- b5368fb Force CL kernel compilation with 64 registers by Viet-Hoa Do · 1 year, 10 months ago
- 304dfdb Fix Batch Matmul nightly failure by Adnan AlSinan · 1 year, 10 months ago
- cf07d11 Enable FP16 when the target is armv8.6-a by Pablo Marquez Tello · 1 year, 10 months ago
- 40b4419 Optimize CPU add layer on quantized data by Viet-Hoa Do · 1 year, 10 months ago
- ff81de5 Fix overflow in NEActivationLayer for FP16 type by Pablo Marquez Tello · 1 year, 10 months ago
- d6b8a71 Add FP32 Neon™ swish activation by Jonathan Deakin · 2 years ago
- ce79ac6 CPU GEMM: Fix overreads in SVE merges. by David Mansell · 1 year, 10 months ago
- ead4d11 Fix unresolved symbol for target armv7a + Android by Pablo Marquez Tello · 1 year, 10 months ago
- a77c6d7 Add test for ClGemmLowpMatrixMultiplyCore to test a batched matrix multiplication with variable input tensors by Ramy Elgammal · 1 year, 11 months ago
- 047e5d0 Fix validation in validate_image2d_support_on_rhs by Gian Marco Iodice · 1 year, 11 months ago
- 622b8ad Fix bug in QASYMM8_SIGNED to F32 cast layer by Viet-Hoa Do · 1 year, 11 months ago
- c4f2743 Optimize Quantized/Integer Bilinear Scale for Neon™ by Gunes Bayir · 1 year, 11 months ago
- 0d05b66 Interpreting tensor as 1D for CPU multiplication by Viet-Hoa Do · 1 year, 11 months ago
- 5687e55 Fix invalid memory access for dynamically fused Cl Elementwise kernels by SiCong Li · 2 years ago
- 926f502 Adding GELU activation by Murray Kornelsen · 2 years, 1 month ago
- 6e09e14 INT8 Quantized MeanStdDevNorm (LayerNorm) by Murray Kornelsen · 2 years, 1 month ago
- a4814e8 Add test case for disable Winograd on fp16 if fast-math = false by Ramy Elgammal · 1 year, 11 months ago
- 26c9d1a Add test for NEGEMM to test a batched matrix multiplication with variable input tensors by Adnan AlSinan · 1 year, 11 months ago
- 4478e1c Rework heuristic in ClConv2d by Gian Marco Iodice · 1 year, 11 months ago
- 0eed305 Optimize FP32/16 Bilinear Scale Kernel for Neon™ by Gunes Bayir · 1 year, 11 months ago
- d11de98 Add a macro guard in all OpenCL kernels in gemmlowp.cl by Gian Marco Iodice · 1 year, 11 months ago
- e4e3b2e Disable Winograd on fp16 if fast-math = false by Ramy Elgammal · 1 year, 11 months ago
- 211a55d Optimize depthwise convolution on OpenCL by Gian Marco Iodice · 1 year, 11 months ago
- 13a2d00 Add test for CLGEMM to test a batched matrix multiplication with variable input tensors by Mohammed Suhail Munshi · 1 year, 11 months ago
- 552fe4c F16 Specialization for MeanStdDevNorm by Murray Kornelsen · 2 years ago
- 1257131 Enable Winograd-based conv2d when IFM>=8 on Gpu by Gian Marco Iodice · 1 year, 11 months ago
- 16789a1 Compute Hard-Swish with a Lookup table for qasymm8_signed. by Pablo Marquez Tello · 2 years ago
- cd083cf Use parent buffer in CLSubTensor. This avoids calling enqueueMapBuffer repeatedly when mapping multiple children of the same parent. by Murray Kornelsen · 2 years, 1 month ago
- a331e48 Fix add for tensors with non-matching strides by Jonathan Deakin · 2 years ago
- 8bab588 Fix validation problem in CLQLSTMLayer by Pablo Marquez Tello · 2 years ago
- a81fc84 Fix macos build errors by Pablo Marquez Tello · 2 years ago
