Age | Commit message (Collapse) | Author |
|
Change-Id: I6d5f91579850906e1eb973ff6c5612195255e631
|
|
Reduce the amount of precommit tests run in DirectConvolution,
Deconvolution and Pooling. Proper investigation scheduled for later.
Change-Id: Idc2510cf6877e7a605cead84f384852b609e3216
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/156466
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com>
|
|
Change-Id: Iac6a95ba7f388e65b7f1c8865c3e9bf289b233ea
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/155490
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
OpenCL
COMPMID-1424 - Add dot product support for CLDepthwise QASYMM8 3x3 NHWC non-unit stride
With this patch we are able to improve the performance of MobileNet v1-qasymm8 by 37 %
Tried to use the dot product instruction in CLDepthwise QASYMM8 3x3 NHWC non-unit stride
but I have not seen any benefit (maybe because we have few arithemtic operation and we
do not have more load instructions). However Depthwise convolution has been improved by
30%
Change-Id: Id768a99c2e53a04276707e427af5d0ec93419ada
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/155082
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
COMPMID-1690: Add tests for NEPermute with PermutationVector dimension > 3
Change-Id: I4bfc6ff88cd46863c2e39975b5663c624db1a63d
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/155316
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
Increase tolerance for fp32 and added absolute tolerance
Change-Id: Iff828457b514d6301ed2c8e04b66ce86867f72b6
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/155086
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
NEWidthConcatenateLayerKernel works with 4D tensors too, hence the check has
been removed and tests have been added.
Change-Id: I73814cabe5fae975a44cc1a03b092c552497e57d
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/155070
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
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>
|
|
Change-Id: Id974efad304c2513b8824a6561ad45ee60b9e7fb
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/153763
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
COMPMID-1651: Fix QASYMM8 CLDeconvolutionLayer
This patch also extends the range of values used for testing Convolution and
Deconvolution to cover quantized [-1.0f, 1.0f].
Change-Id: I8b280669db67bb3ec25bf5d411c8f5954f5b0dab
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149869
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
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>
|
|
NEON and CL normalization layer was generating invalida results for
radius > 4.
Change-Id: I15d846405e6b3492fe44920bbf8cadceb4e5258f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/153161
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Matteo Martincigh <matteo.martincigh@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|
|
Change-Id: Ida71312bcf6dbd854f2ab1efc65f74910c79e152
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/151510
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
|
|
Since this is floating point arithmetic the Winograd results will not be exactly
the same as direct convolution.
Changed to use relative tolerance for the nightly tests.
Change-Id: I45c6d60a097c2d4fb53650a2a33eb29a3e51d7ec
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/152324
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
|
|
Change-Id: I47033fa70881fd32b13266adb6ccbf10c202aabc
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/150344
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|
|
Change-Id: I82d95c4f1c5fed13b213a2591cc2b4e0d0e02a54
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149676
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
Change-Id: I9250b2e8020fe87c6ed4de582bbc7460bbd8e94b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/150287
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
Change-Id: Ice28996959dc666fff5e8ae486c1ff8093db083f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148367
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
Change-Id: I1f55508af6f220e5f41df7b56daffb4761ed0591
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148253
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
Change-Id: I780970f317b979b3230e2b471ac01df7fda9ee14
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148168
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I05d21f9a92013ecfd1128d12cf1561cfd6e5c5e9
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147983
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Fixed by increasing the tolerance in the nightly tests for
1xN and Nx1 kernel sizes.
Mismatches will happen occasionally since Winograd isn't numerically
equivalent to direct convolutionl; specially for the 1xNs where we
have quite a large window.
Change-Id: Ic7c8a002a8a767151b254e915bbd4b17fa96278b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148012
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Refactored the validate method to make it easier to maintain in the future when
adding support for new kernels sizes
Change-Id: I12d9fe7af15ceb0e655cef61ca94407558fb29e8
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146713
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I7422b977538ff29930a90f078badc2edee78af93
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146638
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Also extended tests on NEON
Change-Id: Icb0eced534e904ef807972dd3a31988f501bb02e
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147095
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Removes FP16 from HarrisCorners and CannyEdge.
Change-Id: I5e4f9205fdbe4de85f04f55ecf1568c837e56cc0
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146247
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
|
|
Change-Id: I44369b4a716767163e2233b7d87bff300c523383
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146314
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
COMPMID-1515: Add FP16 support to NEFloor and CLFloor
Change-Id: Ib63a62c7681056ee13be99ce081b4d3949da4217
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146547
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|
|
Change-Id: I6fe198881230e49864c841a3b2366ccf2a9247f9
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145210
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: I68f65b6dea7889d71b4a10021f59e6f0ab82903b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145590
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I33079e07acad83e0740c87b06546cc0f0f51301c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145164
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
+ validate() function
Change-Id: I12e4696a454744f6d493ab3a53520d3acf3a1a26
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145719
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: I7dee44deb360d057a689e92ad4c72c9a4309a789
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145715
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Accuracy issue
Change-Id: Ibbce625251524ee5aa62b15ac78ba0f70efcc7bc
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145585
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I0358de3a1d84ea2bc1be107694df5fcf847e19e2
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145538
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I99ebae61024a7bce9d17292a02c28626ae6c29d5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/144872
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
|
|
Change-Id: I1dd6df9bd4a96cb7cbacce939a89c3a7ccee71c8
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145397
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
On GEMM we had accuracy issue
On Magnitude we have disabled the fp16 acceleration since we do not have feature parity with CL
and this function is not used for ML
Change-Id: Iaebe3bbbd2a9f45db0c714aa5ebaf48eb0b65741
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145467
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
- Fixed GEMMConvolutionLayer test. The issue was related to the tolerance
- Fixed DirectConvolutioNLayer test. The issue was in the convolver_3x3
Change-Id: I9d5b906d7e5e32a0a34300d529d6edb804ac1c4e
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145377
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Simulates exp function in FP32
Change-Id: Ieffceeab64fda6f466f212b56f794cc44d477afa
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145367
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
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>
|
|
Change-Id: I0bdf874e61917903c26f713ec41a7ffc29e07233
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143892
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
DepthwiseConvolution
Change-Id: I751f5d3fb74085d2e67f610ecf52da4736d0cfb5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143870
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I183e4b7081bf12de3546293a00da68b4f4a0dd5e
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143987
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
FP16/QASYMM8
When the GEMM3D check fails, now we fallback to the classic implementation with im2col
and col2im. In this manner the function can work with QASYMM8 and FP16
Change-Id: I359e9da3a63956f33b5acbc9bca4383b14af10e2
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143372
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I4afb19751520a90fee27fb49b775cd10e92a94f5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/140476
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
This changes help to prevent errors like passing a matrix
with less elements than required into the warp functions.
Change-Id: I863f933a5e0568258717cffed3a20788d3d03083
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143044
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
This patch includes:
- Im2Col optimizations for NHWC using a new data layout
- Refactoring of CLIm2ColKernel adding validation method and auto-init
- Removed im2col_reduced from CLIm2ColKernel and created a new kernel CLFlattenLayerKernel
Change-Id: I1620640b6796baa268324b33ae92cdd8de53e27c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/141241
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
|
|
Change-Id: I55f0018ac7214775ebbca63f58a3bf5c93732fec
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/142632
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I429087f8aa436cf0877c3abec8fd7201bec1b81c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/141661
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|