mirror of
https://github.com/llvm/llvm-project.git
synced 2025-04-27 12:36:09 +00:00
0ff05cd165
NOTE: reverts r242077 to reinstate r242058, r242065, 242067
and includes fix for OS X test failures.
- Changed driver pipeline to compile host and device side of CUDA
files and incorporate results of device-side compilation into host
object file.
- Added a test for cuda pipeline creation in clang driver.
New clang options:
--cuda-host-only - Do host-side compilation only.
--cuda-device-only - Do device-side compilation only.
--cuda-gpu-arch=<ARCH> - specify GPU architecture for device-side
compilation. E.g. sm_35, sm_30. Default is sm_20. May be used more
than once in which case one device-compilation will be done per
unique specified GPU architecture.
Differential Revision: http://reviews.llvm.org/D9509
llvm-svn: 242085
10 lines
569 B
Plaintext
10 lines
569 B
Plaintext
// Make sure we can process CUDA file even if driver creates multiple jobs
|
|
// RUN: c-index-test -test-load-source all %s | FileCheck %s -check-prefix=CHECK-ANY
|
|
// Make sure we process correct side of cuda compilation
|
|
// RUN: c-index-test -test-load-source all --cuda-host-only %s | FileCheck %s -check-prefix=CHECK-HOST
|
|
// RUN: c-index-test -test-load-source all --cuda-device-only %s | FileCheck %s -check-prefix=CHECK-DEVICE
|
|
|
|
// CHECK-ANY: macro definition=__cplusplus
|
|
// CHECK-HOST-NOT: macro definition=__CUDA_ARCH__
|
|
// CHECK-DEVICE: macro definition=__CUDA_ARCH__
|