ComputeLibrary

ComputeLibrary copied to clipboard

HI! I'm looking for ways for reusing yours quantization kernels in OpenVINO and see [this example](https://github.com/ARM-software/ComputeLibrary/blob/main/examples/neon_gemm_qasymm8.cpp). I see that you use [main gemm kernel](https://github.com/ARM-software/ComputeLibrary/blob/f2eda6665c12d568e179f5b0e7a24ccdc0ac824d/examples/neon_gemm_qasymm8.cpp#L219) and after that I see [next...

allnes

Different cpu should have different L1_cache_size/L2_cache_size, and I can't find any code in ComputeLibrary that will update these values later. https://github.com/ARM-software/ComputeLibrary/blob/f2eda6665c12d568e179f5b0e7a24ccdc0ac824d/src/core/CPP/CPPTypes.cpp#L37-L38 Thank you in advance.

dervon

NEMeanStdDevNormalizationLayer returns nans for f16 tensors

3

NEMeanStdDevNormalizationLayer returns nans if srd\dst tensors are f16. The issue was reproduced on ACL 23.08 How ACL was built: `scons neon=1 opencl=0 openmp=0 cppthreads=1 arch=armv8.6-a Werror=false validation_tests=1 --jobs=8 os=macos build=native...

alvoron

Add support for QNX. Build and test instruction for QNX: https://github.com/chachoi-world/qnx-ports/blob/main/ComputeLibrary/README.md

chachoi

Thanks for the wonderful library. Apologies if this seems to be a silly question: How can I benchmark gemms on a android target? In line with the docs for [test](https://arm-software.github.io/ComputeLibrary/latest/tests.xhtml)...

FabianSchuetze

NEMeanStdDevNormalizationLayer returns nans if src\dst tensors are f16. The issue was reproduced running OpenVINO notebook [sketch-to-image-pix2pix-turbo](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/sketch-to-image-pix2pix-turbo) with ACL 24.06 on Apple M2. The issue happens with the fix provided in...

alvoron

NEPooling3dLayer performance issue

6

**Output of 'strings libarm_compute.so | grep arm_compute_version':** arm_compute_version=v24.02.1 Build options: {'neon': '1', 'opencl': '0', 'openmp': '0', 'cppthreads': '1', 'arch': 'armv8.6-a', 'Werror': 'false', 'validation_tests': '1', 'os': 'macos', 'build': 'native', 'fixed_format_kernels': '1'}...

alvoron

Arm NN compute library build failure on Raspberry PI 4

7

**Output of 'strings libarm_compute.so | grep arm_compute_version':** arm_compute_version=v24.05 Build options: {'extra_cxx_flags': '-fPIC', 'Werror': '0', 'debug': '0', 'asserts': '0', 'neon': '1', 'opencl': '0', 'os': 'linux', 'arch': 'armv8a', 'examples': '1'} Git hash=b'a53ffdc87869399eb1ff2f9a20c69c8b962e27d2'...

pauljainta

Accuracy problem with F16 NEFullyConnectedLayer

2

Hi, I try to use NEFullyConnectedLayer FP16 in our OpenVINO CPU plugin and my tests is failed by accuracy. Attach reproducer [main.txt](https://github.com/user-attachments/files/15891784/main.txt) Also attach data where it was reproduced: [out_ref.txt](https://github.com/user-attachments/files/15891792/out_ref.txt)...

allnes

Hi, I try to use NEPoolingLayer - PoolingType::AVG - RoundingType::CEIL - DataLayout::NCHW in our OpenVINO CPU plugin and my tests is failed by accuracy. **Output of 'strings libarm_compute.so | grep...

allnes