4 commits

Author	SHA1	Message	Date
Xu Xing	d73131cf0f	[js/webgpu] Use DataType as uniform cpu type (#19281) ... This saves turning data type to string by tensorDataTypeEnumToString.	2024-01-30 21:05:08 -08:00
Xu Xing	624b4e2063	[js/webgpu] Remove enableShapesUniforms (#19279)	2024-01-29 17:49:06 -08:00
Jiajie Hu	acba63c36a	[js/webgpu] Change A/sqrt(B) to A*inverseSqrt(B) in normalization ops (#19101) ... ### Description Change `A / sqrt(B)` to `A * inverseSqrt(B)` in BatchNormalization, InstanceNormalization, LayerNormalization and SkipLayerNormalization. ### Motivation and Context For the same reason as the existence of the `inverseSqrt` built-in in WebGPU spec.	2024-01-12 00:08:16 -08:00
Jiajia Qin	64dacc2892	[js/webgpu] Add BatchNormalization Op (#18468) ... ### Description This PR adds `BatchNormalization` with `float` support. Some Todos: 1. all inputs don't have same data type. For example, x/y is float16, but bias/scale is float32 or double. 2. training mode support. We see many models are using `BatchNormalization` ops. However, due to the missing in jsep, all of them run on cpu, which result very poor performance. With this PR's support, densenet-9 model becomes 20.29 ms from 250.69 ms.	2023-11-22 15:58:06 -08:00