- 53929b1 Use Neon™ kernels for FP Bilinear Resize for SVE by Gunes Bayir · 2 years ago
- 9ee8a3e Revert "Fix performance regression in ClConv2D" by Ramy Elgammal · 2 years ago
- 29db3d2 Add LUT for quantized sigmoid function by Viet-Hoa Do · 2 years ago
- e54d8c0 Fix performance regression in ClConv2D by Gian Marco Iodice · 2 years ago
- fa8ff8e Fix note in guidelines doc by Ramy Elgammal · 2 years ago
- 966218d Update release notes about armv8.6 build flag change by Ramy Elgammal · 2 years ago
- cec1af5 Fix performance regression in Conv2D on OpenCL by Adnan AlSinan · 2 years ago
- cc03419 Disable unsafe FP optimizations in Winograd Output Transform by Gunes Bayir · 2 years ago
- 0d274b7 Update README by Ramy Elgammal · 2 years ago
- 52695f5 Fix CTS/SLTS failure related to Depthwise Convolution by Gunes Bayir · 2 years ago
- 65c8db8 Fix for AI benchmark ResNet regression by Viet-Hoa Do · 2 years ago
- 992a741 Update Errata by Ramy Elgammal · 2 years ago
- a914823 Update SONAME_VERSION in SConscript by Ramy Elgammal · 2 years ago
- 0105ce5 Fix LeNet-f16 convolution regression by Adnan AlSinan · 2 years ago
- 93581a5 [ONCPUML-970] Fast math mode for fixed format kernels by Pablo Marquez Tello · 2 years ago
- f67903b Add Dynamic Fusion Tests with BugFixes by Mohammed Suhail Munshi · 2 years, 1 month ago
- 13b623e [ONCPUML-968] Fixed format kernel support in additional APIs by Milos Puzovic · 2 years ago
- 3c4d085 Update the GPUTarget list by Gian Marco Iodice · 2 years, 1 month ago
- 9b921be Optimize add layer by considering the input tensors as 1D array by Gunes Bayir · 2 years ago
- 385dad2 Fix for OpenMP scheduler work breakdown by Milos Puzovic · 2 years ago
- e748346 Fix building failure with validate_examples set to true by Michalis Spyrou · 2 years ago
- ab659ad Updated documentation by Pablo Marquez Tello · 2 years ago
- aa52b7d Fix compilation error rasied in Nightly_NEW by Ramy Elgammal · 2 years ago
- a89aa53 Fix build android build error by Pablo Tello · 2 years ago
- 9178002 Fix for inclusion of "arm_gemm" from src into "Types.h" from core by Ramy Elgammal · 2 years ago
- bf5274d Enable integrated assembler for Android™ 13 and onwards only by SiCong Li · 2 years ago
- d208f4f Enable march=armv8.6-a in non multi-isa builds by Pablo Marquez Tello · 2 years ago
- 9625318 Mention Arm® Neoverse® in supported systems. by Pablo Marquez Tello · 2 years ago
- e572dff Add GemmLowp MMUL Reshaped Only Rhs Support for QASYMM8/QASYMM8_SIGNED by Freddie Liardet · 2 years, 2 months ago
- e871207 Update ClConv2D heuristic to use direct convolution by Adnan AlSinan · 2 years ago
- c6b7913 Fix direct convolution cases that were failing on Odroid by Adnan AlSinan · 2 years ago
- 5967ee2 Added CONTRIBUTING.md by Pablo Marquez Tello · 2 years ago
- 3964f17 Remove data extraction scripts by Pablo Marquez Tello · 2 years ago
- 553f695 [ONCPUML-951] Variable weight support for Convolution. by Francesco Petrogalli · 2 years, 1 month ago
- 99c4647 Fix multi_isa build failure after Winograd integration by ramelg01 · 2 years ago
- 1f86449 Fix Neoverse V1 heuristics for FP32 fast mode by ramelg01 · 2 years, 1 month ago
- a1f7851 Integrate new winograd APIs from MLTech by ramelg01 · 2 years, 1 month ago
