mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 05:01:59 +01:00
28625d59d9
Summary: Previously, in the NewPM pipeline, TailCallElim recalculates the DomTree when it modifies any instruction in the Function. For example, ``` CallInst *CI = dyn_cast<CallInst>(&I); ... CI->setTailCall(); Modified = true; ... if (!Modified || ...) return PreservedAnalyses::all(); ``` After applying this patch, the DomTree only recalculates if needed (plus an extra insertEdge() + an extra deleteEdge() call). When optimizing SQLite with `-passes="default<O3>"` pipeline of the newPM, the number of DomTree recalculation decreases by 6.2%, the number of nodes visited by DFS decreases by 2.9%. The time used by DomTree will decrease approximately 1%~2.5% after applying the patch. Statistics: ``` Before the patch: 23010 dom-tree-stats - Number of DomTree recalculations 489264 dom-tree-stats - Number of nodes visited by DFS -- DomTree After the patch: 21581 dom-tree-stats - Number of DomTree recalculations 475088 dom-tree-stats - Number of nodes visited by DFS -- DomTree ``` Reviewers: kuhar, dmgreen, brzycki, grosser, davide Reviewed By: kuhar, brzycki Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D49982 llvm-svn: 338954
27 lines
811 B
LLVM
27 lines
811 B
LLVM
; REQUIRES: asserts
|
|
; Duplicate the return into if.end to enable TCE.
|
|
; RUN: opt -tailcallelim -verify-dom-info -stats -disable-output < %s 2>&1 | FileCheck %s
|
|
|
|
; CHECK: Number of return duplicated
|
|
|
|
define i32 @fib(i32 %n) nounwind ssp {
|
|
entry:
|
|
%cmp = icmp slt i32 %n, 2
|
|
br i1 %cmp, label %if.then, label %if.end
|
|
|
|
if.then: ; preds = %entry
|
|
br label %return
|
|
|
|
if.end: ; preds = %entry
|
|
%sub = add nsw i32 %n, -2
|
|
%call = call i32 @fib(i32 %sub)
|
|
%sub3 = add nsw i32 %n, -1
|
|
%call4 = call i32 @fib(i32 %sub3)
|
|
%add = add nsw i32 %call, %call4
|
|
br label %return
|
|
|
|
return: ; preds = %if.end, %if.then
|
|
%retval.0 = phi i32 [ 1, %if.then ], [ %add, %if.end ]
|
|
ret i32 %retval.0
|
|
}
|