[PATCH] D53627: [HotColdSplitting] Identify larger cold regions using domtree queries

[Vedant Kumar via Phabricator via llvm-commits]

vsk created this revision.
vsk added reviewers: tejohnson, sebpop, hiraditya.
Herald added subscribers: kristof.beyls, javed.absar.

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. 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.


https://reviews.llvm.org/D53627

Files:
  llvm/lib/Transforms/IPO/HotColdSplitting.cpp
  llvm/test/Transforms/HotColdSplit/do-not-split.ll
  llvm/test/Transforms/HotColdSplit/multiple-exits.ll
  llvm/test/Transforms/HotColdSplit/outline-if-then-else.ll
  llvm/test/Transforms/HotColdSplit/outline-while-loop.ll
  llvm/test/Transforms/HotColdSplit/split-cold-1.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D53627.170795.patch
Type: text/x-patch
Size: 23725 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20181024/51b55613/attachment.bin>