aboutsummaryrefslogtreecommitdiff
path: root/src/core
AgeCommit message (Collapse)Author
2021-08-04Fix depthwise convolution assembly kernelsFreddie Liardet
Resolves: COMPMID-4710 Change-Id: I35b964731aeed0e6f4f873f59341bee48e4a41fd Signed-off-by: Freddie Liardet <frederick.liardet@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6039 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-08-04Avoid over-allocation of temporary buffers within CpuWinogradConv2dGeorgios Pinitas
Resolves: COMPMID-4716 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ie036d2bb7a243301a62f089b3920ebee0f409190 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6028 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2021-08-02Add missing limits includeFreddie Liardet
Add missing limits include. Remove redundant limits includes. Resolves COMPMID-4756 Signed-off-by: Freddie Liardet <frederick.liardet@arm.com> Change-Id: Ibfd0e48617d2eec79a8558cbe502b50864c0940b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6029 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-08-02Benchmark and set default LWS for GEMM, Direct convolution and WinogradGiorgio Arena
Resolve COMPMID-4487, COMPMID-4488, COMPMID-4489 Change-Id: Id5a1178a5a452a969b41eea48cb36727e4dbe27b Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6014 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-30Compilation issue: neon=1 armv8.2 on Android with NDKr18beta1Gian Marco Iodice
- The issue was related to the __fp16 specialization on the depthwise convolution layer (cpu) Resolves COMPMID-4741 Change-Id: I6072230c60df6659951db2a1adf611eca6ab7efe Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6026 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-29Fix A55 performance constant for fp16 hybrid gemm kernelGeorgios Pinitas
Resolves: COMPMID-4737 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ia334ecacb38d9c39a73fd65c21445f9195b1aa5b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6018 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-29Port NEConvolutionLayerMichalis Spyrou
Resolves: COMPMID-4507 Change-Id: I9557026ec0052b5585994f7a1300a14565c976d0 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5964 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-28Create custom flags for enabling fp16 supportGeorgios Pinitas
Resolves: COMPMID-4655 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I1c1398b39da6da089b288d032074b270d87510c4 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6010 Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-28Reduce binary footprint of CpuConvertFullyConnectedWeightsKernelMichele Di Giorgio
Binary size reduction for this kernel is almost 50%. Also remove unused NEConvertFullyConnectedWeightsManaged. Change-Id: Ia46a1342a0737397b4aac2578d963c2ebb7446e3 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6011 Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-28Fix bare metal build issuesFreddie Liardet
Add missing limits includes. Fix error from std::min/std::max not being found Signed-off-by: Freddie Liardet <frederick.liardet@arm.com> Change-Id: If4146131073fc7f0506833a8529780bc5bde2a2e Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6004 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-28Fix cpu GEMM fp16 issueFreddie Liardet
Fix issue where incorrect window variable was used for calculation in the cpu GEMM fp16 case. Signed-off-by: Freddie Liardet <frederick.liardet@arm.com> Change-Id: I3a0257906e6de312b3d6fd696f118f66aae6e0c1 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6012 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-28Reorganize the kernels into nhwc, nchw and common foldersAdnan AlSinan
- Adding the flags for NCHW and NHWC resolves COMPMID-4453 Change-Id: If6a0783aa04b403d568f0ac0c7cf9016134409cd Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5997 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-28Remove generated kernels that overlap hand-written onesGeorgios Pinitas
Generated kernels are not used at the moment. Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I3ba767a53f78e4409c70a850c8051f6ee7453358 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6008 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-27Port CLGEMMConvolutionLayerManuel Bottini
Details: port CLWeightsReshapeKernel to ClWeightsReshapeKernel port CLGEMMConvolutionLayer to ClGemmConvolution Resolves: COMPMID-4515 Change-Id: I7d5b4ec72db2742f6eb9f3ffc88f717c35b4f2a3 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5983 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-27Update GEMM assembly performance parametersGeorgios Pinitas
