tangjinchuan
tangjinchuan
Dear developers, I am using the dll from AMD (https://developer.amd.com/amd-optimizing-cpu-libraries_eula/) to test its compatibility and performance on Windows. The dll name is AOCL-LibBlis-Win-dll.dll which can be found in C:\Program Files\AMD\AOCL-Windows\amd-blis\lib\LP64....
Dear Pocl team, I tried to install pocl using homebrew. Somehow clinfo could not detect pocl. Is there something wrong with the installation? There is no such problem with LINUX/OpenSUSE....
Dear Intel experts, We have encountered a problem with A770 using CLBLAST sGEMM. The problem is that this sGEMM fails tests on this A770 card but not others. The details...
Dear Intel OpenCL team, I have a kernel file which can be compiled with AMD 7800XT GPU using less than 100MB memory during compilation using AMD driver. However, by using...
Dear virogr, there might be a problem with the precision of elliptic123. I run the following code on 64bit linux version of Matlab: K>> [~, K1]= elliptic123(pi/2, 1+2.*eps(0.5)) K1 =...
Dear Vigor, Could you please add the empty returns (with the same empty size as the input) when calling elliptic123 with two empty inputs? The current version of the code...
Dear apjanke, Matlab has switched from OpenBLAS to Accelerate to achieve many speed-ups (3.7x faster Matrix-Matrix multiplication, 2x faster LU factorisation, 1.7x faster Cholesky Decomp.). Could you please consider bringing...
Hi Artyom, I tried with Apple Silicon M1, python 3.12, pytorch 2.3.1 with the following setting code: > torch.ops.load_library("/Users/tjc/Documents/libpt_ocl.dylib") > torch.utils.rename_privateuse1_backend('ocl') > #torch._register_device_module('ocl','opencl') # as required by Pytorch 2.0 ?...