Fix DAGCombiner to avoid folding a sext-in-reg or similar through a shl

in order to fold it into a load.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@118471 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 7154d9d691c3a848f03b5f0ad9d42e2aa0998e0b..1a0f503378d14900c2617fd26ab9691f4c26ac18 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -4120,6 +4120,7 @@ SDValue DAGCombiner::ReduceLoadWidth(SDNode *N) {
   // we can fold the truncate through the shift.
   unsigned ShLeftAmt = 0;
   if (ShAmt == 0 && N0.getOpcode() == ISD::SHL && N0.hasOneUse() &&
+      ExtVT == VT &&
       TLI.isNarrowingProfitable(N0.getValueType(), VT)) {
     if (ConstantSDNode *N01 = dyn_cast<ConstantSDNode>(N0.getOperand(1))) {
       ShLeftAmt = N01->getZExtValue();

diff --git a/test/CodeGen/X86/narrow-shl-load.ll b/test/CodeGen/X86/narrow-shl-load.ll
index d67a6a5a2f5f9753ca8bb17d9def3793f5378f23..53b03884a58c76126a297e035c9e65bd484ccd42 100644 (file)
--- a/test/CodeGen/X86/narrow-shl-load.ll
+++ b/test/CodeGen/X86/narrow-shl-load.ll
@@ -1,12 +1,11 @@
-; RUN: llc -march=x86-64 < %s
-
-; DAGCombiner should fold this code in finite time.
-
-; rdar://8606584
+; RUN: llc -march=x86-64 < %s | FileCheck %s
 
 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-n8:16:32:64"
 target triple = "x86_64-pc-linux-gnu"
 
+; DAGCombiner should fold this code in finite time.
+; rdar://8606584
+
 define void @D() nounwind readnone {
 bb.nph:
   br label %while.cond
@@ -30,3 +29,37 @@ while.cond:                                       ; preds = %while.cond, %bb.nph
 while.end:                                        ; preds = %while.cond
   ret void
 }
+
+
+; DAGCombiner shouldn't fold the sdiv (ashr) away.
+; rdar://8636812
+; CHECK: main:
+; CHECK:   sarl
+
+define i32 @main() nounwind {
+entry:
+  %i = alloca i32, align 4
+  %j = alloca i8, align 1
+  store i32 127, i32* %i, align 4
+  store i8 0, i8* %j, align 1
+  %tmp3 = load i32* %i, align 4
+  %mul = mul nsw i32 %tmp3, 2
+  %conv4 = trunc i32 %mul to i8
+  %conv5 = sext i8 %conv4 to i32
+  %div6 = sdiv i32 %conv5, 2
+  %conv7 = trunc i32 %div6 to i8
+  %conv9 = sext i8 %conv7 to i32
+  %cmp = icmp eq i32 %conv9, -1
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:                                          ; preds = %entry
+  ret i32 0
+
+if.end:                                           ; preds = %entry
+  call void @abort() noreturn
+  unreachable
+}
+
+declare void @abort() noreturn
+
+declare void @exit(i32) noreturn