From 0cdbc7a2ca4cc45817790790be15d78e2bf27310 Mon Sep 17 00:00:00 2001
From: Chris Lattner <sabre@nondot.org>
Date: Tue, 8 Sep 2009 00:13:52 +0000
Subject: [PATCH] fix ComputeMaskedBits handling of zext/sext/trunc to work
 with vectors. This fixes PR4905

llvm-svn: 81174
---
 llvm/lib/Analysis/ValueTracking.cpp       | 15 +++++++++------
 llvm/test/Transforms/InstCombine/crash.ll | 23 +++++++++++++++++++++--
 2 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index 78bb3dbc65d4..1782edee7bfc 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -232,12 +232,16 @@ void llvm::ComputeMaskedBits(Value *V, const APInt &Mask,
     // FALL THROUGH and handle them the same as zext/trunc.
   case Instruction::ZExt:
   case Instruction::Trunc: {
+    const Type *SrcTy = I->getOperand(0)->getType();
+    
+    unsigned SrcBitWidth;
     // Note that we handle pointer operands here because of inttoptr/ptrtoint
     // which fall through here.
-    const Type *SrcTy = I->getOperand(0)->getType();
-    unsigned SrcBitWidth = TD ?
-      TD->getTypeSizeInBits(SrcTy) :
-      SrcTy->getScalarSizeInBits();
+    if (isa<PointerType>(SrcTy))
+      SrcBitWidth = TD->getTypeSizeInBits(SrcTy);
+    else
+      SrcBitWidth = SrcTy->getScalarSizeInBits();
+    
     APInt MaskIn(Mask);
     MaskIn.zextOrTrunc(SrcBitWidth);
     KnownZero.zextOrTrunc(SrcBitWidth);
@@ -265,8 +269,7 @@ void llvm::ComputeMaskedBits(Value *V, const APInt &Mask,
   }
   case Instruction::SExt: {
     // Compute the bits in the result that are not present in the input.
-    const IntegerType *SrcTy = cast<IntegerType>(I->getOperand(0)->getType());
-    unsigned SrcBitWidth = SrcTy->getBitWidth();
+    unsigned SrcBitWidth = I->getOperand(0)->getType()->getScalarSizeInBits();
       
     APInt MaskIn(Mask); 
     MaskIn.trunc(SrcBitWidth);
diff --git a/llvm/test/Transforms/InstCombine/crash.ll b/llvm/test/Transforms/InstCombine/crash.ll
index 03bad9924426..c252ac9dccf8 100644
--- a/llvm/test/Transforms/InstCombine/crash.ll
+++ b/llvm/test/Transforms/InstCombine/crash.ll
@@ -1,8 +1,8 @@
-; RUN: llvm-as < %s | opt -instcombine | llvm-dis
+; RUN: opt < %s -instcombine | llvm-dis
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
 target triple = "i386-apple-darwin10.0"
 
-define i32 @_Z9model8bitR5Mixeri(i8 %tmp2) ssp {
+define i32 @test0(i8 %tmp2) ssp {
 entry:
   %tmp3 = zext i8 %tmp2 to i32
   %tmp8 = lshr i32 %tmp3, 6 
@@ -12,3 +12,22 @@ entry:
   %tmp12 = xor i32 %tmp11, 0     
   ret i32 %tmp12
 }
+
+; PR4905
+define <2 x i64> @test1(<2 x i64> %x, <2 x i64> %y) nounwind {
+entry:
+  %conv.i94 = bitcast <2 x i64> %y to <4 x i32>   ; <<4 x i32>> [#uses=1]
+  %sub.i97 = sub <4 x i32> %conv.i94, undef       ; <<4 x i32>> [#uses=1]
+  %conv3.i98 = bitcast <4 x i32> %sub.i97 to <2 x i64> ; <<2 x i64>> [#uses=2]
+  %conv2.i86 = bitcast <2 x i64> %conv3.i98 to <4 x i32> ; <<4 x i32>> [#uses=1]
+  %cmp.i87 = icmp sgt <4 x i32> undef, %conv2.i86 ; <<4 x i1>> [#uses=1]
+  %sext.i88 = sext <4 x i1> %cmp.i87 to <4 x i32> ; <<4 x i32>> [#uses=1]
+  %conv3.i89 = bitcast <4 x i32> %sext.i88 to <2 x i64> ; <<2 x i64>> [#uses=1]
+  %and.i = and <2 x i64> %conv3.i89, %conv3.i98   ; <<2 x i64>> [#uses=1]
+  %or.i = or <2 x i64> zeroinitializer, %and.i    ; <<2 x i64>> [#uses=1]
+  %conv2.i43 = bitcast <2 x i64> %or.i to <4 x i32> ; <<4 x i32>> [#uses=1]
+  %sub.i = sub <4 x i32> zeroinitializer, %conv2.i43 ; <<4 x i32>> [#uses=1]
+  %conv3.i44 = bitcast <4 x i32> %sub.i to <2 x i64> ; <<2 x i64>> [#uses=1]
+  ret <2 x i64> %conv3.i44
+}
+