5 Commits

Author SHA1 Message Date
Nikolay Haustov
1771948d72 Revert "AMDGPU/SI: Use amdgpu_kernel calling convention for OpenCL kernels."
This reverts commit f7053ec90d0fc56f0837e43c2c759e85b56c21a1.

It broke calling OpenCL kernel from another kernel.

llvm-svn: 268740
2016-05-06 15:00:51 +00:00
Nikolay Haustov
4961ea85d7 AMDGPU/SI: Use amdgpu_kernel calling convention for OpenCL kernels.
Reviewers: tstellarAMD, arsenm

Subscribers: cfe-commits

Differential Revision: http://reviews.llvm.org/D19918

llvm-svn: 268718
2016-05-06 09:15:24 +00:00
Paul Robinson
65ab102be3 Fix Clang tests that used CHECK-NEXT-NOT and CHECK-DAG-NOT.
FileCheck actually doesn't support combo suffixes.

Differential Revision: http://reviews.llvm.org/D17589

llvm-svn: 262052
2016-02-26 19:34:01 +00:00
Tom Stellard
d8e38a3206 R600: Handle amdgcn triple
For now there is no difference between amdgcn and r600.

llvm-svn: 225294
2015-01-06 20:34:47 +00:00
Matt Arsenault
43fae6c855 Add attributes for AMDGPU register limits.
This is a performance hint that can be applied to kernels
to attempt to limit the number of used registers.

llvm-svn: 223384
2014-12-04 20:38:18 +00:00