x86 measurements

measurements/variant_baseline/x86/1.log

@@ -1,41 +1,58 @@
-rm -f main_* sizes run_tests *.o *.s
-/usr/bin/g++ -O3 -march=native -std=c++23 -Wall -Wextra -flto -DFLOPCOUNT=0 -DRANDOM_SEED=0 -DROOFLINE=0 -DBENCHMARK=1 main.cpp ./variants/variant_baseline.cpp -o main_baseline
-=== N_P=50 N_ITER=1000 ===
-W(n) per iteration: 184500.00 flops
+rm -f main_*  run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
+/usr/bin/g++ main.cpp ./variants/variant_baseline.cpp -o main_baseline -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): 28.33 flops/byte
-W(n): 184500000.00 flops
-T(n): 149741420.00 cycles
-P(n): 1.23 flops/cycle
+I(n): 28.21 flops/byte
+W(n): 36740000.00 flops
+T(n): 27382860.00 cycles
+P(n): 1.34 flops/cycle
 
-=== N_P=100 N_ITER=1000 ===
-W(n) per iteration: 729000.00 flops
+=== N_P=100 N_ITER=200 ===
+W(n) per iteration: 727400.00 flops
 Q(n) per iteration: 12912 bytes
-I(n): 56.46 flops/byte
-W(n): 729000000.00 flops
-T(n): 590173880.00 cycles
+I(n): 56.34 flops/byte
+W(n): 145480000.00 flops
+T(n): 109792660.00 cycles
+P(n): 1.33 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): 434377780.00 cycles
+P(n): 1.33 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): 2801754240.00 cycles
+P(n): 1.29 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): 11397333020.00 cycles
+P(n): 1.26 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): 46474012140.00 cycles
 P(n): 1.24 flops/cycle
 
-=== N_P=200 N_ITER=1000 ===
-W(n) per iteration: 2898000.00 flops
-Q(n) per iteration: 25712 bytes
-I(n): 112.71 flops/byte
-W(n): 2898000000.00 flops
-T(n): 2394306640.00 cycles
-P(n): 1.21 flops/cycle
-
-=== N_P=500 N_ITER=1000 ===
-W(n) per iteration: 18045000.00 flops
-Q(n) per iteration: 64112 bytes
-I(n): 281.46 flops/byte
-W(n): 18045000000.00 flops
-T(n): 15758554280.00 cycles
+=== 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): 313398836040.00 cycles
 P(n): 1.15 flops/cycle
 
-=== N_P=1000 N_ITER=1000 ===
-W(n) per iteration: 72090000.00 flops
-Q(n) per iteration: 128112 bytes
-I(n): 562.71 flops/byte
-W(n): 72090000000.00 flops
-T(n): 61911299420.00 cycles
-P(n): 1.16 flops/cycle