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): 9210738.56 cycles
|
||||
T(n): 9210543.88 cycles
|
||||
P(n): 3.99 flops/cycle
|
||||
|
||||
=== N_P=100 N_ITER=200 ===
|
||||
@@ -13,7 +13,7 @@ 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): 43525263.50 cycles
|
||||
T(n): 43547204.50 cycles
|
||||
P(n): 3.34 flops/cycle
|
||||
|
||||
=== N_P=200 N_ITER=200 ===
|
||||
@@ -21,38 +21,38 @@ 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): 141467337.00 cycles
|
||||
P(n): 4.09 flops/cycle
|
||||
T(n): 141046620.00 cycles
|
||||
P(n): 4.10 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): 870479259.00 cycles
|
||||
P(n): 4.14 flops/cycle
|
||||
T(n): 864905902.00 cycles
|
||||
P(n): 4.17 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): 3340600189.00 cycles
|
||||
P(n): 4.32 flops/cycle
|
||||
T(n): 3329136423.00 cycles
|
||||
P(n): 4.33 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): 13325615778.00 cycles
|
||||
P(n): 4.32 flops/cycle
|
||||
T(n): 13269871529.00 cycles
|
||||
P(n): 4.34 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): 79881699571.00 cycles
|
||||
P(n): 4.51 flops/cycle
|
||||
T(n): 79388198061.00 cycles
|
||||
P(n): 4.54 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_callsite.cpp -o main_cutoff_callsite -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): 9210916.88 cycles
|
||||
P(n): 3.99 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): 43577670.25 cycles
|
||||
P(n): 3.34 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): 141469488.00 cycles
|
||||
P(n): 4.09 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): 866035209.00 cycles
|
||||
P(n): 4.17 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): 3352259719.00 cycles
|
||||
P(n): 4.30 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): 13395601028.00 cycles
|
||||
P(n): 4.30 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): 79459764831.00 cycles
|
||||
P(n): 4.53 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_callsite.cpp -o main_cutoff_callsite -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): 9221152.25 cycles
|
||||
P(n): 3.98 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): 43576456.75 cycles
|
||||
P(n): 3.34 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): 141908818.00 cycles
|
||||
P(n): 4.08 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): 867445885.00 cycles
|
||||
P(n): 4.16 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): 3340595294.00 cycles
|
||||
P(n): 4.32 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): 13419490551.00 cycles
|
||||
P(n): 4.29 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): 79764962547.00 cycles
|
||||
P(n): 4.51 flops/cycle
|
||||
|
||||
Reference in New Issue
Block a user