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

[NVPTX] deal with all aggregate return types. 

Fixes a crash in llvm_unreachable when a function has array return type.

Differential Revision: https://reviews.llvm.org/D22524

llvm-svn: 276154
This commit is contained in:
Artem Belevich 2016-07-20 18:39:52 +00:00
parent b2e76a5e7a
commit 74158b5061
3 changed files with 49 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
View File

@ -368,13 +368,13 @@ void NVPTXAsmPrinter::printReturnValStr(const Function *F, raw_ostream &O) {
} else if (isa<PointerType>(Ty)) {
O << ".param .b" << TLI->getPointerTy(DL).getSizeInBits()
<< " func_retval0";
} else if ((Ty->getTypeID() == Type::StructTyID) || isa<VectorType>(Ty)) {
} else if (Ty->isAggregateType() || Ty->isVectorTy()) {
unsigned totalsz = DL.getTypeAllocSize(Ty);
unsigned retAlignment = 0;
if (!llvm::getAlign(*F, 0, retAlignment))
retAlignment = DL.getABITypeAlignment(Ty);
O << ".param .align " << retAlignment << " .b8 func_retval0[" << totalsz
<< "]";
unsigned retAlignment = 0;
if (!llvm::getAlign(*F, 0, retAlignment))
retAlignment = DL.getABITypeAlignment(Ty);
O << ".param .align " << retAlignment << " .b8 func_retval0[" << totalsz
<< "]";
} else
llvm_unreachable("Unknown return type");
} else {

43
llvm/test/CodeGen/NVPTX/aggregate-return.ll Normal file
View File

@ -0,0 +1,43 @@
; RUN: llc < %s -march=nvptx64 -mcpu=sm_35 | FileCheck %s
declare <2 x float> @barv(<2 x float> %input)
declare [2 x float] @bara([2 x float] %input)
declare {float, float} @bars({float, float} %input)
define void @foov(<2 x float> %input, <2 x float>* %output) {
; CHECK-LABEL: @foov
%call = tail call <2 x float> @barv(<2 x float> %input)
; CHECK: .param .align 8 .b8 retval0[8];
; CHECK: ld.param.v2.f32 {[[ELEMV1:%f[0-9]+]], [[ELEMV2:%f[0-9]+]]}, [retval0+0];
store <2 x float> %call, <2 x float>* %output, align 8
; CHECK: st.v2.f32 [{{%rd[0-9]+}}], {[[ELEMV1]], [[ELEMV2]]}
ret void
}
define void @fooa([2 x float] %input, [2 x float]* %output) {
; CHECK-LABEL: @fooa
%call = tail call [2 x float] @bara([2 x float] %input)
; CHECK: .param .align 4 .b8 retval0[8];
; CHECK-DAG: ld.param.f32 [[ELEMA1:%f[0-9]+]], [retval0+0];
; CHECK-DAG: ld.param.f32 [[ELEMA2:%f[0-9]+]], [retval0+4];
store [2 x float] %call, [2 x float]* %output, align 4
; CHECK: }
; CHECK-DAG: st.f32 [{{%rd[0-9]+}}], [[ELEMA1]]
; CHECK-DAG: st.f32 [{{%rd[0-9]+}}+4], [[ELEMA2]]
ret void
; CHECK: ret
}
define void @foos({float, float} %input, {float, float}* %output) {
; CHECK-LABEL: @foos
%call = tail call {float, float} @bars({float, float} %input)
; CHECK: .param .align 4 .b8 retval0[8];
; CHECK-DAG: ld.param.f32 [[ELEMS1:%f[0-9]+]], [retval0+0];
; CHECK-DAG: ld.param.f32 [[ELEMS2:%f[0-9]+]], [retval0+4];
store {float, float} %call, {float, float}* %output, align 4
; CHECK: }
; CHECK-DAG: st.f32 [{{%rd[0-9]+}}], [[ELEMS1]]
; CHECK-DAG: st.f32 [{{%rd[0-9]+}}+4], [[ELEMS2]]
ret void
; CHECK: ret
}

14
llvm/test/CodeGen/NVPTX/vector-return.ll
View File

@ -1,14 +0,0 @@
; RUN: llc < %s -march=nvptx64 -mcpu=sm_35 | FileCheck %s
declare <2 x float> @bar(<2 x float> %input)
define void @foo(<2 x float> %input, <2 x float>* %output) {
; CHECK-LABEL: @foo
entry:
%call = tail call <2 x float> @bar(<2 x float> %input)
; CHECK: .param .align 8 .b8 retval0[8];
; CHECK: ld.param.v2.f32 {[[ELEM1:%f[0-9]+]], [[ELEM2:%f[0-9]+]]}, [retval0+0];
store <2 x float> %call, <2 x float>* %output, align 8
; CHECK: st.v2.f32 [{{%rd[0-9]+}}], {[[ELEM1]], [[ELEM2]]}
ret void
}