We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
select_algo函数sse分支ret_info默认输入输出的data format都是ndarray,sse_fallback_info中的format也是ndarray,那么gen_algo函数中如何选到n8cx的实现? https://github.com/openppl-public/ppl.kernel.cpu/blob/master/src/ppl/kernel/x86/fp32/conv2d/conv2d_fp32.cpp#L283 另外gen_algo中sse分支关于input data_format的判断是不是写错了? https://github.com/openppl-public/ppl.kernel.cpu/blob/master/src/ppl/kernel/x86/fp32/conv2d/conv2d_fp32.cpp#LL382C67-L382C67
The text was updated successfully, but these errors were encountered:
你好,关于第一点,由于目前PPL.NN X86并没有任何关于N8CX排布相关实现,所以并没有将N8CX的SSE CONV2D加入到默认的算法选择的策略里,如果需要单独使用PPL.KERNEL.CPU,可以自行另写算法选择策略来使用N8CX的算法
关于第二点,这是之前整理代码时引入的错误,我们会尽快修复,感谢反馈
Sorry, something went wrong.
明白了,感谢大佬回复
No branches or pull requests
select_algo函数sse分支ret_info默认输入输出的data format都是ndarray,sse_fallback_info中的format也是ndarray,那么gen_algo函数中如何选到n8cx的实现?
https://github.com/openppl-public/ppl.kernel.cpu/blob/master/src/ppl/kernel/x86/fp32/conv2d/conv2d_fp32.cpp#L283
另外gen_algo中sse分支关于input data_format的判断是不是写错了?
https://github.com/openppl-public/ppl.kernel.cpu/blob/master/src/ppl/kernel/x86/fp32/conv2d/conv2d_fp32.cpp#LL382C67-L382C67
The text was updated successfully, but these errors were encountered: