isAsCheapAsMove instructions can have register src operands. Check if they are really...

This fixes sse.expandfft and sse.stepfft.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@63890 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SimpleRegisterCoalescing.cpp b/lib/CodeGen/SimpleRegisterCoalescing.cpp
index 28d249235d136598e41f588721a1495e03d77823..f09eee64b2cb4c9deb079c9fc8d0af6be1fa6c83 100644 (file)
--- a/lib/CodeGen/SimpleRegisterCoalescing.cpp
+++ b/lib/CodeGen/SimpleRegisterCoalescing.cpp
@@ -558,6 +558,9 @@ bool SimpleRegisterCoalescing::ReMaterializeTrivialDef(LiveInterval &SrcInt,
   const TargetInstrDesc &TID = DefMI->getDesc();
   if (!TID.isAsCheapAsAMove())
     return false;
+  if (!DefMI->getDesc().isRematerializable() ||
+      !tii_->isTriviallyReMaterializable(DefMI))
+    return false;
   bool SawStore = false;
   if (!DefMI->isSafeToMove(tii_, SawStore))
     return false;

diff --git a/test/CodeGen/X86/2009-02-05-CoalescerBug.ll b/test/CodeGen/X86/2009-02-05-CoalescerBug.ll
new file mode 100644 (file)
index 0000000..e57238a
--- /dev/null
+++ b/test/CodeGen/X86/2009-02-05-CoalescerBug.ll
@@ -0,0 +1,12 @@
+; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep movss  | count 2
+; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse2 | grep movaps | count 4
+
+define i1 @cfft2_bb12_bb12_2E_ce([2 x float]* %y, [2 x float]* %w, i32, [2 x float]* %x.pn59, i32 %smax190, i32 %j.1180, <4 x float> %wu.2179, <4 x float> %wr.2178, <4 x float>* %tmp89.out, <4 x float>* %tmp107.out, i32* %indvar.next218.out) nounwind {
+newFuncRoot:
+       %tmp82 = insertelement <4 x float> %wr.2178, float 0.000000e+00, i32 0          ; <<4 x float>> [#uses=1]
+       %tmp85 = insertelement <4 x float> %tmp82, float 0.000000e+00, i32 1            ; <<4 x float>> [#uses=1]
+       %tmp87 = insertelement <4 x float> %tmp85, float 0.000000e+00, i32 2            ; <<4 x float>> [#uses=1]
+       %tmp89 = insertelement <4 x float> %tmp87, float 0.000000e+00, i32 3            ; <<4 x float>> [#uses=1]
+       store <4 x float> %tmp89, <4 x float>* %tmp89.out
+       ret i1 false
+}