aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2022-07-11List licenses used by other projects in READMESiCong Li
Resolves COMPMID-5391 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Iafd42c80ffc7a9659e2b7bc820aefb39338b56c9 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7900 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-07-08Extended direct conv 2d interface for tuning the OpenCl kernelGian Marco Iodice
Resolves COMPMID-5298 Change-Id: Ie9b907e5dcf86aa6add8d08799fa7ba7c264edea Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7888 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-07-07Add missing flag when building cl graph examples and fixMichalis Spyrou
incorrect cl cache behaviour Resolves: COMPMID-5286 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Change-Id: I1aa82825ef7d31d7830a00282d1a3523ccf1d746 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7883 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-by: SiCong Li <sicong.li@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-07-07Move build option explanations in how to build guide to scons help messageMichalis Spyrou
Resolves: COMPMID-5381 Change-Id: I556e2269ff6350f58509624a3d3d94cb0853cb8d Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7882 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-07-07Add OpenBSDĀ® to the list of supported systemsPablo Marquez Tello
Resolves COMPMID-5396 Change-Id: I9bf296b81145c48aabdfb56b7ffdb453f5a76976 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7892 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-07-05Add G57 to GPUTargetSiCong Li
Relates to: COMPMID-5299 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I19f820f698cf11020da019f4a1334cccb1e40c7e Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7880 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-07-04Fix build errors on armv8.6 SVE2 with NDK 23 and 24Michalis Spyrou
Extensive use of templates resulted in a compiler crash on NDK 23 and 24. This rework solves the issue and also reduces the library size by 101Kb. Resolves: COMPMID-5384 Change-Id: I9c5c68c5e36f236b0891e44d25478743417fb16d Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7871 Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-07-01Fix OpenBSD build errorsPablo Marquez Tello
* Partially resolves COMPMID-5396 Change-Id: I7f3e692e73da548a901a07ed6d7212df40b8c26f Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7870 Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-30Wrong arguments for running activation function in CpuGemmDirectConv2dMichalis Spyrou
Resolves: COMPMID-5350 Change-Id: I2f5021ebe9fe4c71371f2cd6cb65cc9c0b2110b5 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7861 Reviewed-by: Francesco Petrogalli <francesco.petrogalli@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-30Fixed native build toolchain and compiler prefixPablo Marquez Tello
* When build=native toolchain_prefix and compiler_prefix must be set to "" instead of auto * Resolves COMPMID-5395 Change-Id: I481ee4596e16d55d2a696af9124a0d06c916cef7 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7855 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2022-06-29Add LUT-based leaky relu for QASYMM8 on CPUViet-Hoa Do
* Add LUT generation function for Leaky ReLU. * Some additional changes in the existing LUT implementation: + Bring back the NEON implementation of hard swish for 32-bit build. Library size of 64-bit build is not affected. + Add some extra #ifdef to remove unnecessary code in 32-bit build. Resolves: COMPMID-5386 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: I1ea49611cc922765ee741e31138c888401d33e9b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7845 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-06-29Fix armv7a on Android "end-of-support" build and documentationSiCong Li
* Only print a warning for this build * Fix the wording in documentation to avoid misunderstanding. User can still run armv7a on Android, but we stop testing it and this build is discouraged Resolves COMPMID-5379 Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I3d00baa2479671bcef8882db0e3d3cc3043d5811 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7838 Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2022-06-28Fix OpenCL Winograd output transformGian Marco Iodice
- num_tiles_x was not initialized when we were passing the argument at compilation time Resolves COMPMID-5394 Change-Id: I6004a2d47656edda3c832f980c78622045de7068 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7857 Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
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>