- 5ff4802 Port operations to CKW prototype by Nikolaj Jensen · 1 year ago
- 4c0a38a Disable kernel size 3 in argminmax for axis 0 by Pablo Marquez Tello · 12 months ago
- 1d06204 Do not include headers necessary for logging when logging is disabled by Matthew Bentham · 12 months ago
- 97f83fa Temporarily fallback to 23.05 links in README by ramy.elgammal@arm.com · 12 months ago
- 019a7d9 Enable transpose convolution with non-square kernels by Viet-Hoa Do · 1 year ago
- 5153fe4 Fix unsupported configuration in CLFullyConnected validation by Gunes Bayir · 12 months ago
- acea407 Fix code formatting in CKW by Nikolaj Jensen · 1 year ago
- e86f992 Pack CKW objects into Compute Library archive by Jakub Sujak · 12 months ago
- 2ae536a Implement ITileOperand and set the relationship to CLTile by Gunes Bayir · 12 months ago
- c9eeee5 Fix nightly failures in MatMulLowpNativeKernel when using bounded activation functions by Mohammed Suhail Munshi · 1 year ago
- ce3c48c Move CKW prototype to separate directory by Viet-Hoa Do · 1 year ago
- 9b392d7 Rewrote CLArgMinMax for axis 0 by Pablo Marquez Tello · 1 year ago
- 4cf8067 Fix unused function warning by Michael Tyler · 12 months ago
- bea5790 Update README by ramy.elgammal@arm.com · 12 months ago
- 8deee9b Depthwise channel pre-multiplication by Michael Tyler · 1 year ago
- 19844f6 Add Kernel Writer driver code to dynamic fusion by SiCong Li · 1 year, 2 months ago
- 2f0ef00 Update README for patch release 23.05.1 by ramy.elgammal@arm.com · 1 year ago
- 7644b91 Fix CKW test failure by Viet-Hoa Do · 1 year ago
- 00474e9 Implement FP32/16 MatMul Lhs T Rhs T/NT kernel using MMUL extension by Gunes Bayir · 1 year ago
- 7a698a3 Improvements to building CKW by Jakub Sujak · 1 year ago
- cdb1ee0 Update SONAME_VERSION in SConscript and CMake for release 23.05.1 by ramy.elgammal@arm.com · 1 year ago
- e1880f0 Fix compute kernel writer build warnings by Viet-Hoa Do · 1 year ago
- bd4f6b9 Compute kernel writer API and prototype by Viet-Hoa Do · 1 year, 1 month ago
- 8c49f16 Add helpers to set CKW tensor components as OpenCL kernel arguments by Jakub Sujak · 1 year, 1 month ago
- 7d9a78e Remove dependency on fp16 definitions from some core include files by Matthew Bentham · 1 year, 1 month ago
- a2bb80e Use MatMul in fully connected layer with dynamic weights when supported by Mohammed Suhail Munshi · 1 year ago
- c952596 Implement FP32/FP16 MatMul NT/T kernel using the MMUL extension by Ramy Elgammal · 1 year, 2 months ago
- 47a50ef Address the issues with the ACL coverage pipeline failures related to matmul. by Renato Arantes · 1 year, 1 month ago
- a2561f0 Fix doxygen warnings by ramy.elgammal@arm.com · 1 year, 1 month ago
- 90d15b9 Bazel and CMake optional fp16 support by David Svantesson · 1 year, 1 month ago
- da9cb70 Include CKW sources in Android.bp by Jakub Sujak · 1 year ago
- 8eb82d2 Fix CPU depthwise convolution in case of large padding by Viet-Hoa Do · 1 year ago
- 3f16c57 Enable vmfa in arm7va/aarch32 when present by Pablo Marquez Tello · 1 year ago
- 68e9c4d Implement CLConstantTile by Gian Marco Iodice · 1 year, 1 month ago
- 59b9ff0 Deprecate legacy libarm_compute_core by Jakub Sujak · 1 year, 1 month ago
