aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2022-06-27Implement new Elementwise Dynamic Fusion Operators: Div, FloorMichalis Spyrou
Resolves: COMPMID-5355 Change-Id: I92f73fbe885f28bbe7b07965b90cfd807c93602f Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7745 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com>
2022-06-24Improve LUT Neon Hard-SwishPablo Marquez Tello
* Changed window_step from 16 to tensor_shape().x() when calling into the assembly byte substitution code. * Resolve COMPMID-5211 Change-Id: I5c1f5273455999bb35f94c76a8afb4290e728858 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7843 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2022-06-23Select neon LUT Hard-Swish kernel on all devicesPablo Marquez Tello
* Resolves COMPMID-5211 Change-Id: I560ab2992c6089774c7ebee3538847905521607d Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7840 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
2022-06-23Enable loading OpenCL symbols in Android App native code, NDK environment.ohadagoogle
* Based on ArmNN work: IVGCVSW-6960 Device not found running MLTS with Support Library Change-Id: I8cb8acc30c8a4afa60bc1cf80eb5b6b2c43dfdc1 Signed-off-by: Ohad Almagor <ohada@google.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7836 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-17Drop support on armv7a on AndroidMichalis Spyrou
Resolves: COMPMID-5379 Change-Id: Ie2564b8ef029241e34b964de524c4a4c288a7846 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7735 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-06-16Fix SVE2 implementation of quantized SoftMax 1DViet-Hoa Do
* Fix integer overflow in substraction step. * Fix incorrect vector when convert the result to qasymm8_signed. Resolves: COMPMID-5389 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: Id745f2eb2a1b0823b02b136560351b5f8fb85624 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7738 Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-15Fix build error v8.2-a-svePablo Marquez Tello
* bf16 instrinsics should be used when __ARM_FEATURE_SVE_BF16 is present * Fixed NDK14 compiler warning declaring copy ctor for Window explicitly * Resolves MLCE-867 Change-Id: I84ac5f213d9700e2fda7da55d83bba7cf79ad52c Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7728 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-06-15Add support OpenCL 3.0 non-uniform workgroupViet-Hoa Do
* Add OpenCL version 3 detection. * Use -cl-std=CL3.0 build option to support non-uniform workgroup when OpenCL 3 is detected and the feature is supported. Resolves: COMPMID-5208 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: Ifd8cbae6b34228c07e761bcb94ee8f35bdf1bace Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7655 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-15Fix performance regression in Winograd Output Transform (OpenCL)Gian Marco Iodice
The regression was caused by NUM_TILES_X passed at runtime. Resolves COMPMID-5327 Change-Id: Id6ccd93784eda93af09f420c0d786050e2bbccd7 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7727 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-13Add support for 2d and 3d indices for axis 1Pablo Marquez Tello
* Resolves COMPMID-5055 Change-Id: I2d14de29d3ec913d20c971bc8bbc9ad71e2d998f Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7547 Reviewed-by: SiCong Li <sicong.li@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-09Fix crash in CpuActivationKernelPablo Marquez Tello
* There was a problem when dst was nullptr * Resolves IVGCVSW-7010 Change-Id: I7e591283906b9a1deaa879fa00387f0ddbf8cc48 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7704 Reviewed-by: TeresaARM <teresa.charlinreyes@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-07Compute Hard-Swish with a Lookup table for qasymm8.Pablo Marquez Tello
* Resolves COMPMID-5211 Change-Id: I5914f971d733174dae67e6b4c589f45c75733cf7 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7654 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-06-06Allow clearer suppression of toolchain and compiler prefixesSiCong Li
Currently it is counterintuitive to disable toolchain prefixes: we need to pass an empty space to it; passing an empty string would not disable prefixes but instead instruct the build script to use a set of default prefixes. With this patch we restore the intuitive approach of passing an empty string "" to disable the prefix. Resolves COMPMID-5353, COMPMID-5380 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I2fe84689df9093cf6baf507dde44ca5ebf61023b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7686 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-06-06Fix build errors in GCC12Pablo Marquez Tello
* Resolved MLCE-862 Change-Id: Ifb58ad1073e2f44d37a7419693be889887719b7d Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7682 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-06-01Fix reference example for fusion of conv2d and addditionSiCong Li
* Make sure the reference is running the same computation as the fused example * Add finer breakdown of start-up time Related to COMPMID-5365 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Ia5c73d4af318cafda1335438f88d0d4f74a5355c Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7643 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-31Add cl_khr_integer_dot_product extension supportViet-Hoa Do
* Replace arm_dot(_acc) with dot when cl_khr_integer_dot_product extension is available. Resolves: COMPMID-5206 Change-Id: I7fd763e2421987584e4dae271008972644ea2f41 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7647 Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-31Add missing new-line to doxygen documentationSiCong Li
Resolves COMPMID-5352 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Ia0ae55ff98993bdbde9033189b2414305abf8b31 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7681 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
