maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU: Don't assert on a16 images on targets without FeatureR128A16 

Currently the lowering for i16 image coordinates asserts on gfx10. I'm
somewhat confused by this though. The feature is missing from the
gfx10 feature lists, but the a16 bit appears to be present in the
manual for MIMG instructions.
This commit is contained in:
Matt Arsenault 2020-01-16 15:44:36 -05:00 committed by Matt Arsenault
parent d1b32f328e
commit 886f9071c6
2 changed files with 22 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
View File

@ -5460,8 +5460,11 @@ SDValue SITargetLowering::lowerImage(SDValue Op,
unsigned DimIdx = AddrIdx + BaseOpcode->NumExtraArgs;
MVT VAddrVT = Op.getOperand(DimIdx).getSimpleValueType();
const MVT VAddrScalarVT = VAddrVT.getScalarType();
if (((VAddrScalarVT == MVT::f16) || (VAddrScalarVT == MVT::i16)) &&
ST->hasFeature(AMDGPU::FeatureR128A16)) {
if (((VAddrScalarVT == MVT::f16) || (VAddrScalarVT == MVT::i16))) {
// Illegal to use a16 images
if (!ST->hasFeature(AMDGPU::FeatureR128A16))
return Op;
IsA16 = true;
const MVT VectorVT = VAddrScalarVT == MVT::f16 ? MVT::v2f16 : MVT::v2i16;
for (unsigned i = AddrIdx; i < (AddrIdx + NumMIVAddrs); ++i) {

17
llvm/test/CodeGen/AMDGPU/unsupported-image-a16.ll Normal file
View File

@ -0,0 +1,17 @@
; RUN: not llc -march=amdgcn -mcpu=fiji -verify-machineinstrs -o /dev/null %s 2>&1 | FileCheck -check-prefix=ERR %s
; Make sure this doesn't assert on targets without the r128-16
; feature, and instead generates a slection error.
; ERR: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.image.load.1d
define amdgpu_ps <4 x float> @load_1d(<8 x i32> inreg %rsrc, <2 x i16> %coords) {
main_body:
%s = extractelement <2 x i16> %coords, i32 0
%v = call <4 x float> @llvm.amdgcn.image.load.1d.v4f32.i16(i32 15, i16 %s, <8 x i32> %rsrc, i32 0, i32 0)
ret <4 x float> %v
}
declare <4 x float> @llvm.amdgcn.image.load.1d.v4f32.i16(i32 immarg, i16, <8 x i32>, i32 immarg, i32 immarg) #0
attributes #0 = { nounwind readonly }