- a8d8058 Implement FP32/FP16 MatMul NT/NT kernel using the MMUL extension by SiCong Li · 1 year, 2 months ago
- 94abde4 Add Fused Activation to OpenCL MatMul by Mohammed Suhail Munshi · 1 year, 1 month ago
- dd8d7f4 Escape double qoutes in embedded version string by Matthew Bentham · 1 year, 1 month ago
- f66a7e8 Fix potential infinite recursion in bfloat16 printer by Matthew Bentham · 1 year, 1 month ago
- 043613f Break up Utils.h a bit to reduce unused code being included everywhere by Matthew Bentham · 1 year, 1 month ago
- f1aeab9 Break up arm_compute/core/Types.h a bit by Matthew Bentham · 1 year, 1 month ago
- bec9b03 Add a Getting Started guide to CKW README by Jakub Sujak · 1 year, 1 month ago
- 3fcf3dc Add multi-sketch support for dynamic fusion by Viet-Hoa Do · 1 year, 2 months ago
- 48cfd5f Refactor activation LUT computation by Pablo Marquez Tello · 1 year, 1 month ago
- 78a17a1 Enable building Compute Kernel Writer from Scons by Jakub Sujak · 1 year, 1 month ago
- 08dfba3 Enable conversion of F32 NumPy files to F16 by Gian Marco Iodice · 1 year, 1 month ago
- 54b41a3 Reorder destructor in src by David Svantesson · 1 year, 1 month ago
- 9c8f9a9 Added int8 support in LeakyRelu/LUT kernel. by Pablo Marquez Tello · 1 year, 1 month ago
- 6c7cf31 Fix build error for armv7a by Pablo Marquez Tello · 1 year, 1 month ago
- 7a31a82 Fix guards for FP16 depthwise kernels by Michael Tyler · 1 year, 1 month ago
- 48c0ed9 Fix ScaleKernel validate method. by Pablo Marquez Tello · 1 year, 2 months ago
- 74921ee Update CPU kernel implementations and guard directives by Michael Tyler · 1 year, 3 months ago
- df5d987 Add CMakeLists to Compute Kernel Writer by Jakub Sujak · 1 year, 1 month ago
- 545358e Fix number of dimensions changed after transpose by Viet-Hoa Do · 1 year, 1 month ago
- 6c113ed Prepare the basic types for the compute kernel writer (CKW) by Gian Marco Iodice · 1 year, 6 months ago
- 1355ec4 Printing out the rerun command of each failed testcase by Ramy Elgammal · 1 year, 2 months ago
- c0463a2 Move lut kernel to sve2 category by SiCong Li · 1 year, 2 months ago
- f15c615 Revert "Check for nullptr when failing to load OpenCL libraries" by Omar Al Khatib · 1 year, 2 months ago
- bea74ca Raise an erratum about sporadic CLArgMinMax nightly failure by SiCong Li · 1 year, 2 months ago
- 9d25461 Check for nullptr when failing to load OpenCL libraries by Jakub Sujak · 1 year, 2 months ago
- 95f1e4a Raise abs_tolerance number for CL/DirectConvolution3D fp16 tests by Ramy Elgammal · 1 year, 2 months ago
- bae01a5 Raise tolerance number for NEDeconvolutionLayer fp16 tests by SiCong Li · 1 year, 2 months ago
- 34a95d1 Move matmul heuristics files from Gemm to MatMul in filelist.json by Ramy Elgammal · 1 year, 2 months ago
- 32a6250 Update release notes for the 23.05 release. by Omar Al Khatib · 1 year, 2 months ago
- 56fabba Fix performance regression in FP16 Deconvolution by Jakub Sujak · 1 year, 2 months ago
- 7997603 Update README to refer to the 23.05 release by Omar Al Khatib · 1 year, 2 months ago
- cd2502c Fix invalid vector length in CL by Viet-Hoa Do · 1 year, 2 months ago
- ed9eb30 Remove check for bias in CPU Depthwise Convolution by Jakub Sujak · 1 year, 2 months ago