Resolves: COMPMID-4709 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I20913c6153b8b86edf6e83d5f64175dcdf76dab4 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6002 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-26Add missing limits includeFreddie Liardet
Signed-off-by: Freddie Liardet <frederick.liardet@arm.com> Change-Id: I663521a99b396a10d3b43947364c27a0ddc299fe Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5994 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-25Reorganize the kernels into nhwc, nchw and common foldersAdnan AlSinan
The Following kernels have been split into nchw/nhwc kernels files: - batchnormalization_layer - batch_to_space - channel_shuffle - depth_to_space - dequantization_layer - im2col - normalization_layer - normalize_planar_yuv_layer - normalize_planar_yuv_layer_quantized - pooling_layer - pooling_layer_quantized - remap - reorg_layer - scale - scale_quantized - space_to_batch - space_to_depth - upsample_layer - winograd_filter_transform - winograd_input_transform - winograd_output_transform The following kernels have been moved to nchw folder: - direct_convolution1x1 - direct_convolution3x3 - direct_convolution5x5 - direct_convolution_quantized - prior_box_layer The following kernels have been moved to nhwc folder: - direct_convolution - dwc_native_fp_nhwc - dwc_native_quantized_nhwc The following kernels have been removed: - sobel_filter While the rest kerenls have been moved to the common folder. Partially resolves COMPMID-4453 Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com> Change-Id: Ic327ac935687ec351c610c65a3c6357f364a5a58 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5919 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-23Fix vector_length identification mechanism for SVEGeorgios Pinitas
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I1196a5e3357a616f76b0ab1e92b15544b3c01247 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5976 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-23Port NEFullyConnectedLayer to memory injecting interfaceMichele Di Giorgio
Resolves: COMPMID-4501 Change-Id: Ib61b3d06974009e501b3fb86467735427e13a94a Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5931 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-23Fix bare metal build errorFreddie Liardet
Resolves: COMPMID-4703 Signed-off-by: Freddie Liardet <frederick.liardet@arm.com> Change-Id: I52d4b6823fefe8a7e992476a89c8d6b721d02c5c Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5980 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2021-07-22Fix oclgrind int overflow warningFreddie Liardet
Fix warning found by oclgrind. Also remove duplicated code. Resolves COMPMID-4675 Signed-off-by: Freddie Liardet <frederick.liardet@arm.com> Change-Id: I6ad56cc0130b5df936f1e070db116695269317df Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5974 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-22Update GEMM assembly kernelsGeorgios Pinitas
- Introduce Fp32 kernels with internal calculations in Bfloat16 when fast_mode is enabled - Improve kernel selection heuristics Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I68a9e7e862b6fd2721b46e0d7cc791091c4ab279 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5965 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-16Include limits header to fix errors reported by GCC11Michele Di Giorgio
Resolves: COMPMID-4654 Change-Id: Idec018f9b2fb267293fc3f54d51e8ccf895df77e Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5961 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-16Avoid multiple Rhs matrix transformation on ClGemmGeorgios Pinitas
ClWinogradConv2d was performing Rhs transformation on every step impacting the performance. Adds scope logging support through ARM_COMPUTE_LOG_MSG_WITH_FUNCNAME Resolves: COMPMID-4596 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ib329d3bc8d8aa21abae9fabfe61de35cc84d4819 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5925 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-16Port CLIm2ColKernel to ClIm2ColKernelManuel Bottini
Resolves: COMPMID-4516 Change-Id: I6a6db66797fa801dfe1238fceca413277241d2ec Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5946 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-15Port NEGEMMConvolutionLayerManuel Bottini
Details: port NEWeightsReshapeKernel to CpuWeightsReshapeKernel port NEGEMMConvolutionLayer to CpuGEMMConvolutionLayer Resolves: COMPMID-4509 Change-Id: I3c7051e2c3f6d808a7ccb898aad70e5b221b9dc3 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5938 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2021-07-15Improve filelist for GPUGeorgios Pinitas
Resolves: COMPMID-4653 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I4f69d42369bf8ab91cd027acf1c97e92ec1ef554 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5948 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-15Port CLCol2ImKernel to ClCol2ImKernelManuel Bottini
