MNN/source/backend/cpu
xinhao.zheng 332912cb6b Integrate KleidiAI sme int4 kernel
Add logic to select micro kernel functions when SME2 is enable.
Thread number will be forced to 1 when run matmul, for better
energy efficiency ratio.
2025-02-11 14:23:54 +08:00
..
arm Integrate KleidiAI sme int4 kernel 2025-02-11 14:23:54 +08:00
bf16 MNN:Sync: Sync Internal 3.0.4 2025-01-22 16:28:36 +08:00
compute Integrate KleidiAI sme int4 kernel 2025-02-11 14:23:54 +08:00
x86_x64 MNN:Sync: Sync Internal 3.0.4 2025-01-22 16:28:36 +08:00
BinaryUtils.hpp [MNN:Sync] Sync Internal 2.9.1 2024-06-03 20:09:34 +08:00
CMakeLists.txt Update the KleidiAI version to r0.5.0. 2024-12-10 18:24:00 +08:00
CPUArgMax.cpp
CPUArgMax.hpp
CPUAttention.cpp MNN:Sync: sync internal 3.0.3 2024-12-31 15:34:41 +08:00
CPUAttention.hpp MNN:Sync: sync internal 3.0.3 2024-12-31 15:34:41 +08:00
CPUBackend.cpp MNN:Sync: Sync Internal 3.0.4 2025-01-22 16:28:36 +08:00
CPUBackend.hpp Merge pull request #3120 from yiyangfan01/kleidiai_0.5.0 2025-01-02 16:06:06 +08:00
CPUBinary.cpp MNN:Sync: Sync Internal 3.0.1 2024-12-02 10:12:08 +08:00
CPUBinary.hpp MNN:Sync: Sync Internal 3.0.1 2024-12-02 10:12:08 +08:00
CPUBinaryInt8.cpp MNN:Sync: Sync Interal 3.0.2 2024-12-19 20:34:17 +08:00
CPUBinaryInt8.hpp [MNN:Sync] Sync Internal 2.8.2 2024-02-29 16:21:40 +08:00
CPUCast.cpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
CPUCast.hpp [MNN:Sync] Sync Internal 2.9.1 2024-06-03 20:09:34 +08:00
CPUConvolution.cpp MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00
CPUConvolution.hpp MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00
CPUConvolutionDepthwise.cpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
CPUConvolutionDepthwise.hpp MNN:Sync: Sync Internal 2.9.6 2024-10-14 19:26:28 +08:00
CPUCropAndResize.cpp
CPUCropAndResize.hpp
CPUDeconvolution.cpp MNN:Sync: Sync Internal 3.0.4 2025-01-22 16:28:36 +08:00
CPUDeconvolution.hpp MNN:Sync: Sync Interal 3.0.2 2024-12-19 20:34:17 +08:00
CPUDeconvolutionDepthwise.cpp MNN:Sync: Sync Internal 2.9.4 2024-08-24 15:46:21 +08:00
CPUDeconvolutionDepthwise.hpp
CPUDepthwiseConvInt8.cpp MNN:Sync: Sync Internal 2.9.6 2024-10-14 19:26:28 +08:00
CPUDepthwiseConvInt8.hpp [MNN:Sync] Sync Internal 2.6.2 2023-07-31 14:24:48 +08:00
CPUDequantize.cpp
CPUDequantize.hpp
CPUDet.cpp [Sync] Sync internal gitlab 2022-05-06 19:51:20 +08:00
CPUDet.hpp [Sync] Sync internal gitlab 2022-05-06 19:51:20 +08:00
CPUDetectionOutput.cpp
CPUDetectionOutput.hpp
CPUDetectionPostProcess.cpp
CPUDetectionPostProcess.hpp
CPUDynamicQuant.cpp MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00
CPUDynamicQuant.hpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUEltwise.cpp MNN:Sync: Sync Internal 3.0.4 2025-01-22 16:28:36 +08:00
CPUEltwise.hpp
CPUEltwiseInt8.cpp MNN:Refractor: Remove external support for mini so, depercerate eltwiseint8 2024-12-20 10:12:53 +08:00
CPUEltwiseInt8.hpp
CPUExternalConst.cpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUFixedPoint.hpp fix: compile error: ‘int32_t’ is not a member of ‘std’ 2023-11-03 17:55:20 +08:00
CPUFloatToInt8.cpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
CPUFloatToInt8.hpp MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00
