aboutsummaryrefslogtreecommitdiff
path: root/src/core/CL/kernels/CLReductionOperationKernel.cpp
AgeCommit message (Collapse)Author
2019-10-04COMPMID-1816: Use parallel reduction on 0 axis in CL ARG_MIN/ARG_MAXManuel Bottini
Parallelization of reduction along x axes Removal of the use of padding Fast vector implementation of reduction operation Change-Id: I3a56c57b9fc1135cf8f79d1021d966ea22b084b1 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/1791 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-09-30COMPMID-2671: Change ArgMinMax NEON/CL output type to Signed32Michele Di Giorgio
Change-Id: I718f3884928271c5b0afb259d5bfe9df284f18e6 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/1995 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-08-24COMPMID-2451: Use kernel lws_hint() on enqueueGeorgios Pinitas
Avoid querying device's default lws on kernel enqueue as this is already cached in the kernel during configuration. Change-Id: Ia26ecb712caeb8f042356815e0cfd23522764d27 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/1803 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-05-24COMPMID-2278: Implement REDUCE_MAX operator for CL.Usama Arif
Change-Id: Ie23e3ddc45d6f5506a63f935758a215ba7412bf5 Signed-off-by: Usama Arif <usama.arif@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/186031 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/1214 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-05-22COMPMID-2281: Implement REDUCE_MIN operator for CLUsama Arif
Change-Id: I60fd3affad0ab5a2f1cef18aaa46dc2dc448caeb Signed-off-by: Usama Arif <usama.arif@arm.com> Reviewed-on: https://review.mlplatform.org/c/1194 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-05-20COMPMID-2243 ArgMinMaxLayer: support new datatypesMichalis Spyrou
Change-Id: I846e833e0c94090cbbdcd6aee6061cea8295f4f9 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/1131 Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-04-11COMPMID-1959: Implements 2D FFT on OpenCLGeorgios Pinitas
Change-Id: I73cf3984a5463acc854c8a59dc2bd9a5234cd99c Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/936 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-03-29COMPMID-1995: Removed layout checks from Reduction opsPablo Tello
Change-Id: Icd8d153da63c53c51d3a2e3ea6bc7de5938934f2 Signed-off-by: Pablo Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/913 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-02-22COMPMID-1710: Add FP16 support checks.Georgios Pinitas
Change-Id: I6291847935996859ab245160714f9fbefb03b5be Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/761 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-02-15COMPMID-1710: Add check on different input/output quantization info were not ↵Isabella Gottardi
supported Change-Id: Id64dab5e2de341316238506d4fb3ab82b992753d Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/697 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-01-14COMPMID-1724: CL Implement ProdManuel Bottini
Change-Id: I17e51f25064b53a8f7e13d6fcbecc14a192de103 Reviewed-on: https://review.mlplatform.org/387 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-12-07COMPMID-1821 (Nighlty) CL/ArgMinMax/Float/ clEnqueueMapBuffer failuresMichalis Spyrou
Change-Id: I5a9d698f459fd7efdbe85d70d092e79e961cb4dd Reviewed-on: https://review.mlplatform.org/368 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-11-30COMPMID-1728 CL: Implement ArgMax/ArgMinMichalis Spyrou
Change-Id: I7eae2e55cc0b0b7bbebb7617299daaca6f75f40c Reviewed-on: https://review.mlplatform.org/292 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-1632 Add CLL2NormalizationLayer for NHWC and FP32Michalis Spyrou
Change-Id: Iae22554d5fe893fd22a000eab5bfd8275ea06eb3 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/154102 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: bsgcomp <bsgcomp@arm.com>
2018-11-02COMPMID-1574 Implement ReduceMean in OpenCLMichalis Spyrou
Change-Id: Id331199f569f52a37280a9ada5bf84694580b93c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/152843 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
2018-11-02COMPMID-1478: Stop relying on static default OpenCL objects in cl2.hppAnthony Barbier
This causes problems when ACL is used as a shared library on Android. Fixes some problems related to creation / destruction order between the Graph's CL backend and core / runtime Change-Id: I716d63fd42f4586df1ffbb6fa97e4db06d3a781b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143228 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-1410 (Nightly) Mismatches in CLMeanStd function for floatMichalis Spyrou
Change CLReductionOperation border to be multiple of 64 instead of 16. The opencl kernel works only with local_size(0) being a power of 2. This will generate a padding of 63 if input_width % 64 = 1, but I don't think it's a big issue and it keeps the border calculation pretty simple. Also, increased tolerance for fp32 because there were mismatches for the 4K image. Change-Id: Id44990a262b2d6eff4c8ce56eb7c886274d9847e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143415 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-1226 Extend CLMeanStdDev to support FP32 / FP16Michalis Spyrou
- Extend support for FP16 in CLReduction. - For F16/F32 MeanStdDev we perform one reduction operation for mean and one for stddev and we calculate the final result in the host CPU. Change-Id: Iad2099f26c0ba7969737d22f00c6c275634d875c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/135870 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-970 : Remove QS8 / QS16 supportVidhya Sudhan Loganathan
Removed fixed point related code. Change-Id: I487acf138dace3b0450e0d72ca7071eaec254566 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/137678 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-1143 - Excessive padding in CLReductionOperationKernel when ↵Michalis Spyrou
configuring window Now max padding is equal to 15 instead of 127. If input width is less than 128 we decrease the number of threads in the WG. Change-Id: I5ff0b6fd8cb46143ba49e745ec9ad01f691bdd80 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/134152 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-948: Remove unused code in CLReductionOperationKernelJohn Richardson
Remove redudant code left over from validation method refactoring. Update output shapes in CL/ReductionOperation Validate test suite. Change-Id: Ica846dd7f65380fa21708472e10b5bc609a32027 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/131207 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-948: Add validation to CLL2NormalizeLayerJohn Richardson
Change-Id: I452a718a60b81da51cd3e98641fd99c86c4debab Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/129451 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-834 Fix arm_compute_nightly_validation getting killedMichalis Spyrou
Changed CLReductionOperationKernel: Now each kernel computes a 2D slice instead of 1D. This reduces the memory footprint from around 1.6Gb for a 4k input image to a few Mb, which was caused by the __local memory and was probably the cause for this bug. Change-Id: I71ac71ff09b041c945a134177600f0f3475e48cf Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/117835 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-417 Fix reduction kernel's __local buffer sizeMichalis Spyrou
Change-Id: If97a79d86b174b1d9b41360303d624e3b2d22001 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/87703 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
2018-11-02COMPMID-476 L2 Normalization for CLMichalis Spyrou
Change-Id: I88f87173645880eb823916c5d4ac884c372a4fb4 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/83269 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-20 13:14:27 +0000