Ahmed moreilp
This commit is contained in:
@@ -5,54 +5,54 @@ 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): 8713477.81 cycles
|
||||
P(n): 4.22 flops/cycle
|
||||
T(n): 8791913.88 cycles
|
||||
P(n): 4.18 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): 40792521.50 cycles
|
||||
P(n): 3.57 flops/cycle
|
||||
T(n): 41158496.75 cycles
|
||||
P(n): 3.53 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): 132995997.00 cycles
|
||||
P(n): 4.35 flops/cycle
|
||||
T(n): 133925307.00 cycles
|
||||
P(n): 4.32 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): 813430901.00 cycles
|
||||
P(n): 4.43 flops/cycle
|
||||
T(n): 823137794.00 cycles
|
||||
P(n): 4.38 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): 3155176718.00 cycles
|
||||
P(n): 4.57 flops/cycle
|
||||
T(n): 3167884952.00 cycles
|
||||
P(n): 4.55 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): 12638893219.00 cycles
|
||||
P(n): 4.56 flops/cycle
|
||||
T(n): 12582829866.00 cycles
|
||||
P(n): 4.58 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): 76387953469.00 cycles
|
||||
P(n): 4.71 flops/cycle
|
||||
T(n): 75970386305.00 cycles
|
||||
P(n): 4.74 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_cutoff.cpp -o main_cutoff -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): 8789882.25 cycles
|
||||
P(n): 4.18 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): 41157310.00 cycles
|
||||
P(n): 3.53 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): 134011989.00 cycles
|
||||
P(n): 4.32 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): 821974719.00 cycles
|
||||
P(n): 4.39 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): 3180457398.00 cycles
|
||||
P(n): 4.53 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): 12572786176.00 cycles
|
||||
P(n): 4.58 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): 76601440906.00 cycles
|
||||
P(n): 4.70 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_cutoff.cpp -o main_cutoff -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): 8791731.94 cycles
|
||||
P(n): 4.18 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): 41240033.75 cycles
|
||||
P(n): 3.53 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): 134229626.00 cycles
|
||||
P(n): 4.31 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): 819718803.00 cycles
|
||||
P(n): 4.40 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): 3157597976.00 cycles
|
||||
P(n): 4.57 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): 12581653566.00 cycles
|
||||
P(n): 4.58 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): 76309138275.00 cycles
|
||||
P(n): 4.72 flops/cycle
|
||||
|
||||
Reference in New Issue
Block a user