Ahmed moreilp
This commit is contained in:
@@ -5,15 +5,15 @@ W(n) per iteration: 95500.00 flops
|
||||
Q(n) per iteration: 3256 bytes
|
||||
I(n): 29.33 flops/byte
|
||||
W(n): 19100000.00 flops
|
||||
T(n): 8858727.00 cycles
|
||||
P(n): 2.16 flops/cycle
|
||||
T(n): 8798921.00 cycles
|
||||
P(n): 2.17 flops/cycle
|
||||
|
||||
=== N_P=100 N_ITER=200 ===
|
||||
W(n) per iteration: 371000.00 flops
|
||||
Q(n) per iteration: 6456 bytes
|
||||
I(n): 57.47 flops/byte
|
||||
W(n): 74200000.00 flops
|
||||
T(n): 35191192.00 cycles
|
||||
T(n): 35175424.00 cycles
|
||||
P(n): 2.11 flops/cycle
|
||||
|
||||
=== N_P=200 N_ITER=200 ===
|
||||
@@ -21,38 +21,38 @@ W(n) per iteration: 1462000.00 flops
|
||||
Q(n) per iteration: 12856 bytes
|
||||
I(n): 113.72 flops/byte
|
||||
W(n): 292400000.00 flops
|
||||
T(n): 136348512.00 cycles
|
||||
P(n): 2.14 flops/cycle
|
||||
T(n): 135894384.00 cycles
|
||||
P(n): 2.15 flops/cycle
|
||||
|
||||
=== N_P=500 N_ITER=200 ===
|
||||
W(n) per iteration: 9055000.00 flops
|
||||
Q(n) per iteration: 32056 bytes
|
||||
I(n): 282.47 flops/byte
|
||||
W(n): 1811000064.00 flops
|
||||
T(n): 881212544.00 cycles
|
||||
P(n): 2.06 flops/cycle
|
||||
T(n): 889473408.00 cycles
|
||||
P(n): 2.04 flops/cycle
|
||||
|
||||
=== N_P=1000 N_ITER=200 ===
|
||||
W(n) per iteration: 36110000.00 flops
|
||||
Q(n) per iteration: 64056 bytes
|
||||
I(n): 563.73 flops/byte
|
||||
W(n): 7222000128.00 flops
|
||||
T(n): 4358949376.00 cycles
|
||||
P(n): 1.66 flops/cycle
|
||||
T(n): 4264077312.00 cycles
|
||||
P(n): 1.69 flops/cycle
|
||||
|
||||
=== N_P=2000 N_ITER=200 ===
|
||||
W(n) per iteration: 144220000.00 flops
|
||||
Q(n) per iteration: 128056 bytes
|
||||
I(n): 1126.23 flops/byte
|
||||
W(n): 28843999232.00 flops
|
||||
T(n): 19275378688.00 cycles
|
||||
P(n): 1.50 flops/cycle
|
||||
T(n): 19037489152.00 cycles
|
||||
P(n): 1.52 flops/cycle
|
||||
|
||||
=== N_P=5000 N_ITER=200 ===
|
||||
W(n) per iteration: 900550016.00 flops
|
||||
Q(n) per iteration: 320056 bytes
|
||||
I(n): 2813.73 flops/byte
|
||||
W(n): 180110000128.00 flops
|
||||
T(n): 158142201856.00 cycles
|
||||
P(n): 1.14 flops/cycle
|
||||
T(n): 156173221888.00 cycles
|
||||
P(n): 1.15 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_symmetry.cpp ./variants/variant_float_inlining_SoA_symmetry_ILP_8.cpp -o main_float_inlining_SoA_symmetry_ILP_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: 95500.00 flops
|
||||
Q(n) per iteration: 3256 bytes
|
||||
I(n): 29.33 flops/byte
|
||||
W(n): 19100000.00 flops
|
||||
T(n): 8862931.00 cycles
|
||||
P(n): 2.16 flops/cycle
|
||||
|
||||
=== N_P=100 N_ITER=200 ===
|
||||
W(n) per iteration: 371000.00 flops
|
||||
Q(n) per iteration: 6456 bytes
|
||||
I(n): 57.47 flops/byte
|
||||
W(n): 74200000.00 flops
|
||||
T(n): 35686564.00 cycles
|
||||
P(n): 2.08 flops/cycle
|
||||
|
||||
=== N_P=200 N_ITER=200 ===
|
||||
W(n) per iteration: 1462000.00 flops
|
||||
Q(n) per iteration: 12856 bytes
|
||||
I(n): 113.72 flops/byte
|
||||
W(n): 292400000.00 flops
|
||||
