6502/llvm-6502
1
0 Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2026-04-27 04:18:42 +00:00
Code Issues Projects Releases Wiki Activity

Merging r235662:

Browse Source 
------------------------------------------------------------------------
r235662 | thomas.stellard | 2015-04-23 18:59:24 -0400 (Thu, 23 Apr 2015) | 2 lines

R600: Correctly lower CONCAT_VECTOR nodes with more than 2 operands

------------------------------------------------------------------------

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@236450 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Tom Stellard committed 2015-05-04 19:50:14 +00:00
1 parent c64ec2996c
commit b968a2dced
2 files changed
+13 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

lib/Target/R600/AMDGPUISelLowering.cpp
+2 -4
View File
@@ -826,11 +826,9 @@ SDValue AMDGPUTargetLowering::LowerGlobalAddress(AMDGPUMachineFunction* MFI,
SDValue AMDGPUTargetLowering::LowerCONCAT_VECTORS(SDValue Op,
SelectionDAG &DAG) const {
SmallVector<SDValue, 8> Args;
SDValue A = Op.getOperand(0);
SDValue B = Op.getOperand(1);
DAG.ExtractVectorElements(A, Args);
DAG.ExtractVectorElements(B, Args);
for (const SDUse &U : Op->ops())
DAG.ExtractVectorElements(U.get(), Args);
return DAG.getNode(ISD::BUILD_VECTOR, SDLoc(Op), Op.getValueType(), Args);
}
test/CodeGen/R600/concat_vectors.ll
+11
View File
@@ -283,3 +283,14 @@ define void @test_concat_v16i16(<32 x i16> addrspace(1)* %out, <16 x i16> %a, <1
store <32 x i16> %concat, <32 x i16> addrspace(1)* %out, align 64
ret void
}
; FUNC-LABEL: {{^}}concat_vector_crash:
; SI: s_endpgm
define void @concat_vector_crash(<8 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in) {
bb:
%tmp = load <2 x float> addrspace(1)* %in, align 4
%tmp1 = shufflevector <2 x float> %tmp, <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
%tmp2 = shufflevector <8 x float> undef, <8 x float> %tmp1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
store <8 x float> %tmp2, <8 x float> addrspace(1)* %out, align 32
ret void
}