aboutsummaryrefslogtreecommitdiff
path: root/src/core/NEON/kernels/NEActivationLayerKernel.cpp
AgeCommit message (Collapse)Author
2019-09-13COMPMID-2659: Activation.SQRT Failure on NEONMichele Di Giorgio
When one of the inputs is zero in a NEON vector our computation of square root returns -nan. This patch adds a small epsilon to the input to avoid this issue. Change-Id: I0357001fd2ff0f868acfaae66b47b6962dbb0144 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/1921 Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-08-23COMPMID-2460: Add ELU activation on NEON,CL,GLESGeorgios Pinitas
Change-Id: I641b12fcfc5dc4a18d2d489c38673b937125dfb9 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/1796 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-07-01COMPMID-2407: Add (logistic and tanh) activation support for QSYMM16 for NEONgiuros01
Change-Id: Ib89c9cfe12975e51d1710af736c73ce79e667363 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/1412 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-06-05COMPMID-2372: Add support for QASYMM8 for TanhGeorgios Pinitas
-Perform calculations in the floating point domain -Extends checks for Logistic as scale should be 1/256 and offset 0 Change-Id: I90ef4a042f053976936f5d28f8e09b54eec196a2 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/1287 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-06-03COMPMID-2225: Add interface support for new quantized data types.Georgios Pinitas
Add support for: -QSYMM8, 8-bit quantized symmetric -QSYMM8_PER_CHANNEL, 8-bit quantized symmetric with per channel quantization Change-Id: I00c4ff98e44af37419470af61419ee95d0de2463 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/1236 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-05-16COMPMID-2194: Add identity function to NEActivationLayerKernel.cppUsama Arif
Change-Id: Id9bc53722b7dfe277812e9e1d749ac4cea35260a Signed-off-by: Usama Arif <usama.arif@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/184712 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/1143 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-05-01COMPMID-1995: Fix clang-tidy warningsMichalis Spyrou
- Remove VirtualCall checks - Fix some unused variables errors - Use std::array insted of C style arrays - Various fixes Change-Id: Ife6170b7102de42b8f04e298dcf8476bf90779f0 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/1049 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-03-15COMPMID-1995: Fix NEActivation LogisticIsabella Gottardi
Code simplified due to accuracy problem. Change-Id: Ife14656ca831655489bf43d6cf59b241d482b11e Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/c/861 Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-02-08COMPMID-1916: Add support for QASYMM8 LOGISTIC activation in NEActivationLayerIsabella Gottardi
Change-Id: Ia9f47e8612b91594773092217c0fe43c6a92c401 Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/625 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-01-30COMPMID-1710: Fix NEActivationLayer map for QASYMM8Isabella Gottardi
Change-Id: I6c11568f8933d074541a28ef782954460e00d851 Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/596 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
2019-01-16COMPMID-1710: Fixes substitution errors in bare_metal build.Georgios Pinitas
Change-Id: Icf76503b4d01e90a682b9bed0798a8a635840e46 Reviewed-on: https://review.mlplatform.org/528 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-14COMPMID-1809: Remove padding in NEGEMMConvolutionLayer 64-bit path.Georgios Pinitas
Change-Id: I1806591a2c73a1f057f13d8c6107d7b9796a82c8 Reviewed-on: https://review.mlplatform.org/370 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
2018-11-21COMPMID-1800: (Nightly) Mismatches in SC9863 board for NEON FP16Michele Di Giorgio
Fixes for: - ReduceMean, reduction on the X axis for FP16 with 8 elements was performed only up to a certain point. The fix now takes into account the number of elements of the vector and does as many reductions as necessary. - YOLOLayer, activation for FP16 has to be performed on 32 bits until the FP16 approximations is fixed. Change-Id: I75373f4edd37de476e6fe1a56de3ef386b65c619
2018-11-02COMPMID-1534: Fix NEActivationLayer for FP16Georgios Pinitas
