Ahmed moreilp
This commit is contained in:
@@ -5,54 +5,54 @@ 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): 11407106.00 cycles
|
||||
P(n): 3.22 flops/cycle
|
||||
T(n): 11356540.00 cycles
|
||||
P(n): 3.24 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): 45941640.00 cycles
|
||||
P(n): 3.17 flops/cycle
|
||||
T(n): 45488284.00 cycles
|
||||
P(n): 3.20 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): 175844320.00 cycles
|
||||
P(n): 3.29 flops/cycle
|
||||
T(n): 175237216.00 cycles
|
||||
P(n): 3.30 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): 1161542784.00 cycles
|
||||
P(n): 3.11 flops/cycle
|
||||
T(n): 1146521600.00 cycles
|
||||
P(n): 3.15 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): 4913180160.00 cycles
|
||||
P(n): 2.93 flops/cycle
|
||||
T(n): 4827586048.00 cycles
|
||||
P(n): 2.99 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): 21352656896.00 cycles
|
||||
P(n): 2.70 flops/cycle
|
||||
T(n): 20706713600.00 cycles
|
||||
P(n): 2.78 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): 153264947200.00 cycles
|
||||
P(n): 2.35 flops/cycle
|
||||
T(n): 150425829376.00 cycles
|
||||
P(n): 2.39 flops/cycle
|
||||
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
|
||||
sudo /usr/bin/g++ main-float.cpp ./variants/variant_float_inlining_SoA.cpp -o main_float_inlining_SoA -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): 11386587.00 cycles
|
||||
P(n): 3.23 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): 45594080.00 cycles
|
||||
P(n): 3.19 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): 175489888.00 cycles
|
||||
P(n): 3.30 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): 1146447744.00 cycles
|
||||
P(n): 3.15 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): 4937291264.00 cycles
|
||||
P(n): 2.92 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): 21289326592.00 cycles
|
||||
P(n): 2.71 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): 154203766784.00 cycles
|
||||
P(n): 2.34 flops/cycle
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
rm -f main_* run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
|
||||
sudo /usr/bin/g++ main-float.cpp ./variants/variant_float_inlining_SoA.cpp -o main_float_inlining_SoA -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): 11384260.00 cycles
|
||||
P(n): 3.23 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): 45578272.00 cycles
|
||||
P(n): 3.19 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): 174984688.00 cycles
|
||||
P(n): 3.31 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): 1151401216.00 cycles
|
||||
P(n): 3.13 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): 4864613888.00 cycles
|
||||
P(n): 2.96 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): 20916678656.00 cycles
|
||||
P(n): 2.76 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): 154187153408.00 cycles
|
||||
P(n): 2.34 flops/cycle
|
||||
|
||||
Reference in New Issue
Block a user