[ConstantFold] Disallow folding vector geps into bitcasts

Summary:
Getelementptr returns a vector of pointers, instead of a single address,
when one or more of its arguments is a vector. In such case it is not
possible to simplify the expression by inserting a bitcast of operand(0)
into the destination type, as it will create a bitcast between different
sizes.

Reviewers: majnemer, mkuper, mssimpso, spatel

Reviewed By: spatel

Subscribers: lebedev.ri, llvm-commits

Differential Revision: https://reviews.llvm.org/D46379

llvm-svn: 333783

llvm/lib/IR/ConstantFold.cpp

@@ -545,7 +545,11 @@ Constant *llvm::ConstantFoldCastInstruction(unsigned opc, Constant *V,
                opc != Instruction::AddrSpaceCast &&
                // Do not fold bitcast (gep) with inrange index, as this loses
                // information.
-               !cast<GEPOperator>(CE)->getInRangeIndex().hasValue()) {
+               !cast<GEPOperator>(CE)->getInRangeIndex().hasValue() &&
+               // Do not fold if the gep type is a vector, as bitcasting
+               // operand 0 of a vector gep will result in a bitcast between
+               // different sizes.
+               !CE->getType()->isVectorTy()) {
       // If all of the indexes in the GEP are null values, there is no pointer
       // adjustment going on.  We might as well cast the source pointer.
       bool isAllNull = true;

llvm/test/Analysis/ConstantFolding/gep-zeroinit-vector.ll

@@ -1,15 +1,15 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -constprop -S -o - | FileCheck %s
 
-; Testcase that point out faulty bitcast that cast between different sizes.
-; See "bitcast ([1 x %rec8]* @a to <2 x i16*>)" in checks below
+; Testcase that verify that we don't get a faulty bitcast that cast between
+; different sizes.
 
 %rec8 = type { i16 }
 @a = global [1 x %rec8] zeroinitializer
 
 define <2 x i16*> @test_gep() {
 ; CHECK-LABEL: @test_gep(
-; CHECK-NEXT:    ret <2 x i16*> bitcast ([1 x %rec8]* @a to <2 x i16*>)
+; CHECK-NEXT:    ret <2 x i16*> <i16* getelementptr inbounds (%rec8, %rec8* extractelement (<2 x %rec8*> getelementptr ([1 x %rec8], [1 x %rec8]* @a, <2 x i64> zeroinitializer, <2 x i64> zeroinitializer), i32 0), i32 0, i32 0), i16* getelementptr inbounds (%rec8, %rec8* extractelement (<2 x %rec8*> getelementptr ([1 x %rec8], [1 x %rec8]* @a, <2 x i64> zeroinitializer, <2 x i64> zeroinitializer), i32 1), i32 0, i32 0)>
 ;
   %A = getelementptr [1 x %rec8], [1 x %rec8]* @a, <2 x i16> zeroinitializer, <2 x i64> zeroinitializer
   %B = bitcast <2 x %rec8*> %A to <2 x i16*>

llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll

@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-vectorize -S -mtriple=x86_64-- -o - %s | FileCheck %s
 
-; Testcase that point out faulty bitcast that cast between different sizes.
-; See "bitcast ([1 x %rec8]* @a to <2 x i16*>)" in checks below
+; Testcase that verify that we don't get a faulty bitcast that cast between
+; different sizes.
 
 %rec8 = type { i16 }
 
@@ -28,7 +28,7 @@ define void @f1() {
 ; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr [2 x i16*], [2 x i16*]* @b, i16 0, i64 [[TMP2]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i16*, i16** [[TMP3]], i32 0
 ; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i16** [[TMP4]] to <2 x i16*>*
-; CHECK-NEXT:    store <2 x i16*> bitcast ([1 x %rec8]* @a to <2 x i16*>), <2 x i16*>* [[TMP5]], align 8
+; CHECK-NEXT:    store <2 x i16*> <i16* getelementptr inbounds (%rec8, %rec8* extractelement (<2 x %rec8*> getelementptr ([1 x %rec8], [1 x %rec8]* @a, <2 x i16> zeroinitializer, <2 x i64> zeroinitializer), i32 0), i32 0, i32 0), i16* getelementptr inbounds (%rec8, %rec8* extractelement (<2 x %rec8*> getelementptr ([1 x %rec8], [1 x %rec8]* @a, <2 x i16> zeroinitializer, <2 x i64> zeroinitializer), i32 1), i32 0, i32 0)>, <2 x i16*>* [[TMP5]], align 8
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 2
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], 2
 ; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0