Do not assume the value passed to memset is an i32.

The code in SelectionDAG::getMemset for some reason assumes the value passed to
memset is an i32. This breaks the generated code for targets that only have
registers smaller than 32 bits because the value might get split into multiple
registers by the calling convention. See the test for the MSP430 target included
in the patch for an example.

This patch ensures that nothing is assumed about the type of the value. Instead,
the type is taken from the selected overload of the llvm.memset intrinsic.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216716 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index ceb2f76..e2ead47 100644 (file)
--- a/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -4361,18 +4361,11 @@ SDValue SelectionDAG::getMemset(SDValue Chain, SDLoc dl, SDValue Dst,
   TargetLowering::ArgListEntry Entry;
   Entry.Node = Dst; Entry.Ty = IntPtrTy;
   Args.push_back(Entry);
-  // Extend or truncate the argument to be an i32 value for the call.
-  if (Src.getValueType().bitsGT(MVT::i32))
-    Src = getNode(ISD::TRUNCATE, dl, MVT::i32, Src);
-  else
-    Src = getNode(ISD::ZERO_EXTEND, dl, MVT::i32, Src);
   Entry.Node = Src;
-  Entry.Ty = Type::getInt32Ty(*getContext());
-  Entry.isSExt = true;
+  Entry.Ty = Src.getValueType().getTypeForEVT(*getContext());
   Args.push_back(Entry);
   Entry.Node = Size;
   Entry.Ty = IntPtrTy;
-  Entry.isSExt = false;
   Args.push_back(Entry);
 
   // FIXME: pass in SDLoc

diff --git a/test/CodeGen/MSP430/memset.ll b/test/CodeGen/MSP430/memset.ll
new file mode 100644 (file)
index 0000000..bf10544
--- /dev/null
+++ b/test/CodeGen/MSP430/memset.ll
@@ -0,0 +1,22 @@
+; RUN: llc < %s | FileCheck %s
+target datalayout = "e-p:16:16:16-i8:8:8-i16:16:16-i32:16:32-n8:16"
+target triple = "msp430---elf"
+
+@buf = external global i8*
+
+; Function Attrs: nounwind
+define void @test() nounwind {
+entry:
+; CHECK-LABEL: test:
+  %0 = load i8** @buf, align 2
+; CHECK: mov.w &buf, r15
+; CHECK-NEXT: mov.w #5, r14
+; CHECK-NEXT: mov.w #128, r13
+; CHECK-NEXT: call #memset
+  call void @llvm.memset.p0i8.i16(i8* %0, i8 5, i16 128, i32 1, i1 false)
+  ret void
+}
+
+; Function Attrs: nounwind
+declare void @llvm.memset.p0i8.i16(i8* nocapture, i8, i16, i32, i1) nounwind
+