Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ComputeLibrary
/
e5563d9b0102846973f144cba42fb9002bebd09b
/
src
/
core
/
CL
/
cl_kernels
/
gemm.cl
e5563d9
COMPMID-3560: Fix F16 performance regression (OpenCL)
by Gian Marco Iodice
· 4 years, 1 month ago
e3a849a
COMPMID-3320: Add cl_image support for GEMMReshaped T_NT
by Gian Marco Iodice
· 4 years, 2 months ago
1a37810
COMPMID-3290: Test improvement for CLGEMMMatrixMultiplyReshapedOnlyRHSKernel
by Sheri Zhang
· 4 years, 3 months ago
a07ce15
COMPMID-2741: [CL] GEMMMatrixMultiplyReshaped clCreateKernel Error
by Georgios Pinitas
· 4 years, 10 months ago
0c17aa2
COMPMID-2571: Add mixed-precision support in CLGEMMReshaped for FP16
by Gian Marco Iodice
· 4 years, 10 months ago
05639f6
COMPMID-2571: Add support for FP16 in CLGEMMReshaped - part 1
by Gian Marco Iodice
· 4 years, 10 months ago
7b9d7ca
COMPMID-2675: Fix arguments passed at compile time for GEMM - OpenCL
by Gian Marco Iodice
· 4 years, 10 months ago
ae99b6e
COMPMID-1965 Extend CLGEMMMatrixMultiplyReshapedKernel to support transposed LHS (t) and not-transpose RHS
by Giorgio Arena
· 5 years ago
d1f5476
COMPMID-1979: Fuse Activation Function in CLGEMM - part 3
by Gian Marco Iodice
· 5 years ago
ca1f460
COMPMID-1979: Fuse Activation Function in CLGEMM - part 2
by Gian Marco Iodice
· 5 years ago
944170e
COMPMID-2172: Fuse bias addition with CLGEMMMatrixMultiplyNativeKernel
by Gian Marco Iodice
· 5 years ago
e16c890
COMPMID-2053: Fuse bias addition with CLGEMMMatrixMultiplyReshapedKernel
by Gian Marco Iodice
· 5 years ago
b0f342e
COMPMID-2171: Fuse bias addition with CLGEMMMatrixMultiplyReshapedOnlyRHSKernel
by Georgios Pinitas
· 5 years ago
5fc07aa
COMPMID-2338: Remove CLGEMMInterleave4x4 and CLGEMMTranspose1xW
by Gian Marco Iodice
· 5 years ago
b3204e7
COMPMID-2093: Implement CLGEMMNative
by giuros01
· 5 years ago
0681e3b
COMPMID-2041: Create GEMM helper file for OpenCL.
by Usama Arif
· 5 years ago
62251f7
COMPMID-2002: Implement CLGEMMLowpMatrixMultiplyReshapedOnlyRHS - Transposed
by Gian Marco Iodice
· 5 years ago
b0c5037
COMPMID-2043: Add support for "dummy threads" in CLGEMMReshaped
by Gian Marco Iodice
· 5 years ago
ba5e096
COMPMID-1964: Implement CLGEMMMatrixMultiplyReshapedOnlyRHS - Not transposed
by Gian Marco Iodice
· 5 years ago
adc5395
COMPMID-2000: Implement CLGEMMMatrixMultiplyReshapedOnlyRHS - Transposed
by Gian Marco Iodice
· 5 years ago
ebc3a90
COMPMID-1706: Fuse the bias addition within CLGEMM
by Michele Di Giorgio
· 6 years ago
20b527a
COMPMID-1900: Nightly issue with GEMMReshapeLHSMatrix
by Gian Marco Iodice
· 6 years ago
b87b95e
COMPMID-1899: Fix NaN issue in CLGEMMMatrixMultiplyReshapedKernel
by Gian Marco Iodice
· 6 years ago
bacfec5
COMPMID-1687: Optimize CLGEMMMatrixMultiplyKernel (part 1)
by Gian Marco Iodice
· 6 years ago
17b0f8b
COMPMID-1837 : Implement REPEAT utility macro on OpenCL
by Vidhya Sudhan Loganathan
· 6 years ago
8912434
COMPMID-1858: Fix boundary check in gemm_reshape_rhs_matrix_t and gemm_reshape_rhs_matrix_nt
by Gian Marco Iodice
· 6 years ago
08ddd7b
COMPMID-1834: Add transpose support to CLGEMMReshapeLHSMatrixKernel
by Gian Marco Iodice
· 6 years ago
49b1015
COMPMID-1710: Fixing gemm_mm_reshaped_lhs_nt_rhs_t with REINTERPRET_OUTPUT_AS_3D
by Gian Marco Iodice
· 6 years ago
bf9731e
COMPMID-1687: Optimize CLGEMMMatrixMultiplyKernel for Mali-G76 - Part1
by Gian Marco Iodice
· 6 years ago
3b0a265
COMPMID-1775: Implement CLGEMMReshapeRHSMatrixKernel to reshape the RHS matrix of GEMM/GEMMLowp
by Gian Marco Iodice
· 6 years ago
5ba5e09
COMPMID-1774: Implement CLGEMMReshapeLHSMatrixKernel to reshape the LHS matrix of GEMM/GEMMLowp
by Gian Marco Iodice