CPUGridSample.cpp MNN:Sync: Sync Internal 3.0.1 2024-12-02 10:12:08 +08:00
CPUGridSample.hpp [MNN:Sync] Sync Internal 2.8.0 2023-12-04 11:19:10 +08:00
CPUHistogram.cpp [MNN:Sync] Sync Internal 2.5.3 2023-06-16 09:42:45 +08:00
CPUHistogram.hpp Sync Internal 2.0.4 2022-08-12 10:30:48 +08:00
CPUImageProcess.cpp MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00
CPUImageProcess.hpp [MNN:Sync] Sync Internal 2.8.2 2024-02-29 16:21:40 +08:00
CPUInstanceNorm.cpp MNN:Sync: Sync Interal 3.0.2 2024-12-19 20:34:17 +08:00
CPUInstanceNorm.hpp
CPUInt8ToFloat.cpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
CPUInt8ToFloat.hpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
CPUInterp.cpp [MNN:Sync] Sync Internal 2.6.0 2023-07-05 11:44:25 +08:00
CPUInterp.hpp [MNN:Sync] Sync Internal 2.6.0 2023-07-05 11:44:25 +08:00
CPUInterp3D.cpp [MNN:Sync] Sync Internal 2.5.3 2023-06-16 09:42:45 +08:00
CPUInterp3D.hpp [MNN:Sync] Sync Internal 2.5.3 2023-06-16 09:42:45 +08:00
CPULayerNorm.cpp [MNN:Sync] Sync Internal 2.9.1 2024-06-03 20:09:34 +08:00
CPULayerNorm.hpp [MNN:Sync] Sync Internal 2.9.1 2024-06-03 20:09:34 +08:00
CPULinSpace.cpp
CPULinSpace.hpp
CPUMatMul.cpp MNN:Sync: Sync Internal 2.9.3 2024-07-22 20:51:06 +08:00
CPUMatMul.hpp [MNN:Sync] Sync Internal 2.9.1 2024-06-03 20:09:34 +08:00
CPUMatrixBandPart.cpp
CPUMatrixBandPart.hpp
CPUMoments.cpp MNN:Sync: Sync Interal 3.0.2 2024-12-19 20:34:17 +08:00
CPUMoments.hpp
CPUNonMaxSuppressionV2.cpp [Sync] Sync internal Gitlab 2022-02-18 11:30:27 +08:00
CPUNonMaxSuppressionV2.hpp
CPUOPRegister.cpp MNN:Sync: Sync Interal 3.0.2 2024-12-19 20:34:17 +08:00
CPUOneHot.cpp
CPUOneHot.hpp
CPUPlugin.cpp
CPUPool.cpp [MNN:Sync] Sync Internal 2.7.2 2023-10-18 10:31:02 +08:00
CPUPool.hpp [MNN:Sync] Sync Internal 2.7.2 2023-10-18 10:31:02 +08:00
CPUPoolInt8.cpp [MNN:Sync] Sync Internal Gitlab 2.4.3 2023-04-18 18:54:46 +08:00
CPUPoolInt8.hpp [MNN:Sync] Sync Internal Gitlab 2.4.3 2023-04-18 18:54:46 +08:00
CPUProposal.cpp MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00
CPUProposal.hpp MNN:Sync: Sync Internal 2.9.5 2024-09-12 12:57:57 +08:00
CPUQuanConvolutionDepthwise.cpp [MNN:Sync] Sync internal Gitlab to 2.0.2 2022-07-19 13:52:07 +08:00
CPUQuanConvolutionDepthwise.hpp
CPUQuantizationUtils.hpp
CPUQuantizedAdd.cpp [MNN:Sync] Sync internal Gitlab to 2.0.2 2022-07-19 13:52:07 +08:00
CPUQuantizedAdd.hpp
CPUQuantizedAvgPool.cpp [MNN:Sync] Sync internal Gitlab to 2.0.2 2022-07-19 13:52:07 +08:00
CPUQuantizedAvgPool.hpp
CPUQuantizedLogistic.cpp [MNN:Sync] Sync internal Gitlab to 2.0.2 2022-07-19 13:52:07 +08:00
CPUQuantizedLogistic.hpp
CPUQuantizedMaxPool.cpp [MNN:Sync] Sync internal Gitlab to 2.0.2 2022-07-19 13:52:07 +08:00
CPUQuantizedMaxPool.hpp
CPUQuantizedSoftmax.cpp [MNN:Sync] Sync internal Gitlab to 2.0.2 2022-07-19 13:52:07 +08:00
CPUQuantizedSoftmax.hpp
CPURNNSequenceGRU.cpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
CPURNNSequenceGRU.hpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
CPUROIAlign.cpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUROIAlign.hpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUROIPooling.cpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUROIPooling.hpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPURandomUniform.cpp [MNN:Sync] Sync internal gitlab 2022-01-04 10:50:40 +08:00
