Commit Graph

17 Commits

Author SHA1 Message Date
Roman Lebedev 1d51dc38d8
[SimplifyCFG][LoopRotate] SimplifyCFG: disable common instruction hoisting by default, enable late in pipeline
I've been looking at missed vectorizations in one codebase.
One particular thing that stands out is that some of the loops
reach vectorizer in a rather mangled form, with weird PHI's,
and some of the loops aren't even in a rotated form.

After taking a more detailed look, that happened because
the loop's headers were too big by then. It is evident that
SimplifyCFG's common code hoisting transform is at fault there,
because the pattern it handles is precisely the unrotated
loop basic block structure.

Surprizingly, `SimplifyCFGOpt::HoistThenElseCodeToIf()` is enabled
by default, and is always run, unlike it's friend, common code sinking
transform, `SinkCommonCodeFromPredecessors()`, which is not enabled
by default and is only run once very late in the pipeline.

I'm proposing to harmonize this, and disable common code hoisting
until //late// in pipeline. Definition of //late// may vary,
here currently i've picked the same one as for code sinking,
but i suppose we could enable it as soon as right after
loop rotation happens.

Experimentation shows that this does indeed unsurprizingly help,
more loops got rotated, although other issues remain elsewhere.

Now, this undoubtedly seriously shakes phase ordering.
This will undoubtedly be a mixed bag in terms of both compile- and
run- time performance, codesize. Since we no longer aggressively
hoist+deduplicate common code, we don't pay the price of said hoisting
(which wasn't big). That may allow more loops to be rotated,
so we pay that price. That, in turn, that may enable all the transforms
that require canonical (rotated) loop form, including but not limited to
vectorization, so we pay that too. And in general, no deduplication means
more [duplicate] instructions going through the optimizations. But there's still
late hoisting, some of them will be caught late.

As per benchmarks i've run {F12360204}, this is mostly within the noise,
there are some small improvements, some small regressions.
One big regression i saw i fixed in rG8d487668d09fb0e4e54f36207f07c1480ffabbfd, but i'm sure
this will expose many more pre-existing missed optimizations, as usual :S

llvm-compile-time-tracker.com thoughts on this:
http://llvm-compile-time-tracker.com/compare.php?from=e40315d2b4ed1e38962a8f33ff151693ed4ada63&to=c8289c0ecbf235da9fb0e3bc052e3c0d6bff5cf9&stat=instructions
* this does regress compile-time by +0.5% geomean (unsurprizingly)
* size impact varies; for ThinLTO it's actually an improvement

The largest fallout appears to be in GVN's load partial redundancy
elimination, it spends *much* more time in
`MemoryDependenceResults::getNonLocalPointerDependency()`.
Non-local `MemoryDependenceResults` is widely-known to be, uh, costly.
There does not appear to be a proper solution to this issue,
other than silencing the compile-time performance regression
by tuning cut-off thresholds in `MemoryDependenceResults`,
at the cost of potentially regressing run-time performance.
D84609 attempts to move in that direction, but the path is unclear
and is going to take some time.

If we look at stats before/after diffs, some excerpts:
* RawSpeed (the target) {F12360200}
  * -14 (-73.68%) loops not rotated due to the header size (yay)
  * -272 (-0.67%) `"Number of live out of a loop variables"` - good for vectorizer
  * -3937 (-64.19%) common instructions hoisted
  * +561 (+0.06%) x86 asm instructions
  * -2 basic blocks
  * +2418 (+0.11%) IR instructions
* vanilla test-suite + RawSpeed + darktable  {F12360201}
  * -36396 (-65.29%) common instructions hoisted
  * +1676 (+0.02%) x86 asm instructions
  * +662 (+0.06%) basic blocks
  * +4395 (+0.04%) IR instructions

It is likely to be sub-optimal for when optimizing for code size,
so one might want to change tune pipeline by enabling sinking/hoisting
when optimizing for size.

Reviewed By: mkazantsev

Differential Revision: https://reviews.llvm.org/D84108
2020-07-29 20:05:30 +03:00
Roman Lebedev c3b8bd1eea
[InstCombine] Always try to invert non-canonical predicate of an icmp
Summary:
The actual transform i was going after was:
https://rise4fun.com/Alive/Tp9H
```
Name: zz
Pre: isPowerOf2(C0) && isPowerOf2(C1) && C1 == C0
%t0 = and i8 %x, C0
%r = icmp eq i8 %t0, C1
  =>
%t = icmp eq i8 %t0, 0
%r = xor i1 %t, -1

Name: zz
Pre: isPowerOf2(C0)
%t0 = and i8 %x, C0
%r = icmp ne i8 %t0, 0
  =>
%t = icmp eq i8 %t0, 0
%r = xor i1 %t, -1
```
but as it can be seen from the current tests, we already canonicalize most of it,
and we are only missing handling multi-use non-canonical icmp predicates.

If we have both `!=0` and `==0`, even though we can CSE them,
we end up being stuck with them. We should canonicalize to the `==0`.

I believe this is one of the cleanup steps i'll need after `-scalarizer`
if i end up proceeding with my WIP alloca promotion helper pass.

