aboutsummaryrefslogtreecommitdiff
path: root/arm_compute
AgeCommit message (Collapse)Author
2020-05-28move ndrange.hpp header into arm_compute directoryv20.05branches/arm_compute_20_05Vincent ABRIOU
ndrange.hpp file is needed by arm_gemm_compute_iface.hpp when building armnn. In a cross compilation environment like Yocto Openembedded, the installed include files comes from either /arm_compute, /include or /support directories. So to avoid armnn build failure, ndrange.hpp need to be moved in arm_compute/core/NEON/kernels/arm_gemm directory. Other files that need ndrange.hpp to build are updated accordingly. Signed-off-by: Vincent ABRIOU <vincent.abriou@st.com> Change-Id: Icc8e18b23dd06c56e0c49a84d4a51bfd85fe2290 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3271 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2020-05-22COMPMID-3069: Removing deprecated functions and classes from 20.05 releaseManuel Bottini
Change-Id: Ic4d20995d6c6bb76d07113e86247bad2722e4e83 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3244 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-20COMPMID-3497: Fix build LSTMParams<TensorInfo>Sang-Hoon Park
Copy of missing parameters is added to the build function. Change-Id: I06d665729a61f2f01dcfab21c6e6d55359fc81cb Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3226 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: James Conroy <james.conroy@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-05-15COMPMID-3289: Test improvement CLGEMMMatrixMultiplyReshapedKernel.morgolock
Change-Id: Ia6c2f115849889baceafaf716477456e41f96037 Signed-off-by: morgolock <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3186 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
2020-05-15COMPMID-3457: vexp failure in QASYMM8_SIGNED overflowingmorgolock
Change-Id: Ied11a4a3e9d04615a1a1f0bfa552f3dd8293a170 Signed-off-by: morgolock <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3178 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-13COMPMID-3483: Refactor NEDepthwiseConvolutionLayerNativeKernelMichalis Spyrou
Removed is_per_channel template arguments since it wasn't used anywhere and also made has_biases a runtime parameter. The total size reduction from this change is 28.6kb. Change-Id: I292ac27ae3ea2885b8438f613390486323982664 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3189 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-05-13Introduce CL kernel cache featureInki Dae
This patch introduces CL kernel cache feature for NN runtimes such as ARMNN or other in-house versions. Originally, this feature came from utils/Utils.cpp and utils/Utils.h files but was used just for testing. Caching CL kernel binaries is mandatory and required for real product because inference performance at first run is one of very important factors. This patch exposes two API - save_program_cache_to_file and restore_program_cache_from_file so that NN runtimes can use these API to cache the compiled CL kernel binaries. Changelog v1. - Reordered including headers suggested by Manuel Bottini. - Updated description. Changelog v2. - Drop function descriptions. Changelog v3. - Fix build error with opencl = 0. As for this, it moves two functions, save_program_cache_to_file and restore_program_cache_from_file, to src/runtime/CL/Utils.cpp and arm_compute/runtime/CL/Utils.h, and set ARM_COMPUTE_CL flag only when opencl = 1. This change makes CL kernel cache feature to depend on OpenCL support. Changelog v4. - Fix coding_standard_checks error. Changelog v5. - Add a new cpp file to Android.bp to fix coding_standard_checks error. Changelog v6. - rebased on top of master, and dropped _new_built_programs_map object so it adds compiled CL kerne binaries per model to a given file. Changelog v7. - Correct descriptions. - Correct arm_compute/runtime/CL/Utils.h file description. - Correct src/runtime/CL/Utils.cpp file description. - Drop ARM_COMPUTE_CL ifdef ~ endif from examples/cl_cache.cpp - Do not add 'ARM_COMPUTE_CL' flag at SConscript. Change-Id: I8c640fb1809ca79191daf5b1ff72a50dd492c36d Signed-off-by: Inki Dae <inki.dae@samsung.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2914 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-13COMPMID-3108: Add Winograd 3x3,4x4 FP16 support for NEONGeorgios Pinitas
Change-Id: I20680dc74a3d709297539e2132417308a7aecc9d Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3159 Reviewed-by: Michele Di Giorgio <michele.digiorgio@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>
2020-05-13COMPMID-3463 Refactor NECropKernelMichalis Spyrou
Removed most of the templates used in this kernel. This resulted in a reduction of 35Kb. Change-Id: I0d50aa769b361790d47a8017d795f2c92c6d8a6f Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3158 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
