From 516ab96de3eb0c80ac9c4867cc2076ef4749625e Mon Sep 17 00:00:00 2001
From: Bob Wilson <bob.wilson@apple.com>
Date: Sat, 16 Jan 2010 00:29:50 +0000
Subject: [PATCH] Run the pre-register allocation tail duplication pass by
 default.  Remove the -pre-regalloc-taildup command-line option, and add a new
 -disable-early-taildup option.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@93597 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/CodeGen/LLVMTargetMachine.cpp                     | 8 +++-----
 test/CodeGen/ARM/indirectbr.ll                        | 4 ++++
 test/CodeGen/Thumb/2009-12-17-pre-regalloc-taildup.ll | 2 +-
 test/CodeGen/Thumb2/2010-01-06-TailDuplicateLabels.ll | 2 +-
 4 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/lib/CodeGen/LLVMTargetMachine.cpp b/lib/CodeGen/LLVMTargetMachine.cpp
index 758c81dc593..837e1848aa5 100644
--- a/lib/CodeGen/LLVMTargetMachine.cpp
+++ b/lib/CodeGen/LLVMTargetMachine.cpp
@@ -39,6 +39,8 @@ static cl::opt<bool> DisableBranchFold("disable-branch-fold", cl::Hidden,
     cl::desc("Disable branch folding"));
 static cl::opt<bool> DisableTailDuplicate("disable-tail-duplicate", cl::Hidden,
     cl::desc("Disable tail duplication"));
+static cl::opt<bool> DisableEarlyTailDup("disable-early-taildup", cl::Hidden,
+    cl::desc("Disable pre-register allocation tail duplication"));
 static cl::opt<bool> DisableCodePlace("disable-code-place", cl::Hidden,
     cl::desc("Disable code placement"));
 static cl::opt<bool> DisableSSC("disable-ssc", cl::Hidden,
@@ -77,9 +79,6 @@ EnableFastISelOption("fast-isel", cl::Hidden,
 static cl::opt<bool> EnableSplitGEPGVN("split-gep-gvn", cl::Hidden,
     cl::desc("Split GEPs and run no-load GVN"));
 
-static cl::opt<bool> PreAllocTailDup("pre-regalloc-taildup", cl::Hidden,
-    cl::desc("Pre-register allocation tail duplication"));
-
 LLVMTargetMachine::LLVMTargetMachine(const Target &T,
                                      const std::string &TargetTriple)
   : TargetMachine(T) {
@@ -351,8 +350,7 @@ bool LLVMTargetMachine::addCommonCodeGenPasses(PassManagerBase &PM,
   }
 
   // Pre-ra tail duplication.
-  if (OptLevel != CodeGenOpt::None &&
-      !DisableTailDuplicate && PreAllocTailDup) {
+  if (OptLevel != CodeGenOpt::None && !DisableEarlyTailDup) {
     PM.add(createTailDuplicatePass(true));
     printAndVerify(PM, "After Pre-RegAlloc TailDuplicate",
                    /* allowDoubleDefs= */ true);
diff --git a/test/CodeGen/ARM/indirectbr.ll b/test/CodeGen/ARM/indirectbr.ll
index cd16084dbdb..5135d036e24 100644
--- a/test/CodeGen/ARM/indirectbr.ll
+++ b/test/CodeGen/ARM/indirectbr.ll
@@ -12,6 +12,10 @@ define internal arm_apcscc i32 @foo(i32 %i) nounwind {
 entry:
   %0 = load i8** @nextaddr, align 4               ; <i8*> [#uses=2]
   %1 = icmp eq i8* %0, null                       ; <i1> [#uses=1]
+; indirect branch gets duplicated here
+; ARM: bx
+; THUMB: mov pc, r1
+; THUMB2: mov pc, r1
   br i1 %1, label %bb3, label %bb2
 
 bb2:                                              ; preds = %entry, %bb3
diff --git a/test/CodeGen/Thumb/2009-12-17-pre-regalloc-taildup.ll b/test/CodeGen/Thumb/2009-12-17-pre-regalloc-taildup.ll
index 3401915eacb..2a5d9d68570 100644
--- a/test/CodeGen/Thumb/2009-12-17-pre-regalloc-taildup.ll
+++ b/test/CodeGen/Thumb/2009-12-17-pre-regalloc-taildup.ll
@@ -1,4 +1,4 @@
-; RUN: llc -O3 -pre-regalloc-taildup < %s | FileCheck %s
+; RUN: llc -O3 < %s | FileCheck %s
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:64:64-v128:128:128-a0:0:32-n32"
 target triple = "thumbv7-apple-darwin10"
 
diff --git a/test/CodeGen/Thumb2/2010-01-06-TailDuplicateLabels.ll b/test/CodeGen/Thumb2/2010-01-06-TailDuplicateLabels.ll
index 6a05df11147..07a35277b81 100644
--- a/test/CodeGen/Thumb2/2010-01-06-TailDuplicateLabels.ll
+++ b/test/CodeGen/Thumb2/2010-01-06-TailDuplicateLabels.ll
@@ -1,4 +1,4 @@
-; RUN: llc -relocation-model=pic -pre-regalloc-taildup < %s | grep {:$} | sort | uniq -d | count 0
+; RUN: llc -relocation-model=pic < %s | grep {:$} | sort | uniq -d | count 0
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:64:64-v128:128:128-a0:0:32-n32"
 target triple = "thumbv7-apple-darwin10"