aboutsummaryrefslogtreecommitdiff
path: root/src/runtime
AgeCommit message (Collapse)Author
2023-04-28Fix OMPScheduler run_workloads single thread issueSiCong Li
Resolves COMPMID-6032 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Icca60deac7308173fc3a8282af91434b4d1c0b06 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9520 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-04-26Change fp16 GeMM heuristic for Arm® Mali™-G77Gian Marco Iodice
- Replace existing heuristic with look-up tables - Expected performance improvement is between 5-15% on various models Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Change-Id: Ie26ddf66895ede131aa06fde7b200ef94d2dd467 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9472 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-04-26Integrate multi-threaded pretranspose_B_arraySiCong Li
This is required for the case where rhs (B) is dynamic and needs to be pretransposed in every run. In a multi-threaded setting, this means the previously single-threaded pretranspose_B_array would become the bottleneck Resolves COMPMID-5896 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Id508c46992188a0f76a505152931d4955d04c16d Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9455 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-04-14Fix dynamic weights for CPU connected layerViet-Hoa Do
Resolves: COMPMID-5995 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I707b8918bebee7e70d4de5207ef555c806e7a305 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9405 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-04-13Implement MatMul Function and Operator with Floating Point support for CPUMohammed Suhail Munshi
- Implements MatMul function and operator for floating point datatype FP16/FP32 - Includes support for transposing dynamic tensors prior to matrix multiplication. - Adds tests for 2D/3D/4D+ tensors in MatMul with F32/F16 datatype (with all combinations of transposed/not-transposed tensors) - Updates fixture to allow for testing fused activation in MatMul - Adds tests for matmul with and without fused activation Resolved: [COMPMID-5898] Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> Change-Id: Iefa84b26dd723c9a51e6c3f91023152c6c31ace2 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9411 Reviewed-by: SiCong Li <sicong.li@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-04-04Support dynamic weights for Fully Connected layers on GPUJakub Sujak
The fully connected function and operator running on GPU have been adapted to support dynamic weights. Dynamic weights require the reshape and data layout conversion of weight tensors at runtime in the prepare stage of the operator. The implementation for GPU is identical to the CPU implementation. This patch also deprecates the `are_weights_reshaped` option in Fully Connected. Resolves: COMPMID-5870 Change-Id: I28f967695879d82cc91a928d95308a4e0e52a597 Signed-off-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9403 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-04-03Implement MatMul FunctionRamy Elgammal
Resolves: COMPMID-5949 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: Idd8cfe6ea94a14f0b23178f6781251b5f0955563 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9390 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-04-03Add Cropping to CLBatchToSpaceOmar Al Khatib
- Deprecate dynamic block shape interface - Iterate over output window instead of input window for simpler implementation and better performance. - Add cropping support and cropping tests Resolves [COMPMID-5865] Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com> Change-Id: Ic67d44a6a39299ecdafc507f12e3dc5d517dfb62 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9385 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-03-30Add cropping support to NEBatchToSpaceSiCong Li
- Deprecate dynamic block shape interface - Iterate over output window instead of input window for simpler implementation and better performance - Add cropping support and cropping tests Resolves COMPMID-5918 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Ifea0f5f7760ffd0f4d5d4f3a5ae8d14d0b98b790 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9378 Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-03-21Add dynamic weights for CPU fully connected layerViet-Hoa Do
Resolves: COMPMID-5917 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I073067b490f2a1b96b81a037ea431c9a2e5c7503 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9322 Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-03-14Add CropInfo to BatchToSpace reference and fixtureSiCong Li
Partially resolves COMPMID-5918, COMPMID-5865 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Ib3b01e7dc1c944184a4c038045bf0469fbb9ff45 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9321 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-03-06Fix LWS search space used by CLTunerSiCong Li
