1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
llvm-mirror/test/CodeGen/NVPTX/atomics-sm60.ll
Justin Lebar 8f48b0a3d7 [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

llvm-svn: 317623
2017-11-07 22:10:54 +00:00

20 lines
920 B
LLVM

; RUN: llc < %s -march=nvptx -mcpu=sm_60 | FileCheck %s
; RUN: llc < %s -march=nvptx64 -mcpu=sm_60 | FileCheck %s
; CHECK-LABEL .func test(
define void @test(double* %dp0, double addrspace(1)* %dp1, double addrspace(3)* %dp3, double %d) {
; CHECK: atom.add.f64
%r1 = call double @llvm.nvvm.atomic.load.add.f64.p0f64(double* %dp0, double %d)
; CHECK: atom.global.add.f64
%r2 = call double @llvm.nvvm.atomic.load.add.f64.p1f64(double addrspace(1)* %dp1, double %d)
; CHECK: atom.shared.add.f64
%ret = call double @llvm.nvvm.atomic.load.add.f64.p3f64(double addrspace(3)* %dp3, double %d)
ret void
}
declare double @llvm.nvvm.atomic.load.add.f64.p0f64(double* nocapture, double) #1
declare double @llvm.nvvm.atomic.load.add.f64.p1f64(double addrspace(1)* nocapture, double) #1
declare double @llvm.nvvm.atomic.load.add.f64.p3f64(double addrspace(3)* nocapture, double) #1
attributes #1 = { argmemonly nounwind }