T(n): 137157216.00 cycles
|
||||
P(n): 2.13 flops/cycle
|
||||
|
||||
=== N_P=500 N_ITER=200 ===
|
||||
W(n) per iteration: 9055000.00 flops
|
||||
Q(n) per iteration: 32056 bytes
|
||||
I(n): 282.47 flops/byte
|
||||
W(n): 1811000064.00 flops
|
||||
T(n): 887476736.00 cycles
|
||||
P(n): 2.04 flops/cycle
|
||||
|
||||
=== N_P=1000 N_ITER=200 ===
|
||||
W(n) per iteration: 36110000.00 flops
|
||||
Q(n) per iteration: 64056 bytes
|
||||
I(n): 563.73 flops/byte
|
||||
W(n): 7222000128.00 flops
|
||||
T(n): 4329847808.00 cycles
|
||||
P(n): 1.67 flops/cycle
|
||||
|
||||
=== N_P=2000 N_ITER=200 ===
|
||||
W(n) per iteration: 144220000.00 flops
|
||||
Q(n) per iteration: 128056 bytes
|
||||
I(n): 1126.23 flops/byte
|
||||
W(n): 28843999232.00 flops
|
||||
T(n): 19318816768.00 cycles
|
||||
P(n): 1.49 flops/cycle
|
||||
|
||||
=== N_P=5000 N_ITER=200 ===
|
||||
W(n) per iteration: 900550016.00 flops
|
||||
Q(n) per iteration: 320056 bytes
|
||||
I(n): 2813.73 flops/byte
|
||||
W(n): 180110000128.00 flops
|
||||
T(n): 157832298496.00 cycles
|
||||
P(n): 1.14 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_symmetry.cpp ./variants/variant_float_inlining_SoA_symmetry_ILP_8.cpp -o main_float_inlining_SoA_symmetry_ILP_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: 95500.00 flops
|
||||
Q(n) per iteration: 3256 bytes
|
||||
I(n): 29.33 flops/byte
|
||||
W(n): 19100000.00 flops
|
||||
T(n): 8850936.00 cycles
|
||||
P(n): 2.16 flops/cycle
|
||||
|
||||
=== N_P=100 N_ITER=200 ===
|
||||
W(n) per iteration: 371000.00 flops
|
||||
Q(n) per iteration: 6456 bytes
|
||||
I(n): 57.47 flops/byte
|
||||
W(n): 74200000.00 flops
|
||||
T(n): 35237568.00 cycles
|
||||
P(n): 2.11 flops/cycle
|
||||
|
||||
=== N_P=200 N_ITER=200 ===
|
||||
W(n) per iteration: 1462000.00 flops
|
||||
Q(n) per iteration: 12856 bytes
|
||||
I(n): 113.72 flops/byte
|
||||
W(n): 292400000.00 flops
|
||||
T(n): 137259488.00 cycles
|
||||
P(n): 2.13 flops/cycle
|
||||
|
||||
=== N_P=500 N_ITER=200 ===
|
||||
W(n) per iteration: 9055000.00 flops
|
||||
Q(n) per iteration: 32056 bytes
|
||||
I(n): 282.47 flops/byte
|
||||
W(n): 1811000064.00 flops
|
||||
T(n): 894708160.00 cycles
|
||||
P(n): 2.02 flops/cycle
|
||||
|
||||
=== N_P=1000 N_ITER=200 ===
|
||||
W(n) per iteration: 36110000.00 flops
|
||||
Q(n) per iteration: 64056 bytes
|
||||
I(n): 563.73 flops/byte
|
||||
W(n): 7222000128.00 flops
|
||||
T(n): 4392257536.00 cycles
|
||||
P(n): 1.64 flops/cycle
|
||||
|
||||
=== N_P=2000 N_ITER=200 ===
|
||||
W(n) per iteration: 144220000.00 flops
|
||||
Q(n) per iteration: 128056 bytes
|
||||
I(n): 1126.23 flops/byte
|
||||
W(n): 28843999232.00 flops
|
||||
T(n): 19428847616.00 cycles
|
||||
P(n): 1.48 flops/cycle
|
||||
|
||||
=== N_P=5000 N_ITER=200 ===
|
||||
W(n) per iteration: 900550016.00 flops
|
||||
Q(n) per iteration: 320056 bytes
|
||||
I(n): 2813.73 flops/byte
|
||||
W(n): 180110000128.00 flops
|
||||
T(n): 157138927616.00 cycles
|
||||
P(n): 1.15 flops/cycle
|
||||
|
||||
Reference in New Issue
Block a user