* Ensure CLTuner uses the real GWS used by run(), instead of the static GWS (which is usually changed at run time), by caching GWS in each kernel Note this is a somewhat inelegant workaround. The real issue stems from the fact that execution window and scheduler are very much coupled with our operator run() / run_op() method. (Please see COMPMID-5934) * Restrict LWS values to explore within GWS bound for exhaustive mode * Refactor gws_from_window() to include all the information required to calculate GWS * Log lws search space used for tuning * Fix ClDirectConv2dKernel config id Resolves COMPMID-5892 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I420490d8b94d13ada2e44eb0a12078f883379334 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9193 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-03-03Add weights_info as optional input for NEDeconvolutionLayerAnnop Wongwathanarat
This is so that we can leverage fixed format kernel when using gemm convolution method. Partially resolves: [ONCPUML-1129] Change-Id: I61ffa74f5cd9d75579dbc1f9aa187371f855e932 Signed-off-by: Annop Wongwathanarat <annop.wongwathanarat@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9248 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-02-14Extend skip upsampling for deconvolution for non-1x1 kernelsAnnop Wongwathanarat
Skip upsampling step for deconvolution when input strides are 1 regardless of kernel size. This is achieved by setting correct paddings for unit strides convolution. Resolve: [ONCPUML-1183] Change-Id: Ief88f9fe30f6f56d3358e3cf6a506ab8b5691f18 Signed-off-by: Annop Wongwathanarat <annop.wongwathanarat@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9134 Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-02-09Fix performance regression in Transposed ConvolutionGunes Bayir
Resolves: COMPMID-5849 Change-Id: I86f8bbc1f3a7c12c66d5ad8fcd74dd9e69629aa0 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9102 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Dynamic-Fusion: Jakub Sujak <jakub.sujak@arm.com>
2023-02-01Add new operator AddMulAdd for Neon™ backend for Float/Quantized typesGunes Bayir
This is a fused operator that merges Add + Mul + Add [+ Relu-based-Activation] layers and have an intermediate output after the first Add. It's supported for FP16/32/QASYMM8/QASYMM8_SIGNED data types. The subsequent Add and Mul are intended for scaling and the coefficients only have one dimension (per channel). The inputs are - input1 : nD tensor [X, Y, Z, W, ..] - input2 : nD tensor [X, Y, Z, W, ..] - add_coef : 1D tensor [X] - mul_coef : 1D tensor [X] The outputs are - out1 : nD tensor (intermediate output) [X, Y, Z, W, ..] - out2 : nD tensor (final output) [X, Y, Z, W, ..] The operation can be summarized as follows: out1 <- input1 + input2 out2 <- Act(out1 * mul_coef + add_coef) The activation function can be Identity, Relu, Bounded Relu or Lower/Upper Bounded Relu. The intermediate output can be skipped by providing a nullptr. The reason of providing this operator is to be able to fuse in case of Residual network patterns and save computations by reducing memory back and forward. Resolves: COMPMID-5463 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Change-Id: I8ef577aa623b036e9a9f655cc088493fd19a6109 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9055 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-02-01Remove fixed format strides hackJonathan Deakin
- Remove hack in CpuGemmAssemblyDispatch.cpp which tried to guess strides for fixed format kernels. Instead, expect that strides will have been correctly set on weights externally - Update fixed format test fixtures to set the strides - If the fixed format uses fast math mode, then weights should be of type BFLOAT16. Change the validation logic to accept this. Resolves: [ONCPUML-1131] Co-authored-by: Milos Puzovic <Milos.Puzovic@arm.com> Change-Id: I0f18d8b86b0f639be25fd122fa06a591e90645f2 Signed-off-by: Jonathan Deakin <jonathan.deakin@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8985 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-01-30Skip upsampling for deconvolution when not neededAnnop Wongwathanarat
If the input tensor's stride is 1 and the kernel size is 1x1, skip upsampling step and pass the input tensor pointer for convolution directly. Partially resolve: [ONCPUML-1137] Change-Id: I9de9444ff99cf35d44a51ccbe0fa6facc1035d27 Signed-off-by: Annop Wongwathanarat <annop.wongwathanarat@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8994 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-01-23Fix performance regression when stride equal to kernel sizeGunes Bayir