CPURandomUniform.hpp [MNN:Sync] Sync internal gitlab 2022-01-04 10:50:40 +08:00
CPURange.cpp [Sync] Sync Internal 2.1.2 2022-09-30 10:02:52 +08:00
CPURange.hpp
CPURaster.cpp MNN:Sync: Sync Internal 3.0.4 2025-01-22 16:28:36 +08:00
CPURaster.hpp MNN:Sync: Sync Internal 3.0.1 2024-12-02 10:12:08 +08:00
CPUReduction.cpp [MNN:Sync] Sync Internal 2.9.1 2024-06-03 20:09:34 +08:00
CPUReduction.hpp
CPURelu.cpp MNN:Sync: Sync Interal 3.0.2 2024-12-19 20:34:17 +08:00
CPURelu.hpp [MNN:Sync] Sync Internal 2.7.2 2023-10-18 10:31:02 +08:00
CPUResize.cpp [MNN:Sync] Sync Internal 2.5.3 2023-06-16 09:42:45 +08:00
CPUResize.hpp [MNN:Sync] Sync Internal 2.6.0 2023-07-05 11:44:25 +08:00
CPUResizeCache.cpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUResizeCache.hpp [MNN:Sync] Sync Internal 2.7.0 2023-09-04 10:42:11 +08:00
CPURuntime.cpp Resolve some conflicts 2025-02-11 10:28:51 +08:00
CPURuntime.hpp Refactor MNN KleidiAI interface 2025-01-07 10:18:20 +08:00
CPUScale.cpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUScale.hpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUScaleInt8.cpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUScaleInt8.hpp [MNN:Sync] Sync Internal 2.5.3 2023-06-16 09:42:45 +08:00
CPUSegmentMean.cpp
CPUSelect.cpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUSelect.hpp
CPUSetDiff1D.cpp
CPUSetDiff1D.hpp
CPUSoftmax.cpp MNN:Sync: Sync Internal 2.9.3 2024-07-22 20:51:06 +08:00
CPUSoftmax.hpp MNN:Sync: Sync Internal 2.9.3 2024-07-22 20:51:06 +08:00
CPUStft.cpp Optimize Stft func 2025-02-10 11:27:48 +08:00
CPUStft.hpp Optimize Stft func 2025-02-10 11:27:48 +08:00
CPUSvd.cpp Sync Internal 2.0.4 2022-08-12 10:30:48 +08:00
CPUSvd.hpp [Sync] Sync internal 2.0.3 2022-07-22 09:59:30 +08:00
CPUTFQuantizedConv2D.cpp [MNN:Sync] Sync internal Gitlab to 2.0.2 2022-07-19 13:52:07 +08:00
CPUTFQuantizedConv2D.hpp
CPUTensorConvert.cpp [MNN:Sync] Sync Internal 2.8.4 2024-04-19 11:58:21 +08:00
CPUTensorConvert.hpp
CPUTopKV2.cpp [MNN:Sync] Sync Internal 2.7.2 2023-10-18 10:31:02 +08:00
CPUTopKV2.hpp [MNN:Sync] Sync internal gitlab 2022-01-04 10:50:40 +08:00
CPUUnary.cpp MNN:Sync: Sync Internal 3.0.1 2024-12-02 10:12:08 +08:00
CPUUnary.hpp [MNN:Sync] Sync Internal 2.7.2 2023-10-18 10:31:02 +08:00
CPUUnique.cpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
CPUUnique.hpp
CPUUnravelIndex.cpp [MNN:Sync] Sync internal gitlab 2021-11-30 10:10:53 +08:00
CPUUnravelIndex.hpp
CPUWhere.cpp [MNN:Sync] Sync internal gitlab 2021-11-30 10:10:53 +08:00
CPUWhere.hpp
GridSampler.hpp MNN:Sync: Sync Internal 2.9.6 2024-10-14 19:26:28 +08:00
KVCacheManager.cpp MNN:Sync: sync internal 3.0.3 2024-12-31 15:34:41 +08:00
KVCacheManager.hpp MNN:Sync: sync internal 3.0.3 2024-12-31 15:34:41 +08:00
OneDNNConvInt8.cpp MNN:Sync: Sync Internal 3.0.0 2024-11-18 14:40:27 +08:00
OneDNNConvInt8.hpp
OneDNNConvolution.cpp
OneDNNConvolution.hpp
ThreadPool.cpp MNN:Sync: Sync Internal 2.9.3 2024-07-22 20:51:06 +08:00
ThreadPool.hpp MNN:Sync: Sync Internal 2.9.3 2024-07-22 20:51:06 +08:00
UnaryUtils.hpp [MNN:Sync] Sync Internal 2.8.0 2023-12-04 11:19:10 +08:00