admin/263-0007-00L-Advanced-Systems-Lab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Perf plot

Browse Source
This commit is contained in:
[Quy Anh] «Elliot» Nguyen
2026-06-18 11:59:50 +02:00
committed by Linus Baumberger
parent ca969564a6
commit e7af3103e8
153 changed files with 22042 additions and 24220 deletions
Download Patch File Download Diff File Expand all files Collapse all files
measurements/variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt/x86/1.log
+23 -15
View File
@@ -1,58 +1,66 @@
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
/usr/bin/g++ main.cpp ./variants/variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt.cpp -o main_inlining_8_SoA_AVX512_polyexp_fastinvsqrt -O3 -march=native -std=c++23 -Wall -Wextra -flto -DFLOPCOUNT=0 -DRANDOM_SEED=0 -DROOFLINE=0 -DBENCHMARK=1
/usr/bin/g++ main.cpp ./variants/variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt_expfix.cpp -o main_inlining_8_SoA_AVX512_polyexp_fastinvsqrt_expfix -O3 -march=native -std=c++23 -Wall -Wextra -flto -DFLOPCOUNT=0 -DRANDOM_SEED=0 -DROOFLINE=0 -DBENCHMARK=1
=== N_P=50 N_ITER=200 ===
W(n) per iteration: 183700.00 flops
Q(n) per iteration: 6512 bytes
I(n): 28.21 flops/byte
W(n): 36740000.00 flops
T(n): 7287068.75 cycles
P(n): 5.04 flops/cycle
T(n): 8339301.25 cycles
P(n): 4.41 flops/cycle
=== N_P=100 N_ITER=200 ===
W(n) per iteration: 727400.00 flops
Q(n) per iteration: 12912 bytes
I(n): 56.34 flops/byte
W(n): 145480000.00 flops
T(n): 24479917.50 cycles
P(n): 5.94 flops/cycle
T(n): 28662660.00 cycles
P(n): 5.08 flops/cycle
=== N_P=200 N_ITER=200 ===
W(n) per iteration: 2894800.00 flops
Q(n) per iteration: 25712 bytes
I(n): 112.59 flops/byte
W(n): 578960000.00 flops
T(n): 88304220.00 cycles
P(n): 6.56 flops/cycle
T(n): 104402900.00 cycles
P(n): 5.55 flops/cycle
=== N_P=500 N_ITER=200 ===
W(n) per iteration: 18037000.00 flops
Q(n) per iteration: 64112 bytes
I(n): 281.34 flops/byte
W(n): 3607400000.00 flops
T(n): 532537300.00 cycles
P(n): 6.77 flops/cycle
T(n): 636519040.00 cycles
P(n): 5.67 flops/cycle
=== N_P=1000 N_ITER=200 ===
W(n) per iteration: 72074000.00 flops
Q(n) per iteration: 128112 bytes
I(n): 562.59 flops/byte
W(n): 14414800000.00 flops
T(n): 2074603460.00 cycles
P(n): 6.95 flops/cycle
T(n): 2499027620.00 cycles
P(n): 5.77 flops/cycle
=== N_P=2000 N_ITER=200 ===
W(n) per iteration: 288148000.00 flops
Q(n) per iteration: 256112 bytes
I(n): 1125.09 flops/byte
W(n): 57629600000.00 flops
T(n): 8222911780.00 cycles
P(n): 7.01 flops/cycle
T(n): 9941452140.00 cycles
P(n): 5.80 flops/cycle
=== N_P=5000 N_ITER=200 ===
W(n) per iteration: 1800370000.00 flops
Q(n) per iteration: 640112 bytes
I(n): 2812.59 flops/byte
W(n): 360074000000.00 flops
T(n): 51149290420.00 cycles
P(n): 7.04 flops/cycle
T(n): 61650558000.00 cycles
P(n): 5.84 flops/cycle
=== N_P=10000 N_ITER=200 ===
W(n) per iteration: 2905772704.00 flops
Q(n) per iteration: 1280112 bytes
I(n): 2269.94 flops/byte
W(n): 581154540800.00 flops
T(n): 246792591620.00 cycles
P(n): 2.35 flops/cycle
measurements/variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt/x86/2.log
+17 -17
View File
@@ -1,66 +1,66 @@
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
/usr/bin/g++ main.cpp ./variants/variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt.cpp -o main_inlining_8_SoA_AVX512_polyexp_fastinvsqrt -O3 -march=native -std=c++23 -Wall -Wextra -flto -DFLOPCOUNT=0 -DRANDOM_SEED=0 -DROOFLINE=0 -DBENCHMARK=1
/usr/bin/g++ main.cpp ./variants/variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt_expfix.cpp -o main_inlining_8_SoA_AVX512_polyexp_fastinvsqrt_expfix -O3 -march=native -std=c++23 -Wall -Wextra -flto -DFLOPCOUNT=0 -DRANDOM_SEED=0 -DROOFLINE=0 -DBENCHMARK=1
=== N_P=50 N_ITER=200 ===
W(n) per iteration: 183700.00 flops
Q(n) per iteration: 6512 bytes
I(n): 28.21 flops/byte
W(n): 36740000.00 flops