2020-05-13COMPMID-3464: Address NESoftmaxLayer failures for QASYMM8_SIGNEDGeorgios Pinitas
Normalization with the maximum value was causing results to wrap-around As a work-around we use saturating intrinsics to perform the operation Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I719b7ac7ad274dc2ae339bc4a055f9200134ed97 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3184 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-12COMPMID-3439: Fix peephole and projection in CLQLSTMLayerSang-Hoon Park
The followings are essential to make it work - QSYMM16 is added as supported data type in CLGEMMLowpOutputStage - Internal TensorCopyKernel is added similar to NEQLSTMLayer The followings are fix for related things. - Projection is modified to remove copy of projection_bias from NEQLSTMLayer. - Fix wrong argument for validate_mm() - validate_mm() now returns on error. Change-Id: Icbd04e9fdb8821eb41dd3e0a6a0980965b779714 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3177 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2020-05-12COMPMID-3442: Add support of negative axis in NESoftmaxLayer and reference codeSheri Zhang
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: I285cc3b74ac0a45f0ad5830baed5237cea568f15 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3147 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-12COMPMID-3470: Modify NE/CLQLSTMLayer interface to provide 3 outputsMichele Di Giorgio
Change-Id: I895b697c89c9a7509d48a54ac1effb7fbd8cca19 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3174 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
2020-05-12IVGCVSW-4744 CTS: RandomGraphTest LargeGraph failures in CpuAcc HAL 1.2 and 1.3Sadik Armagan
* Retain data layout for SpaceToBatchLayerKernel and BatchToSpaceLayerKernel Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I5bd0c3ca90a4964eda9f838c97c784aced0f4579 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3166 Reviewed-by: Manuel Bottini <manuel.bottini@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>
2020-05-12COMPMID-3316: NEDeconvolutionLayer failing for a big inputManuel Bottini
- Using NEDirectConvolution for big shapes since the memory required explodes for 9x9 kernel - Adding test cases - Fix enables only the NEON Deconvolution for NHWC Change-Id: I8a541346428e5686818f8ecb7f69e2a9106cbceb Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3135 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
2020-05-11COMPMID-3239: Fix projection and peephole in NEQLSTMLayerSang-Hoon Park
- Peephole and projection has been fixed to be working - Small internal kernel copying data between tensors to cover the case where num_units and output_size is different is added. Below is strictly outside of this patch's scope but are changes helping this patch working (directly or indirectly) or making NEQLSTM more complete. - Consideration for layer normalization is added to InfoHelpers - QSYMM8 data type is added to helper function to print out tensors. - NE/CLLSTMLayer::validate() logic has been modified to use correct value for shape validation. Change-Id: I40b4e71dfdbe8432caa2fe4a9af60a725362cc33 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3157 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-10[ONCPUML-7] arm_compute support for ND parallelismJoseph Dobson
Currently 1D ranges of work are specified by the scheduler via two integers, start and end. This limit opportunities for advance parallelism and scheduling This patch expands the interfaces to allow for ND parallism. `GemmCommon::get_window_size` now returns an `NDRange` specifying the work in N-dimensions rather than with the single integer it used prior (1D) Execute now takes an `NDCoordinate` which specifies an `NDRange` with a start position for that work along with an `NDCoordinate` to specify the thread location In addition to expanding the interface to enable this functionality, we have added the capability to SGEMM when the number of threads is high this has the effective of allowing a much greater degree of parallelism where te problem dimension would previously have limited the number of threads. Change-Id: I3e1a8b7276216627bec4ff6f24ac2147552ea9fb Signed-off-by: Joseph Dobson <joseph.dobson@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2962 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-05MLCE-166: Add support for extracting indices in NEPoolingLayer 2x2 NHWCmorgolock
* Added support for pooling indices in NHWC Poolsize 2x2 Change-Id: Ib2a3468e794f58bbf2c03aba9f6b184b9d76b183 Signed-off-by: morgolock <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2997 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-04COMPMID-3441: Nightly failed due to NEScale QASYMM8_SIGNED output wrong resultMichele Di Giorgio
Change-Id: I4a97523408f44c509ba0f6bf180c56ea33b964cf Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3138 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-01COMPMID-3379: Add support for QASYMM8_SIGNED in NEScaleSheri Zhang