This patch prefers Gemm-based transposed deconvolution algorithm in case kernel sizes and strides are equal to each other in each dimension. Resolves: COMPMID-5815 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Change-Id: I22052e48341f3284d6bafbdbcce4a48399dc8e87 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8970 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2023-01-20Add enable_fast_math for NEDeconvolutionLayerAnnop Wongwathanarat
Resolves: [ONCPUML-1128] Signed-off-by: Annop Wongwathanarat <annop.wongwathanarat@arm.com> Change-Id: I287a71222d3f0289d8cccfcb15383b0a930a55e6 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8952 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2023-01-18Revert "Update the heuristic for CLDepthwiseConvolutionNative kernel"Gian Marco Iodice
Resolves COMPMID-5813 Change-Id: I5ef6fe9fb6a54db18e41a71085896fd08bc08dbb Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8975 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-01-12Update the heuristic for CLDepthwiseConvolutionNative kernelGian Marco Iodice
- Use T_LOAD2D_INDIRECT macro instead of T_LOAD_NHWC_WITH_DILATION in the depthwise convolution opencl kernels - Update the heuristic for Arm® Mali™-G77 Resolves COMPMID-5716 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Change-Id: I32d375b220e04bf05f5d8f0af2231bde600f0665 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8930 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-12-30Move DWC native heuristic into the heuristic folderGian Marco Iodice
- Move the DWC native heuristic from CLDepthwiseConvolutionLayer to heuristic/ - Update the heuristic for Arm® Mali™-G77. Use a smaller block size (4x2) for Fp16 - Call the new heuristic in GpuDepthwiseConv2d Resolves COMPMID-5798 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Change-Id: I6bfd30cea76bea2e98202a7a5c1d51709f3382a4 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8889 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-12-29Update the ClConv2d heuristicGian Marco Iodice
- Update the ClConv2d heuristic to call indirect convolution on Arm® Mali™-G77 Gpus - Implement the indirect conv2d heuristic for selecting the block size Resolves COMPMID-5713 Change-Id: If6ad49124561207153685c6abd4f54950a376fbc Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8886 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-12-21Optimize MeanReduce by integer acc. and removing upfront dequant.Omar Al Khatib
Resolves: [COMPMID-5466] Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com> Change-Id: I68af0bb54580bebd2ace1fba30aa73f7f68a4dbb Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8804 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-12-14Optimize Transposed Convolution for CL backend (Quantized)Gunes Bayir
This patch optimizes transposed convolution for QASYMM and QASYMM8_SIGNED types, by extending the transposed convolution kernel written for FP32/16. Resolves: COMPMID-5723 Change-Id: Iab8f09231938adb949c506fd915ed45b885e5c7c Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8792 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-12-09Use heuristics for setting dynamic fusion direct conv2d tile sizesRamy Elgammal
Resolves: COMPMID-5735 Change-Id: I9958413b69c5052cfa205dd0e9457cc4953aaf35 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/474818 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8724 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-12-09Implement the OpenCL kernel to compute the indirect convolutionGian Marco Iodice
- Implement indirect convolution kernel - Add operator support - Add test Resolves COMPMID-5709 Change-Id: I9272304163471a5a40da7fdec204599f3c1d8e32 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8701 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-11-22Remove dynamic fusion prototype with tests and examplesSiCong Li
Public headers of the new experimental dynamic fusion can be found in arm_compute/dynamic_fusion/ New examples on how to use the interface can be found in tests/validation/dynamic_fusion/gpu/Integration.cpp Resolves COMPMID-5683 Change-Id: I7ccb902a227fb487562df15fc3c30118d1d95bbd Signed-off-by: SiCong Li <sicong.li@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8671 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-11-18Add num_threads_to_use to OMPScheduler based on workload sizecfRod
Fixes benchdnn test failures in ONCPUML-1104 when num_threads is greater than workload size. Signed-off-by: Crefeda Rodrigues <crefeda.rodrigues@arm.com> Change-Id: Ic351a3ab5b548aa1843042a053130b02d0f1d40e Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8655 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-11-14Optimize Transposed Convolution for CL backend (FP32/16)Gunes Bayir
