maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
241,540 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

9 Commits

Author SHA1 Message Date
Matt Arsenault fbfd828d2a Replace nextafter implementation 
This one passes conformance.

llvm-svn: 280961
 2016-09-08 16:37:56 +00:00
Matt Arsenault 958fce3192 amdgcn: Fix return type of get_num_groups 
llvm-svn: 279723
 2016-08-25 07:31:40 +00:00
Matt Arsenault 26d9c41ff6 amdgcn: Fix return type for get_global_size 
llvm-svn: 279644
 2016-08-24 17:52:04 +00:00
Matt Arsenault 220268d177 amdgcn: Fix get_local_size IR return type 
llvm-svn: 279350
 2016-08-20 00:01:21 +00:00
Jan Vesely 74f02db922 AMDGPU: Use clang intrinsics for workitem builtins 
v2: split into 2 patches
    use clang builtins for other intrinsics as well

v3: Fix warnings
    Switch r600 to use implictarg.ptr

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 276442
 2016-07-22 17:24:20 +00:00
Matt Arsenault 633d749da7 amdgpu: Use right builtn for rsq 
The r600 path has never actually worked sinced double is not implemented
there.

llvm-svn: 276009
 2016-07-19 19:02:01 +00:00
Matt Arsenault b456c6dd56 Replace llvm.AMDGPU.ldexp with llvm.amdgcn.ldexp 
It didn't really work on r600 to begin with, which should
get its own intrinsic.

llvm-svn: 275813
 2016-07-18 16:42:50 +00:00
Matt Arsenault 45e6eaaa05 amdgcn: Use new workitem intrinsics 
llvm-svn: 261042
 2016-02-17 00:27:27 +00:00
Matt Arsenault a48e15c6cb Split sources for amdgcn and r600 
Most files remain in a common amdgpu directory.

Also switches barriers to to use convergent,
and use llvm.amdgcn.s.barrier.

This now requires 3.9/trunk to build amdgcn.

llvm-svn: 260777
 2016-02-13 01:01:59 +00:00