Update QASYMM8_SIGNED support document Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: Ia0cb0d2eed13e7e38b165dc317af06e7f2df4285 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3132 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-05-01[ONCPUML-7] Improvement to Window::split_windowJoseph Dobson
If the total passed to split window did not fit nicely into the selected Dimensions size then the size of of the window return will vary considerably for different ids This change means that the amount of work each id will vary by the minimal amount. For example: If total was 10 and a Dimensions size was 19 With then with the old code : * id 0 - 8 would get back 1, * id 9 would get 10 With the new code: * id 0-8 would get 2 * id 9 would get 1 Change-Id: I6b74b81d7ddcea06db7aa9fbaf8cb47a659994c1 Signed-off-by: Joseph Dobson <joseph.dobson@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/224448 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/ml/ComputeLibrary/+/2961 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-28COMPMID-3292: Clean tests for Im2ColKernel.Georgios Pinitas
Change-Id: I005ac542a94aeed8df806699d3d237ac8973d1e6 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3003 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
2020-04-26COMPMID-3240: Add support for layer normalization to CLQLSTMLayerSheri Zhang
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: I45359a4ddb46c059097a2d77c008f802e8f4c143 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3065 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>
2020-04-23COMPMID-3280: Make all ML primitives for CL use the new interface - Part 2Manuel Bottini
- CLFunctions have been updated Change-Id: Ie3256a6c775bc12f3126482bd8e8a46da54b267c Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3053 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-23COMPMID-3394: Replace get_cl_type_from_data_type in AllSheri Zhang
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: I978050182817c964779c775cdefd88d2c7df0ca5 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3069 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2020-04-23COMPMID-3406: Fix build issue of gcc <= 5.4Sang-Hoon Park
Use double pairs of curly brackets to initizalie std::array. (Single pair of brackets doesn't cause issue with gcc >= 6.3) Change-Id: I1e49e92f44ffd5f359cce804d6c2c899b2f10f66 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3082 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-04-22COMPMID-3280: Make all ML primitives for CL use the new interface - Part1 - Fix3Manuel Bottini
- const fix in the CLKernels part 3 Change-Id: I9cfb896f334145249a97c9287fa00399b8319a8e Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3075 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-22COMPMID-3280: Make all ML primitives for CL use the new interface - Part1 - Fix2Manuel Bottini
- const fix in the CLKernels part 2 Change-Id: Ia12845e291b4137cbaf76eb8438e381c4fd0368a Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3071 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-04-22COMPMID-3241: Add Layer Normalization to NEQLSTMLayerSang-Hoon Park
- Add output quantization calculation to Layer Normalization - Add members for Layer Normalization to NEQLSTMLayer - Add configure/validate/run of Layer Normalization to NEQLSTMLayer Change-Id: I278c8e0edbb21212f3afa4d4a336df0f1a4c1bfb Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3059 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-22COMPMID-3280: Make all ML primitives for CL use the new interface - Part1 - Fix1Manuel Bottini
- const fix in the CLKernels part 1 Change-Id: I17340cb6ff26afd52b14b46645efedbe07aef1b6 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3067 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-04-21COMPMID-3236: Implement CLQLSTMLayerMichele Di Giorgio
COMPMID-3081: Extend CLQLSTMLayer with enhancements Change-Id: Idb7aaaacdba957e5ad61e94edeab2e898730a109 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3057 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-20COMPMID-3241: Fix hidden scale in NEQLSTMLayerSang-Hoon Park
- Fix wrong data types in LSTMParams - Add logic to ignore epsilon for quantization multiplier computation - Ignore epsilon for hidden gate scale computation Change-Id: Ia0b2f523b1c2ad325f3523439a8eea051d81958c Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3058 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-04-20COMPMID-3304: Update OpenCL GEMM heuristic for Int8Gian Marco Iodice
Change-Id: I6b7ff678d8d0437a1639db2ff602ea1cdb155464 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3056 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-20COMPMID-3237: Implement NEQLSTMLayerMichele Di Giorgio
