CodeGen peephole: fold redundant phys reg copies

[oota-llvm.git] / test / CodeGen / X86 / shift-folding.ll

diff --git a/test/CodeGen/X86/shift-folding.ll b/test/CodeGen/X86/shift-folding.ll
index 7eac116e020ef2701c185e51eaf4a02ea63b638e..69887870897785ffcb9cac66b0c55ea40a656116 100644 (file)
--- a/test/CodeGen/X86/shift-folding.ll
+++ b/test/CodeGen/X86/shift-folding.ll
@@ -1,7 +1,7 @@
-; RUN: llc < %s -march=x86 | FileCheck %s
+; RUN: llc < %s -march=x86 -verify-coalescing | FileCheck %s
 
 define i32* @test1(i32* %P, i32 %X) {
-; CHECK: test1:
+; CHECK-LABEL: test1:
 ; CHECK-NOT: shrl
 ; CHECK-NOT: shll
 ; CHECK: ret
@@ -9,12 +9,12 @@ define i32* @test1(i32* %P, i32 %X) {
 entry:
   %Y = lshr i32 %X, 2
   %gep.upgrd.1 = zext i32 %Y to i64
-  %P2 = getelementptr i32* %P, i64 %gep.upgrd.1
+  %P2 = getelementptr i32, i32* %P, i64 %gep.upgrd.1
   ret i32* %P2
 }
 
 define i32* @test2(i32* %P, i32 %X) {
-; CHECK: test2:
+; CHECK-LABEL: test2:
 ; CHECK: shll $4
 ; CHECK-NOT: shll
 ; CHECK: ret
@@ -22,29 +22,49 @@ define i32* @test2(i32* %P, i32 %X) {
 entry:
   %Y = shl i32 %X, 2
   %gep.upgrd.2 = zext i32 %Y to i64
-  %P2 = getelementptr i32* %P, i64 %gep.upgrd.2
+  %P2 = getelementptr i32, i32* %P, i64 %gep.upgrd.2
   ret i32* %P2
 }
 
 define i32* @test3(i32* %P, i32 %X) {
-; CHECK: test3:
+; CHECK-LABEL: test3:
 ; CHECK-NOT: shrl
 ; CHECK-NOT: shll
 ; CHECK: ret
 
 entry:
   %Y = ashr i32 %X, 2
-  %P2 = getelementptr i32* %P, i32 %Y
+  %P2 = getelementptr i32, i32* %P, i32 %Y
   ret i32* %P2
 }
 
 define fastcc i32 @test4(i32* %d) {
-; CHECK: test4:
+; CHECK-LABEL: test4:
 ; CHECK-NOT: shrl
 ; CHECK: ret
 
 entry:
-  %tmp4 = load i32* %d
+  %tmp4 = load i32, i32* %d
   %tmp512 = lshr i32 %tmp4, 24
   ret i32 %tmp512
 }
+
+define i64 @test5(i16 %i, i32* %arr) {
+; Ensure that we don't fold away shifts which have multiple uses, as they are
+; just re-introduced for the second use.
+; CHECK-LABEL: test5:
+; CHECK-NOT: shrl
+; CHECK: shrl $11
+; CHECK-NOT: shrl
+; CHECK: ret
+
+entry:
+  %i.zext = zext i16 %i to i32
+  %index = lshr i32 %i.zext, 11
+  %index.zext = zext i32 %index to i64
+  %val.ptr = getelementptr inbounds i32, i32* %arr, i64 %index.zext
+  %val = load i32, i32* %val.ptr
+  %val.zext = zext i32 %val to i64
+  %sum = add i64 %val.zext, %index.zext
+  ret i64 %sum
+}