- a0ae8d2 Optimize Transposed Convolution for CL backend (Quantized) by Gunes Bayir · 1 year, 7 months ago
- 76335eb Implement the OpenCL kernel to compute the indirect convolution by Gian Marco Iodice · 1 year, 8 months ago
- 5d01681 Implement address precalculation for indirect conv2d - OpenCL by Gian Marco Iodice · 1 year, 8 months ago
- ec0113d Optimize Transposed Convolution for CL backend (FP32/16) by Gunes Bayir · 1 year, 8 months ago
- 3394f3e Rework direct convolution heuristic on OpenCL by Gian Marco Iodice · 1 year, 10 months ago
- 2ffab6d Workaround CL compiler issue on FP16 by Viet-Hoa Do · 1 year, 9 months ago
- ad9a7ed Rework DepthwiseConvolution heuristic on OpenCL by Gian Marco Iodice · 1 year, 10 months ago
- 211a55d Optimize depthwise convolution on OpenCL by Gian Marco Iodice · 1 year, 10 months ago
- c6b7913 Fix direct convolution cases that were failing on Odroid by Adnan AlSinan · 2 years ago
- b1fcefd Implement new Elementwise Dynamic Fusion Operators: Div, Floor by Michalis Spyrou · 2 years, 1 month ago
- 0c68704 Fix performance regression in Winograd Output Transform (OpenCL) by Gian Marco Iodice · 2 years, 1 month ago
- 5e549fa Add CLPool3d Int8 Support by Mohammed Suhail Munshi · 2 years, 4 months ago
- 3751569 Implementation of ClPooling3d by ramelg01 · 2 years, 4 months ago
- bb6877a Improve start-up time for winograd_output_transform_*_nhwc by ramelg01 · 2 years, 5 months ago
- 6863fa0 Remove deprecated remap functions. by Adnan AlSinan · 2 years, 5 months ago
- 2a86a30 Improve start-up time for winograd_input_transform_*_nhwc by ramelg01 · 2 years, 5 months ago
- ba8690b Improve start-up time for winograd_filter_transform_*_nhwc by ramelg01 · 2 years, 5 months ago
- 8d07127 Use #if directive instead of regular condition in CLDirectConv2D by Giorgio Arena · 2 years, 7 months ago
- 78baa48 Improve start-up direct convolution on OpenCL by Gian Marco Iodice · 2 years, 7 months ago
- 56d5512 Use loop unrolling only when the kernel height is less than 5 by Gian Marco Iodice · 2 years, 7 months ago
- e330fb4 Improve start-up timer for ClIm2Col by Giorgio Arena · 2 years, 8 months ago
- e3b1974 Improve start-up time for depthwise convolution by Sheri Zhang · 2 years, 8 months ago
- 17975a6 Improve start-up time for ClScale by Adnan AlSinan · 2 years, 8 months ago
- 51847d5 Implement CLDirectConv3DKernel - uint8/int8 by Giorgio Arena · 2 years, 9 months ago
- 273c28c Fix CLConv3D filelist and comments by Giorgio Arena · 2 years, 9 months ago
- 945ae9e Implement CLDirectConv3D f32/f16 by Giorgio Arena · 2 years, 9 months ago
- 7bc1a77 Optimize ClScaleKernel on NHWC (f32/f16/int8) by Gian Marco Iodice · 2 years, 10 months ago
- 511771f Remove padding from ClScaleKernel by Giorgio Arena · 2 years, 11 months ago
- 7075fe2 Reorganize the kernels into nhwc, nchw and common folders by Adnan AlSinan · 3 years ago