[InstCombine] When canonicalizing gep indices, prefer zext when possible

If we know that the sign bit of a value being sign extended is zero, we can use a zero extension instead.  This is motivated by the fact that zero extensions are generally cheaper on x86 (and most other architectures?).  We already apply a similar transform in DAGCombine, this just extends that to the IR level.

This comes up when we eagerly canonicalize gep indices to the width of a machine register (i64 on x86_64). To do so, we insert sign extensions (sext) to promote smaller types.

Differential Revision: http://reviews.llvm.org/D7255

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@229189 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/InstCombine/InstCombineCasts.cpp b/lib/Transforms/InstCombine/InstCombineCasts.cpp
index 3c11c7c352944d1ee3b1db618c426142063ed5b0..9db4e7d2a4bb833800f4b1ad1190548182c8d60f 100644 (file)
--- a/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -1064,6 +1064,15 @@ Instruction *InstCombiner::visitSExt(SExtInst &CI) {
   Value *Src = CI.getOperand(0);
   Type *SrcTy = Src->getType(), *DestTy = CI.getType();
 
+  // If we know that the value being extended is positive, we can use a zext
+  // instead. 
+  bool KnownZero, KnownOne;
+  ComputeSignBit(Src, KnownZero, KnownOne, 0, &CI);
+  if (KnownZero) {
+    Value *ZExt = Builder->CreateZExt(Src, DestTy);
+    return ReplaceInstUsesWith(CI, ZExt);
+  }
+
   // Attempt to extend the entire input expression tree to the destination
   // type.   Only do this if the dest type is a simple type, don't convert the
   // expression tree to something weird like i93 unless the source is also

diff --git a/test/Transforms/InstCombine/gep-sext.ll b/test/Transforms/InstCombine/gep-sext.ll
new file mode 100644 (file)
index 0000000..3d23dab
--- /dev/null
+++ b/test/Transforms/InstCombine/gep-sext.ll
@@ -0,0 +1,61 @@
+; RUN: opt < %s -instcombine -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-win32"
+
+declare void @use(i32) readonly
+
+; We prefer to canonicalize the machine width gep indices early
+define void @test(i32* %p, i32 %index) {
+; CHECK-LABEL: @test
+; CHECK-NEXT: %1 = sext i32 %index to i64
+; CHECK-NEXT: %addr = getelementptr i32* %p, i64 %1
+  %addr = getelementptr i32* %p, i32 %index
+  %val = load i32* %addr
+  call void @use(i32 %val)
+  ret void
+}
+; If they've already been canonicalized via zext, that's fine
+define void @test2(i32* %p, i32 %index) {
+; CHECK-LABEL: @test2
+; CHECK-NEXT: %i = zext i32 %index to i64
+; CHECK-NEXT: %addr = getelementptr i32* %p, i64 %i
+  %i = zext i32 %index to i64
+  %addr = getelementptr i32* %p, i64 %i
+  %val = load i32* %addr
+  call void @use(i32 %val)
+  ret void
+}
+; If we can use a zext, we prefer that.  This requires
+; knowing that the index is positive.
+define void @test3(i32* %p, i32 %index) {
+; CHECK-LABEL: @test3
+; CHECK:   zext
+; CHECK-NOT: sext
+  %addr_begin = getelementptr i32* %p, i64 40
+  %addr_fixed = getelementptr i32* %addr_begin, i64 48
+  %val_fixed = load i32* %addr_fixed, !range !0
+  %addr = getelementptr i32* %addr_begin, i32 %val_fixed
+  %val = load i32* %addr
+  call void @use(i32 %val)
+  ret void
+}
+; Replace sext with zext where possible
+define void @test4(i32* %p, i32 %index) {
+; CHECK-LABEL: @test4
+; CHECK:   zext
+; CHECK-NOT: sext
+  %addr_begin = getelementptr i32* %p, i64 40
+  %addr_fixed = getelementptr i32* %addr_begin, i64 48
+  %val_fixed = load i32* %addr_fixed, !range !0
+  %i = sext i32 %val_fixed to i64
+  %addr = getelementptr i32* %addr_begin, i64 %i
+  %val = load i32* %addr
+  call void @use(i32 %val)
+  ret void
+}
+
+;;  !range !0
+!0 = !{i32 0, i32 2147483647}
+
+
+