maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/and-gcn.ll

27 lines
879 B
LLVM
Raw Normal View History

AMDGPU/SI: Detect uniform branches and emit s_cbranch instructions Reviewers: arsenm Subscribers: mareko, MatzeB, qcolombet, arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D16603 llvm-svn: 260765
2016-02-13 07:45:29 +08:00
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
; FUNC-LABEL: {{^}}v_and_i64_br:
[AMDGPU] Switch scalarize global loads ON by default Differential revision: https://reviews.llvm.org/D34407 llvm-svn: 307097
2017-07-05 01:32:00 +08:00
; SI: s_and_b64
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @v_and_i64_br(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 addrspace(1)* %bptr) {
AMDGPU/SI: Detect uniform branches and emit s_cbranch instructions Reviewers: arsenm Subscribers: mareko, MatzeB, qcolombet, arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D16603 llvm-svn: 260765
2016-02-13 07:45:29 +08:00
entry:
%tid = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) #0
%tmp0 = icmp eq i32 %tid, 0
br i1 %tmp0, label %if, label %endif
if:
%a = load i64, i64 addrspace(1)* %aptr, align 8
%b = load i64, i64 addrspace(1)* %bptr, align 8
%and = and i64 %a, %b
br label %endif
endif:
%tmp1 = phi i64 [%and, %if], [0, %entry]
store i64 %tmp1, i64 addrspace(1)* %out, align 8
ret void
}
declare i32 @llvm.amdgcn.mbcnt.lo(i32, i32) #0
attributes #0 = { nounwind readnone }