Resolves: COMPMID-4517 Change-Id: I50cb02116a1ab86fc29200371944c4774e830746 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5949 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-14Fix CL kernel compilation failureMichalis Spyrou
A typo was causing errors when building some CL kernels. Resolves: COMPMID-4637 Change-Id: I7d1821e1a046ef8ccd306f72afe192732dd2ad1e Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5944 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-13Add in-place calculation support for CL elementwise arithmetic kernelsSheri Zhang
- Add in-place calculation support in ClArithmeticKernel, ClSaturatedArithmeticKernel and ClMulKernel - Add in-place test cases Resolves: COMPMID-4431 Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: Id484bdb76b74478a33fedb471ae0c7f799c599f6 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5885 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-13Port NEWinogradConvolutionLayerMichalis Spyrou
Rename to CpuWinogradConv2d Allow memory to be injected externally Change-Id: I1f0a26ea533e326a7c63df86e708895c31752a39 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5926 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2021-07-09Limit the LOOP_UNROLLING on the kernel heightGian Marco Iodice
To reduce the risk of having a long OpenCL kernel, we limit the loop unrolling on the kernel height. In particular, we unroll only if the kernel height is less than or equal to 5 Resolves COMPMID-4604 Change-Id: Iece787989f36afb90f1c7676b53d9015e652bdbd Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5916 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-09Port NECol2ImKernelManuel Bottini
Resolves: COMPMID-4511 Change-Id: Id6335cb23ef22bba02083498025da0ecb1647714 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5898 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-08Remove redundant implementations of Add/Sub operatorsGeorgios Pinitas
Allows only implementations where inputs/output are of the same data type and removes legacy Computer Vision ones. Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ia2b3d23a04236aab682f0c36a1110a30f7c06d1c Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5900 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-08Port NEGEMMLowp Part 2Manuel Bottini
Details: Extend NEConvertQuantizedSignednessKernel Port NEGEMMInterleave4x4Kernel to CpuGemmInterleave4x4Kernel Port NEGEMMTranspose1xWKernel to CpuGemmTranspose1xWKernel Port NEGEMMLowpMatrixAReductionKernel to CpuGemmLowpMatrixAReductionKernel Port NEGEMMLowpMatrixBReductionKernel to CpuGemmLowpMatrixBReductionKernel Port NEGEMMLowpOffsetContributionOutputStageKernel to CpuGemmLowpOffsetContributionOutputStageKernel Port NEGEMMLowpOffsetContributionKernel to CpuGemmLowpOffsetContributionKernel Resolves: COMPMID-4403 Change-Id: I3227f052f25e7b41d073bbea1da8a881fcd78b8e Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5875 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2021-07-07Validate unsupported data types with runtime informationGeorgios Pinitas
Check for Fp16 and Bfloat16 support was done using compile time information. Switch to use runtime information through CPUInfo Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ia3fa20c2b9b93be889667deb2e9366eb7cbe4aea Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5915 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-06Fix manual LOOP_UNROLLINGGian Marco Iodice
The issue is caused by the number of iterations passed to LOOP_UNROLLING. When we use the manual LOOP_UNROLLING, the number of iterations must be less than or equal to 128. To overcome this problem, we create a utility function to check if any of the critical iterations (kernel dimensions) are beyond that limit. If so, the utility function, disable the manual loop unrolling. Resolves COMPMID-4609 Change-Id: I7221c967609e462a5abd1cbb74e2a120f344fcb3 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5913 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-06Port NEIm2ColKernelManuel Bottini
Resolves: COMPMID-4510 Change-Id: Ia3e588f599449d975dabad4afafb2974dd44d0ad Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5899 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-05Improve implementation selection speed of CpuElementwiseUnaryGeorgios Pinitas
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I94f2b9135a7de78888418f0af33e3e5f78e2a1fa Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5901 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-02Rework OpenCL Depthwise ConvolutionGian Marco Iodice
