Skip to content

[CUDA] compilation error: invalid input constraint 'x' in asm #1353

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

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

Jump to bottom
Closed
cgleggett opened this issue Mar 19, 2020 · 3 comments
Closed

[CUDA] compilation error: invalid input constraint 'x' in asm #1353

cgleggett opened this issue Mar 19, 2020 · 3 comments
Assignees
@Ruyk
Labels
cuda CUDA back-end

Comments

@cgleggett
Copy link

when compiling a simple program with CUDA backend against d9b178f :

/home/leggett/intel/git/build/bin/clang++ -std=c++14 -fsycl -pthread -g -O2 -fsycl-targets=nvptx64-nvidia-cuda-sycldevice -o prog.o -c prog.cpp
clang-11: warning: Unknown CUDA version 10.2. Assuming the latest supported version 10.1 [-Wunknown-cuda-version]
In file included from FindPrimesSYCL.cpp:1:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl.hpp:11:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl/accessor.hpp:13:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl/buffer.hpp:10:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl/detail/buffer_impl.hpp:17:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl/handler.hpp:13:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl/detail/cg.hpp:17:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl/group.hpp:15:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl/detail/generic_type_traits.hpp:16:
In file included from /home/leggett/intel/git/build/bin/../include/sycl/CL/sycl/half_type.hpp:15:
In file included from /opt/rh/devtoolset-8/root/usr/lib/gcc/x86_64-redhat-linux/8/../../../../include/c++/8/cmath:45:
In file included from /usr/include/math.h:413:
/usr/include/bits/mathinline.h:131:43: error: invalid input constraint 'x' in asm
  __asm ("pmovmskb %1, %0" : "=r" (__m) : "x" (__x));
                                          ^
/usr/include/bits/mathinline.h:143:43: error: invalid input constraint 'x' in asm
  __asm ("pmovmskb %1, %0" : "=r" (__m) : "x" (__x));
                                          ^
2 errors generated.
@cgleggett cgleggett mentioned this issue Mar 19, 2020
Closed
@bader bader added the cuda CUDA back-end label Mar 19, 2020
@AlexeySachkov
Copy link
Contributor

This might be a side effect of #1341

@AlexeySachkov
Copy link
Contributor

@cgleggett, could you please check if #1366 helps to resolve this problem?

@cgleggett
Copy link
Author

looks good. thanks.

aelovikov-intel pushed a commit to aelovikov-intel/llvm that referenced this issue Feb 23, 2023
@steffenlarsen
[SYCL] Prevent use of fp64 and fp16 when unsupported in more tests (i…
023c631 
…ntel#1353)

A number of tests currently use double and sycl::half despite them not
being supported by the used device. Although it does not necessarily
fail to run on those devices, they are not considered supported by the
SYCL specification and should not be used in testing on those devices.
This commit prevent parts of a selection of tests from running on
devices that do not support the types used.

Signed-off-by: Larsen, Steffen <steffen.larsen@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Ruyk Ruyk

Labels
cuda CUDA back-end
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@bader @Ruyk @AlexeySachkov @cgleggett