Ahmed moreilp

This commit is contained in:
Ahmed Kallala
2026-06-17 03:01:19 +02:00
parent 42b3c7097e
commit 816626664c
167 changed files with 6415 additions and 269 deletions
+12 -12
View File
@@ -5,15 +5,15 @@ W(n) per iteration: 183700.00 flops
Q(n) per iteration: 3256 bytes
I(n): 56.42 flops/byte
W(n): 36740000.00 flops
T(n): 10775829.00 cycles
P(n): 3.41 flops/cycle
T(n): 10744000.00 cycles
P(n): 3.42 flops/cycle
=== N_P=100 N_ITER=200 ===
W(n) per iteration: 727400.00 flops
Q(n) per iteration: 6456 bytes
I(n): 112.67 flops/byte
W(n): 145480000.00 flops
T(n): 47963000.00 cycles
T(n): 47936504.00 cycles
P(n): 3.03 flops/cycle
=== N_P=200 N_ITER=200 ===
@@ -21,7 +21,7 @@ W(n) per iteration: 2894800.00 flops
Q(n) per iteration: 12856 bytes
I(n): 225.17 flops/byte
W(n): 578960000.00 flops
T(n): 190335120.00 cycles
T(n): 190173216.00 cycles
P(n): 3.04 flops/cycle
=== N_P=500 N_ITER=200 ===
@@ -29,30 +29,30 @@ W(n) per iteration: 18037000.00 flops
Q(n) per iteration: 32056 bytes
I(n): 562.67 flops/byte
W(n): 3607399936.00 flops
T(n): 1412006400.00 cycles
P(n): 2.55 flops/cycle
T(n): 1404110336.00 cycles
P(n): 2.57 flops/cycle
=== N_P=1000 N_ITER=200 ===
W(n) per iteration: 72074000.00 flops
Q(n) per iteration: 64056 bytes
I(n): 1125.17 flops/byte
W(n): 14414799872.00 flops
T(n): 6137234944.00 cycles
P(n): 2.35 flops/cycle
T(n): 6120075776.00 cycles
P(n): 2.36 flops/cycle
=== N_P=2000 N_ITER=200 ===
W(n) per iteration: 288148000.00 flops
Q(n) per iteration: 128056 bytes
I(n): 2250.17 flops/byte
W(n): 57629601792.00 flops
T(n): 27256184832.00 cycles
P(n): 2.11 flops/cycle
T(n): 27074254848.00 cycles
P(n): 2.13 flops/cycle
=== N_P=5000 N_ITER=200 ===
W(n) per iteration: 1800369920.00 flops
Q(n) per iteration: 320056 bytes
I(n): 5625.17 flops/byte
W(n): 360073986048.00 flops
T(n): 194280062976.00 cycles
P(n): 1.85 flops/cycle
T(n): 192850231296.00 cycles
P(n): 1.87 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.cpp ./variants/variant_float_inlining.cpp -o main_float_inlining -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: 3256 bytes
I(n): 56.42 flops/byte
W(n): 36740000.00 flops
T(n): 10826171.00 cycles
P(n): 3.39 flops/cycle
=== N_P=100 N_ITER=200 ===
W(n) per iteration: 727400.00 flops
Q(n) per iteration: 6456 bytes
I(n): 112.67 flops/byte
W(n): 145480000.00 flops
T(n): 48929320.00 cycles
P(n): 2.97 flops/cycle
=== N_P=200 N_ITER=200 ===
W(n) per iteration: 2894800.00 flops
Q(n) per iteration: 12856 bytes
I(n): 225.17 flops/byte
W(n): 578960000.00 flops
T(n): 190686384.00 cycles
P(n): 3.04 flops/cycle
=== N_P=500 N_ITER=200 ===
W(n) per iteration: 18037000.00 flops
Q(n) per iteration: 32056 bytes
I(n): 562.67 flops/byte
W(n): 3607399936.00 flops
T(n): 1427274624.00 cycles
P(n): 2.53 flops/cycle
=== N_P=1000 N_ITER=200 ===
W(n) per iteration: 72074000.00 flops
Q(n) per iteration: 64056 bytes
I(n): 1125.17 flops/byte
W(n): 14414799872.00 flops
T(n): 6172825600.00 cycles
P(n): 2.34 flops/cycle
=== N_P=2000 N_ITER=200 ===
W(n) per iteration: 288148000.00 flops
Q(n) per iteration: 128056 bytes
I(n): 2250.17 flops/byte
W(n): 57629601792.00 flops
T(n): 27468242944.00 cycles
P(n): 2.10 flops/cycle
=== N_P=5000 N_ITER=200 ===
W(n) per iteration: 1800369920.00 flops
Q(n) per iteration: 320056 bytes
I(n): 5625.17 flops/byte
W(n): 360073986048.00 flops
T(n): 192917569536.00 cycles
P(n): 1.87 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.cpp ./variants/variant_float_inlining.cpp -o main_float_inlining -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: 3256 bytes
I(n): 56.42 flops/byte
W(n): 36740000.00 flops
T(n): 10837919.00 cycles
P(n): 3.39 flops/cycle
=== N_P=100 N_ITER=200 ===
W(n) per iteration: 727400.00 flops
Q(n) per iteration: 6456 bytes
I(n): 112.67 flops/byte
W(n): 145480000.00 flops
T(n): 48233604.00 cycles
P(n): 3.02 flops/cycle
=== N_P=200 N_ITER=200 ===
W(n) per iteration: 2894800.00 flops
Q(n) per iteration: 12856 bytes
I(n): 225.17 flops/byte
W(n): 578960000.00 flops
T(n): 191050976.00 cycles
P(n): 3.03 flops/cycle
=== N_P=500 N_ITER=200 ===
W(n) per iteration: 18037000.00 flops
Q(n) per iteration: 32056 bytes
I(n): 562.67 flops/byte
W(n): 3607399936.00 flops
T(n): 1424769280.00 cycles
P(n): 2.53 flops/cycle
=== N_P=1000 N_ITER=200 ===
W(n) per iteration: 72074000.00 flops
Q(n) per iteration: 64056 bytes
I(n): 1125.17 flops/byte
W(n): 14414799872.00 flops
T(n): 6287727104.00 cycles
P(n): 2.29 flops/cycle
=== N_P=2000 N_ITER=200 ===
W(n) per iteration: 288148000.00 flops
Q(n) per iteration: 128056 bytes
I(n): 2250.17 flops/byte
W(n): 57629601792.00 flops
T(n): 27565033472.00 cycles
P(n): 2.09 flops/cycle
=== N_P=5000 N_ITER=200 ===
W(n) per iteration: 1800369920.00 flops
Q(n) per iteration: 320056 bytes
I(n): 5625.17 flops/byte
W(n): 360073986048.00 flops
T(n): 195009839104.00 cycles
P(n): 1.85 flops/cycle