maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[CUDA] Added stubs for __nvvm_atom_add_*_d() builtins. 

They show up in CUDA headers but are not currently supported by
NVPTX back-end.

Differential Revision: http://reviews.llvm.org/D11694

llvm-svn: 245502
This commit is contained in:
Artem Belevich 2015-08-19 21:11:37 +00:00
parent 1d0f1996df
commit 46db9e822c
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
clang/include/clang/Basic/BuiltinsNVPTX.def
View File

@ -453,6 +453,9 @@ BUILTIN(__nvvm_atom_add_gen_ll, "LLiLLiD*LLi", "n")
BUILTIN(__nvvm_atom_add_g_f, "ffD*1f", "n")
BUILTIN(__nvvm_atom_add_s_f, "ffD*3f", "n")
BUILTIN(__nvvm_atom_add_gen_f, "ffD*f", "n")
BUILTIN(__nvvm_atom_add_g_d, "ddD*1d", "n")
BUILTIN(__nvvm_atom_add_s_d, "ddD*3d", "n")
BUILTIN(__nvvm_atom_add_gen_d, "ddD*d", "n")
BUILTIN(__nvvm_atom_sub_g_i, "iiD*1i", "n")
BUILTIN(__nvvm_atom_sub_s_i, "iiD*3i", "n")