OSDN Git Service

[NVPTX] Implement __nvvm_atom_add_gen_d builtin.
authorJustin Lebar <jlebar@google.com>
Tue, 7 Nov 2017 22:10:54 +0000 (22:10 +0000)
committerJustin Lebar <jlebar@google.com>
Tue, 7 Nov 2017 22:10:54 +0000 (22:10 +0000)
commitd8660fa5dc39cff9877b4f885d7a4d10aad20a65
tree6be1b717127ae93d9d00de18a62606c616e510d4
parent595a4486c103fb5761e1f1354c9b8c7958781f77
[NVPTX] Implement __nvvm_atom_add_gen_d builtin.

Summary:
This just seems to have been an oversight.  We already supported the f64
atomic add with an explicit scope (e.g. "cta"), but not the scopeless
version.

Reviewers: tra

Subscribers: jholewinski, sanjoy, cfe-commits, llvm-commits, hiraditya

Differential Revision: https://reviews.llvm.org/D39638

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317623 91177308-0d34-0410-b5e6-96231b3b80d8
include/llvm/IR/IntrinsicsNVVM.td
lib/Target/NVPTX/NVPTXISelLowering.cpp
lib/Target/NVPTX/NVPTXIntrinsics.td
test/CodeGen/NVPTX/atomics-sm60.ll [new file with mode: 0644]