Coup de grâce

This commit is contained in:
[Quy Anh] «Elliot» Nguyen
2026-06-19 12:06:29 +02:00
parent 22052263c9
commit cd94ec06eb
5 changed files with 165 additions and 200 deletions
+7 -7
View File
@@ -268,13 +268,13 @@ variant_inlining_7_symmetry_2_ilp_2,500,200,3461000000,64112.0,269.92,2800723726
variant_inlining_7_symmetry_2_ilp_2,1000,200,13822000000,128112.0,539.45,11627472146.7,1.189
variant_inlining_7_symmetry_2_ilp_2,2000,200,55244000000,256112.0,1078.51,47722643580.0,1.158
variant_inlining_7_symmetry_2_ilp_2,5000,200,345110000000,640112.0,2695.7,316224530286.7,1.091
variant_inlining_8,50,200,36750000,6512.0,28.22,25967831.7,1.415
variant_inlining_8,100,200,145500000,12912.0,56.34,102344446.7,1.422
variant_inlining_8,200,200,579000000,25712.0,112.59,412337820.0,1.404
variant_inlining_8,500,200,3607500000,64112.0,281.34,2712489206.7,1.33
variant_inlining_8,1000,200,14415000000,128112.0,562.59,10911941346.7,1.321
variant_inlining_8,2000,200,57630000000,256112.0,1125.09,44617296533.3,1.292
variant_inlining_8,5000,200,360075000000,640112.0,2812.59,302676303926.7,1.19
variant_inlining_8,50,200,36750000,6512.0,28.22,25930980.8,1.417
variant_inlining_8,100,200,145500000,12912.0,56.34,102418540.0,1.421
variant_inlining_8,200,200,579000000,25712.0,112.59,412514933.3,1.404
variant_inlining_8,500,200,3607500000,64112.0,281.34,2688542773.3,1.342
variant_inlining_8,1000,200,14415000000,128112.0,562.59,10866744550.0,1.327
variant_inlining_8,2000,200,57630000000,256112.0,1125.09,44404254580.0,1.298
variant_inlining_8,5000,200,360075000000,640112.0,2812.59,301663825136.7,1.194
variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt,50,200,42720000,6512.0,32.8,8373508.8,5.102
variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt,100,200,155520000,12912.0,60.22,28637320.0,5.431
variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt,200,200,591360000,25712.0,115.0,104580140.0,5.655
1 variant n n_iter W Q_per_iter I cycles flops_per_cycle
268 variant_inlining_7_symmetry_2_ilp_2 1000 200 13822000000 128112.0 539.45 11627472146.7 1.189
269 variant_inlining_7_symmetry_2_ilp_2 2000 200 55244000000 256112.0 1078.51 47722643580.0 1.158
270 variant_inlining_7_symmetry_2_ilp_2 5000 200 345110000000 640112.0 2695.7 316224530286.7 1.091
271 variant_inlining_8 50 200 36750000 6512.0 28.22 25967831.7 25930980.8 1.415 1.417
272 variant_inlining_8 100 200 145500000 12912.0 56.34 102344446.7 102418540.0 1.422 1.421
273 variant_inlining_8 200 200 579000000 25712.0 112.59 412337820.0 412514933.3 1.404
274 variant_inlining_8 500 200 3607500000 64112.0 281.34 2712489206.7 2688542773.3 1.33 1.342
275 variant_inlining_8 1000 200 14415000000 128112.0 562.59 10911941346.7 10866744550.0 1.321 1.327
276 variant_inlining_8 2000 200 57630000000 256112.0 1125.09 44617296533.3 44404254580.0 1.292 1.298
277 variant_inlining_8 5000 200 360075000000 640112.0 2812.59 302676303926.7 301663825136.7 1.19 1.194
278 variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt 50 200 42720000 6512.0 32.8 8373508.8 5.102
279 variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt 100 200 155520000 12912.0 60.22 28637320.0 5.431
280 variant_inlining_8_SoA_AVX512_polyexp_fastinvsqrt 200 200 591360000 25712.0 115.0 104580140.0 5.655