- Make sure you have the latest graphics driver
- Make sure your device is not low on memory when pinv is called. Write a toy version which only calls pinv and uses small arrays.
- Reimplement avoiding cuSolver. Can your code use backslash instead? pinvA = A\eye(size(A,1))
Standalone Compiler gpuArray RTX 4090 CUDA 12.0
조회 수: 5 (최근 30일)
이전 댓글 표시
Hi,
got a new ML machine with an NVIDIA RTX 4090. I have tried to run a quick benchmark written on my own as a compiled standalone application. What I have done:
- Use another machine to compile my code as an app via Compiler Toolbox (R2022b)
- Installed this on the new machine with the RTX 4090 including newest MCR
- Test GPU gets recognized by the app using gpuDeviceTable - works
- Try a simple feedforward network training with GPU - works
- Try my own implementation of some code with gpuArrays - failed (see below)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1233332/image.jpeg)
Is the latest MCR not compatabile with the new RTX 4090 in some parts of functions (as here with pinv)?
댓글 수: 5
Joss Knight
2022년 12월 19일
By the way, what I gave you was actually inv. If A is rectangular or singular you want pinvA = (A'*A)\(A'*eye(size(A,1));
Joss Knight
2022년 12월 19일
답변 (0개)
참고 항목
카테고리
Help Center 및 File Exchange에서 GPU Computing에 대해 자세히 알아보기
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!