maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/libclc/amdgcn/lib
History
Jan Vesely 999b1d9426 amdgcn: rewrite barrier() using fence and clang __builtin_amdgcn_s_barrier 
Specs require using fences when barrier() is invoked:
"The barrier function will either flush any variables stored in local memory
or queue a memory fence to ensure correct ordering of memory operations to local memory."
and
"The barrier function will queue a memory fence to ensure correct ordering
of memory operations to global memory."

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
Tested-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 311022
 		2017-08-16 17:09:00 +00:00
..
math Replace llvm.AMDGPU.ldexp with llvm.amdgcn.ldexp 2016-07-18 16:42:50 +00:00
mem_fence amdgcn: Implement {read_,write_,}mem_fence builtin 2017-08-16 17:08:56 +00:00
synchronization amdgcn: rewrite barrier() using fence and clang __builtin_amdgcn_s_barrier 2017-08-16 17:09:00 +00:00
workitem amdgcn: Fix return type of get_num_groups 2016-08-25 07:31:40 +00:00
OVERRIDES
…
SOURCES amdgcn: rewrite barrier() using fence and clang __builtin_amdgcn_s_barrier 2017-08-16 17:09:00 +00:00