Perf plot

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
@@ -1,66 +1,66 @@
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
/usr/bin/g++ main-float.cpp ./variants/variant_float_inlining_SoA_AVX2_polyexp.cpp -o main_float_inlining_SoA_AVX2_polyexp -O3 -march=native -std=c++23 -Wall -Wextra -flto -DFLOPCOUNT=0 -DRANDOM_SEED=0 -DROOFLINE=0 -DBENCHMARK=1
/usr/bin/g++ main-float.cpp ./variants/variant_float_inlining_SoA_AVX2_polyexp_expfix.cpp -o main_float_inlining_SoA_AVX2_polyexp_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: 3256 bytes
I(n): 56.42 flops/byte
W(n): 36740000.00 flops
T(n): 4573347.00 cycles
P(n): 8.03 flops/cycle
T(n): 5885449.00 cycles
P(n): 6.24 flops/cycle
=== N_P=100 N_ITER=200 ===
W(n) per iteration: 727400.00 flops
Q(n) per iteration: 6456 bytes
I(n): 112.67 flops/byte
W(n): 145480000.00 flops
T(n): 14972852.00 cycles
P(n): 9.72 flops/cycle
T(n): 19775262.00 cycles
P(n): 7.36 flops/cycle
=== N_P=200 N_ITER=200 ===
W(n) per iteration: 2894800.00 flops
Q(n) per iteration: 12856 bytes
I(n): 225.17 flops/byte
W(n): 578960000.00 flops
T(n): 53246808.00 cycles
P(n): 10.87 flops/cycle
T(n): 71759640.00 cycles
P(n): 8.07 flops/cycle
=== N_P=500 N_ITER=200 ===
W(n) per iteration: 18037000.00 flops
Q(n) per iteration: 32056 bytes
I(n): 562.67 flops/byte
W(n): 3607399936.00 flops
T(n): 317441728.00 cycles
P(n): 11.36 flops/cycle
T(n): 442073856.00 cycles
P(n): 8.16 flops/cycle
=== N_P=1000 N_ITER=200 ===
W(n) per iteration: 72074000.00 flops
Q(n) per iteration: 64056 bytes
I(n): 1125.17 flops/byte
W(n): 14414799872.00 flops
T(n): 1237166592.00 cycles
P(n): 11.65 flops/cycle
T(n): 1698162944.00 cycles
P(n): 8.49 flops/cycle
=== N_P=2000 N_ITER=200 ===
W(n) per iteration: 288148000.00 flops
Q(n) per iteration: 128056 bytes
I(n): 2250.17 flops/byte
W(n): 57629601792.00 flops
T(n): 4899325440.00 cycles
P(n): 11.76 flops/cycle
T(n): 6719285248.00 cycles
P(n): 8.58 flops/cycle
=== N_P=5000 N_ITER=200 ===
W(n) per iteration: 1800369920.00 flops
Q(n) per iteration: 320056 bytes
I(n): 5625.17 flops/byte
W(n): 360073986048.00 flops
T(n): 30502610944.00 cycles
P(n): 11.80 flops/cycle
T(n): 41795964928.00 cycles
P(n): 8.62 flops/cycle
=== N_P=10000 N_ITER=200 ===
W(n) per iteration: 2905772800.00 flops
Q(n) per iteration: 640056 bytes
I(n): 4539.87 flops/byte
W(n): 581154570240.00 flops
T(n): 122120396800.00 cycles
P(n): 4.76 flops/cycle
T(n): 166340608000.00 cycles
P(n): 3.49 flops/cycle