- 83d0674 Fix undefined ClMatMulNativeKernel::validate for high priority build by SiCong Li · 1 year, 2 months ago
- 318782b Remove inclusion of NEReorderKernel header from NEReorderLayer by Ramy Elgammal · 1 year, 2 months ago
- 4494b55 Update SONAME_VERSION in SConscript by Omar Al Khatib · 1 year, 2 months ago
- 0ed0ddd Fix validation issue with CPU scale on FP16 by Viet-Hoa Do · 1 year, 2 months ago
- a8db612 Re-enable dyanmic weights in Neon™ depthwise convolution by Ramy Elgammal · 1 year, 2 months ago
- e9b3ee2 Connect CLMatMul function to quantized kernels and resolve NE BatchMatMul int_8 failures by Jakub Sujak · 1 year, 3 months ago
- edafe7f Disable dynamic weights in unsupported operators by Viet-Hoa Do · 1 year, 2 months ago
- 76e7b63 Make NECast::validate take args by const pointer by Matthew Bentham · 1 year, 2 months ago
- 352c07d Implement OpenCL MatMul heuristic for Arm® Mali™-G710 by Gian Marco Iodice · 1 year, 2 months ago
- 5713294 Fix im2col for fast-maths mode with padding. by Renato Arantes · 1 year, 2 months ago
- cdd1e03 Support multi-dimensional indices in the CL Gather Layer up to four-dimensional output tensors by Omar Al Khatib · 1 year, 2 months ago
- 911d572 [scons multi_isa] extend multi_isa build to support armv8-a march by Sunita Nadampalli · 1 year, 2 months ago
- cd8b40d Guards to make NEReorder aarch64 only by David Svantesson · 1 year, 2 months ago
- 8964c89 Update a64_transpose_interleave_16.hpp by David Svantesson · 1 year, 2 months ago
- b5d6c28 Bazel and CMake updates by David Svantesson · 1 year, 2 months ago
- 54e52a9 Fix CPU MatMul broadcast detection by Viet-Hoa Do · 1 year, 2 months ago
- 60ab4e6 Fix export_to_cl_image issue in the fp16 GeMM implementation by Gian Marco Iodice · 1 year, 2 months ago
- d7113e4 Removes `experimental` from `experimental_fixed_format_kernels` flag by Nathan John Sircombe · 1 year, 2 months ago
- 7a0f1bd Add fp16 GeMM heuristic for Arm® Mali™-G710 by Gian Marco Iodice · 1 year, 2 months ago
- a62129a Fix fully connected and matmul mismatches by Viet-Hoa Do · 1 year, 2 months ago
- f0ff76d Add Reorder to changelog by David Svantesson · 1 year, 2 months ago
- 3b162e5 Reorder added by David Svantesson · 1 year, 3 months ago
- a25582c Fix the gather layer indices check by Viet-Hoa Do · 1 year, 4 months ago
- eaae899 Fix OMPScheduler run_workloads single thread issue by SiCong Li · 1 year, 2 months ago
- 99b6fd2 Fix filelist issue with CPU MatMul by Viet-Hoa Do · 1 year, 2 months ago
- a7db356 Avoid printing error message for each not found OpenCl library by Ramy Elgammal · 1 year, 3 months ago
- 5e99a3e Add quantized CL MatMul kernel for LHS NT, RHS T by Jakub Sujak · 1 year, 3 months ago
- f16eed9 Change fp16 GeMM heuristic for Arm® Mali™-G77 by Gian Marco Iodice · 1 year, 3 months ago
- 905a3c1 Improve Winograd performance on OpenCL by Gian Marco Iodice · 1 year, 3 months ago
- b2758f3 Add FP16 depthwise kernels for SME2 by David Mansell · 1 year, 3 months ago
- af15076 Only define validation test tolerance for quantized types in case of aarch64 for Neon™ Matmul by Ramy Elgammal · 1 year, 2 months ago
- dba672c Integrate multi-threaded pretranspose_B_array by SiCong Li · 1 year, 3 months ago