Fix the expansion of umax and smax in the case where one or more of

the operands have pointer type, so that the resulting type matches
the original SCEV type, and so that unnecessary ptrtoints are
avoided in common cases.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@75680 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 171 insertions, 6 deletions

diff --git a/lib/Analysis/ScalarEvolutionExpander.cpp b/lib/Analysis/ScalarEvolutionExpander.cpp
index ecfbc8e..20d6e20 100644
--- a/lib/Analysis/ScalarEvolutionExpander.cpp
+++ b/lib/Analysis/ScalarEvolutionExpander.cpp
@@ -609,9 +609,15 @@ Value *SCEVExpander::visitSignExtendExpr(const SCEVSignExtendExpr *S) {
 }
 
 Value *SCEVExpander::visitSMaxExpr(const SCEVSMaxExpr *S) {
-  const Type *Ty = SE.getEffectiveSCEVType(S->getType());
-  Value *LHS = expandCodeFor(S->getOperand(0), Ty);
-  for (unsigned i = 1; i < S->getNumOperands(); ++i) {
+  Value *LHS = expand(S->getOperand(S->getNumOperands()-1));
+  const Type *Ty = LHS->getType();
+  for (int i = S->getNumOperands()-2; i >= 0; --i) {
+    // In the case of mixed integer and pointer types, do the
+    // rest of the comparisons as integer.
+    if (S->getOperand(i)->getType() != Ty) {
+      Ty = SE.getEffectiveSCEVType(Ty);
+      LHS = InsertNoopCastOfTo(LHS, Ty);
+    }
     Value *RHS = expandCodeFor(S->getOperand(i), Ty);
     Value *ICmp = Builder.CreateICmpSGT(LHS, RHS, "tmp");
     InsertedValues.insert(ICmp);
@@ -619,13 +625,23 @@ Value *SCEVExpander::visitSMaxExpr(const SCEVSMaxExpr *S) {
     InsertedValues.insert(Sel);
     LHS = Sel;
   }
+  // In the case of mixed integer and pointer types, cast the
+  // final result back to the pointer type.
+  if (LHS->getType() != S->getType())
+    LHS = InsertNoopCastOfTo(LHS, S->getType());
   return LHS;
 }
 
 Value *SCEVExpander::visitUMaxExpr(const SCEVUMaxExpr *S) {
-  const Type *Ty = SE.getEffectiveSCEVType(S->getType());
-  Value *LHS = expandCodeFor(S->getOperand(0), Ty);
-  for (unsigned i = 1; i < S->getNumOperands(); ++i) {
+  Value *LHS = expand(S->getOperand(S->getNumOperands()-1));
+  const Type *Ty = LHS->getType();
+  for (int i = S->getNumOperands()-2; i >= 0; --i) {
+    // In the case of mixed integer and pointer types, do the
+    // rest of the comparisons as integer.
+    if (S->getOperand(i)->getType() != Ty) {
+      Ty = SE.getEffectiveSCEVType(Ty);
+      LHS = InsertNoopCastOfTo(LHS, Ty);
+    }
     Value *RHS = expandCodeFor(S->getOperand(i), Ty);
     Value *ICmp = Builder.CreateICmpUGT(LHS, RHS, "tmp");
     InsertedValues.insert(ICmp);
@@ -633,6 +649,10 @@ Value *SCEVExpander::visitUMaxExpr(const SCEVUMaxExpr *S) {
     InsertedValues.insert(Sel);
     LHS = Sel;
   }
+  // In the case of mixed integer and pointer types, cast the
+  // final result back to the pointer type.
+  if (LHS->getType() != S->getType())
+    LHS = InsertNoopCastOfTo(LHS, S->getType());
   return LHS;
 }
 
