Age | Commit message (Collapse) | Author |
|
Change-Id: I0e388e9898ea82a7a1af16a987890696bb489547
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2781
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: Iefdebff9d480d3a2bb9446af9ac12edb52500916
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2797
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Luca Foschiani <luca.foschiani@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I271317fd8f27145e22f857659f79095c523c2c1a
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2790
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
In the prior version, the outputs from MAX and MIN Reduction operation
kernels would never be written to the output, because they are
stored in vec_res_value, not vec_res_value[1-4].
Also, the prior branch test is probably a mistake, because ARG_MIN_IDX
case is handled in the previous if statement, so that branch could
never actually get executed.
This commit adds a path that will correctly write the reduction
operation results to the ouput.
Signed-off-by: Nate Craun <nate@natecraun.net>
Change-Id: Id977a6240fbee4668426a9c6b487ae65fab246d2
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2796
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Wrong data type was used for MIN/MAX reduction causing segfaults. This
patch also simplifies window calculation for non-parallel reduction.
Change-Id: I0abd9e84540801f92b306accd1439ff5df126a9e
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2792
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I048d1d7dda7edf587d37ce83a93b557d8a95754a
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2771
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I156d110ffbf06b07c74dec5be063c9aec864cd03
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2785
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com>
Change-Id: If7fc27b074e1fe758cf1474c323f432a096c3abf
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2772
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I6ea0ab7af7d2b9cb2dcb23627eb909cf7e88a5b0
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2775
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
|
|
Change-Id: I3f098c3c2c2031d8cbe7326eab88a4e78bda867f
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2704
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
|
|
Change-Id: I2cd0b5ee0ae2e3c65a04c7be70478b0452e55132
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2730
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I358c729cb81b83d35f1bc7f70ea593d5bff5f1ed
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2738
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
|
|
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Change-Id: Ie073d5fa6612381958c4bcb2405e607d5f4d6081
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2782
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
NEReduceMean and NEArgMinMaxLayer
Signed-off-by: Luca Foschiani <luca.foschiani@arm.com>
Change-Id: Icf198a983c8ce2c6cd8451a1190bb99115eac3af
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2652
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I943b4e03c2e7a9db9a78f80413b2d5d470381488
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2770
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com>
Change-Id: I0c153f7d880005aeced38cc64b7571578a5ea7f3
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2753
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
|
|
Signed-off-by: Luca Foschiani <luca.foschiani@arm.com>
Change-Id: I96d8cbef2e167e09484b0e9b5d8a12ffee0f6e67
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2755
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: Ia78cf1ec6cfcf047595ac6f9a866c36918ffe7be
Signed-off-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2744
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
types in PoolingLayer
Change-Id: I30af78f0d727389f81a8eb291020a1b6b305adf8
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2747
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
|
|
mobilenet quant
Rounding-to-nearest is already taken into account by adding 0.5f to the
result, so no need to use vcvtnq.
Change-Id: I2ee78d0abd5d1fb2c7d3133c316cb48d59d2497b
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2751
Reviewed-by: James Conroy <james.conroy@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Adds the ability to set the padding value in the pad layer node.
Change-Id: I2f323146cbdfdfd6cfd617ee4bcafb5ffafedbbb
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2727
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: If413b3fd45d81281627a2cdeaadfaa565b376b4d
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2724
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
source code
Change-Id: Ie1f31a49ea8c5da6a122367816961b80931308fa
Signed-off-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/225493
Tested-by: bsgcomp <bsgcomp@arm.com>
Signed-off-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2740
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Using a single requantization functions instead of dequantizing and quantizing every time
Change-Id: Ie62e4299d9e1dc2ae95fc742ef3ee3bb17cd4c78
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2693
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Both rounding-to-zero and rounding-to-nearest even generate mismatches
with difference of 1 between reference and OpenCL implementation.
Therefore, this patch adds a tolerance to the test.
