Truong Gia Ngoc
Truong Gia Ngoc
- Add GLU operation with contiguous forward and contiguous backward kernels. - Add driver and gtest for kernels. - MIOpen performs better if: - Input and output tensors are contiguous...
- Add Where operation with contiguous backward kernel. - Add driver and gtest for kernel. - MIOpen performs better if: - Input, other and condition tensors have the same shape...
Add ImageTransform kernels: - `ImageAdjustBrightness` (`ImageAdjustBrightnessFwdContiguous`) - `ImageAdjustHue` (Including `ImageAdjustHue` and `ImageAdjustHuecontiguous`) - `ImageAdjustSaturation` (`RGBToGrayscale`, `RGBToGrayscaleContiguous`, `BlendContiguous`) - `ImageNormalize` (`ImageNormalizeFwdContiguous`) Detailed performance results are [here](https://docs.google.com/spreadsheets/d/1DBncEW_Df_RLpA2gDhEHJna1SCkRc6peRdw4Yh4m4Bs/edit?usp=sharing) Average performance: ### ImageAdjustBrightness ||contiguous|...
- Add Softmax operation with forward and backward kernels. - Add driver and gtest for kernels. ### Average improvement over ROCm | type | fwd | bwd | |:--------:|:----:|:----:| |...
- Add EmbeddingBag operation with forward kernels. - Add driver and gtest for kernels. - MIOpen performs better if: - Mode: Max - Mode: Mean or Sum, when the tensor...
- Add MaskedFill operation with forward and backward kernels. - Add driver and gtest for kernels. - MIOpen performs better if: - Forward: tensors are not all contiguous - Backward:...
- Add Embedding operation with backward kernels. - Add driver and gtest for kernels. - MIOpen performs better if: - Split dimension is 0 - Number of elements in input...
- Add Trace operation with forward and backward kernels. - Add driver and gtest for kernels. ### Average improvement over ROCm | type | fwd | bwd | |----------|------|------| |...
- Add Gather operation with forward kernel. - Add driver and gtest for kernel. ### Average improvement over ROCm | type | bwd | |----------|------| | float16 | 1.39 |...
- Detail of [operation](https://www.tensorflow.org/api_docs/python/tf/gather_nd) (Tensorflow) - Add GatherND operation with backward kernel. - Add driver and gtest for kernels. ### Average improvement over ROCm | type | bwd | |----------|------|...