diff --git a/test/Transforms/IndVarSimplify/max-pointer.ll b/test/Transforms/IndVarSimplify/max-pointer.ll
new file mode 100644
index 0000000..ba2b2fa
--- /dev/null
+++ b/test/Transforms/IndVarSimplify/max-pointer.ll
@@ -0,0 +1,145 @@
+; RUN: llvm-as < %s | opt -indvars | llvm-dis > %t
+; RUN: grep {icmp ugt i8\\\*} %t | count 1
+; RUN: grep {icmp sgt i8\\\*} %t | count 1
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
+
+	%struct.CKenCodeCodec = type <{ i8 }>
+
+define void @foo(i8* %str1Ptr, i8* %str2Ptr, i8* %inLastBytePtr) nounwind {
+entry:
+	%0 = icmp ult i8* %str2Ptr, %str1Ptr		; <i1> [#uses=1]
+	%str2Ptr_addr.0 = select i1 %0, i8* %str1Ptr, i8* %str2Ptr		; <i8*> [#uses=1]
+	br label %bb2
+
+bb2:		; preds = %bb2, %entry
+	%str2Ptr_addr.1 = phi i8* [ %str2Ptr_addr.0, %entry ], [ %1, %bb2 ]		; <i8*> [#uses=1]
+	%1 = getelementptr i8* %str2Ptr_addr.1, i64 1		; <i8*> [#uses=2]
+	%2 = icmp ult i8* %1, %inLastBytePtr		; <i1> [#uses=0]
+	br i1 false, label %bb2, label %return
+
+return:		; preds = %bb2
+	ret void
+}
+
+define void @bar(i8* %str1Ptr, i64 %s, i8* %inLastBytePtr) nounwind {
+entry:
+        %str2Ptr = inttoptr i64 %s to i8*
+	%0 = icmp ult i8* %str2Ptr, %str1Ptr		; <i1> [#uses=1]
+	%str2Ptr_addr.0 = select i1 %0, i8* %str1Ptr, i8* %str2Ptr		; <i8*> [#uses=1]
+	br label %bb2
+
+bb2:		; preds = %bb2, %entry
+	%str2Ptr_addr.1 = phi i8* [ %str2Ptr_addr.0, %entry ], [ %1, %bb2 ]		; <i8*> [#uses=1]
+	%1 = getelementptr i8* %str2Ptr_addr.1, i64 1		; <i8*> [#uses=2]
+	%2 = icmp ult i8* %1, %inLastBytePtr		; <i1> [#uses=0]
+	br i1 false, label %bb2, label %return
+
+return:		; preds = %bb2
+	ret void
+}
+
+define void @qux(i64 %t, i64 %s, i8* %inLastBytePtr) nounwind {
+entry:
+        %str1Ptr = inttoptr i64 %t to i8*
+        %str2Ptr = inttoptr i64 %s to i8*
+	%0 = icmp ult i8* %str2Ptr, %str1Ptr		; <i1> [#uses=1]
+	%str2Ptr_addr.0 = select i1 %0, i8* %str1Ptr, i8* %str2Ptr		; <i8*> [#uses=1]
+	br label %bb2
+
+bb2:		; preds = %bb2, %entry
+	%str2Ptr_addr.1 = phi i8* [ %str2Ptr_addr.0, %entry ], [ %1, %bb2 ]		; <i8*> [#uses=1]
+	%1 = getelementptr i8* %str2Ptr_addr.1, i64 1		; <i8*> [#uses=2]
+	%2 = icmp ult i8* %1, %inLastBytePtr		; <i1> [#uses=0]
+	br i1 false, label %bb2, label %return
+
+return:		; preds = %bb2
+	ret void
+}
+
+define void @vor(i64 %t, i8* %str2Ptr, i8* %inLastBytePtr) nounwind {
+entry:
+        %str1Ptr = inttoptr i64 %t to i8*
+	%0 = icmp ult i8* %str2Ptr, %str1Ptr		; <i1> [#uses=1]
+	%str2Ptr_addr.0 = select i1 %0, i8* %str1Ptr, i8* %str2Ptr		; <i8*> [#uses=1]
+	br label %bb2
+
+bb2:		; preds = %bb2, %entry
+	%str2Ptr_addr.1 = phi i8* [ %str2Ptr_addr.0, %entry ], [ %1, %bb2 ]		; <i8*> [#uses=1]
