67 lines
1.9 KiB
Plaintext
67 lines
1.9 KiB
Plaintext
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_AVX512_polyexp_expfix.cpp -o main_float_inlining_SoA_AVX512_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): 4618692.00 cycles
|
|
P(n): 7.95 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): 14020708.00 cycles
|
|
P(n): 10.38 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): 47426524.00 cycles
|
|
P(n): 12.21 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): 271672832.00 cycles
|
|
P(n): 13.28 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): 1041892096.00 cycles
|
|
P(n): 13.84 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): 4086357760.00 cycles
|
|
P(n): 14.10 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): 25345890304.00 cycles
|
|
P(n): 14.21 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): 100797374464.00 cycles
|
|
P(n): 5.77 flops/cycle
|
|
|