COMPMID-3082: Extend NEQLSTMLayer with enhancements Change-Id: I88175b7bf69494a4eae510b74176fe8a0d6cd770 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2969 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-17COMPMID-3280: Make all ML primitives for CL use the new interface - Part 1Manuel Bottini
- Only CLKernels have been updated Change-Id: Ife55b847c2e39e712a186eb6ca452503d5b66937 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3001 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-04-15COMPMID-3236: Add support QSYMM16 into S32 CLPixelwiseMultiplicationKernelMichele Di Giorgio
Change-Id: Ifc519f53f04fcb14ddb9c17f98cc687f34285c97 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3018 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-14COMPMID-3349: Fixed performance regression Mali-G71Gian Marco Iodice
Change-Id: I2c9cc9ebd7fe6cc6431d25ac795046b0539db616 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3014 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2020-04-14COMPMID-3239: Implement QSYMM16 LayerNormalizationKernel for CLSheri Zhang
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Change-Id: Ib1577c4a9aa29293a903731b2a4083b0d2243e1e Signed-off-by: Sheri Zhang <sheri.zhang@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2994 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2020-04-08COMPMID-3112: Reworking heuristic for CLGEMM - part1Gian Marco Iodice
The new heuristic only affects the floating point execution Change-Id: Ia6edc14ab1bdda4cee31b7afb096d0305d99b809 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2942 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-08COMPMID-3279: Create CLCompiler interfaceMichalis Spyrou
Change-Id: Ic9dd5288d72a690651aa03d474f2bfd6e1ebe8b2 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2957 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2020-04-08COMPMID-3236: Extend CLGEMMLowpReduction kernels to multiply by a scalar valueMichele Di Giorgio
Change-Id: Iebd6afac65d10a42d60c2c9df9e1895fadb205ae Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2981 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-07COMPMID-2765 Add support for QASYMM8_SIGNED in NEDeconvolutionLayerLuca Foschiani
Signed-off-by: Luca Foschiani <luca.foschiani@arm.com> Change-Id: I8295fadee15311a9ab846aa24c031b82c0b799eb Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2952 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com>
2020-04-07COMPMID-3281: Implement QSYMM16 Layer Normalization for NEON QLSTMSang-Hoon Park
- Reference kernel is modified to use the same algorithm as NEON kernel. - NEON kernel is implemented. - Tests for validation and run are added. Change-Id: I3533bc2bd12c6e9cc75d837ecf193f74ceddf796 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2948 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2020-04-03COMPMID-3101 Fuse activation with floating point elementwise operation ↵Giorgio Arena
layers in CL Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Change-Id: I1693f8664ba7c0dc8c076bbe7365cef1e667bd25 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2718 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-02Missing include for ARM_COMPUTE_ERROR_ON in QuantizationInfo.h for clangManuel Bottini
Change-Id: I3773a4142afd2e660fed4acc970fbafe48420366 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2968 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-01MLCE-166: Add support for extracting indices in NEPoolingLayer 2x2 NCHWmorgolock
* Added initial support for pooling indices * Only supported for NCHW Poolsize 2 Change-Id: I92ce767e64fcc01aae89411064b4cb2be272a1e9 Signed-off-by: morgolock <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2927 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-04-01COMPMID-3237: Add support for QSYMM16 into S32 NEPixelwiseMultiplicationKernelMichele Di Giorgio
Change-Id: I8dc3348db37b041f442639ac0d072740ca639878 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2960 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-03-27COMPMID-3237: Add support for QSYMM16 ArithmeticSubtraction on NEONMichele Di Giorgio
Change-Id: Ib38796e52665233351b181bf3417eb5650ad7ca7 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2939 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-03-27COMPMID-3248: Align SONAME and version in Version.hGeorgios Pinitas
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: Ia8911f559f0a33ccc62e42d47825577c998c85d7 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2937 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-03-27COMPMID-3284 add utilities for layer normalization of NEON QLSTMSang-Hoon Park
Change-Id: Ie98a8c4c30ac7859a989a29cbe7602c1c6fec26b Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2934 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-17 21:17:10 +0000