Fix rdar://9289512 - not folding load into compare at -O0

The basic issue here is that bottom-up isel is matching the branch
and compare, and was failing to fold the load into the branch/compare
combo.  Fixing this (by allowing folding into any instruction of a
sequence that is selected) allows us to produce things like:


cmpb    $0, 52(%rax)
je      LBB4_2

instead of:

movb    52(%rax), %cl
cmpb    $0, %cl
je      LBB4_2

This makes the generated -O0 code run a bit faster, but also speeds up
compile time by putting less pressure on the register allocator and 
generating less code.

This was one of the biggest classes of missing load folding.  Implementing
this shrinks 176.gcc's c-decl.s (as a random example) by about 4% in (verbose-asm)
line count.

llvm-svn: 129656

1 files changed, 22 insertions, 1 deletions

diff --git a/llvm/test/CodeGen/X86/fast-isel-x86-64.ll b/llvm/test/CodeGen/X86/fast-isel-x86-64.ll
index b2d1263ca77..6137b48736f 100644
--- a/llvm/test/CodeGen/X86/fast-isel-x86-64.ll
+++ b/llvm/test/CodeGen/X86/fast-isel-x86-64.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s | FileCheck %s
+; RUN: llc < %s  -fast-isel -O0 -regalloc=fast | 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-apple-darwin10.0.0"
@@ -12,3 +12,24 @@ define i32 @test1(i32 %i) nounwind ssp {
 
 ; CHECK: test1:
 ; CHECK: andl	$8, 
+
+
+; rdar://9289512 - The load should fold into the compare.
+define void @test2(i64 %x) nounwind ssp {
+entry:
+  %x.addr = alloca i64, align 8
+  store i64 %x, i64* %x.addr, align 8
+  %tmp = load i64* %x.addr, align 8
+  %cmp = icmp sgt i64 %tmp, 42
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:                                          ; preds = %entry
+  br label %if.end
+
+if.end:                                           ; preds = %if.then, %entry
+  ret void
+}
+
+; CHECK: test2:
+; CHECK: movq	%rdi, -8(%rsp)
+; CHECK: cmpq	$42, -8(%rsp)