Ahmed Kallala
59 lines
1.7 KiB
Plaintext
59 lines
1.7 KiB
Plaintext
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
|
|
sudo /usr/bin/g++ main-float_symmetry.cpp ./variants/variant_float_inlining_SoA_symmetry.cpp -o main_float_inlining_SoA_symmetry -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: 95500.00 flops
|
|
Q(n) per iteration: 3256 bytes
|
|
I(n): 29.33 flops/byte
|
|
W(n): 19100000.00 flops
|
|
T(n): 12256982.00 cycles
|
|
P(n): 1.56 flops/cycle
|
|
|
|
=== N_P=100 N_ITER=200 ===
|
|
W(n) per iteration: 371000.00 flops
|
|
Q(n) per iteration: 6456 bytes
|
|
I(n): 57.47 flops/byte
|
|
W(n): 74200000.00 flops
|
|
T(n): 50311960.00 cycles
|
|
P(n): 1.47 flops/cycle
|
|
|
|
=== N_P=200 N_ITER=200 ===
|
|
W(n) per iteration: 1462000.00 flops
|
|
Q(n) per iteration: 12856 bytes
|
|
I(n): 113.72 flops/byte
|
|
W(n): 292400000.00 flops
|
|
T(n): 205116992.00 cycles
|
|
P(n): 1.43 flops/cycle
|
|
|
|
=== N_P=500 N_ITER=200 ===
|
|
W(n) per iteration: 9055000.00 flops
|
|
Q(n) per iteration: 32056 bytes
|
|
I(n): 282.47 flops/byte
|
|
W(n): 1811000064.00 flops
|
|
T(n): 1430680320.00 cycles
|
|
P(n): 1.27 flops/cycle
|
|
|
|
=== N_P=1000 N_ITER=200 ===
|
|
W(n) per iteration: 36110000.00 flops
|
|
Q(n) per iteration: 64056 bytes
|
|
I(n): 563.73 flops/byte
|
|
W(n): 7222000128.00 flops
|
|
T(n): 6433722368.00 cycles
|
|
P(n): 1.12 flops/cycle
|
|
|
|
=== N_P=2000 N_ITER=200 ===
|
|
W(n) per iteration: 144220000.00 flops
|
|
Q(n) per iteration: 128056 bytes
|
|
I(n): 1126.23 flops/byte
|
|
W(n): 28843999232.00 flops
|
|
T(n): 28671172608.00 cycles
|
|
P(n): 1.01 flops/cycle
|
|
|
|
=== N_P=5000 N_ITER=200 ===
|
|
W(n) per iteration: 900550016.00 flops
|
|
Q(n) per iteration: 320056 bytes
|
|
I(n): 2813.73 flops/byte
|
|
W(n): 180110000128.00 flops
|
|
T(n): 226077196288.00 cycles
|
|
P(n): 0.80 flops/cycle
|
|
|