ComputeLibrary

ComputeLibrary copied to clipboard

Wrong result of NESoftmaxLayer with multi-dimensions

1

**Output of 'strings libarm_compute.so | grep arm_compute_version':** arm_compute_version=v22.02 Build options: {'Werror': '1', 'debug': '1', 'neon': '1', 'opencl': '0', 'os': 'linux', 'arch': 'arm64-v8.2-a-sve', 'benchmark_tests': '1', 'validation_tests': '1'} Git hash=unknown **Platform:** Arm64...

daoxian

Need help with TensorFlow Model Data Extraction

6

I want to run inference using ACL. I am using examples/graph_resnet50.cpp and examples/graph_resnet_v2_50.cpp as reference. I got models from following locations: http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz http://download.tensorflow.org/models/resnet_v2_50_2017_04_14.tar.gz These contains .ckpt files only. To convert...

asharma-ampere

My need is to multiply two int8 tensors ([-127, 127]) to get the result S32 tensor (signed int32). I run the codes below: ``` q_src1.allocator()->init(TensorInfo(TensorShape(2, 2), 1, DataType::QASYMM8_SIGNED, src1_qinfo)); q_src2.allocator()->init(TensorInfo(TensorShape(2,...

zjersey

how to support sve in ndk

4

In linux system,I try to use Android.mk to compile an executable file including SVE intrinsics, which is supported in armv8.2, and the system config as follows: 1. TARGET_ARCH=arm64; 2. TARGET_ARCH_VARIANT=armv8-2a;...

xxxxxxLD

How to Reduce CL target run Time at intialisation stage ( Prepare time)

3

Hello I try to use the ACL 20.2 As you know when we run any example for ACL in iteration Example mobilenet SSD v1 -> 1st time call for graph_run(0...

abhajaswal

Use of `std::thread::hardware_concurrency()` does not take into account it may return `0` as the number of threads.

1

**Output of 'strings libarm_compute.so | grep arm_compute_version':** `arm_compute_version=22.05 Build options: {'arch': 'armv8.2-a', 'debug': '0', 'examples': '1', 'opencl': '0', 'mali': '0', 'neon': '1', 'cppthreads': '1', 'benchmark_examples': 'true', 'validate_examples': 'true'} Git hash=b'a175e887d64450decf80ea47d4049832c5805565'`...

matt-gretton-dann

why clEnqueueReadImage is not linkable in the built lib.

3

Dear , I built a program with arm_compute-v22.05-bin-android-arm64-v8a-cl\lib\arm64-v8a-cl\libarm_compute.so , it got an error as below: undefined reference to **`clEnqueueReadImage**' clang++.exe: error: linker command failed with exit code 1 other cl...

lyz9801

Hello, I have a question while analyzing the internal implementation. 1. What is an indirect convolution? If I think, is it similar to the paper below? [Paper](https://arxiv.org/abs/1907.02129) [Code](https://github.com/ARM-software/ComputeLibrary/blob/main/src/core/NEON/kernels/arm_gemm/gemm_hybrid_indirect.hpp)

Piorosen

**Output of 'strings libarm_compute.so | grep arm_compute_version':** arm_compute_version=v22.05 Build options: {'Werror': '0', 'debug': '0', 'neon': '1', 'opencl': '0', 'embed_kernels': '0', 'os': 'linux', 'arch': 'armv8a', 'build': 'native', 'multi_isa': '1'} Git hash=b'a175e887d64450decf80ea47d4049832c5805565'...

lilh9598

Hello, I have some questions: * Could I somewhere find information about use parallel threading in Arm Compute Library? * Do you use pinning cores in Arm Compute Library if...

allnes