- bcf9552 Fix compilation error with clang and multi-isa by Viet-Hoa Do · 9 months ago
- 704c22f [GPU] Update Reverse layer to allow negative axis and reversed axis order by Adnan AlSinan · 10 months ago
- fde45d8 Extend CKW MatMul with nt_t by Adnan AlSinan · 10 months ago
- 5ef0bdd Fix SVE kernel using SVE2 instruction by Viet-Hoa Do · 10 months ago
- 29254ae Optimize CL softmax by Viet-Hoa Do · 10 months ago
- e5362e7 DirectConv and Im2Col changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 10 months ago
- 72b7471 Add check to disable dynamic bias with quantized datatypes in Conv2D layer by Mohammed Suhail Munshi · 10 months ago
- 074b985 FuseBatchNorm changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 10 months ago
- 0fa92b8 arm_gemm: Add SME2 FP16 GEMV using FP16->FP32 dot product. by David Mansell · 10 months ago
- 098efc4 Revert "arm_gemm: Add SME2 FP16 GEMV." by David Mansell · 10 months ago
- c1204c7 Connect MatMul MMUL kernels to ClMatMul operator by Gunes Bayir · 10 months ago
- d8a397e Fix build error in CpuScale by Pablo Marquez Tello · 10 months ago
- b5cb4d2 Scale changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 10 months ago
- aeced74 arm_gemm: Add SME2 FP16 GEMV. by David Mansell · 10 months ago
- 95d477e Remove padding from CL comparison operator by Viet-Hoa Do · 10 months ago
- c210c85 Optimize CL reduction operation by Viet-Hoa Do · 10 months ago
- fb9c25d arm_gemm: fix 2D threading mode for SME2 by David Mansell · 11 months ago
- 9aa153a Fix build error by Pablo Marquez Tello · 10 months ago
- dfd56a6 Fix NEReorderKernel validation by David Svantesson · 10 months ago
- d9c1d44 Port MatMul to Dynamic Fusion + CKW boilerplate code by Adnan AlSinan · 10 months ago
- 0b72aa4 Optimize NEStackLayer by Gunes Bayir · 10 months ago
- b6718c8 Fix compilation error caused by ambiguous std::abs call by Gunes Bayir · 10 months ago
- 6777359 CpuSubKernel changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 10 months ago
- 1434155 Change heuristics for FP16 Deconv by Sangwon Ha · 10 months ago
- 68b6dce Pool2d changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 10 months ago
- a23b468 Optimize CLTranspose operator by Jakub Sujak · 10 months ago
- a04ae3e Port DepthwiseConv2d operator to Ckw by ramy.elgammal@arm.com · 1 year ago
- 745153b NEDeconvolutionLayer validation fix by Pablo Marquez Tello · 10 months ago
- 0a99c79 Fix nightly NEON Reverse reference failure by Adnan AlSinan · 10 months ago
- c2a51bd Optimize CL and Neon Winograd tests by Gunes Bayir · 10 months ago
- a396da1 Implement Quantized Matmul T/T and T/Nt kernels using MMUL extension by Gunes Bayir · 11 months ago
- 6e56bf3 Revise clang-format configuration by Jakub Sujak · 12 months ago
- 2ad0a6b Implement Quantized Matmul Nt/T kernel using MMUL extension by Gunes Bayir · 11 months ago
- ef9da00 Reimplement erf function by Viet-Hoa Do · 10 months ago
- afd38f0 Apply clang-format on repository by Felix Thomasmathibalan · 10 months ago
- bdcb4c1 Implement tflite compliant reverse for CPU by Adnan AlSinan · 11 months ago
- 729099c Enable job-chaining with incremental job_chaining_size. by Anitha Raj · 11 months ago
- 0392160 Re-arrange header inclusion order by Felix Thomasmathibalan · 11 months ago
- 6d87887 Select changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- 6b6ba9e Maxunpooling changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- 8562a4e Remove CommonGraphOptions from Utils target and warnings by Paolo Tricerri · 11 months ago
- 1f841a5 Optimize the main loop in mat_mul_native_quantized_mmul_nt_nt by Gunes Bayir · 11 months ago
- e9fd8b4 L2Norm changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- f57d6ec Gemm changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- e071b5e Fix the validation issue in AddMulAdd fused kernel by Gunes Bayir · 11 months ago
- 500e10b Add CL command buffer class by Viet-Hoa Do · 11 months ago
- a116cd3 Implement Quantized MatMul kernel using MMUL extension by Gunes Bayir · 11 months ago
- 40a9d3e Remove deprecated support for BF16 in CpuCast by Adnan AlSinan · 11 months ago
- 2ffc85e GenerateProposals changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- 7e58980 Fuse batch normalization changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- c071328 Fix include dependencies for mass reformatting patch by Gunes Bayir · 11 months ago
