Ahmed Kallala
59 lines
1.6 KiB
Plaintext
59 lines
1.6 KiB
Plaintext
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
|
|
sudo /usr/bin/g++ main-symmetry.cpp ./variants/variant_inlining_7_symmetry_1.cpp -o main_inlining_7_symmetry_1 -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: 6512 bytes
|
|
I(n): 14.67 flops/byte
|
|
W(n): 19100000.00 flops
|
|
T(n): 16282625.38 cycles
|
|
P(n): 1.17 flops/cycle
|
|
|
|
=== N_P=100 N_ITER=200 ===
|
|
W(n) per iteration: 371000.00 flops
|
|
Q(n) per iteration: 12912 bytes
|
|
I(n): 28.73 flops/byte
|
|
W(n): 74200000.00 flops
|
|
T(n): 66366868.00 cycles
|
|
P(n): 1.12 flops/cycle
|
|
|
|
=== N_P=200 N_ITER=200 ===
|
|
W(n) per iteration: 1462000.00 flops
|
|
Q(n) per iteration: 25712 bytes
|
|
I(n): 56.86 flops/byte
|
|
W(n): 292400000.00 flops
|
|
T(n): 281595120.00 cycles
|
|
P(n): 1.04 flops/cycle
|
|
|
|
=== N_P=500 N_ITER=200 ===
|
|
W(n) per iteration: 9055000.00 flops
|
|
Q(n) per iteration: 64112 bytes
|
|
I(n): 141.24 flops/byte
|
|
W(n): 1811000000.00 flops
|
|
T(n): 2180955081.00 cycles
|
|
P(n): 0.83 flops/cycle
|
|
|
|
=== N_P=1000 N_ITER=200 ===
|
|
W(n) per iteration: 36110000.00 flops
|
|
Q(n) per iteration: 128112 bytes
|
|
I(n): 281.86 flops/byte
|
|
W(n): 7222000000.00 flops
|
|
T(n): 9224037046.00 cycles
|
|
P(n): 0.78 flops/cycle
|
|
|
|
=== N_P=2000 N_ITER=200 ===
|
|
W(n) per iteration: 144220000.00 flops
|
|
Q(n) per iteration: 256112 bytes
|
|
I(n): 563.11 flops/byte
|
|
W(n): 28844000000.00 flops
|
|
T(n): 40458642557.00 cycles
|
|
P(n): 0.71 flops/cycle
|
|
|
|
=== N_P=5000 N_ITER=200 ===
|
|
W(n) per iteration: 900550000.00 flops
|
|
Q(n) per iteration: 640112 bytes
|
|
I(n): 1406.86 flops/byte
|
|
W(n): 180110000000.00 flops
|
|
T(n): 283134924244.00 cycles
|
|
P(n): 0.64 flops/cycle
|
|
|