· 6 years ago
38d93bd
COMPMID-1801 : (Nightly) CLWinogradConvolutionLayer FP16 mismatches
by Vidhya Sudhan Loganathan
· 6 years ago
a25d16c
COMPMID-1266 : Add support for FP16 in CLWinogradConvolutionLayer: 5x5 kernels
by Vidhya Sudhan Loganathan
· 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
68a3f56
COMPMID-1276 - Allow GEMM to work with 3D input tensor
by Gian Marco Iodice
· 6 years ago
e8bd2c7
COMPMID-1384: graph_mobilenet fails for NHWC on OpenCL
by Georgios Pinitas
· 6 years ago
7485d5a
COMPMID-970 : Remove QS8 / QS16 support
by Vidhya Sudhan Loganathan
· 6 years ago
cfac9a1
COMPMID-1307: Mismatches in CLGEMMConvolutionLayer F16
by Georgios Pinitas
· 6 years ago
8e74f44
COMPMID-911: Allow GEMM to work with 3D tensors
by Isabella Gottardi
· 6 years ago
76c8564
COMPMID-1083 : Compute library should be made usable on non-ARM platforms
by Vidhya Sudhan Loganathan
· 6 years ago
bdff491
COMPMID-1083 : Compute library should be made usable on non-ARM platforms
by Vidhya Sudhan Loganathan
· 6 years ago
f6f08da
COMPMID-1044: Optimizing GCGEMM - Support for not reshaped GEMM on GLES
by Michele Di Giorgio
· 6 years ago
8422558
COMPMID-1150 : (OCLGrind) Kernel compilation error and assertion
by Georgios Pinitas
· 6 years ago
bb36a8e
COMPMID-922 - CLGEMM FP16 optimizations - part2
by Gian Marco Iodice
· 6 years ago
c9c62c2
COMPMID-1056 - Optimizing CLGEMMMatrixMultiplyKernel refactoring the inner loop
by Gian Marco Iodice
· 6 years ago
fd68311
COMPMID-922 - CLGEMM FP16 optimizations - part1
by Gian Marco Iodice
· 6 years ago
81b28c4
COMPMID-1032 - Fixing bug in CLGEMM when is_interleaved_transposed=true
by Gian Marco Iodice
· 6 years ago
d2fab73
COMPMID-935 - Implementing Convolution with Winograd on OpenCL (part 4)
by Gian Marco Iodice
· 6 years ago
ae2af74
COMPMID-935 - Implementing Convolution with Winograd on OpenCL (Part 1)
by Gian Marco
· 6 years ago
19835e5
COMPMID-882 - Optimizing GEMMLowp on OpenCL reshaping matrices
by Gian Marco
· 6 years ago
36a0a46
COMPMID-748 - Integrating optimized SGEMM for bifrost
by Gian Marco
· 7 years ago
05288a2
COMPMID-697 - Rework GEMMLowp interface on OpenCL
by Gian Marco
· 7 years ago
3e80c7f
COMPMID-661: Optimize FC layer with 2 new Bifrost kernels and LWS tuning (#33)
by Anton Lokhmotov
· 7 years ago
6f31f8c
Allow running without cl_khr_fp16
by Matthew Bentham
· 7 years ago
96880cf
COMPMID-640: FullyConnectedLayer failures on both NEON/CL
by Georgios Pinitas
· 7 years ago
edfa9f4
COMPMID-477 - Optimized batched case in CLConvolutionLayer
by Gian Marco Iodice
· 7 years ago
e49e266
COMPMID-415: Use half_float library for F16
by Moritz Pflanzer
· 7 years ago
368da83
COMPMID-420, COMPMID-414 - Port CLConvolutionLayer and CLFullyConnectedLayer to use 8 bit fixed point
by Gian Marco Iodice
· 7 years ago
b93f5de
COMPMID-417 - Fixed bug in gemm_interleave_16bit and gemm_interleave_32_bit due to the non non representable numbers in half and float
by Gian Marco Iodice
· 7 years ago
8a38369
COMPMID-434 - Port CLGEMM to support 16 bit fixed point
by Gian Marco Iodice
· 7 years ago
ac69aa1
COMPMID-418 Add check and fix comments after preprocessor conditions
by Anthony Barbier
· 7 years ago
3a3066b
COMPMID-411 - Port CLGEMM to support 8 bit fixed point
by Gian Marco Iodice
· 7 years ago
578ab61
COMPMID-414 - Port CLConvolutionLayer to support 8 bit fixed point - CLGEMMMatrixAccumulateBiasesKernel
by Gian Marco Iodice
· 7 years ago
9f89bae
COMPMID-411 - Ported CLGEMMInterleave4x4Kernel and CLGEMMTranspose1xWKernel to support 8 bit fixed point
by Gian Marco Iodice
· 7 years ago
6ff3b19
COMPMID-344 Updated doxygen
by Anthony Barbier
· 7 years ago