This patch optimizes transposed convolution for CL backend by rewriting it in a single kernel instead of three (flip_kernel + upsample + conv). The new kernel skips the upsampling step which reduces the input space of convolution by stride_x * stride_y, resulting in significant performance improvement. It also skips the kernel flipping by traversing the weights accordingly, thus reduces the memory footprint. Resolves: COMPMID-5676 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Change-Id: I8a333212dc7c5f7f0597aa58b0d56d44814baa14 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8588 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-10-06Rework DepthwiseConvolution heuristic on OpenCLGian Marco Iodice
Resolves COMPMID-5632 Change-Id: I2bdbe69a610ca2510fbd74d5d412842679299762 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8365 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-09-16Optimize Quantized/Integer Bilinear Scale for Neon™Gunes Bayir
This patch introduces several performance optimizations regarding the Bilinear Scale operator with REPLICATE Border mode. Changes apply only to NHWC. This patch - Reduces the memory footprint by disabling precomputation of indices and weights when they're not used - Rewrites the kernels for QASYMM8/QASYMM8_SIGNED/U8(Uint8) - Adds S8(Int8) Bilinear Scale for Border mode REPLICATE - Removes Bilinear Scale SVE kernels for Quantized and Integer types and adjust the heuristics to choose the Neon™ implementation - Adds new test cases where the input and output of the Bilinear Scale operator have different quantization scale and offset Resolves: COMPMID-5453, COMPMID-5454 Change-Id: I3d251e76e0c6978fd5a0a1795ec62ab536bec93c Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8250 Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-09-09Optimize FP32/16 Bilinear Scale Kernel for Neon™Gunes Bayir
This patch removes index and weight pre-computations where it's not used and reduces some calculations inside the inner-most loop of Scale. Resolves: COMPMID-5452 Change-Id: Ie149b1b76a90a8cb659ada0f97aef78caf69932f Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8220 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-09-07Optimize depthwise convolution on OpenCLGian Marco Iodice
The optimization concerns the case where the depth multiplier is > 1. The depth multiplier for loop has been removed from the OpenCL kernel and the GWS has been mapped to the output shape. In this way, we can still perform a tile with N0 columns and improve the performance of depthwise conv over 80% when depth multiplier is > 1. Resolves COMPMID-5568 Change-Id: I604e287d4eeb31c54b9cc6c3072a698cd0e3e136 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8184 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-09-01Use parent buffer in CLSubTensor. This avoids calling enqueueMapBuffer ↵Murray Kornelsen
repeatedly when mapping multiple children of the same parent. Signed-off-by: Murray Kornelsen <murray.kornelsen@mail.mcgill.ca> Change-Id: I7ff554915a37320dfd94f15a6fb01a72a235cf39 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7920 Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-08-24Fix validation problem in CLQLSTMLayerPablo Marquez Tello
* Resolves MLCE-799 Change-Id: I3d5b2afbf65d159aa5e645743c1e139110dfc20e Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8093 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-08-11Fix CTS/SLTS failure related to Depthwise ConvolutionGunes Bayir
The issue is caused by GPUTarget not being set explicitly for the Depthwise convolution kernel, but it's being used in its build configuration. This causes the default value to be used and enables some unsafe FP optimizations. Resolves: COMPMID-5490 Change-Id: I5300a1168962cacb62cf49db795f052cf6740c7e Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8059 Reviewed-by: SiCong Li <sicong.li@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-08-03[ONCPUML-968] Fixed format kernel support in additional APIsMilos Puzovic
Implements required plumbing in order to be able to ask and execute fixed format kernels from NEFullyConnected, NEGEMM and NEGEMMConv2d. These APIs are used to accelerate oneDNN primitives (inner product, matrix multiplication and indirect GEMM respectively) and without changes it would not be possible to call fixed format kernels from those oneDNN primitives. Change-Id: I27534f0491ce28d0ccb98c19f318bd33dcdf2ff5 Signed-off-by: Milos Puzovic <milos.puzovic@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7999 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-08-01Fix for OpenMP scheduler work breakdownMilos Puzovic
If number of work items is greater than number of available threads then OpenMP scheduler will only execute as many work items as there are threads. This fix makes sure that we iterate through all work items and execute all of them. Change-Id: I3ad4b732c01fadc70dacaf09af3007d2b31086c7 Signed-off-by: Milos Puzovic <milos.puzovic@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8001 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
