mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
8b8c6ce97c
The current splitting algorithm works in three stages: 1) Identify cold blocks, then 2) Use forward/backward propagation to mark hot blocks, then 3) Grow a SESE region of blocks *outside* of the set of hot blocks and start outlining. While testing this pass on Apple internal frameworks I noticed that some kinds of control flow (e.g. loops) are never outlined, even though they unconditionally lead to / follow cold blocks. I noticed two other issues related to how cold regions are identified: - An inconsistency can arise in the internal state of the hotness propagation stage, as a block may end up in both the ColdBlocks set and the HotBlocks set. Further inconsistencies can arise as these sets do not match what's in ProfileSummaryInfo. - It isn't necessary to limit outlining to single-exit regions. This patch teaches the splitting algorithm to identify maximal cold regions and outline them. A maximal cold region is defined as the set of blocks post-dominated by a cold sink block, or dominated by that sink block. This approach can successfully outline loops in the cold path. As a side benefit, it maintains less internal state than the current approach. Due to a limitation in CodeExtractor, blocks within the maximal cold region which aren't dominated by a single entry point (a so-called "max ancestor") are filtered out. Results: - X86 (LNT + -Os + externals): 134KB of TEXT were outlined compared to 47KB pre-patch, or a ~3x improvement. Did not see a performance impact across two runs. - AArch64 (LNT + -Os + externals + Apple-internal benchmarks): 149KB of TEXT were outlined. Ditto re: performance impact. - Outlining results improve marginally in the internal frameworks I tested. Follow-ups: - Outline more than once per function, outline large single basic blocks, & try to remove unconditional branches in outlined functions. Differential Revision: https://reviews.llvm.org/D53627 llvm-svn: 345209
68 lines
1.9 KiB
LLVM
68 lines
1.9 KiB
LLVM
; RUN: opt -S -hotcoldsplit < %s | FileCheck %s
|
|
|
|
; Source:
|
|
;
|
|
; extern void sideeffect(int);
|
|
; extern void __attribute__((cold)) sink();
|
|
; void foo(int cond) {
|
|
; if (cond) { //< Start outlining here.
|
|
; while (cond > 10) {
|
|
; --cond;
|
|
; sideeffect(0);
|
|
; }
|
|
; sink();
|
|
; }
|
|
; sideeffect(1);
|
|
; }
|
|
|
|
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.14.0"
|
|
|
|
; CHECK-LABEL: define {{.*}}@foo(
|
|
; CHECK: br i1 {{.*}}, label %if.end, label %codeRepl
|
|
; CHECK-LABEL: codeRepl:
|
|
; CHECK-NEXT: call void @foo.cold.1
|
|
; CHECK-LABEL: if.end:
|
|
; CHECK: call void @sideeffect(i32 1)
|
|
define void @foo(i32 %cond) {
|
|
entry:
|
|
%tobool = icmp eq i32 %cond, 0
|
|
br i1 %tobool, label %if.end, label %while.cond.preheader
|
|
|
|
while.cond.preheader: ; preds = %entry
|
|
%cmp3 = icmp sgt i32 %cond, 10
|
|
br i1 %cmp3, label %while.body.preheader, label %while.end
|
|
|
|
while.body.preheader: ; preds = %while.cond.preheader
|
|
br label %while.body
|
|
|
|
while.body: ; preds = %while.body.preheader, %while.body
|
|
%cond.addr.04 = phi i32 [ %dec, %while.body ], [ %cond, %while.body.preheader ]
|
|
%dec = add nsw i32 %cond.addr.04, -1
|
|
tail call void @sideeffect(i32 0) #3
|
|
%cmp = icmp sgt i32 %dec, 10
|
|
br i1 %cmp, label %while.body, label %while.end.loopexit
|
|
|
|
while.end.loopexit: ; preds = %while.body
|
|
br label %while.end
|
|
|
|
while.end: ; preds = %while.end.loopexit, %while.cond.preheader
|
|
tail call void (...) @sink()
|
|
ret void
|
|
|
|
if.end: ; preds = %entry
|
|
tail call void @sideeffect(i32 1)
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: define {{.*}}@foo.cold.1
|
|
; CHECK: phi i32
|
|
; CHECK-NEXT: add nsw i32
|
|
; CHECK-NEXT: call {{.*}}@sideeffect
|
|
; CHECK-NEXT: icmp
|
|
; CHECK-NEXT: br
|
|
|
|
declare void @sideeffect(i32)
|
|
|
|
declare void @sink(...) cold
|