[Quy Anh] «Elliot» Nguyen
67 lines
1.8 KiB
Plaintext
67 lines
1.8 KiB
Plaintext
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
|
|
/usr/bin/g++ main.cpp ./variants/variant_AVX512_1.cpp -o main_AVX512_1 -O3 -march=native -std=c++23 -Wall -Wextra -flto -lsleef -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): 12329020.00 cycles
|
|
P(n): 2.98 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): 42651410.00 cycles
|
|
P(n): 3.41 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): 147914080.00 cycles
|
|
P(n): 3.91 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): 894537280.00 cycles
|
|
P(n): 4.03 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): 3432966440.00 cycles
|
|
P(n): 4.20 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): 13503535040.00 cycles
|
|
P(n): 4.27 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): 83704334600.00 cycles
|
|
P(n): 4.30 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): 346159550800.00 cycles
|
|
P(n): 1.68 flops/cycle
|
|
|