CPU Tasks
LoadModel       1.49776 seconds
RunComplete     110.474 seconds
Run     110.407 seconds
Callbacks       14.0412 milliseconds, 44 calls, 319.118 microseconds average
Spectrogram     201.605 milliseconds, 41 calls, 4.91719 milliseconds average
Sample  65.5117 milliseconds, 527 calls, 124.311 microseconds average
Encode  64.8806 seconds, 9 calls, 7.20896 seconds average
Decode  45.5097 seconds, 9 calls, 5.05663 seconds average
DecodeStep      45.4439 seconds, 527 calls, 86.2313 milliseconds average
    GPU Tasks
LoadModel       951.086 milliseconds
Run     110.123 seconds
Encode  65.7998 seconds, 9 calls, 7.31109 seconds average
EncodeLayer     56.2581 seconds, 288 calls, 195.341 milliseconds average
Decode  44.3232 seconds, 9 calls, 4.9248 seconds average
DecodeStep      44.3227 seconds, 527 calls, 84.1039 milliseconds average
DecodeLayer     41.6477 seconds, 16864 calls, 2.46962 milliseconds average
    Compute Shaders
mulMatTiledEx   51.4882 seconds, 2880 calls, 17.8778 milliseconds average
mulMatByRowTiled        17.0626 seconds, 166278 calls, 102.615 microseconds average
mulMatTiled     15.2984 seconds, 3465 calls, 4.41513 milliseconds average
mulMatByRowTiledEx      9.04106 seconds, 33152 calls, 272.715 microseconds average
softMaxFixed    3.04176 seconds, 17152 calls, 177.342 microseconds average
norm    1.98157 seconds, 51704 calls, 38.3254 microseconds average
convolutionMain2Fixed   1.8145 seconds, 9 calls, 201.611 milliseconds average
matReshapePanels        1.526 seconds, 1737 calls, 878.526 microseconds average
addRepeatGelu   1.24631 seconds, 17170 calls, 72.5866 microseconds average
scaleInPlace    1.23743 seconds, 17152 calls, 72.1448 microseconds average
copyConvert     1.02044 seconds, 34880 calls, 29.2557 microseconds average
fmaRepeat1      993.664 milliseconds, 51704 calls, 19.2183 microseconds average
addRepeatEx     953.85 milliseconds, 51168 calls, 18.6415 microseconds average
copyTranspose   705.073 milliseconds, 34304 calls, 20.5537 microseconds average
addRepeat       581.089 milliseconds, 17728 calls, 32.778 microseconds average
addRepeatScale  553.89 milliseconds, 33728 calls, 16.4222 microseconds average
softMaxLong     387.949 milliseconds, 527 calls, 736.147 microseconds average
convolutionMain 363.351 milliseconds, 9 calls, 40.3723 milliseconds average
softMax 242.956 milliseconds, 16864 calls, 14.4068 microseconds average
diagMaskInf     179.046 milliseconds, 16864 calls, 10.617 microseconds average
convolutionPrep1        45.2096 milliseconds, 18 calls, 2.51164 milliseconds average
convolutionPrep2        28.6853 milliseconds, 18 calls, 1.59363 milliseconds average
add     8.1107 milliseconds, 9 calls, 901.189 microseconds average
addRows 1.542 milliseconds, 527 calls, 2.926 microseconds average
    Memory Usage
Model   892.591 KB RAM, 2.8815 GB VRAM
Context 92.2612 MB RAM, 1.19934 GB VRAM
Total   93.1329 MB RAM, 4.08084 GB VRAM