Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Set -arch in the compiler options unconditionally #8157

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

Merged
merged 2 commits into from
Feb 5, 2024
Merged

Set -arch in the compiler options unconditionally #8157

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3a45734
set -arch in compiler options unconditionally
leofang Feb 4, 2024
03c8f70
update test
leofang Feb 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions cupy/cuda/compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -280,6 +280,12 @@ def compile_using_nvrtc(source, options=(), arch=None, filename='kern.cu',
def _compile(
source, options, cu_path, name_expressions, log_stream, jitify):

if not runtime.is_hip:
arch_opt, method = _get_arch_for_options_for_nvrtc(arch)
options += (arch_opt,)
else:
method = 'ptx'

if jitify:
options, headers, include_names = _jitify_prep(
source, options, cu_path)
Expand All @@ -291,12 +297,6 @@ def _compile(
# tests cause an error if the following option is not included.
options += ('--device-as-default-execution-space',)

if not runtime.is_hip:
arch_opt, method = _get_arch_for_options_for_nvrtc(arch)
options += (arch_opt,)
else:
method = 'ptx'

prog = _NVRTCProgram(source, cu_path, headers, include_names,
name_expressions=name_expressions, method=method)
try:
Expand Down
4 changes: 3 additions & 1 deletion tests/cupy_tests/core_tests/test_raw.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -685,7 +685,9 @@ def test_dynamical_parallelism_compile_failure(self):
x = cupy.zeros((N,), dtype=cupy.float32)
use_ptx = os.environ.get(
'CUPY_COMPILE_WITH_PTX', False)
if self.backend == 'nvrtc' and (
if self.jitify:
error = cupy.cuda.compiler.JitifyException
elif self.backend == 'nvrtc' and (
use_ptx or
(cupy.cuda.driver._is_cuda_python()
and cupy.cuda.runtime.runtimeGetVersion() < 11010) or
Expand Down