Simulates Logistic, Tanh and SoftRelu in FP32 Change-Id: I9950f7636b8ff2f3e054937e5ef414e45dfe06f5 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145357 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-1419: Make NEGEMMAssemblyDispatch dynamically typed instead of templatedAnthony Barbier
This makes it easier to integrate in GEMMLowpMatrixMultiplyCore Change-Id: Ibf80803f016a2e6a24d943ffafb50b48f04ec545 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/140868 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@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-959: Fix bug in NEActivationLayerKernel (CONST_0-QASYMM8)Isabella Gottardi
Change-Id: I05ca7f6c22e110f3a748c1940847cdcdf2359ba7 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/122242 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-871: Remove vst4q/vld4q from NEActivationLayer.Georgios Pinitas
Change-Id: Iebd2a8fece1af87c93d6795e176d8c37ca64bbf6 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118187 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-842: Add NEON QASYMM8 RELU ActivationMichele Di Giorgio
Change-Id: I7197d2ad7ac08112eba1570a257ad011b1ce0b75 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/117404 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02IVGCVSW-820: Add QASYMM8 support to NeonActivationLayerKernelMichel Iwaniec
Change-Id: Ic3881e97b4fcbae0ac287a1e010cfc6f0fd8d7d1 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/112139 Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-617 Add validation methods to KernelsMichalis Spyrou
- NEActivationLayer - NESoftmax - NEDirectConvolutionLayer - NENormalizationLayer - NEPoolingLayer Change-Id: Ib279f1c1b7f9247679b0d6593aed7393da8fe87b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111335 Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-556: Add support to build arm64-v8.2-a for Android platform (clang ↵Ioan-Cristian Szabo
compiler) Change-Id: Ibb779dd3a8d10786da6d8f70590e654e14654d7b Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95530 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com>
2018-11-02COMPMID-634: Enable clang with libc++ to compile for Android (32 and 64 bits)Ioan-Cristian Szabo
Change-Id: I693f64e70cd478e93675a8b04360128ded3b60d4 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/93015 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-481: Add thread info parameterMoritz Pflanzer
Change-Id: Iebb50a88d017445b6b37a86563ebd4abd86c5cf5 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/86788 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-519: Add support for Lower and Upper Bounded RELU for CL/NEONGeorgios Pinitas
Change-Id: I7b16216ac59c899a33942bf17757b54535256d7a Reviewed-on: http://mpd-gerrit.cambridge.arm.com/86172 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-09-17COMPMID-421: Added FP16 support in ActivationLayer.Pablo Tello
Change-Id: I7ba573b19d56e3c87996edb5218a00e5bfca451e Reviewed-on: http://mpd-gerrit.cambridge.arm.com/79755 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
2018-09-17COMPMID-417: Add Leaky RELU support for both NEON/CL.Georgios Pinitas
-Adds parametrizable leaky relu (x>0) ? x : a*x. Change-Id: Ief19a435b5832a30b56f4aaaf55125787addee94 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/80575 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
2018-09-17COMPMID-427: Port NEActivationLayer in 16bit fixed point.Georgios Pinitas
Change-Id: Iebd61807f7b597c6bd990673bc7655c68ee16f4b Reviewed-on: http://mpd-gerrit.cambridge.arm.com/79085 Reviewed-by: Moritz Pflanzer <moritz.pflanzer@arm.com> Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-09-17COMPMID-417: DepthConvert NEON for QS8/QS16.Georgios Pinitas
Change-Id: Ieb120bccf146045b3a0001ceb3893d4e67fd19df Reviewed-on: http://mpd-gerrit.cambridge.arm.com/79763 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Steven Niu <steven.niu@arm.com>
2018-09-17COMPMID-345 - In-place computation for Activation LayerGian Marco Iodice
Change-Id: I25ebfccc3d3e758cc8164e0b33805c0bb303891a Reviewed-on: http://mpd-gerrit.cambridge.arm.com/78226 Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-09-17COMPMID-344 Updated doxygenAnthony Barbier
Change-Id: I32f7b84daa560e460b77216add529c8fa8b327ae