DAGCombine: fold "(zext x) == C" into "x == (trunc C)" if the trunc is lossless.

On x86 this allows to fold a load into the cmp, greatly reducing register pressure.
  movzbl	(%rdi), %eax
  cmpl	$47, %eax
->
  cmpb	$47, (%rdi)

This shaves 8k off gcc.o on i386. I'll leave applying the patch in README.txt to Chris :)

llvm-svn: 130005

1 files changed, 36 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/shrink-compare.ll b/llvm/test/CodeGen/X86/shrink-compare.ll
new file mode 100644
index 00000000000..7eaf9411c1b
--- /dev/null
+++ b/llvm/test/CodeGen/X86/shrink-compare.ll
@@ -0,0 +1,36 @@
+; RUN: llc < %s -march=x86-64 | FileCheck %s
+
+declare void @bar()
+
+define void @test1(i32* nocapture %X) nounwind {
+entry:
+  %tmp1 = load i32* %X, align 4
+  %and = and i32 %tmp1, 255
+  %cmp = icmp eq i32 %and, 47
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:
+  tail call void @bar() nounwind
+  br label %if.end
+
+if.end:
+  ret void
+; CHECK: test1:
+; CHECK: cmpb $47, (%rdi)
+}
+
+define void @test2(i32 %X) nounwind {
+entry:
+  %and = and i32 %X, 255
+  %cmp = icmp eq i32 %and, 47
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:
+  tail call void @bar() nounwind
+  br label %if.end
+
+if.end:
+  ret void
+; CHECK: test2:
+; CHECK: cmpb $47, %dil
+}