Merge branch 'elliot/flop-count' into 'main'

Flop Count Calculations + x86 Measurements + c13 Fix

See merge request course-asl-fastcode26/team70!60

measurements/variant_inlining_7_symmetry_2_ilp_1/x86/2.log

@@ -0,0 +1,58 @@
+rm -f main_*  run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
+/usr/bin/g++ main-symmetry.cpp ./variants/variant_inlining_7_symmetry_2_ilp_1.cpp -o main_inlining_7_symmetry_2_ilp_1 -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: 6512 bytes
+I(n): 14.67 flops/byte
+W(n): 19100000.00 flops
+T(n): 26434750.00 cycles
+P(n): 0.72 flops/cycle
+
+=== N_P=100 N_ITER=200 ===
+W(n) per iteration: 371000.00 flops
+Q(n) per iteration: 12912 bytes
+I(n): 28.73 flops/byte
+W(n): 74200000.00 flops
+T(n): 103076140.00 cycles
+P(n): 0.72 flops/cycle
+
+=== N_P=200 N_ITER=200 ===
+W(n) per iteration: 1462000.00 flops
+Q(n) per iteration: 25712 bytes
+I(n): 56.86 flops/byte
+W(n): 292400000.00 flops
+T(n): 414752620.00 cycles
+P(n): 0.70 flops/cycle
+
+=== N_P=500 N_ITER=200 ===
+W(n) per iteration: 9055000.00 flops
+Q(n) per iteration: 64112 bytes
+I(n): 141.24 flops/byte
+W(n): 1811000000.00 flops
+T(n): 2727126060.00 cycles
+P(n): 0.66 flops/cycle
+
+=== N_P=1000 N_ITER=200 ===
+W(n) per iteration: 36110000.00 flops
+Q(n) per iteration: 128112 bytes
+I(n): 281.86 flops/byte
+W(n): 7222000000.00 flops
+T(n): 11087200940.00 cycles
+P(n): 0.65 flops/cycle
+
+=== N_P=2000 N_ITER=200 ===
+W(n) per iteration: 144220000.00 flops
+Q(n) per iteration: 256112 bytes
+I(n): 563.11 flops/byte
+W(n): 28844000000.00 flops
+T(n): 45051280280.00 cycles
+P(n): 0.64 flops/cycle
+
+=== N_P=5000 N_ITER=200 ===
+W(n) per iteration: 900550000.00 flops
+Q(n) per iteration: 640112 bytes
+I(n): 1406.86 flops/byte
+W(n): 180110000000.00 flops
+T(n): 210209411220.00 cycles
+P(n): 0.86 flops/cycle
+

measurements/variant_inlining_7_symmetry_2_ilp_1/x86/3.log

@@ -0,0 +1,58 @@
+rm -f main_*  run_tests *.o *.s variants/*.s variants/*.o headers/*.s headers/*.o
+/usr/bin/g++ main-symmetry.cpp ./variants/variant_inlining_7_symmetry_2_ilp_1.cpp -o main_inlining_7_symmetry_2_ilp_1 -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: 6512 bytes
+I(n): 14.67 flops/byte
+W(n): 19100000.00 flops
+T(n): 26387870.00 cycles
+P(n): 0.72 flops/cycle
+
+=== N_P=100 N_ITER=200 ===
+W(n) per iteration: 371000.00 flops
+Q(n) per iteration: 12912 bytes
+I(n): 28.73 flops/byte
+W(n): 74200000.00 flops
+T(n): 102030060.00 cycles
+P(n): 0.73 flops/cycle
+
+=== N_P=200 N_ITER=200 ===
+W(n) per iteration: 1462000.00 flops
+Q(n) per iteration: 25712 bytes
+I(n): 56.86 flops/byte
+W(n): 292400000.00 flops
+T(n): 414172500.00 cycles
+P(n): 0.71 flops/cycle
+
+=== N_P=500 N_ITER=200 ===
+W(n) per iteration: 9055000.00 flops
+Q(n) per iteration: 64112 bytes
+I(n): 141.24 flops/byte
+W(n): 1811000000.00 flops
+T(n): 2720855140.00 cycles
+P(n): 0.67 flops/cycle
+
+=== N_P=1000 N_ITER=200 ===
+W(n) per iteration: 36110000.00 flops
+Q(n) per iteration: 128112 bytes
+I(n): 281.86 flops/byte
+W(n): 7222000000.00 flops
+T(n): 11113087680.00 cycles
+P(n): 0.65 flops/cycle
+
+=== N_P=2000 N_ITER=200 ===
+W(n) per iteration: 144220000.00 flops
+Q(n) per iteration: 256112 bytes
+I(n): 563.11 flops/byte
+W(n): 28844000000.00 flops
+T(n): 44960698300.00 cycles
+P(n): 0.64 flops/cycle
+
+=== N_P=5000 N_ITER=200 ===
+W(n) per iteration: 900550000.00 flops
+Q(n) per iteration: 640112 bytes
+I(n): 1406.86 flops/byte
+W(n): 180110000000.00 flops
+T(n): 208987223120.00 cycles
+P(n): 0.86 flops/cycle
+