Jiajia Qin 25f427466e [js/webgpu] Optimize ConvTranspose (Continue) (#23429) ... BUG #23273 This PR does below optimizations: 1. When output channels is one, 1) calculate the offset before the inchannel loop to reduce indices to offsets calculation, 2) split the `inputChannelsPerGroup` into `inputChannelsPerGroupInt` and `inputChannelsRemainder` parts so that we can always access 4 data for `inputChannelsPerGroupInt`. 2. Use precise initial value to reduce useless loop iterations. Thanks @jiangzhaoming 's suggestion's on this. With this PR, ConvTranspose becomes 3.7s from 8.4s on Intel Meteor Lake. On NV RTX 2000 Ada, it becomes 1.6s from 2.7s.		2025-01-22 08:59:17 -08:00
..
ops	[js/webgpu] Optimize ConvTranspose (Continue) (#23429)	2025-01-22 08:59:17 -08:00
attribute-with-cache-key.ts	[js] change default formatter for JavaScript/TypeScript from clang-format to Prettier (#21728)	2024-08-14 16:51:22 -07:00
gpu-data-manager.ts	[js/webgpu] Destroy staging buffers aggressively during weights uploading (#22726)	2024-11-06 08:55:15 -08:00
op-resolve-rules.ts	[js/webgpu] Add GatherND (#22847)	2024-12-04 09:57:32 -08:00
program-manager.ts	[JS/WebGPU] Creating devices with subgroup features enabled if possible (#21833)	2024-11-07 02:13:40 -08:00
types.ts	[JS/WebGPU] Creating devices with subgroup features enabled if possible (#21833)	2024-11-07 02:13:40 -08:00