880,0.2971,11.0277,299.3378,9.6561 +200,4x32x8,32,32768,5898.2400,786.4320,4325.3760,0.5972,10.9748,300.7808,9.7026 +200,4x32x16,32,65536,11796.4800,1572.8640,8650.7520,1.2769,10.2653,321.5702,10.3732 +200,4x32x32,32,131072,23592.9600,3145.7280,17301.5040,2.6224,9.9963,330.2237,10.6524 +200,4x32x64,32,262144,47185.9200,6291.4560,34603.0080,5.3057,9.8816,334.0550,10.7760 +200,4x64x2,32,16384,2949.1200,393.2160,2162.6880,0.2971,11.0311,299.2447,9.6531 +200,4x64x4,32,32768,5898.2400,786.4320,4325.3760,0.6015,10.8958,302.9599,9.7729 +200,4x64x8,32,65536,11796.4800,1572.8640,8650.7520,1.2819,10.2248,322.8439,10.4143 +200,4x64x16,32,131072,23592.9600,3145.7280,17301.5040,2.6160,10.0209,329.4108,10.6262 +200,4x64x32,32,262144,47185.9200,6291.4560,34603.0080,5.2811,9.9276,332.5078,10.7261 +200,4x64x64,32,524288,94371.8400,12582.9120,69206.0160,10.6519,9.8441,335.3289,-33.6676 +200,8x4x2,32,2048,368.6400,49.1520,270.3360,0.0368,11.1330,296.5056,9.5647 +200,8x4x4,32,4096,737.2800,98.3040,540.6720,0.0740,11.0736,298.0970,9.6160 +200,8x4x8,32,8192,1474.5600,196.6080,1081.3440,0.1483,11.0501,298.7301,9.6365 +200,8x4x16,32,16384,2949.1200,393.2160,2162.6880,0.2933,11.1714,295.4874,9.5319 +200,8x4x32,32,32768,5898.2400,786.4320,4325.3760,0.5981,10.9567,301.2773,9.7186 +200,8x4x64,32,65536,11796.4800,1572.8640,8650.7520,1.2789,10.2488,322.0863,10.3899 +200,8x8x2,32,4096,737.2800,98.3040,540.6720,0.0739,11.0912,297.6237,9.6008 +200,8x8x4,32,8192,1474.5600,196.6080,1081.3440,0.1482,11.0545,298.6125,9.6327 +200,8x8x8,32,16384,2949.1200,393.2160,2162.6880,0.2974,11.0180,299.5995,9.6645 +200,8x8x16,32,32768,5898.2400,786.4320,4325.3760,0.5904,11.0999,297.3889,9.5932 +200,8x8x32,32,65536,11796.4800,1572.8640,8650.7520,1.2774,10.2611,321.6992,10.3774 +200,8x8x64,32,131072,23592.9600,3145.7280,17301.5040,2.6137,10.0297,329.1226,10.6169 +200,8x16x2,32,8192,1474.5600,196.6080,1081.3440,0.1483,11.0470,298.8150,9.6392 +200,8x16x4,32,16384,2949.1200,393.2160,2162.6880,0.2975,11.0131,299.7339,9.6688 +200,8x16x8,32,32768,5898.2400,786.4320,4325.3760,0.5982,10.9562,301.2905,9.7190 +200,8x16x16,32,65536,11796.4800,1572.8640,8650.7520,1.2760,10.2721,321.3560,10.3663 +200,8x16x32,32,131072,23592.9600,3145.7280,17301.5040,2.6146,10.0263,329.2351,10.6205 +200,8x16x64,32,262144,47185.9200,6291.4560,34603.0080,5.2848,9.9206,332.7404,10.7336 +200,8x32x2,32,16384,2949.1200,393.2160,2162.6880,0.2967,11.0446,298.8779,9.6412 +200,8x32x4,32,32768,5898.2400,786.4320,4325.3760,0.5983,10.9536,301.3623,9.7214 +200,8x32x8,32,65536,11796.4800,1572.8640,8650.7520,1.2785,10.2522,321.9806,10.3865 +200,8x32x16,32,131072,23592.9600,3145.7280,17301.5040,2.6162,10.0200,329.4416,10.6271 +200,8x32x32,32,262144,47185.9200,6291.4560,34603.0080,5.2818,9.9263,332.5517,10.7275 +200,8x32x64,32,524288,94371.8400,12582.9120,69206.0160,10.6656,9.8314,335.7605,-33.7109 +200,8x64x2,32,32768,5898.2400,786.4320,4325.3760,0.5981,10.9568,301.2731,9.7185 +200,8x64x4,32,65536,11796.4800,1572.8640,8650.7520,1.2759,10.2726,321.3416,10.3659 +200,8x64x8,32,131072,23592.9600,3145.7280,17301.5040,2.6177,10.0143,329.6278,10.6332 +200,8x64x16,32,262144,47185.9200,6291.4560,34603.0080,5.2981,9.8957,333.5791,10.7606 +200,8x64x32,32,524288,94371.8400,12582.9120,69206.0160,10.6569,9.8394,335.4876,-33.6835 +200,8x64x64,32,1048576,188743.6800,25165.8240,138412.0320,22.0848,9.4959,347.6238,-34.9020 +200,16x4x2,32,4096,737.2800,98.3040,540.6720,0.0734,11.1599,295.7909,9.5416 +200,16x4x4,32,8192,1474.5600,196.6080,1081.3440,0.1483,11.0457,298.8502,9.6403 +200,16x4x8,32,16384,2949.1200,393.2160,2162.6880,0.2969,11.0351,299.1364,9.6496 +200,16x4x16,32,32768,5898.2400,786.4320,4325.3760,0.6002,10.9182,302.3381,9.7528 +200,16x4x32,32,65536,11796.4800,1572.8640,8650.7520,1.2791,10.2475,322.1284,10.3912 +200,16x4x64,32,131072,23592.9600,3145.7280,17301.5040,2.6199,10.0058,329.9076,10.6422 +200,16x8x2,32,8192,1474.5600,196.6080,1081.3440,0.1471,11.1387,296.3547,9.5598 +200,16x8x4,32,16384,2949.1200,393.2160,2162.6880,0.2965,11.0523,298.6703,9.6345 +200,16x8x8,32,32768,5898.2400,786.4320,4325.3760,0.6002,10.9183,302.3378,9.7528 +200,16x8x16,32,65536,11796.4800,1572.8640,8650.7520,1.2728,10.2978,320.5541,10.3405 +200,16x8x32,32,131072,23592.9600,3145.7280,17301.5040,2.6176,10.0146,329.6201,10.6329 +200,16x8x64,32,262144,47185.9200,6291.4560,34603.0080,5.3039,9.8849,333.9450,10.7724 +200,16x16x2,32,16384,2949.1200,393.2160,2162.6880,0.2931,11.1816,295.2182,9.5232 +200,16x16x4,32,32768,5898.2400,786.4320,4325.3760,0.5996,10.9300,302.0115,9.7423 +200,16x16x8,32,65536,11796.4800,1572.8640,8650.7520,1.2755,10.2760,321.2350,10.3624 +200,16x16x16,32,131072,23592.9600,3145.7280,17301.5040,2.6117,10.0374,328.8698,10.6087 +200,16x16x32,32,262144,47185.9200,6291.4560,34603.0080,5.2872,9.9162,332.8884,10.7383 +200,16x16x64,32,524288,94371.8400,12582.9120,69206.0160,10.6518,9.8441,335.3272,-33.6674 +200,16x32x2,32,32768,5898.2400,786.4320,4325.3760,0.5951,11.0130,299.7369,9.6689 +200,16x32x4,32,65536,11796.4800,1572.8640,8650.7520,1.2710,10.3123,320.1036,10.3259 +200,16x32x8,32,131072,23592.9600,3145.7280,17301.5040,2.6168,10.0177,329.5162,10.6296 +200,16x32x16,32,262144,47185.9200,6291.4560,34603.0080,5.2696,9.9493,331.7830,10.7027 +200,16x32x32,32,524288,94371.8400,12582.9120,69206.0160,10.6700,9.8274,335.8990,-33.7248 +200,16x32x64,32,1048576,188743.6800,25165.8240,138412.0320,21.3463,9.8244,335.9986,-33.7348 +200,16x64x2,32,65536,11796.4800,1572.8640,8650.7520,1.2744,10.2853,320.9430,10.3530 +200,16x64x4,32,131072,23592.9600,3145.7280,17301.5040,2.6233,9.9930,330.3298,10.6558 +200,16x64x8,32,262144,47185.9200,6291.4560,34603.0080,5.2958,9.9000,333.4339,10.7559 +200,16x64x16,32,524288,94371.8400,12582.9120,69206.0160,10.6676,9.8295,335.8249,-33.7174 +200,16x64x32,32,1048576,188743.6800,25165.8240,138412.0320,21.3328,9.8306,335.7866,-33.7135 +200,16x64x64,32,2097152,377487.3600,50331.6480,276824.0640,43.2515,9.6975,340.3977,1215.7060 +200,32x4x2,32,8192,1474.5600,196.6080,1081.3440,0.1467,11.1717,295.4785,9.5316 +200,32x4x4,32,16384,2949.1200,393.2160,2162.6880,0.2932,11.1753,295.3833,9.5285 +200,32x4x8,32,32768,5898.2400,786.4320,4325.3760,0.5962,10.9931,300.2802,9.6865 +200,32x4x16,32,65536,11796.4800,1572.8640,8650.7520,1.2727,10.2991,320.5145,10.3392 +200,32x4x32,32,131072,23592.9600,3145.7280,17301.5040,2.6218,9.9985,330.1501,10.6500 +200,32x4x64,32,262144,47185.9200,6291.4560,34603.0080,5.2997,9.8928,333.6772,10.7638 +200,32x8x2,32,16384,2949.1200,393.2160,2162.6880,0.2982,10.9877,300.4260,9.6912 +200,32x8x4,32,32768,5898.2400,786.4320,4325.3760,0.5999,10.9247,302.1584,9.7470 +200,32x8x8,32,65536,11796.4800,1572.8640,8650.7520,1.2737,10.2905,320.7800,10.3477 +200,32x8x16,32,131072,23592.9600,3145.7280,17301.5040,2.6220,9.9977,330.1746,10.6508 +200,32x8x32,32,262144,47185.9200,6291.4560,34603.0080,5.2694,9.9497,331.7683,10.7022 +200,32x8x64,32,524288,94371.8400,12582.9120,69206.0160,10.6605,9.8361,335.6015,-33.6949 +200,32x16x2,32,32768,5898.2400,786.4320,4325.3760,0.5981,10.9581,301.2397,9.7174 +200,32x16x4,32,65536,11796.4800,1572.8640,8650.7520,1.2765,10.2682,321.4795,10.3703 +200,32x16x8,32,131072,23592.9600,3145.7280,17301.5040,2.6141,10.0280,329.1777,10.6186 +200,32x16x16,32,262144,47185.9200,6291.4560,34603.0080,5.2722,9.9444,331.9453,10.7079 +200,32x16x32,32,524288,94371.8400,12582.9120,69206.0160,10.6403,9.8548,334.9650,-33.6310 +200,32x16x64,32,1048576,188743.6800,25165.8240,138412.0320,21.3337,9.8302,335.8002,-33.7149 +200,32x32x2,32,65536,11796.4800,1572.8640,8650.7520,1.2759,10.2729,321.3320,10.3655 +200,32x32x4,32,131072,23592.9600,3145.7280,17301.5040,2.6127,10.0333,329.0044,10.6130 +200,32x32x8,32,262144,47185.9200,6291.4560,34603.0080,5.2880,9.9147,332.9401,10.7400 +200,32x32x16,32,524288,94371.8400,12582.9120,69206.0160,10.6384,9.8565,334.9068,-33.6252 +200,32x32x32,32,1048576,188743.6800,25165.8240,138412.0320,21.3562,9.8199,336.1558,-33.7506 +200,32x32x64,32,2097152,377487.3600,50331.6480,276824.0640,42.9627,9.7627,338.1252,1207.5901 +200,32x64x2,32,131072,23592.9600,3145.7280,17301.5040,2.6187,10.0106,329.7513,10.6371 +200,32x64x4,32,262144,47185.9200,6291.4560,34603.0080,5.2917,9.9078,333.1709,10.7474 +200,32x64x8,32,524288,94371.8400,12582.9120,69206.0160,10.6475,9.8481,335.1905,-33.6537 +200,32x64x16,32,1048576,188743.6800,25165.8240,138412.0320,21.3369,9.8288,335.8512,-33.7200 +200,32x64x32,32,2097152,377487.3600,50331.6480,276824.0640,42.7122,9.8199,336.1533,1200.5474 +200,32x64x64,32,4194304,754974.7200,100663.2960,553648.1280,86.3545,9.7141,339.8136,1213.6201 +200,64x4x2,32,16384,2949.1200,393.2160,2162.6880,0.2938,11.1517,296.0095,9.5487 +200,64x4x4,32,32768,5898.2400,786.4320,4325.3760,0.5981,10.9565,301.2815,9.7188 +200,64x4x8,32,65536,11796.4800,1572.8640,8650.7520,1.2762,10.2702,321.4139,10.3682 +200,64x4x16,32,131072,23592.9600,3145.7280,17301.5040,2.6196,10.0069,329.8709,10.6410 +200,64x4x32,32,262144,47185.9200,6291.4560,34603.0080,5.3022,9.8882,333.8331,10.7688 +200,64x4x64,32,524288,94371.8400,12582.9120,69206.0160,10.6430,9.8523,335.0502,-33.6396 +200,64x8x2,32,32768,5898.2400,786.4320,4325.3760,0.5980,10.9588,301.2187,9.7167 +200,64x8x4,32,65536,11796.4800,1572.8640,8650.7520,1.2720,10.3042,320.3540,10.3340 +200,64x8x8,32,131072,23592.9600,3145.7280,17301.5040,2.6136,10.0298,329.1186,10.6167 +200,64x8x16,32,262144,47185.9200,6291.4560,34603.0080,5.2814,9.9272,332.5222,10.7265 +200,64x8x32,32,524288,94371.8400,12582.9120,69206.0160,10.6593,9.8372,335.5619,-33.6910 +200,64x8x64,32,1048576,188743.6800,25165.8240,138412.0320,21.3728,9.8123,336.4161,-33.7767 +200,64x16x2,32,65536,11796.4800,1572.8640,8650.7520,1.2737,10.2904,320.7839,10.3479 +200,64x16x4,32,131072,23592.9600,3145.7280,17301.5040,2.6248,9.9870,330.5291,10.6622 +200,64x16x8,32,262144,47185.9200,6291.4560,34603.0080,5.2807,9.9284,332.4815,10.7252 +200,64x16x16,32,524288,94371.8400,12582.9120,69206.0160,10.6290,9.8653,334.6079,-33.5952 +200,64x16x32,32,1048576,188743.6800,25165.8240,138412.0320,21.3837,9.8072,336.5883,-33.7940 +200,64x16x64,32,2097152,377487.3600,50331.6480,276824.0640,42.8648,9.7850,337.3547,1204.8384 +200,64x32x2,32,131072,23592.9600,3145.7280,17301.5040,2.6133,10.0311,329.0782,10.6154 +200,64x32x4,32,262144,47185.9200,6291.4560,34603.0080,5.2990,9.8941,333.6320,10.7623 +200,64x32x8,32,524288,94371.8400,12582.9120,69206.0160,10.6473,9.8483,335.1850,-33.6531 +200,64x32x16,32,1048576,188743.6800,25165.8240,138412.0320,21.3139,9.8394,335.4895,-33.6837 +200,64x32x32,32,2097152,377487.3600,50331.6480,276824.0640,42.7194,9.8183,336.2104,1200.7513 +200,64x32x64,32,4194304,754974.7200,100663.2960,553648.1280,86.0053,9.7536,338.4393,1208.7117 +200,64x64x2,32,262144,47185.9200,6291.4560,34603.0080,5.2792,9.9312,332.3876,10.7222 +200,64x64x4,32,524288,94371.8400,12582.9120,69206.0160,10.6422,9.8530,335.0261,-33.6372 +200,64x64x8,32,1048576,188743.6800,25165.8240,138412.0320,21.3188,9.8371,335.5660,-33.6914 +200,64x64x16,32,2097152,377487.3600,50331.6480,276824.0640,42.7500,9.8112,336.4510,1201.6108 +200,64x64x32,32,4194304,754974.7200,100663.2960,553648.1280,86.0358,9.7501,338.5595,1209.1409 +200,64x64x64,32,8388608,1509949.4400,201326.5920,1107296.2560,175.8321,9.5416,345.9584,1235.5657 diff --git a/scripts/run_stub.sh b/scripts/run_stub.sh index ff1a6b9..2cf15a2 100644 --- a/scripts/run_stub.sh +++ b/scripts/run_stub.sh @@ -1,6 +1,6 @@ #!/bin/bash -while getopts "a:f:n:r:x:y:z:" flag; do +while getopts "a:f:n:o:r:x:y:z:" flag; do case "${flag}" in a) atoms_per_unit_cell=${OPTARG};; f) frequency=${OPTARG};; diff --git a/src/main-stub.c b/src/main-stub.c index 0f7aa71..bc8bc79 100644 --- a/src/main-stub.c +++ b/src/main-stub.c @@ -201,7 +201,7 @@ int main(int argc, const char *argv[]) { double T_accum = E-S; const double atoms_updates_per_sec = atom->Nlocal * param.ntimes / T_accum; const double cycles_per_atom = T_accum * freq / (atom->Nlocal * param.ntimes); - const double cycles_per_neigh = T_accum * freq / (atom->Nlocal * (atoms_per_unit_cell - 1) * param.ntimes); + const double cycles_per_neigh = cycles_per_atom / (atoms_per_unit_cell - 1); if(!csv) { printf("Total time: %.4f, Mega atom updates/s: %.4f\n", T_accum, atoms_updates_per_sec / 1.E6);