Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ComputeLibrary
/
a28aebc5f80630683f50ce934e8584c6b0004beb
/
src
/
core
/
CL
/
kernels
/
CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp
a28aebc
COMPMID-2383: DepthwiseConv use output qinfo
by Pablo Tello
· 5 years ago
4c5469b
COMPMID-2225: Add interface support for new quantized data types.
by Georgios Pinitas
· 5 years ago
6a98a6e
COMPMID-2194: Refactor activation function macro in OpenCL. Change all activation calls to macro from activation_float_helpers.h
by Usama Arif
· 5 years ago
a788c2f
COMPMID-2108: Fuse Activation Layer in CLDepthwiseConvolutionLayer3x3Kernels for F32
by Manuel Bottini
· 5 years ago
e73686a
COMPMID-2047: Add support for dilation in CLDepthwiseConvolution.
by Usama Arif
· 5 years ago
da0e513
COMPMID-1882: Improve memory coalescence when reshaping the weights for CLDepthwiseConvolution
by Pablo Tello
· 5 years ago
4710436
COMPMID-1882: Improve memory coalescence when reshaping the weights for CLDepthwiseConvolution
by Pablo Tello
· 5 years ago
9197c96
COMPMID-1995: Fix output quantization CLDeptwiseConv3x3 when activation is fused
by Isabella Gottardi
· 5 years ago
83e3e75
COMPMID-1776: Revert QuantizeDownStage to use fixed-point
by Georgios Pinitas
· 6 years ago
4b90865
COMPMID-1413 - Improve the performance of GEMMLowp with 8 bit dot product on OpenCL
by Gian Marco Iodice
· 6 years ago
60e9825
COMPMID-1451: Fuse activation in DepthwiseConvolution.
by Georgios Pinitas
· 6 years ago
e55b40a
COMPMID-1581: Collapse windows
by Georgios Pinitas
· 6 years ago
b6eb353
COMPMID-1478: Stop relying on static default OpenCL objects in cl2.hpp
by Anthony Barbier
· 6 years ago
eff8d95
COMPMID-1316 Using 8 bit dot product instruction in CLDepthWiseConvolution with QASYMM8
by Giorgio Arena
· 6 years ago
d304e80
COMPMID-1349: Add support for QASYMM8 LOGISTIC activation in CLActivationLayer
by Michele Di Giorgio
· 6 years ago
fa23f11
COMPMID-1246 CLDepthwiseConvolution QASYMM8 NHWC kernel cleanup
by Giorgio Arena
· 6 years ago
d4b2c9f
COMPMID-1270: Allow having weights with 1 IFM and multiple OFMs in CLDepthwiseConvolution3x3NCHW
by Michele Di Giorgio
· 6 years ago
f1f4906
COMPMID-655 : Check FP16 is supported by the GPU
by Vidhya Sudhan Loganathan
· 6 years ago
ad0c738
COMPMID-1068 Create validate method to CLDepthWiseConvolution
by Giorgio Arena
· 6 years ago
7657224
COMPMID-926 Add depth multiplier support to NEON/CL/GLES depthwise convolution
by Giorgio Arena
· 6 years ago
dfca60b
COMPMID-811 Add NHWC data format support for CL depthwise convolution QASYMM8
by Giorgio Arena
· 6 years ago
[Renamed (93%) from src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3Kernel.cpp]
56e8e86
COMPMID-1031: Use LWS hints for G51, G51BIG, G51LIT, and TNOX
by Sam Laynton
· 6 years ago
3ebef32
COMPMID-949: Optimizing CLDepthwiseConvolution3x3Kernel for FP16
by Michele Di Giorgio
· 6 years ago
99ac60b
COMPMID-853 Fuse CL DepthwiseConvolution with Activation for QASYM8
by Giorgio Arena
· 6 years ago
a967611
COMPMID-886 Don't use LWS hints by default for GPU post Mali-G72
by Michalis Spyrou
· 6 years ago
1a03d76
COMPMID-765: Fix windows in DirectConvLayer and DepthwiseConvLayer
by Georgios Pinitas
· 6 years ago
1599787
COMPMID-934: Asymmetric padding support.
by Georgios Pinitas
· 6 years ago
933fe86
COMPMID-927: Adding support for FP16 in CLDepthwiseConvolutionLayer3x3
by Michele Di Giorgio
· 6 years ago
287b570
COMPMID-853 Use tile 2 for CL depthwise convolution QASYM8
by Giorgio Arena
· 6 years ago
c799ed8
COMPMID-895 - Optimizing CLDepthwiseConvolution3x3Kernel
by Gian Marco
· 6 years ago
85e6f51
COMPMID-891 - Use OpenCL timer in CLTuner
by Gian Marco
· 6 years ago
944d3f7
COMPMID-751 Processing 8 elements makes computation up to 80us faster on MobileNet QASYMM8 dwc layers
by Giorgio Arena
· 7 years ago
1250a5a
COMPMID-767 : Propagate hints to subgraph.
by Georgios Pinitas
· 7 years ago
57f249b
COMPMID-661: Add Bifrost lws heuristics dwc with pad=1 [new_dev] #52
by Georgios Pinitas
· 7 years ago
04a8f8c
COMPMID-692 Consistent names for the interfaces
by Giorgio Arena
· 7 years ago
[Renamed (94%) from src/core/CL/kernels/CLDepthwiseConvolution3x3Kernel.cpp]
236bfe7
COMPIMID-553: MobileNet use case.
by Georgios Pinitas
· 7 years ago
a2ea753
COMPMID-661 Add Bifrost lws heuristics for several depthwise_convolution kernels #49
by Anthony Barbier
· 7 years ago
b6f182d3
COMPMID-556: Fix CLDepthwiseConvolution3x3 Kernel.
by Georgios Pinitas
· 7 years ago
d7295b7
COMPMID-661: Add QASYMM8 support (and basic tests) to CLDepthwiseConvolution3x3 kernel (#28)
by Dmitry Savenko
· 7 years ago
82afedf
COMPMID-678 Align Convolution Interfaces
by Giorgio Arena
· 7 years ago
16cdf89
IVGCVSW-657 : fix asymmetric padding for 3x3 depthwise conv
by Jaroslaw Rzepecki
· 7 years ago
81a26ad
COMPMID-643: Add bias to CLDepthwiseConvolution.
by Georgios Pinitas
· 7 years ago
c26ecf8
COMPIMID-523: Fix CLDepthwiseConvolution test.
by Georgios Pinitas
· 7 years ago
9fe4144
COMPMID-452 CL Generic Depthwise Convolution implementation.
by Giorgio Arena
· 7 years ago
[Renamed (91%) from src/core/CL/kernels/CLDepthwiseConvolutionKernel.cpp]
93a690e
COMPMID-452 CL Depthwise Separable Convolution Layer kernel implementation, validation and benchmarking for 3x3xC depthwise filter and DataType::F32.
by Giorgio Arena
· 7 years ago