T(n): 7237100.00 cycles
P(n): 5.08 flops/cycle
T(n): 8445907.50 cycles
P(n): 4.35 flops/cycle
=== N_P=100 N_ITER=200 ===
W(n) per iteration: 727400.00 flops
Q(n) per iteration: 12912 bytes
I(n): 56.34 flops/byte
W(n): 145480000.00 flops
T(n): 24227557.50 cycles
P(n): 6.00 flops/cycle
T(n): 28691310.00 cycles
P(n): 5.07 flops/cycle
=== N_P=200 N_ITER=200 ===
W(n) per iteration: 2894800.00 flops
Q(n) per iteration: 25712 bytes
I(n): 112.59 flops/byte
W(n): 578960000.00 flops
T(n): 87321790.00 cycles
P(n): 6.63 flops/cycle
T(n): 104933160.00 cycles
P(n): 5.52 flops/cycle
=== N_P=500 N_ITER=200 ===
W(n) per iteration: 18037000.00 flops
Q(n) per iteration: 64112 bytes
I(n): 281.34 flops/byte
W(n): 3607400000.00 flops
T(n): 529210780.00 cycles
P(n): 6.82 flops/cycle
T(n): 639568720.00 cycles
P(n): 5.64 flops/cycle
=== N_P=1000 N_ITER=200 ===
W(n) per iteration: 72074000.00 flops
Q(n) per iteration: 128112 bytes
I(n): 562.59 flops/byte
W(n): 14414800000.00 flops
T(n): 2064752120.00 cycles
P(n): 6.98 flops/cycle
T(n): 2515964020.00 cycles
P(n): 5.73 flops/cycle
=== N_P=2000 N_ITER=200 ===
W(n) per iteration: 288148000.00 flops
Q(n) per iteration: 256112 bytes
I(n): 1125.09 flops/byte
W(n): 57629600000.00 flops
T(n): 8154495340.00 cycles
P(n): 7.07 flops/cycle
T(n): 9996713720.00 cycles
P(n): 5.76 flops/cycle
=== N_P=5000 N_ITER=200 ===
W(n) per iteration: 1800370000.00 flops
Q(n) per iteration: 640112 bytes
I(n): 2812.59 flops/byte
W(n): 360074000000.00 flops
T(n): 50962729840.00 cycles
P(n): 7.07 flops/cycle
T(n): 62098746740.00 cycles
P(n): 5.80 flops/cycle
=== N_P=10000 N_ITER=200 ===
W(n) per iteration: 2905772704.00 flops
Q(n) per iteration: 1280112 bytes
I(n): 2269.94 flops/byte
W(n): 581154540800.00 flops
T(n): 203476930280.00 cycles
P(n): 2.86 flops/cycle
T(n): 247013435860.00 cycles
P(n): 2.35 flops/cycle
measurements/variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt/x86/3.log
+66
View File
@@ -0,0 +1,66 @@
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
/usr/bin/g++ main.cpp ./variants/variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt_expfix.cpp -o main_inlining_8_SoA_AVX512_polyexp_fastinvsqrt_expfix -O3 -march=native -std=c++23 -Wall -Wextra -flto -DFLOPCOUNT=0 -DRANDOM_SEED=0 -DROOFLINE=0 -DBENCHMARK=1
=== N_P=50 N_ITER=200 ===
W(n) per iteration: 183700.00 flops
Q(n) per iteration: 6512 bytes
I(n): 28.21 flops/byte
W(n): 36740000.00 flops
T(n): 8335317.50 cycles
P(n): 4.41 flops/cycle
=== N_P=100 N_ITER=200 ===
W(n) per iteration: 727400.00 flops
Q(n) per iteration: 12912 bytes
I(n): 56.34 flops/byte
W(n): 145480000.00 flops
T(n): 28557990.00 cycles
P(n): 5.09 flops/cycle
=== N_P=200 N_ITER=200 ===
W(n) per iteration: 2894800.00 flops
Q(n) per iteration: 25712 bytes
I(n): 112.59 flops/byte
W(n): 578960000.00 flops
T(n): 104404360.00 cycles
P(n): 5.55 flops/cycle
=== N_P=500 N_ITER=200 ===
W(n) per iteration: 18037000.00 flops
Q(n) per iteration: 64112 bytes
I(n): 281.34 flops/byte
W(n): 3607400000.00 flops
T(n): 635858120.00 cycles
P(n): 5.67 flops/cycle
=== N_P=1000 N_ITER=200 ===
W(n) per iteration: 72074000.00 flops
Q(n) per iteration: 128112 bytes
I(n): 562.59 flops/byte
W(n): 14414800000.00 flops
T(n): 2509183840.00 cycles
P(n): 5.74 flops/cycle
=== N_P=2000 N_ITER=200 ===
W(n) per iteration: 288148000.00 flops
Q(n) per iteration: 256112 bytes
I(n): 1125.09 flops/byte
W(n): 57629600000.00 flops
T(n): 9956726160.00 cycles
P(n): 5.79 flops/cycle
=== N_P=5000 N_ITER=200 ===
W(n) per iteration: 1800370000.00 flops
Q(n) per iteration: 640112 bytes
I(n): 2812.59 flops/byte
W(n): 360074000000.00 flops
T(n): 61839346220.00 cycles
P(n): 5.82 flops/cycle
=== N_P=10000 N_ITER=200 ===
W(n) per iteration: 2905772704.00 flops
Q(n) per iteration: 1280112 bytes
I(n): 2269.94 flops/byte
W(n): 581154540800.00 flops
T(n): 246699025260.00 cycles
P(n): 2.36 flops/cycle