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/insert_subreg.ll

17 lines
583 B
LLVM
Raw Normal View History

AMDGPU: Remove -mcpu=SI Leftover from before amdgcn/r600 split. llvm-svn: 310277
2017-08-08 02:30:35 +08:00
; RUN: llc -march=amdgcn -mcpu=tahiti -mattr=-promote-alloca -verify-machineinstrs < %s
R600/SI: Enable all tests that pass on VI without changes llvm-svn: 227214
2015-01-28 01:27:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-promote-alloca -verify-machineinstrs < %s
R600/SI: Legalize INSERT_SUBREG instructions during PostISelFolding LLVM assumes INSERT_SUBREG will always have register operands, so we need to legalize non-register operands, like FrameIndexes, to avoid random assertion failures. llvm-svn: 219420
2014-10-10 02:09:15 +08:00
; Test that INSERT_SUBREG instructions don't have non-register operands after
; instruction selection.
; Make sure this doesn't crash
; CHECK-LABEL: test:
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 @test(i64 addrspace(1)* %out) {
R600/SI: Legalize INSERT_SUBREG instructions during PostISelFolding LLVM assumes INSERT_SUBREG will always have register operands, so we need to legalize non-register operands, like FrameIndexes, to avoid random assertion failures. llvm-svn: 219420
2014-10-10 02:09:15 +08:00
entry:
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
%tmp0 = alloca [16 x i32], addrspace(5)
%tmp1 = ptrtoint [16 x i32] addrspace(5)* %tmp0 to i32
R600/SI: Legalize INSERT_SUBREG instructions during PostISelFolding LLVM assumes INSERT_SUBREG will always have register operands, so we need to legalize non-register operands, like FrameIndexes, to avoid random assertion failures. llvm-svn: 219420
2014-10-10 02:09:15 +08:00
%tmp2 = sext i32 %tmp1 to i64
store i64 %tmp2, i64 addrspace(1)* %out
ret void
}