- Remove dedicated kernels for NCHW. Now we only use NHWC with permute - Remove specialized kernels for 3x3 NHWC - Simplify CLDepthwiseConvolutionLayer.cpp to call just the native implementation for both floating-point and quantized data types - Develop two parametric opencl kernels for depthwise convolution layer NHWC (floating-point and quantized) - Add support to export the weights to cl_image - Extend test for depthwise convolution on opencl Resolves COMPMID-4417 Change-Id: Ibe533f79c2860f9cac8e921895d5a8f947753a5c Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5893 Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-02Align kernel/operator header layoutGeorgios Pinitas
- Redirect validate documentation to configure - Align header names - Align class layout Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ia40f67383826a66e9f9a33745d66805551e31a3a Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5897 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2021-07-02Implement FP GPU depthwise convolution 1x1 kernel for in-place computationSiCongLi
* Implement in-place graph node mutator for 1x1 depthwise convolution * Add in-place to validation fixture except for DepthwiseConvolutionLayerNativeValidationFixture as it would be a duplicate test otherwise (DepthwiseConvolutionLayerNative test tests the underlying kernel) Resolves: COMPMID-4432 Change-Id: Id7f10f5ebdce7d49f550c0b62dbaaab7f5b59d29 Signed-off-by: SiCongLi <sicong.li@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5874 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2021-07-01Add quantization helper functions for OpenCLGeorgios Pinitas
Add `T_QUANTIZE8_PER_TENSOR` and `T_QUANTIZE8_PER_CHANNEL` that can be used to perform quantization on tile constructs. Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ie8e1efcb895c64715620acf2212b1de9a857ee0a Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5891 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-07-01Reduce binary size footprint of CpuGemmInterleave4x4KernelMichele Di Giorgio
Change-Id: I7f3790d8ca592ec46ff2e2de810cf402191a990e Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5881 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-07-01Adjust minimum DDK version for manual unrollGiorgio Arena
Resolve COMPMID-4602 Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Change-Id: I4727586711a0dbdc859b043cfd55d0335f1c8eb0 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5888 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-06-30Revert "Rework OpenCL Depthwise Convolution"Gian Marco Iodice
This reverts commit 561c176598cd14245e2e7918fdf136d1c888d1da. Reason for revert: <validation> Change-Id: I6f2d61c27520439bb538e9265736532104b24cf8 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5127 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-06-29Port the ClGemmLowp kernels to the new APIGeorgios Pinitas
Ported kernels: - CLGEMMLowpMatrixMultiplyNativeKernel - CLGEMMLowpMatrixMultiplyReshapedKernel - CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel - CLGEMMLowpOffsetContributionKernel - CLGEMMLowpOffsetContributionOutputStageKernel - CLGEMMLowpQuantizeDownInt32ScaleByFixedPointKernel - CLGEMMLowpQuantizeDownInt32ScaleByFloatKernel - CLGEMMLowpQuantizeDownInt32ScaleKernel Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I9d5a744d6a2dd2f2726fdfb291bad000b6970de2 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5870 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-06-29Port NEGEMM to memory injecting interface (Part 2)Michele Di Giorgio
- Port NEGEMMMatrixMultiplyKernel to the new API Partially resolves: COMPMID-4402 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Change-Id: I52b67055dc24bb3a417d6ec5aeeee86e21b74320 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5873 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-06-29Enable global pooling optimization on OpenCLGian Marco Iodice
- Add loop unrolling on X and use POOL_X and POOL_Y defines for the for loop Resolves COMPMID-4573 Change-Id: I33cb825cfb55912ccb0ab9d03bd33a3dab4c8b44 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5872 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-06-29Port NEGEMM to memory injecting interface (Part 1)Michele Di Giorgio
- Start porting NEGEMM to the new API - Port NEGEMMInterleave4x4Kernel to the new API - Port NEGEMMMatrixAdditionKernel to the new API - Port NEGEMMTranspose1xWKernel to the new API - Remove padding from NEGEMMMatrixAdditionKernel - Remove unused INESimpleKernel and ICPPSimpleKernel Partially resolves: COMPMID-4402 Change-Id: I63edadddfe00a54586e5384d6a0211db25ae9042 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5857 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-02 09:45:13 +0000