From 23d933982a4465dc527c5a9635be6aea13e43e03 Mon Sep 17 00:00:00 2001 From: Philip Reames Date: Thu, 3 Mar 2016 00:01:42 +0000 Subject: [PATCH] [MBP] Avoid placing random blocks between loop preheader and header If we have a loop with a rarely taken path, we will prune that from the blocks which get added as part of the loop chain. The problem is that we weren't then recognizing the loop chain as schedulable when considering the preheader when forming the function chain. We'd then fall to various non-predecessors before finally scheduling the loop chain (as if the CFG was unnatural.) The net result was that there could be lots of garbage between a loop preheader and the loop, even though we could have directly fallen into the loop. It also meant we separated hot code with regions of colder code. The particular reason for the rejection of the loop chain was that we were scanning predecessor of the header, seeing the backedge, believing that was a globally more important predecessor (true), but forgetting to account for the fact the backedge precessor was already part of the existing loop chain (oops!. Differential Revision: http://reviews.llvm.org/D17830 llvm-svn: 262547 --- llvm/lib/CodeGen/MachineBlockPlacement.cpp | 3 +- llvm/test/CodeGen/X86/mbp-false-cfg-break.ll | 39 ++++++++++++++++++++ 2 files changed, 41 insertions(+), 1 deletion(-) create mode 100644 llvm/test/CodeGen/X86/mbp-false-cfg-break.ll diff --git a/llvm/lib/CodeGen/MachineBlockPlacement.cpp b/llvm/lib/CodeGen/MachineBlockPlacement.cpp index c190b2a66c64..c7d9212e7c93 100644 --- a/llvm/lib/CodeGen/MachineBlockPlacement.cpp +++ b/llvm/lib/CodeGen/MachineBlockPlacement.cpp @@ -466,7 +466,8 @@ MachineBlockPlacement::selectBestSuccessor(MachineBasicBlock *BB, MBFI->getBlockFreq(BB) * RealSuccProb * HotProb.getCompl(); bool BadCFGConflict = false; for (MachineBasicBlock *Pred : Succ->predecessors()) { - if (Pred == Succ || (BlockFilter && !BlockFilter->count(Pred)) || + if (Pred == Succ || BlockToChain[Pred] == &SuccChain || + (BlockFilter && !BlockFilter->count(Pred)) || BlockToChain[Pred] == &Chain) continue; BlockFrequency PredEdgeFreq = diff --git a/llvm/test/CodeGen/X86/mbp-false-cfg-break.ll b/llvm/test/CodeGen/X86/mbp-false-cfg-break.ll new file mode 100644 index 000000000000..bc8b0de3eef0 --- /dev/null +++ b/llvm/test/CodeGen/X86/mbp-false-cfg-break.ll @@ -0,0 +1,39 @@ +; RUN: llc < %s -march=x86-64 | FileCheck %s + +define void @test(i1 %cnd) !prof !{!"function_entry_count", i64 1024} { +; CHECK-LABEL: @test +; Using the assembly comments to indicate block order.. +; CHECK: # %loop +; CHECK: # %backedge +; CHECK: # %exit +; CHECK: # %rare +; CHECK: # %rare.1 + + br i1 undef, label %rare.1, label %preheader, !prof !{!"branch_weights", i32 0, i32 1000} +rare.1: + call void @foo() + br label %preheader + +preheader: + br label %loop + +loop: + %iv = phi i32 [0, %preheader], [%iv.next, %backedge] + call void @foo() + br i1 %cnd, label %backedge, label %rare, !prof !{!"branch_weights", i32 1000000, i32 1} +rare: + call void @foo() + br label %backedge +backedge: + call void @foo() + %iv.next = add i32 %iv, 1 + %cmp = icmp eq i32 %iv.next, 200 + br i1 %cmp, label %loop, label %exit, !prof !{!"branch_weights", i32 1000, i32 1} + +exit: + ret void + +} + + +declare void @foo()