2022-05-31Fix compilation error in 32-bit with logging buildViet-Hoa Do
* Use %zu format specifier for size_t data. Resolves: COMPMID-5377 Change-Id: I84e6aea8ab34ca4616eeecfb06d573eaa329bd67 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7649 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-30Fix doxygen typosViet-Hoa Do
Change-Id: Ia54918091e985e21641610ca7652aead7c0dd20a Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7621 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
2022-05-26Disable unsafe FP optimizations causing accuracy issuesGunes Bayir
Resolves: COMPMID-5324 Change-Id: I289b1bb42296c562cb90b918c20def8c6c1825d2 Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7639 Reviewed-by: SiCong Li <sicong.li@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-24[arm_gemm] Import fixed-format kernels from gemm_linux.Francesco.Petrogalli@arm.com
This is a No Functional Change Intended (NFCI) patch. It imports the kernel in the code, but the interface to select them and expose the format of the weight tensors to the user will be provided in a subsequent patch. Kernels and kernel selection code in arm_gemm has been provided by David.Mansell <David.Mansell@arm.com>. The kernels are not compiled in the library by default, but need to be selected via the `scons` option `experimental_fixed_format_kernels=1`. Resolves: ONCPUML-829 Signed-off-by: Francesco.Petrogalli@arm.com <francesco.petrogalli@arm.com> Change-Id: If00ccb2b9b7221e01b214cf9783111226ccc8bf4 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7380 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-19Properly format SConscript filesMichalis Spyrou
Partially resolves COMPMID-5287 Change-Id: I65a95eb978908bed0a3c7d385c4c4f171f3b2c86 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7605 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-18Fix doxygen page layoutSiCong Li
Resolves: COMPMID-5349 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I6ac32616feaa2a0c79857e0bcffc516564b37f39 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7589 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-17DepthwiseConv reports full assembly kernel namePablo Marquez Tello
* Resolves MLCE-706 Change-Id: Ia15c925c13464397c79056dffe2a756e06020682 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7571 Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-17Update ErrataAdnan AlSinan
Resolves: COMPMID-5264 Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com> Change-Id: I1420a0da0356417c97158935f13bd43631a14dc7 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7577 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com>
2022-05-17Update READMEAdnan AlSinan
- Update change log. - Update main branch warnings. Resolves: COMPMID-5265 Change-Id: I571e56e46562af1a6959904b8181cbd6b6c069b9 Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7585 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-16Update SONAME_VERSION in SConscriptMohammed Suhail Munshi
Part of : COMPMID-5265 Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> Change-Id: I23e76647610055f8a40757e0a9db133f38ea156e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/419688 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7572 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-12Revert "Add support for 2d and 3d indices for axis 0"Mohammed Suhail Munshi
This reverts commit 0db8b8bbd941b3dab4238c03e734e7ac43c662ed. Relates to [COMPMID-5055] Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> Change-Id: I143e7965e21b956abb05ba5c41e12c5b73b7345a Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7558 Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-11Fix inclusion guard for dynamic fusion moduleSiCong Li
Resolves COMPMID-5318 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I59594632c9891b9569089764ae26cc7be6b78fcd Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7550 Reviewed-by: Nikhil Raj Arm <nikhil.raj@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-10Add support for 2d and 3d indices for axis 0Pablo Marquez Tello
* Partially resolves COMPMID-5055 Change-Id: Id05374b8c69e6b9ab4c2790a4de93d7172063b71 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Change-Id: Ic6e2c2d1d34abbf6222c8d56859514e267447266 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7488 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-09Mismatches in dynamically fused direct conv2d + add kernelMichalis Spyrou
Resolves: COMPMID-5269 Change-Id: I4372ea4365d14ead79153e4b08b690a1e20ab0b7 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7531 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-06Integrate Dynamic Fusion patchesSiCong Li
* Add public interfaces: * OperatorGraph: Describe a workload that could contain fused kernels * IWorkload: Generic interface for workloads built from OperatorGraph * ClWorkload: OpenCL workloads built from OperatorGraph * ClCompositeOperator: Runtime async operator to execute a ClWorkload * DependencyGraph (will likely be deprecated in later iterations) * Add example * cl_fused_conv2d_elementwise_add.cpp to explain how to use the new interfaces * Add internal translation layer * Refactor ClKernelBuildingAPI * Remove non-tile based gemm native kernel component * Minor interface changes * Add integration tests Resolves COMPMID-5161 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Ib987ed79289ab0bcbd3130d54f5793408d9f1240 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7510 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-06Add a note to clarify pretranspose option in GEMM and GEMMLowp fixturesAdnan AlSinan
Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com> Change-Id: Ie65f9096a75610dc20ffbb25dc43fd2f632f2f03 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7530 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-06Updating a64_gemm_u8 a64_gemm_s8 kernels headersramelg01
Resolves: COMPMID-5272 Signed-off-by: ramy.elgammal@arm.com Change-Id: I185182430ca952e5bb661e0a47163965b3565a49 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7517 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-06QLSTM add support for different qinfoMike Kelly
* Resolves MLCE-604 Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ice3d6f361588f1a6bd0bff301c27b0d063a5c014 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7529 Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-06Use svcreate instead of list initializations.Michalis Spyrou
Partially resolves COMPMID-5250 when building with SVE2. Change-Id: I16bd74d4cd6c70371efd8235c507ba5e7f8f906f Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7498 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-06Extend GEMM to support batch matmul operationMohammed Suhail Munshi
- Added values to supports transpose operations prior to gemm. Resolves: COMPMID-5072 Change-Id: Ia8bc39b3ded8a507c2314a4926f1f7809da03649 Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7485 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-06Extend GemmLowp reference to support BATCH MATMUL for quantized data typeAdnan AlSinan
- Extends GEMMInfo class to include flags for transposing A and B. - Extends GEMMLowp fixtrues to have an option for transposing A and B. Resolves COMPMID-5075 Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com> Change-Id: If5e4b7e2b7b19ca30808a78a9641d8ba3f176a26 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7458 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2022-05-05Fix for Neon™ Depthwise Android P VTS test failureramelg01
Resolves: COMPMID-5237 Signed-off-by: ramy.elgammal@arm.com Change-Id: Ib1f5e262030e915a038cef587001708bbaf14c56 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7508 Reviewed-by: David Mansell Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-05-04Add a missing validation check to CPU Pool3dAdnan AlSinan
- Add a check for pooling region that is entirely outside input tensor. Signed-off-by: Adnan AlSinan <adnan.alsinan@arm.com> Change-Id: Ib6b4565b1cb64235e714fe065b4a95f96a5adbd9 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7497 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-05-03Update public mailing list in READMESiCong Li
Resolves COMPMID-5194 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I049c12572e37090c85f5493045412b6d3763eedc Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7487 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-04-29Add a few sections on security consernsMichalis Spyrou
Change-Id: If94171d52a37e917aaa75e1a137d7df561698290 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7469 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-04-27Add security related / good coding practicesMichalis Spyrou
build options for our pre-built binaries to README.md. Change-Id: I2ab49097052d0e8b8a04ed3f7dd36e021b19f119 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7462 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-04-26Update Neon™ depthwise kernelramelg01
- Reduce duplication and simplify overall structure. - Improve multi-threaded performance by sharing more data in lower-level caches. Partially Resolves: COMPMID-5054 Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com> Change-Id: Iac747f39b21c540122fa75218762631c4d787911 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7449 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Andrew Mundy Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-04-25Update Neon™ pooling kernelramelg01
- Reduce duplication and simplify overall structure. - Improve multi-threaded performance by sharing more data in lower-level caches. Partially Resolves: COMPMID-5054 Signed-off-by: Ramy Elgammal<ramy.elgammal@arm.com> Change-Id: I5f4dc50913401d5c1cbfc10b866fae9490cbc4d7 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7404 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Andrew Mundy Reviewed-by: Sheri Zhang <sheri.zhang@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-04-25Document data layout of weight tensors in convolution layersSiCong Li
Resolves COMPMID-5187 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I4fddd1f1e7134896a40f62553d705fa5e411e00b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7405 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-04-25Add LU_BOUNDED_RELU support for QSYMM16Pablo Marquez Tello
Partially resolves MLCE-604 Change-Id: Id585ab19fe5cd8f61c07a0aae6faac6ba5545d6d Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7379 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-04-22[CpuGemmConv2d] Extract skip_im2col and skip_col2im computation.Francesco.Petrogalli@arm.com
This is just refactoring some duplicate code. No functional changes intented. Change-Id: Iff96798b03d25b490341598e676d0e4f2ebd132b Signed-off-by: Francesco.Petrogalli@arm.com <francesco.petrogalli@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7408 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-04-21Add missing noexcept.Michalis Spyrou
This fixes building faillures with gcc9. Change-Id: I993116866b0f1e41cb2518e880798ad1f8c2e0af Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7448 Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2022-04-21NEQLSTM: perform type conversion in prepare method.Pablo Marquez Tello
* When input_to_forget_weights is QASYMM8_SIGNED, the conversion to QSYMM8 is done in the prepare method * Partially resolves MLCE-604 Change-Id: Iddadbc50d77381542451ac4e46de49b2706bc88c Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7441 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-26 10:15:03 +0000