aboutsummaryrefslogtreecommitdiff
path: root/src/cpu/kernels/CpuElementwiseUnaryKernel.cpp
AgeCommit message (Collapse)Author
2023-05-17Move lut kernel to sve2 categoryv23.05branches/arm_compute_23_05SiCong Li
This specific Lut kernel uses sve2 instructions Resolves: COMPMID-6268 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I44fa3812e96fa79b3d1e1e3a31d587581f59f0e1 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9675 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> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2023-04-17Fix unhandled case in ElementwiseUnaryRamy Elgammal
- Case: when the dequantized float value < 0.f the unary op was not called if operator is not LOG or RSQRT Resolves: COMPMID-5994 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: I24d69db22042701f506188ace91ea4ab3dafeccf Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9437 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
2023-04-11Enable quantized data types for CpuElementwiseUnary on Armv7aRamy Elgammal
- Adding fallback functions neon_qasymm8_signed_elementwise_unary() and neon_qasymm8_elementwise_unary() - They would be called in case target is not aarch64 Resolves: COMPMID-5994 Change-Id: Id0db1e7cb0fe92f1eaef0b3a9ed2bea01b3f2a15 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9416 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>
2023-03-29Add quantized support for unary elementwise in CPUViet-Hoa Do
* Add quantized unary elementwise in CPU using LUT. * Widen the input data range of the test suite. - Fix CPU exponential function overflow/underflow range. - Fix saturation issue of CL round operator. Resolves: COMPMID-5763 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I41445de2b4a33ec6b01e0ab701516c240c852d0b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9367 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-02-14Add kernel selection UT for submitted kernelsDana Zlotnik
* Softmax kernel * Elementwise unary kernel * Elementwise binary ** This change require some refactor in the kernel cpp and h files Resolves COMPMID-5043 Change-Id: I58979b023ec31d759690847b3f85fc4baefbbf98 Signed-off-by: Dana Zlotnik <dana.zlotnik@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7033 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
2022-02-01 Enable kernel selection testing (Phase #2)Yair Schwarzbaum
Resolves COMPMID-4987 Change-Id: I1201ca3eae107989d13b6a2c6d9560de24fe112d Signed-off-by: Yair Schwarzbaum <yair.schwarzbaum@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7015 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-01-24Fix nightly failure within the elementwise unary build.Dana Zlotnik
Resolves COMPMID-5059 Change-Id: Ic3a76114cc4b0149e80b09494c33c896b6fe9012 Signed-off-by: Dana Zlotnik <dana.zlotnik@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6990 Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-01-19Decouple CpuElementwiseKernelDana Zlotnik
1- reorganize the folders struct according the new definition 2- separate between unary and binary implementations 3- decuple kernels - unary , binary op and binary comparision Resolves COMPMID-4634 Change-Id: I0195846cc372e74a63c659069a4508de53a22110 Signed-off-by: Dana Zlotnik <dana.zlotnik@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6860 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-01-12Enable kernel selection testing (Phase #1)Giorgio Arena
Change-Id: I1d65fb9d3a7583cf8d4163ca7c0fbee27dc52633 Signed-off-by: Yair Schwarzbaum <yair.schwarzbaum@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6767 Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-10-06Add missing ISA selection heuristicsGeorgios Pinitas
- Fixes identification heuristics for SVE2 based kernels in CpuAdd - Adds identification heuristics for SVE to CpuElementwise Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Id287dbd72fba81afc415d7aec74e06aae11984e3 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6369 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2021-08-25Move CPU/GPU files from Core/Runtime to the respective backend foldersGeorgios Pinitas
Legacy structure contained two libraries core/runtime with two backends in each. We reduce the core/runtime libraries to a single library thus merging the backend files Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I69545765fe7a730368105cdbd067d3135ec7a174 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6155 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>