Change-Id: Id01a04c2b738ba0cc2981b675824cf3a838dc7e9
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2737
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Removes fpermissive flag and fixes build errors on Android
with the addition of -ldl.
Change-Id: Ibc49e645e9d7d5ba67d4862c6e17f7151d65a1d6
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2722
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
NDK r20 is not consistent with how linkers/archivers are prefixed when compared to the compilers for 32-bit
e.g.
armv7a-linux-androideabi29-clang++
vs
arm-linux-androideabi-ld
Signed-off-by: alered01 <Alex.Redshaw@arm.com>
Change-Id: I7b9e271b34531b42af1ff8204effb8725669b558
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2707
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
++performance on few other networks
Change-Id: I2e1ec3f34543d43da649c3fb07f4a8e75d25a10b
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2716
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
The correct minimum/maximum values of QASYMM8 is used for padding.
Change-Id: Ia54e886e5acfd9c1236459b34d445bdc16446e3e
Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2721
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Move ERROR macros out of default branches in switch statements, to the
end of the function.
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I66d47eb0f2fc0a3ab4bf2dd4a01d8b0907786c98
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2709
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Pooling shape calculator was performing operations in the unsigned
domain leading to overflows in irregular shapes.
Thus, we perform all operations in the signed domain and we get the
maximum between the given shape and 1, returning always a valid tensor.
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: Ia95d7e54929c8bc29e99dc80a61065e403b29a94
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2467
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I3e642ea0bffca038a697b8cfb5db38e337876edc
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2703
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
|
|
Change-Id: I034f5aa023642f2323372495ddd14fc62b4c12e0
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2681
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
CLReduceMean
Change-Id: Ib6babd9ad80c57cf21c2f0ee2aab404221088595
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2670
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
|
|
Change-Id: Ibff0ea3b4420cb8a46a451e3c471eafeb8cfa473
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2694
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I25f004311342cc78189254aafab763ac87e6486d
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2692
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Disallows generation of scales equal to 0 on CustomConvolution fixture
as it is expected to fail according to the OpenVX specification.
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: Ie1311c1ebbb34c72dee62da8bfc6016c4e05b83e
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2687
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I4354c8940c4ab9b4f4bf21b5cbd04d96d812c8c0
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2686
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I48492f8c48b818b563bba1e0b48831ac5cdf1420
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2685
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
CLInstanceNormalizationLayer
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I91482e2e4b723606aef76afef09a8277813e5d1b
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2668
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I0114d6999413cbb0602db19c68b9c41c419c6df0
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2682
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I35276a3d95dc99a7f4dea00e89c8ed206a5f13f1
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2669
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
|
|
MMLA is a matrix-multiply instruction introduced on armv8.6-A
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I572a54981d48f5a1e0e9e51102cb7ae28ad87806
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2663
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Alters build system to build test framework only when at least one test
suite is needed.
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I97cfe55b7727210249478e321a9fd150b84f898f
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2653
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
"undeclared identifier" errors are fixed by putting missing
types for local variables.
Change-Id: I7adde6afb4554058657a37fb73c36a991ced1ee0
Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2667
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
|
|
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I6c9edd75c9462c1d27b21b9a5ba64b0431da5e81
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2662
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Removal of nightlies for 32bits architecture failures
Change-Id: I3569df2c20b6bccfb11600728be94183f6192393
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2655
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Use std::negate to negate the values of a vector instead std::bind1st
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I063c0d9a75df34cd4669e55ebc63b028a5f861f1
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2656
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
- use data layout from PoolingLayerInfo if it's available
- deprecate constructors without data_layout
- (3RDPARTY_UPDATE) modify examples and test suites to give data layout
Change-Id: Ie9ae8cc4837c339ff69a16a816110be704863c2d
Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2603
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Add support for all types in validation of
CLDepthwiseConvolutionLayerReshapeWeightsKernel. Also
added a few missing parentheses in reduction_operation.cl.
Change-Id: I7371ce6d5e402e9c2faafd7948e4643298bc1ace
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2641
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|