+	%1 = getelementptr i8* %str2Ptr_addr.1, i64 1		; <i8*> [#uses=2]
+	%2 = icmp ult i8* %1, %inLastBytePtr		; <i1> [#uses=0]
+	br i1 false, label %bb2, label %return
+
+return:		; preds = %bb2
+	ret void
+}
+
+define void @sfoo(i8* %str1Ptr, i8* %str2Ptr, i8* %inLastBytePtr) nounwind {
+entry:
+	%0 = icmp slt i8* %str2Ptr, %str1Ptr		; <i1> [#uses=1]
+	%str2Ptr_addr.0 = select i1 %0, i8* %str1Ptr, i8* %str2Ptr		; <i8*> [#uses=1]
+	br label %bb2
+
+bb2:		; preds = %bb2, %entry
+	%str2Ptr_addr.1 = phi i8* [ %str2Ptr_addr.0, %entry ], [ %1, %bb2 ]		; <i8*> [#uses=1]
+	%1 = getelementptr i8* %str2Ptr_addr.1, i64 1		; <i8*> [#uses=2]
+	%2 = icmp slt i8* %1, %inLastBytePtr		; <i1> [#uses=0]
+	br i1 false, label %bb2, label %return
+
+return:		; preds = %bb2
+	ret void
+}
+
+define void @sbar(i8* %str1Ptr, i64 %s, i8* %inLastBytePtr) nounwind {
+entry:
+        %str2Ptr = inttoptr i64 %s to i8*
+	%0 = icmp slt i8* %str2Ptr, %str1Ptr		; <i1> [#uses=1]
+	%str2Ptr_addr.0 = select i1 %0, i8* %str1Ptr, i8* %str2Ptr		; <i8*> [#uses=1]
+	br label %bb2
+
+bb2:		; preds = %bb2, %entry
+	%str2Ptr_addr.1 = phi i8* [ %str2Ptr_addr.0, %entry ], [ %1, %bb2 ]		; <i8*> [#uses=1]
+	%1 = getelementptr i8* %str2Ptr_addr.1, i64 1		; <i8*> [#uses=2]
+	%2 = icmp slt i8* %1, %inLastBytePtr		; <i1> [#uses=0]
+	br i1 false, label %bb2, label %return
+
+return:		; preds = %bb2
+	ret void
+}
+
+define void @squx(i64 %t, i64 %s, i8* %inLastBytePtr) nounwind {
+entry:
+        %str1Ptr = inttoptr i64 %t to i8*
+        %str2Ptr = inttoptr i64 %s to i8*
+	%0 = icmp slt i8* %str2Ptr, %str1Ptr		; <i1> [#uses=1]
+	%str2Ptr_addr.0 = select i1 %0, i8* %str1Ptr, i8* %str2Ptr		; <i8*> [#uses=1]
+	br label %bb2
+
+bb2:		; preds = %bb2, %entry
+	%str2Ptr_addr.1 = phi i8* [ %str2Ptr_addr.0, %entry ], [ %1, %bb2 ]		; <i8*> [#uses=1]
+	%1 = getelementptr i8* %str2Ptr_addr.1, i64 1		; <i8*> [#uses=2]
+	%2 = icmp slt i8* %1, %inLastBytePtr		; <i1> [#uses=0]
+	br i1 false, label %bb2, label %return
+
+return:		; preds = %bb2
+	ret void
+}
+
+define void @svor(i64 %t, i8* %str2Ptr, i8* %inLastBytePtr) nounwind {
+entry:
+        %str1Ptr = inttoptr i64 %t to i8*
+	%0 = icmp slt i8* %str2Ptr, %str1Ptr		; <i1> [#uses=1]
+	%str2Ptr_addr.0 = select i1 %0, i8* %str1Ptr, i8* %str2Ptr		; <i8*> [#uses=1]
+	br label %bb2
+
+bb2:		; preds = %bb2, %entry
+	%str2Ptr_addr.1 = phi i8* [ %str2Ptr_addr.0, %entry ], [ %1, %bb2 ]		; <i8*> [#uses=1]
+	%1 = getelementptr i8* %str2Ptr_addr.1, i64 1		; <i8*> [#uses=2]
+	%2 = icmp slt i8* %1, %inLastBytePtr		; <i1> [#uses=0]
+	br i1 false, label %bb2, label %return
+
+return:		; preds = %bb2
+	ret void
+}
+
+