diff options
| author | Konstantin <const@const.me> | 2023-01-24 18:29:47 +0100 |
|---|---|---|
| committer | Konstantin <const@const.me> | 2023-01-24 18:29:47 +0100 |
| commit | 993cfa55dcae112822a2e9681056e49697d71338 (patch) | |
| tree | 184746cafd2a650d8a00288cfeb9c7758dc6603a /SampleClips/jfk-medium-vega7.txt | |
| parent | 3cdb0f3cc721a0aee7330f4167e3904bdd5b4e18 (diff) | |
Performance results for version 1.5
Diffstat (limited to 'SampleClips/jfk-medium-vega7.txt')
| -rw-r--r-- | SampleClips/jfk-medium-vega7.txt | 83 |
1 files changed, 42 insertions, 41 deletions
diff --git a/SampleClips/jfk-medium-vega7.txt b/SampleClips/jfk-medium-vega7.txt index 0be45d3..7753030 100644 --- a/SampleClips/jfk-medium-vega7.txt +++ b/SampleClips/jfk-medium-vega7.txt @@ -1,46 +1,47 @@ CPU Tasks -LoadModel 1.44983 seconds -RunComplete 9.9723 seconds -Run 9.8953 seconds -Callbacks 876.5 microseconds, 4 calls, 219.125 microseconds average -Spectrogram 100.602 milliseconds, 3 calls, 33.5339 milliseconds average -Sample 8.2281 milliseconds, 28 calls, 293.861 microseconds average -Encode 8.28685 seconds -Decode 1.60728 seconds -DecodeStep 1.599 seconds, 28 calls, 57.1073 milliseconds average +LoadModel 1.79203 seconds +RunComplete 8.79853 seconds +Run 8.71884 seconds +Callbacks 626.8 microseconds, 4 calls, 156.7 microseconds average +Spectrogram 17.3373 milliseconds, 3 calls, 5.7791 milliseconds average +Sample 5.449 milliseconds, 28 calls, 194.607 microseconds average +Encode 7.29966 seconds +Decode 1.41824 seconds +DecodeStep 1.41276 seconds, 28 calls, 50.4557 milliseconds average GPU Tasks -LoadModel 751.497 milliseconds -Run 9.73531 seconds -Encode 8.28303 seconds -EncodeLayer 7.19651 seconds, 24 calls, 299.855 milliseconds average -Decode 1.45228 seconds -DecodeStep 1.45225 seconds, 28 calls, 51.866 milliseconds average -DecodeLayer 1.31372 seconds, 672 calls, 1.95494 milliseconds average +LoadModel 930.123 milliseconds +Run 8.64946 seconds +Encode 7.34021 seconds +EncodeLayer 6.40759 seconds, 24 calls, 266.983 milliseconds average +Decode 1.30925 seconds +DecodeStep 1.30389 seconds, 28 calls, 46.5676 milliseconds average +DecodeLayer 1.19422 seconds, 672 calls, 1.77711 milliseconds average Compute Shaders -mulMatTiledEx 5.73474 seconds, 240 calls, 23.8947 milliseconds average -mulMatTiled 1.59442 seconds, 289 calls, 5.51703 milliseconds average -mulMatByRowTiled 708.039 milliseconds, 6507 calls, 108.812 microseconds average -mulMatByRowTiledEx 292.797 milliseconds, 1296 calls, 225.923 microseconds average -convolutionMain2Fixed 267.762 milliseconds -softMaxFixed 252.702 milliseconds, 696 calls, 363.078 microseconds average -addRepeat 122.774 milliseconds, 2808 calls, 43.7229 microseconds average -matReshapePanels 116.085 milliseconds, 145 calls, 800.583 microseconds average -convolutionMain 100.111 milliseconds -addRepeatGelu 78.6895 milliseconds, 698 calls, 112.736 microseconds average -normFixed 64.6521 milliseconds, 2093 calls, 30.8897 microseconds average -scaleInPlace 64.0629 milliseconds, 696 calls, 92.0444 microseconds average -copyConvert 62.7305 milliseconds, 1440 calls, 43.5628 microseconds average -softMax 50.9006 milliseconds, 700 calls, 72.7151 microseconds average -fmaRepeat1 49.6347 milliseconds, 2093 calls, 23.7146 microseconds average -copyTranspose 44.2248 milliseconds, 1392 calls, 31.7707 microseconds average -addInPlace 44.1766 milliseconds, 1392 calls, 31.7361 microseconds average -addRepeatScale 31.3737 milliseconds, 1344 calls, 23.3435 microseconds average -add 19.0564 milliseconds, 673 calls, 28.3156 microseconds average -convolutionPrep1 8.494 milliseconds, 2 calls, 4.247 milliseconds average -diagMaskInf 6.9839 milliseconds, 672 calls, 10.3927 microseconds average -convolutionPrep2 6.0876 milliseconds, 2 calls, 3.0438 milliseconds average -addRows 72 microseconds, 28 calls, 2.57143 microseconds average +mulMatTiledEx 4.91773 seconds, 240 calls, 20.4906 milliseconds average +mulMatTiled 1.47531 seconds, 289 calls, 5.10489 milliseconds average +mulMatByRowTiled 627.1 milliseconds, 6507 calls, 96.3731 microseconds average +softMaxFixed 268.285 milliseconds, 696 calls, 385.467 microseconds average +convolutionMain2Fixed 266.261 milliseconds +mulMatByRowTiledEx 241.609 milliseconds, 1296 calls, 186.427 microseconds average +matReshapePanels 156.683 milliseconds, 145 calls, 1.08057 milliseconds average +convolutionMain 102.091 milliseconds +copyConvert 77.6113 milliseconds, 1440 calls, 53.8967 microseconds average +addRepeatGelu 71.5118 milliseconds, 698 calls, 102.452 microseconds average +copyTranspose 63.3929 milliseconds, 1392 calls, 45.5409 microseconds average +normFixed 60.9615 milliseconds, 2093 calls, 29.1264 microseconds average +scaleInPlace 59.9341 milliseconds, 696 calls, 86.1122 microseconds average +fmaRepeat1 56.3539 milliseconds, 2093 calls, 26.9249 microseconds average +addRepeatEx 51.8785 milliseconds, 2064 calls, 25.1349 microseconds average +addRepeat 48.1192 milliseconds, 744 calls, 64.6763 microseconds average +softMaxLong 28.3411 milliseconds, 28 calls, 1.01218 milliseconds average +addRepeatScale 21.3646 milliseconds, 1344 calls, 15.8963 microseconds average +softMax 10.198 milliseconds, 672 calls, 15.1756 microseconds average +convolutionPrep1 9.1072 milliseconds, 2 calls, 4.5536 milliseconds average +diagMaskInf 8.3764 milliseconds, 672 calls, 12.4649 microseconds average +convolutionPrep2 7.4623 milliseconds, 2 calls, 3.73115 milliseconds average +add 2.3886 milliseconds +addRows 97.6 microseconds, 28 calls, 3.48571 microseconds average Memory Usage Model 877.966 KB RAM, 1.42785 GB VRAM -Context 1.9836 MB RAM, 771.354 MB VRAM -Total 2.84099 MB RAM, 2.18113 GB VRAM +Context 1.9831 MB RAM, 771.235 MB VRAM +Total 2.84049 MB RAM, 2.18101 GB VRAM |
