maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

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
This commit is contained in:
Chandler Carruth 2012-12-28 14:43:42 +00:00
parent 753e21d057
commit 86ed53089f
2 changed files with 54 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llvm/lib/Analysis/InlineCost.cpp
View File

@ -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;

38
llvm/test/Transforms/Inline/inline_constprop.ll
View File

@ -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