You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "AIYoungcino (via GitHub)" <gi...@apache.org> on 2024/08/12 02:54:58 UTC
[PR] [CUDA][shared memory allocation]fix 'ptxas error : Entry function 'fu… [tvm]
AIYoungcino opened a new pull request, #17267:
URL: https://github.com/apache/tvm/pull/17267
I convert a vit model from onnx, and then run relay.build with NVIDAI-RTX4090 for compilation.
with tvm.transform.PassContext(opt_level=3):
lib = relay.build(mod, target=target, params=params)
and then meet an error like this: Compilation error:
ptxas error : Entry function 'tvmgen_default_fused_nn_conv2d_add_kernel' uses too much shared data (0x2ab44 bytes, 0x29000 max)
I apologize for resorting to this temporary solution to address the issue I encountered. As a stepping stone, I hope the experts can offer some advice to help me resolve this problem more effectively. Thank you.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [CUDA][shared memory allocation]fix 'ptxas error : Entry function 'fu… [tvm]
Posted by "AIYoungcino (via GitHub)" <gi...@apache.org>.
AIYoungcino commented on PR #17267:
URL: https://github.com/apache/tvm/pull/17267#issuecomment-2292622935
> Dynamic shared memory (`shared.dyn` scope) should be used in this case to bypass the size limit
Thank you for your advice. if the size of the result of conv2d exceeds the maximum shared memory limit, storing it in shared memory would lead to overflow. It's typically passed as a parameter to the kernel function or allocated GDRAm space through static extern at compile time.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [CUDA][shared memory allocation]fix 'ptxas error : Entry function 'fu… [tvm]
Posted by "vinx13 (via GitHub)" <gi...@apache.org>.
vinx13 commented on PR #17267:
URL: https://github.com/apache/tvm/pull/17267#issuecomment-2292479707
Dynamic shared memory (`shared.dyn` scope) should be used in this case to bypass the size limit
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [CUDA][shared memory allocation]fix 'ptxas error : Entry function 'fu… [tvm]
Posted by "AIYoungcino (via GitHub)" <gi...@apache.org>.
AIYoungcino commented on PR #17267:
URL: https://github.com/apache/tvm/pull/17267#issuecomment-2283036048
I searched for information provided by NVIDIA, and the following are the maximum shared memory limits corresponding to each generation of GPU architecture，
5.x : 64kb
6.x : 64kb
7.x : 96kb
8.x : 164kb
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [CUDA][shared memory allocation]fix 'ptxas error : Entry function 'fu… [tvm]
Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen closed pull request #17267: [CUDA][shared memory allocation]fix 'ptxas error : Entry function 'fu…
URL: https://github.com/apache/tvm/pull/17267
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For additional commands, e-mail: discuss-archive-help@tvm.apache.org