6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-07-21 02:29:22 +00:00
Code Issues Projects Releases Wiki Activity

[inliner] Significantly improve the compile time in cases like PR19499

Browse Source 
by avoiding inlining massive switches merely because they have no
instructions in them. These switches still show up where we fail to form
lookup tables, and in those cases they are actually going to cause
a very significant code size hit anyways, so inlining them is not the
right call. The right way to fix any performance regressions stemming
from this is to enhance the switch-to-lookup-table logic to fire in more
places.

This makes PR19499 about 5x less bad. It uncovers a second compile time
problem in that test case that is unrelated (surprisingly!).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207403 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chandler Carruth 2014-04-28 08:52:44 +00:00
parent 0ddc7447d9
commit d6d57bc3fb
2 changed files with 83 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
lib/Analysis/IPA/InlineCost.cpp
View File

@ -808,9 +808,29 @@ bool CallAnalyzer::visitBranchInst(BranchInst &BI) {
bool CallAnalyzer::visitSwitchInst(SwitchInst &SI) {
// We model unconditional switches as free, see the comments on handling
// branches.
return isa<ConstantInt>(SI.getCondition()) ||
dyn_cast_or_null<ConstantInt>(
SimplifiedValues.lookup(SI.getCondition()));
if (isa<ConstantInt>(SI.getCondition()))
return true;
if (Value *V = SimplifiedValues.lookup(SI.getCondition()))
if (isa<ConstantInt>(V))
return true;
// Otherwise, we need to accumulate a cost proportional to the number of
// distinct successor blocks. This fan-out in the CFG cannot be represented
// for free even if we can represent the core switch as a jumptable that
// takes a single instruction.
//
// NB: We convert large switches which are just used to initialize large phi
// nodes to lookup tables instead in simplify-cfg, so this shouldn't prevent
// inlining those. It will prevent inlining in cases where the optimization
// does not (yet) fire.
SmallPtrSet<BasicBlock *, 8> SuccessorBlocks;
SuccessorBlocks.insert(SI.getDefaultDest());
for (auto I = SI.case_begin(), E = SI.case_end(); I != E; ++I)
SuccessorBlocks.insert(I.getCaseSuccessor());
// Add cost corresponding to the number of distinct destinations. The first
// we model as free because of fallthrough.
Cost += (SuccessorBlocks.size() - 1) * InlineConstants::InstrCost;
return false;
}
bool CallAnalyzer::visitIndirectBrInst(IndirectBrInst &IBI) {

60
test/Transforms/Inline/switch.ll Normal file
View File

@ -0,0 +1,60 @@
; RUN: opt < %s -inline -inline-threshold=20 -S | FileCheck %s
define i32 @callee(i32 %a) {
switch i32 %a, label %sw.default [
i32 0, label %sw.bb0
i32 1, label %sw.bb1
i32 2, label %sw.bb2
i32 3, label %sw.bb3
i32 4, label %sw.bb4
i32 5, label %sw.bb5
i32 6, label %sw.bb6
i32 7, label %sw.bb7
i32 8, label %sw.bb8
i32 9, label %sw.bb9
]
sw.default:
br label %return
sw.bb0:
br label %return
sw.bb1:
br label %return
sw.bb2:
br label %return
sw.bb3:
br label %return
sw.bb4:
br label %return
sw.bb5:
br label %return
sw.bb6:
br label %return
sw.bb7:
br label %return
sw.bb8:
br label %return
sw.bb9:
br label %return
return:
ret i32 42
}
define i32 @caller(i32 %a) {
; CHECK-LABEL: @caller(
; CHECK: call i32 @callee(
%result = call i32 @callee(i32 %a)
ret i32 %result
}