- e87fa66 Add skeleton of ClMatMulLowpNativeMMULKernel by Gunes Bayir · 11 months ago
- 7ce8a83 Softmax changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- 145e82e Changes to InstanceNrom to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- cf219a4 Changes in NECropResize to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- 3912f47 Meanstddevnorm changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- 45e5b5a Changes to BoundingBoxTransform to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- ea9bd8f Changes to ElementwiseOp to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- b566b6e Extend Neon ReshapeLayer validation tests by Anitha Raj · 12 months ago
- 0d27b2e Remove legacy PostOps code by Jakub Sujak · 12 months ago
- 7ff03b6 DWC changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- 324ba7a Pool3d changes to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- 2e6d659 Port ClTemplatePool2d to ckw by Adnan AlSinan · 12 months ago
- 91cb733 Port Resize operator to CKW by Gunes Bayir · 1 year ago
- 8770669 Changes in roi_align to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 11 months ago
- b7aefd7 GEMM: AArch32: Split assembler block in a32_merge_float_8x6.hpp by David Mansell · 12 months ago
- cea7060 NEFuseBatchNormalizationKernel rework by Pablo Marquez Tello · 12 months ago
- 3a9ecdf CpuAdd rework to enable fp16 in armv8a multi_isa builds by Pablo Marquez Tello · 12 months ago
- 082630b Update CpuGemmConv2d and CpuFlatten to use CpuReshape operator by Anitha Raj · 12 months ago
- 1b2ee3e CPU: Depthwise: Generate correct size for input indirection array. by David Mansell · 12 months ago
- eb5696d Optimize CpuReshapeKernel by Anitha Raj · 1 year, 1 month ago
- 580ecd7 Fix depthwise convolution not using assembly kernel by Viet-Hoa Do · 12 months ago
- 246fe08 Fix various static check issues by Viet-Hoa Do · 12 months ago
- 48b6d17 Check CL command buffer extension by Viet-Hoa Do · 12 months ago
- 7d91c61 Fix out-of-scope CLBufferMemoryRegion's buffer still in queue issue by SiCong Li · 12 months ago
- 338ef46 Optimize CLReduce for Min/Max Axis=0 by Gunes Bayir · 1 year, 1 month ago
- 29e27b0 Add support for S64 output in NEArgMinMaxLayer by Pablo Marquez Tello · 1 year ago
- 66b4a6a Setup pre-commit and include code formatting scripts by Gunes Bayir · 1 year, 1 month ago
- f77b969 Avoid using CLMatMul in CLFullyConnected when GPUTarget is Midgard by ramy.elgammal@arm.com · 1 year ago
- e1c96e7 Port DirectConv2d to CKW backend by Jakub Sujak · 1 year ago
- 78ce273 Document the Conv2D heuristic by Gian Marco Iodice · 1 year ago
- 4f76a00 Fix ReduceMean validate issue by Viet-Hoa Do · 1 year ago
- 0c19f59 Fix CL Tile operator by Viet-Hoa Do · 1 year ago
- 16b3752 Port ElementwiseBinary to CKW part 2 by SiCong Li · 1 year, 1 month ago
- 9129549 Retain back-compatibility for arm_compute/core/Types.h by SiCong Li · 1 year, 1 month ago
- 23882a9 Add GpuKernelArgumentBinding for runtime argument setting by SiCong Li · 1 year, 1 month ago
- 0a59e69 Fix problem with exception handling in CPPScheduler by Matthew Bentham · 1 year, 1 month ago
- 8dfb882 Enable S64 output in CLArgMinMax by Pablo Marquez Tello · 1 year, 1 month ago
- 2e0714d Fix failing CTS tests by disabling matmul when weights conversion is required. by Mohammed Suhail Munshi · 1 year, 1 month ago
- 4a1c917 Add support for input S64/U64 in CpuCastKernel by Pablo Marquez Tello · 1 year, 1 month ago
- 314d3e2 Break up core/Utils.h to reduce unused code being included everywhere by Matthew Bentham · 1 year, 2 months ago
- 66f3d38 Port ClTemplateCast into Ckw by Adnan AlSinan · 1 year, 1 month ago
- 4184e86 Port ClTemplateActivation into Ckw by Adnan AlSinan · 1 year, 1 month ago
- 205ba24 Added S64/U64 support for the input in CLCast by Pablo Marquez Tello · 1 year, 1 month ago
- a359ee9 Fix excessive calls to clReleaseCommandQueue by SiCong Li · 1 year, 4 months ago
- 4c30de0 Enable premultiplication for depthwise convolution with fp16 and quantized types by Michael Tyler · 1 year, 1 month ago
- c8e1617 Add compute kernel writer arguments export by Viet-Hoa Do · 1 year, 1 month ago
- 8e2dede Add Bias to MatMul Kernels and add support for use in Fully Connected Layer by Mohammed Suhail Munshi · 1 year, 1 month ago
- 5ff4802 Port operations to CKW prototype by Nikolaj Jensen · 1 year, 1 month ago
- 4c0a38a Disable kernel size 3 in argminmax for axis 0 by Pablo Marquez Tello · 1 year, 1 month ago