- 4bfc70e Add Gemm MMUL Reshaped Only Rhs Support for FP32/FP16 by Gunes Bayir · 2 years, 8 months ago
- 29cab36 Fixed clang-cl errors on Windows native builds. by Pablo Tello · 2 years, 5 months ago
- 2186aef List licenses used by other projects in README by SiCong Li · 2 years, 1 month ago
- 2cc50b3 Extended direct conv 2d interface for tuning the OpenCl kernel by Gian Marco Iodice · 2 years, 2 months ago
- 22dd8b9 Add missing flag when building cl graph examples and fix by Michalis Spyrou · 2 years, 1 month ago
- a3f7cd2 Move build option explanations in how to build guide to scons help message by Michalis Spyrou · 2 years, 1 month ago
- fa08c37 Add OpenBSD® to the list of supported systems by Pablo Marquez Tello · 2 years, 1 month ago
- a3cf241 Add G57 to GPUTarget by SiCong Li · 2 years, 1 month ago
- e417ff1 Fix build errors on armv8.6 SVE2 with NDK 23 and 24 by Michalis Spyrou · 2 years, 1 month ago
- 84a0941 Fix OpenBSD build errors by Pablo Marquez Tello · 2 years, 1 month ago
- 16aa474 Wrong arguments for running activation function in CpuGemmDirectConv2d by Michalis Spyrou · 2 years, 1 month ago
- ddf2f6c Fixed native build toolchain and compiler prefix by Pablo Marquez Tello · 2 years, 1 month ago
- b042e39 Add LUT-based leaky relu for QASYMM8 on CPU by Viet-Hoa Do · 2 years, 1 month ago
- 13f96d0 Fix armv7a on Android "end-of-support" build and documentation by SiCong Li · 2 years, 1 month ago
- d8804fd Fix OpenCL Winograd output transform by Gian Marco Iodice · 2 years, 1 month ago
- b1fcefd Implement new Elementwise Dynamic Fusion Operators: Div, Floor by Michalis Spyrou · 2 years, 1 month ago
- 41eb2d9 Improve LUT Neon Hard-Swish by Pablo Marquez Tello · 2 years, 1 month ago
- 700b913 Select neon LUT Hard-Swish kernel on all devices by Pablo Marquez Tello · 2 years, 1 month ago
- 3efdfb3 Enable loading OpenCL symbols in Android App native code, NDK environment. by ohadagoogle · 2 years, 1 month ago
- 14ce094 Drop support on armv7a on Android by Michalis Spyrou · 2 years, 2 months ago
- f1f7779 Fix SVE2 implementation of quantized SoftMax 1D by Viet-Hoa Do · 2 years, 1 month ago
- 586fff9 Fix build error v8.2-a-sve by Pablo Marquez Tello · 2 years, 2 months ago
- f8bb092 Add support OpenCL 3.0 non-uniform workgroup by Viet-Hoa Do · 2 years, 2 months ago
- 0c68704 Fix performance regression in Winograd Output Transform (OpenCL) by Gian Marco Iodice · 2 years, 2 months ago
- 894659a Add support for 2d and 3d indices for axis 1 by Pablo Marquez Tello · 2 years, 3 months ago
- c3bc093 Fix crash in CpuActivationKernel by Pablo Marquez Tello · 2 years, 2 months ago
- d75cd8a Compute Hard-Swish with a Lookup table for qasymm8. by Pablo Marquez Tello · 2 years, 2 months ago
- fe1b1f6 Allow clearer suppression of toolchain and compiler prefixes by SiCong Li · 2 years, 2 months ago
- a774d63 Fix build errors in GCC12 by Pablo Marquez Tello · 2 years, 2 months ago
- 0e7053d Fix reference example for fusion of conv2d and adddition by SiCong Li · 2 years, 2 months ago
- 82169b3 Add cl_khr_integer_dot_product extension support by Viet-Hoa Do · 2 years, 2 months ago
- 56c3ca8 Add missing new-line to doxygen documentation by SiCong Li · 2 years, 2 months ago