2022-07-26Fix for inclusion of "arm_gemm" from src into "Types.h" from coreRamy Elgammal
- Added arm_compute::WeightFormat and converted to/from arm_gemm::WeightFormat when needed through two map function. - Moved to_string(WeightFormat) to TypePrinter.h Resolves: COMPMID-5415 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: I65f7942100bcd4dbf2c5cf6c07f26c8e1e3bf86e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/438511 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Sicong Li <sicong.li@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7985 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-07-19[ONCPUML-951] Variable weight support for Convolution.Francesco Petrogalli
API changes for NEGEMMConvolutionLayer and CpuGemmConv2d Built with: scons neon=1 opencl=0 os=linux arch=armv8.2-a multi_isa=1 \ build=native -j32 Werror=false validation_tests=1 build_dir=opt \ standalone=1 asserts=1 experimental_fixed_format_kernels=1 . Tested with: ./build/opt/tests/arm_compute_validation Hardware where the test executable was run: Neoverse N1 Test coverage: * NEGEMMConvolutionLayer, CpuGemmConv2d * NHWC (the only one supported by the fixed-format kernels) * F16, F32 * Shapes: RunSmall Change-Id: I4fd3e495a7cbf61210ea02d37440ba9652934e99 Signed-off-by: Francesco Petrogalli <francesco.petrogalli@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7632 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-07-14Integrate new winograd APIs from MLTechramelg01
Resolves: COMPMID-5400 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: Ib4428436dd7a6e40d8b2d8a2f8dac1b079154551 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7894 Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-07-13Add Gemm MMUL Reshaped Only Rhs Support for FP32/FP16Gunes Bayir
This patch introduces a GEMM routine that is optimized for Arm(R) Mali(TM)-G715 and Arm(R) Mali(TM)-G615 Resolves: COMPMID-5216 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Change-Id: I2e5d7806f5904347185bb3e250f73d73d6669dba Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7914 Reviewed-by: SiCong Li <sicong.li@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-07-07Add missing flag when building cl graph examples and fixMichalis Spyrou
incorrect cl cache behaviour Resolves: COMPMID-5286 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Change-Id: I1aa82825ef7d31d7830a00282d1a3523ccf1d746 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7883 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-31Fix compilation error in 32-bit with logging buildViet-Hoa Do
* Use %zu format specifier for size_t data. Resolves: COMPMID-5377 Change-Id: I84e6aea8ab34ca4616eeecfb06d573eaa329bd67 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7649 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-06Integrate Dynamic Fusion patchesSiCong Li
* Add public interfaces: * OperatorGraph: Describe a workload that could contain fused kernels * IWorkload: Generic interface for workloads built from OperatorGraph * ClWorkload: OpenCL workloads built from OperatorGraph * ClCompositeOperator: Runtime async operator to execute a ClWorkload * DependencyGraph (will likely be deprecated in later iterations) * Add example * cl_fused_conv2d_elementwise_add.cpp to explain how to use the new interfaces * Add internal translation layer * Refactor ClKernelBuildingAPI * Remove non-tile based gemm native kernel component * Minor interface changes * Add integration tests Resolves COMPMID-5161 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Ib987ed79289ab0bcbd3130d54f5793408d9f1240 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7510 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-06QLSTM add support for different qinfoMike Kelly
* Resolves MLCE-604 Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ice3d6f361588f1a6bd0bff301c27b0d063a5c014 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7529 Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-04-21NEQLSTM: perform type conversion in prepare method.Pablo Marquez Tello
* When input_to_forget_weights is QASYMM8_SIGNED, the conversion to QSYMM8 is done in the prepare method * Partially resolves MLCE-604 Change-Id: Iddadbc50d77381542451ac4e46de49b2706bc88c Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7441 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-04-14Enable dynamic cl tuning for dynamically fused kernelsSiCong Li
* Add new tune_kernel_dynamic interface * Add generate_config_id Resolves: COMPMID-5154 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I39870e59fceda875487970061ceb2048995c5a45 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7400 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-27 06:42:23 +0000