index
:
ComputeLibrary.git
branches/arm_compute_19_02
branches/arm_compute_19_05
branches/arm_compute_19_08
branches/arm_compute_19_11
branches/arm_compute_20_02
branches/arm_compute_20_05
branches/arm_compute_20_08
branches/arm_compute_20_11
branches/arm_compute_21_02
branches/arm_compute_21_05
branches/arm_compute_21_08
branches/arm_compute_21_11
branches/arm_compute_22_02
branches/arm_compute_22_05
branches/arm_compute_22_08
branches/arm_compute_22_11
branches/arm_compute_23_02
branches/arm_compute_23_02_1
branches/arm_compute_23_05
branches/arm_compute_23_05_1
branches/arm_compute_23_08
branches/arm_compute_23_11
branches/arm_compute_24_01
branches/arm_compute_24_02
branches/arm_compute_24_02_1
branches/arm_compute_24_04
branches/arm_compute_24_05
branches/arm_compute_24_06
branches/arm_compute_24_07
dev/21_02_int8_optim
dev/21_05_int8_optim
main
master
release_candidate
about
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
src
/
runtime
/
NEON
/
functions
Age
Commit message (
Expand
)
Author
2018-11-02
COMPMID-1277 - Optimizing CLIm2ColKernel for NHWC.
Gian Marco Iodice
2018-11-02
COMPMID-1248 Enabled memory manager in NEWinogradConvolutionLayer
Anthony Barbier
2018-11-02
COMPMID-1406: Refactor gemm_interleaved to use our own types and scheduler
Anthony Barbier
2018-11-02
COMPMID-872 - Rework NEGEMMConvolutionLayer to use NEGEMM
Gian Marco Iodice
2018-11-02
MLCE-36: FC tranpose weights
Georgios Pinitas
2018-11-02
COMPMID-1188 - Fixed CLGEMMConvolutionLayer/NEGEMMConvolutionLayer for NHWC
Gian Marco Iodice
2018-11-02
COMPMID-1445: Fixed NEON GEMM assembly dispatch for QASYMM8
Anthony Barbier
2018-11-02
COMPMID-1440: Access original B in gemm assembly when not pretransposed.
Georgios Pinitas
2018-11-02
COMPMID-1434: Fix NEWinograd for NHWC and sub-tensors
Georgios Pinitas
2018-11-02
COMPMID-1386: Add FC convert weights on NEON
Georgios Pinitas
2018-11-02
COMPMID-1401 Implement NEFullyConnectedLayer for QASYMM8
Giorgio Arena
2018-11-02
COMPMID-1419: Make NEGEMMAssemblyDispatch dynamically typed instead of templated
Anthony Barbier
2018-11-02
COMPMID-1405: Create our own gemm_native kernel / function.
Anthony Barbier
2018-11-02
COMPMID-1386: Add support for converting weights for CL.
Georgios Pinitas
2018-11-02
COMPMID-1364: Add support for NHWC in NEDepthConcatenateLayer
Georgios Pinitas
2018-11-02
COMPMID-1357: Stop passing around raw pointers in NEWinogradConvolution
Anthony Barbier
2018-11-02
COMPMID-1357: Port NEWinogradConvolution to use NEGEMMAssemblyDispatch
Anthony Barbier
2018-11-02
COMPMID-1365: Add support for NHWC in CLDepthConcatenateLayer
Georgios Pinitas
2018-11-02
COMPMID-1381: Fix nightly build failure on armv7
Anthony Barbier
2018-11-02
COMPMID-1381: Cleaned up the AssemblyHelper interface
Anthony Barbier
2018-11-02
COMPMID-1167: Validation for NEDepthwiseConvolutionLayer
Abe Mbise
2018-11-02
COMPMID-970 : Remove QS8 / QS16 support
Vidhya Sudhan Loganathan
2018-11-02
COMPMID-1352: Disable support for 4D softmax layer.
Georgios Pinitas
2018-11-02
COMPMID-1334 (Nightly) Fix std::bad_alloc error in 32-bit NEON runs
Giorgio Arena
2018-11-02
COMPMID-1253: Nightly: Fix Canny Edge NEON failing
Michele Di Giorgio
2018-11-02
COMPMID-1287: Extending NEWinogradLayer test suite
Pablo Tello
2018-11-02
COMPMID-1067 NEON RNN FP32 / FP16
Michalis Spyrou
2018-11-02
COMPMID-1145: (API) Introduce prepare() stage (NEON/CL/GLES)
Georgios Pinitas
2018-11-02
COMPMID-1162: Enable NHWC data layout support for NEWinogradConvolutionLayer ...
Pablo Tello
2018-11-02
COMPMID-1160 Turn Graph hints into heuristics
Giorgio Arena
2018-11-02
COMPMID-1209: Enable memory manager for the GEMM workspace buffer
Georgios Pinitas
2018-11-02
COMPMID-568: Implement Canny edge function for CL/NEON
Abe Mbise
2018-11-02
COMPMID-1168: enabling memory manager for _gemm_output gives wrong results
Georgios Pinitas
2018-11-02
COMPMID-1163: NEON Scale NHWC failures
Georgios Pinitas
2018-11-02
COMPMID-959 - Fix Validate in Convolution Layer
Isabella Gottardi
2018-11-02
COMPMID-1106 Add fast math support in NEWinogradConvolutionLayer
Giorgio Arena
2018-11-02
COMPMID-814: Add validate method to scale.
Georgios Pinitas
2018-11-02
COMPMID-1166: Fixed alpha/beta mixup for some merges.
David Mansell
2018-11-02
COMPMID-792 - Re-enabled Winograd on NEON in all graph examples.
Gian Marco Iodice
2018-11-02
COMPMID-1102 : Enable the use of 4x4 tile sizes in neon implementation of win...
Vidhya Sudhan Loganathan
2018-11-02
COMPMID-948: Add validation to NEL2NormalizeLayer
John Richardson
2018-11-02
COMPMID-814: NEScale NHWC support
Georgios Pinitas
2018-11-02
COMPMID-1050 CL/NEON: Create a function to convert the 2D weights of FC layer...
Giorgio Arena
2018-11-02
COMPMID-810 Add NHWC data format support for NEON convolution
Michalis Spyrou
2018-11-02
COMPMID-959: Assembly kernel marks weights as unused when pretranspose
Georgios Pinitas
2018-11-02
COMPMID-959: Perform pretranspose if allowed on NEON assembly
Georgios Pinitas
2018-11-02
COMPMID-808 Add NHWC data format support for NEON direct convolution
Giorgio Arena
2018-11-02
COMPMID-926 Add depth multiplier support to NEON/CL/GLES depthwise convolution
Giorgio Arena
2018-11-02
COMPMID-806 Add NHWC data format support format for NEON pooling
Michalis Spyrou
2018-11-02
COMPMID-1074: Rename WinograLayer.cpp to WinogradConvolutionLayer.cpp
Georgios Pinitas
[next]