Introduce a loop block rotation optimization to the new block placement

pass. This is designed to achieve one of the important optimizations
that the old code placement pass did, but more simply.

This is a somewhat rough and *very* conservative version of the
transform. We could get a lot fancier here if there are profitable cases
to do so. In particular, this only looks for a single pattern, it
insists that the loop backedge being rotated away is the last backedge
in the chain, and it doesn't provide any means of doing better in-loop
placement due to the rotation. However, it appears that it will handle
the important loops I am finding in the LLVM test suite.

llvm-svn: 145158

1 files changed, 30 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/block-placement.ll b/llvm/test/CodeGen/X86/block-placement.ll
index f87d1a6daf7..d0afee6ada6 100644
--- a/llvm/test/CodeGen/X86/block-placement.ll
+++ b/llvm/test/CodeGen/X86/block-placement.ll
@@ -169,6 +169,36 @@ exit:
   ret i32 %sum
 }
 
+define i32 @test_loop_rotate(i32 %i, i32* %a) {
+; Check that we rotate conditional exits from the loop to the bottom of the
+; loop, eliminating unconditional branches to the top.
+; CHECK: test_loop_rotate:
+; CHECK: %entry
+; CHECK: %body1
+; CHECK: %body0
+; CHECK: %exit
+
+entry:
+  br label %body0
+
+body0:
+  %iv = phi i32 [ 0, %entry ], [ %next, %body1 ]
+  %base = phi i32 [ 0, %entry ], [ %sum, %body1 ]
+  %next = add i32 %iv, 1
+  %exitcond = icmp eq i32 %next, %i
+  br i1 %exitcond, label %exit, label %body1
+
+body1:
+  %arrayidx = getelementptr inbounds i32* %a, i32 %iv
+  %0 = load i32* %arrayidx
+  %sum = add nsw i32 %0, %base
+  %bailcond1 = icmp eq i32 %sum, 42
+  br label %body0
+
+exit:
+  ret i32 %base
+}
+
 define i32 @test_loop_align(i32 %i, i32* %a) {
 ; Check that we provide basic loop body alignment with the block placement
 ; pass.