From 86ed53089fc0bff84b472f89ba42da8ea1a3df86 Mon Sep 17 00:00:00 2001
From: Chandler Carruth <chandlerc@gmail.com>
Date: Fri, 28 Dec 2012 14:43:42 +0000
Subject: [PATCH] Fix a stunning oversight in the inline cost analysis. It was
 never propagating one of the values it simplified to a constant across a
 myriad of instructions. Notably, ptrtoint instructions when we had a constant
 pointer (say, 0) didn't propagate that, blocking a massive number of
 down-stream optimizations.

This was uncovered when investigating why we fail to inline and delete
the boilerplate in:

  void f() {
    std::vector<int> v;
    v.push_back(1);
  }

It turns out most of the efforts I've made thus far to improve the
analysis weren't making it far purely because of this. After this is
fixed, the store-to-load forwarding patch enables LLVM to optimize the
above to an empty function. We still can't nuke a second push_back, but
for different reasons.

There is a very real chance this will cause somewhat noticable changes
in inlining behavior, so please let me know if you see regressions (or
improvements!) because of this patch.

llvm-svn: 171196
---
 llvm/lib/Analysis/InlineCost.cpp              | 20 ++++++++--
 .../Transforms/Inline/inline_constprop.ll     | 38 +++++++++++++++++++
 2 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/llvm/lib/Analysis/InlineCost.cpp b/llvm/lib/Analysis/InlineCost.cpp
index 685050765a72..835b8343b284 100644
--- a/llvm/lib/Analysis/InlineCost.cpp
+++ b/llvm/lib/Analysis/InlineCost.cpp
@@ -358,7 +358,10 @@ bool CallAnalyzer::visitGetElementPtr(GetElementPtrInst &I) {
 
 bool CallAnalyzer::visitBitCast(BitCastInst &I) {
   // Propagate constants through bitcasts.
-  if (Constant *COp = dyn_cast<Constant>(I.getOperand(0)))
+  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
+  if (!COp)
+    COp = SimplifiedValues.lookup(I.getOperand(0));
+  if (COp)
     if (Constant *C = ConstantExpr::getBitCast(COp, I.getType())) {
       SimplifiedValues[&I] = C;
       return true;
@@ -383,7 +386,10 @@ bool CallAnalyzer::visitBitCast(BitCastInst &I) {
 
 bool CallAnalyzer::visitPtrToInt(PtrToIntInst &I) {
   // Propagate constants through ptrtoint.
-  if (Constant *COp = dyn_cast<Constant>(I.getOperand(0)))
+  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
+  if (!COp)
+    COp = SimplifiedValues.lookup(I.getOperand(0));
+  if (COp)
     if (Constant *C = ConstantExpr::getPtrToInt(COp, I.getType())) {
       SimplifiedValues[&I] = C;
       return true;
@@ -416,7 +422,10 @@ bool CallAnalyzer::visitPtrToInt(PtrToIntInst &I) {
 
 bool CallAnalyzer::visitIntToPtr(IntToPtrInst &I) {
   // Propagate constants through ptrtoint.
-  if (Constant *COp = dyn_cast<Constant>(I.getOperand(0)))
+  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
+  if (!COp)
+    COp = SimplifiedValues.lookup(I.getOperand(0));
+  if (COp)
     if (Constant *C = ConstantExpr::getIntToPtr(COp, I.getType())) {
       SimplifiedValues[&I] = C;
       return true;
@@ -443,7 +452,10 @@ bool CallAnalyzer::visitIntToPtr(IntToPtrInst &I) {
 
 bool CallAnalyzer::visitCastInst(CastInst &I) {
   // Propagate constants through ptrtoint.
-  if (Constant *COp = dyn_cast<Constant>(I.getOperand(0)))
+  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
+  if (!COp)
+    COp = SimplifiedValues.lookup(I.getOperand(0));
+  if (COp)
     if (Constant *C = ConstantExpr::getCast(I.getOpcode(), COp, I.getType())) {
       SimplifiedValues[&I] = C;
       return true;
diff --git a/llvm/test/Transforms/Inline/inline_constprop.ll b/llvm/test/Transforms/Inline/inline_constprop.ll
index b2a14fe0b716..77bc3784acb4 100644
--- a/llvm/test/Transforms/Inline/inline_constprop.ll
+++ b/llvm/test/Transforms/Inline/inline_constprop.ll
@@ -149,6 +149,44 @@ bb.false:
   ret i8 %z8
 }
 
+define i64 @caller5(i64 %y) {
+; Check that we can round trip constants through various kinds of casts etc w/o
+; losing track of the constant prop in the inline cost analysis.
+;
+; CHECK: @caller5
+; CHECK-NOT: call
+; CHECK: ret i64 -1
+
+entry:
+  %x = call i64 @callee5(i64 42, i64 %y)
+  ret i64 %x
+}
+
+define i64 @callee5(i64 %x, i64 %y) {
+  %inttoptr = inttoptr i64 %x to i8*
+  %bitcast = bitcast i8* %inttoptr to i32*
+  %ptrtoint = ptrtoint i32* %bitcast to i64
+  %trunc = trunc i64 %ptrtoint to i32
+  %zext = zext i32 %trunc to i64
+  %cmp = icmp eq i64 %zext, 42
+  br i1 %cmp, label %bb.true, label %bb.false
+
+bb.true:
+  ret i64 -1
+
+bb.false:
+  ; This block musn't be counted in the inline cost.
+  %y1 = add i64 %y, 1
+  %y2 = add i64 %y1, 1
+  %y3 = add i64 %y2, 1
+  %y4 = add i64 %y3, 1
+  %y5 = add i64 %y4, 1
+  %y6 = add i64 %y5, 1
+  %y7 = add i64 %y6, 1
+  %y8 = add i64 %y7, 1
+  ret i64 %y8
+}
+
 
 define i32 @PR13412.main() {
 ; This is a somewhat complicated three layer subprogram that was reported to