Ahmed moreilp
This commit is contained in:
@@ -5,7 +5,7 @@ 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): 15054758.12 cycles
|
||||
T(n): 15034834.12 cycles
|
||||
P(n): 2.44 flops/cycle
|
||||
|
||||
=== N_P=100 N_ITER=200 ===
|
||||
@@ -13,46 +13,46 @@ 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): 59392245.00 cycles
|
||||
P(n): 2.45 flops/cycle
|
||||
T(n): 58645676.50 cycles
|
||||
P(n): 2.48 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): 238841666.00 cycles
|
||||
P(n): 2.42 flops/cycle
|
||||
T(n): 235921558.00 cycles
|
||||
P(n): 2.45 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): 1555607186.00 cycles
|
||||
P(n): 2.32 flops/cycle
|
||||
T(n): 1541488178.00 cycles
|
||||
P(n): 2.34 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): 6418988746.00 cycles
|
||||
P(n): 2.25 flops/cycle
|
||||
T(n): 6547730136.00 cycles
|
||||
P(n): 2.20 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): 25996385057.00 cycles
|
||||
P(n): 2.22 flops/cycle
|
||||
T(n): 26624031387.00 cycles
|
||||
P(n): 2.16 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): 183377209437.00 cycles
|
||||
P(n): 1.96 flops/cycle
|
||||
T(n): 187629482331.00 cycles
|
||||
P(n): 1.92 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_8.cpp -o main_inlining_8 -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): 14962674.50 cycles
|
||||
P(n): 2.46 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): 57946813.00 cycles
|
||||
P(n): 2.51 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): 232750706.00 cycles
|
||||
P(n): 2.49 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): 1534213485.00 cycles
|
||||
P(n): 2.35 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): 6376421798.00 cycles
|
||||
P(n): 2.26 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): 26048973254.00 cycles
|
||||
P(n): 2.21 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): 183555765943.00 cycles
|
||||
P(n): 1.96 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_8.cpp -o main_inlining_8 -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): 14940687.25 cycles
|
||||
P(n): 2.46 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): 57942023.00 cycles
|
||||
P(n): 2.51 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): 232072320.00 cycles
|
||||
P(n): 2.49 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): 1533490796.00 cycles
|
||||
P(n): 2.35 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): 6371340222.00 cycles
|
||||
P(n): 2.26 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): 25947418004.00 cycles
|
||||
P(n): 2.22 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): 183383408820.00 cycles
|
||||
P(n): 1.96 flops/cycle
|
||||
|
||||
Reference in New Issue
Block a user