Ahmed moreilp
This commit is contained in:
@@ -5,39 +5,39 @@ 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): 16465719.25 cycles
|
||||
P(n): 2.23 flops/cycle
|
||||
T(n): 16982433.12 cycles
|
||||
P(n): 2.16 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): 68986819.50 cycles
|
||||
P(n): 2.11 flops/cycle
|
||||
T(n): 69901888.50 cycles
|
||||
P(n): 2.08 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): 296100633.00 cycles
|
||||
P(n): 1.96 flops/cycle
|
||||
T(n): 302888308.00 cycles
|
||||
P(n): 1.91 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): 2015322383.00 cycles
|
||||
P(n): 1.79 flops/cycle
|
||||
T(n): 2052868152.00 cycles
|
||||
P(n): 1.76 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): 8425401169.00 cycles
|
||||
T(n): 8417635258.00 cycles
|
||||
P(n): 1.71 flops/cycle
|
||||
|
||||
=== N_P=2000 N_ITER=200 ===
|
||||
@@ -45,14 +45,14 @@ 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): 35087107382.00 cycles
|
||||
P(n): 1.64 flops/cycle
|
||||
T(n): 35363573917.00 cycles
|
||||
P(n): 1.63 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): 225285744034.00 cycles
|
||||
P(n): 1.60 flops/cycle
|
||||
T(n): 228532646195.00 cycles
|
||||
P(n): 1.58 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.cpp ./variants/variant_inlining_7.cpp -o main_inlining_7 -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: 6512 bytes
|
||||
I(n): 28.21 flops/byte
|
||||
W(n): 36740000.00 flops
|
||||
T(n): 16532863.38 cycles
|
||||
P(n): 2.22 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): 68951749.50 cycles
|
||||
P(n): 2.11 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): 297964775.00 cycles
|
||||
P(n): 1.94 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): 2043353865.00 cycles
|
||||
P(n): 1.77 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): 8411006888.00 cycles
|
||||
P(n): 1.71 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): 35078318181.00 cycles
|
||||
P(n): 1.64 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): 226390920838.00 cycles
|
||||
P(n): 1.59 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.cpp ./variants/variant_inlining_7.cpp -o main_inlining_7 -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: 6512 bytes
|
||||
I(n): 28.21 flops/byte
|
||||
W(n): 36740000.00 flops
|
||||
T(n): 16539475.50 cycles
|
||||
P(n): 2.22 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): 68733742.50 cycles
|
||||
P(n): 2.12 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): 299082818.00 cycles
|
||||
P(n): 1.94 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): 2023139542.00 cycles
|
||||
P(n): 1.78 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): 8391580635.00 cycles
|
||||
P(n): 1.72 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): 35018999759.00 cycles
|
||||
P(n): 1.65 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): 225594949413.00 cycles
|
||||
P(n): 1.60 flops/cycle
|
||||
|
||||
Reference in New Issue
Block a user