Reviewers: spatel, jdoerfert, nikic

Reviewed By: nikic

Subscribers: zzheng, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D83139
2020-07-04 18:12:04 +03:00
Jay Foad 6fdd5a28b7 Revert "[IR] Clean up dead instructions after simplifying a conditional branch"
This reverts commit 69bdfb075b.

Reverting to investigate https://bugs.llvm.org/show_bug.cgi?id=46343
2020-06-16 10:32:15 +01:00
Jay Foad 69bdfb075b [IR] Clean up dead instructions after simplifying a conditional branch
Change BasicBlock::removePredecessor to optionally return a vector of
instructions which might be dead. Use this in ConstantFoldTerminator to
delete them if they are dead.

Reapply with a bug fix: don't drop the "!KeepOneInputPHIs" argument when
removePredecessor calls PHINode::removeIncomingValue.

Differential Revision: https://reviews.llvm.org/D80206
2020-06-11 14:53:01 +01:00
Jay Foad f45c65aa41 Revert "[IR] Clean up dead instructions after simplifying a conditional branch"
This reverts commit 4494e45316.

It caused problems for sanitizer buildbots.
2020-06-11 14:22:16 +01:00
Jay Foad 4494e45316 [IR] Clean up dead instructions after simplifying a conditional branch
Change BasicBlock::removePredecessor to optionally return a vector of
instructions which might be dead. Use this in ConstantFoldTerminator to
delete them if they are dead.

Differential Revision: https://reviews.llvm.org/D80206
2020-06-11 13:28:10 +01:00
Sanjay Patel 2f7c24fe30 [InstCombine] (A + B) + B --> A + (B << 1)
This eliminates a use of 'B', so it can enable follow-on transforms
as well as improve analysis/codegen.

The PhaseOrdering test was added for D61726, and that shows
the limits of instcombine vs. real reassociation. We would
need to run some form of CSE to collapse that further.

The intermediate variable naming here is intentional because
there's a test at llvm/test/Bitcode/value-with-long-name.ll
that would break with the usual nameless value. I'm not sure
how to improve that test to be more robust.

The naming may also be helpful to debug regressions if this
change exposes weaknesses in the reassociation pass for example.
2020-05-22 11:46:59 -04:00
Max Kazantsev 403810557b [InstCombine] Sink pure instructions down to return and unreachable blocks
If the only user of `Instr` is in a return or unreachable block, we can
sink `Instr` to the`User` safely (unless it reads/writes memory).
Return or unreachable blocks are guaranteed to execute zero
or one time, and `Instr` always dominates `User`, so they either will
be executed together (execution of `User` always implies execution
of `Instr`) or not executed at all.

Differential Revision: https://reviews.llvm.org/D80120
Reviewed By: asbirlea, jdoerfert
2020-05-22 14:33:42 +07:00
Max Kazantsev 20de2323a0 [Test] Add missing auto-generated checks into tests 2020-05-20 12:03:37 +07:00
Hiroshi Yamauchi 7b9f8e17d1 [PGO][CHR] Guard against 0-to-0 branch weight and avoid division by zero crash.
Summary: This fixes a crash in internal builds under SamplePGO.

Reviewers: davidxl

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D72653
2020-01-13 14:38:58 -08:00
Roman Lebedev 10151f6618 [SimplifyCFG] FoldTwoEntryPHINode(): consider *total* speculation cost, not per-BB cost
Summary:
Previously, if the threshold was 2, we were willing to speculatively
execute 2 cheap instructions in both basic blocks (thus we were willing
to speculatively execute cost = 4), but weren't willing to speculate
when one BB had 3 instructions and other one had no instructions,
even thought that would have total cost of 3.

This looks inconsistent to me.
I don't think `cmov`-like instructions will start executing
until both of it's inputs are available: https://godbolt.org/z/zgHePf
So i don't see why the existing behavior is the correct one.

Also, let's add it's own `cl::opt` for this threshold,
with default=4, so it is not stricter than the previous threshold:
will allow to fold when there are 2 BB's each with cost=2.
And since the logic has changed, it will also allow to fold when
one BB has cost=3 and other cost=1, or there is only one BB with cost=4.

This is an alternative solution to D65148:
This fix is mainly motivated by `signbit-like-value-extension.ll` test.
That pattern comes up in JPEG decoding, see e.g.
`Figure F.12 – Extending the sign bit of a decoded value in V`
of `ITU T.81` (JPEG specification).
That branch is not predictable, and it is within the innermost loop,
so the fact that that pattern ends up being stuck with a branch
instead of `select` (i.e. `CMOV` for x86) is unlikely to be beneficial.

This has great results on the final assembly (vanilla test-suite + RawSpeed): (metric pass - D67240)
| metric                                 |     old |     new | delta |      % |
| x86-mi-counting.NumMachineFunctions    |   37720 |   37721 |     1 |  0.00% |
| x86-mi-counting.NumMachineBasicBlocks  |  773545 |  771181 | -2364 | -0.31% |
| x86-mi-counting.NumMachineInstructions | 7488843 | 7486442 | -2401 | -0.03% |
| x86-mi-counting.NumUncondBR            |  135770 |  135543 |  -227 | -0.17% |
| x86-mi-counting.NumCondBR              |  423753 |  422187 | -1566 | -0.37% |
| x86-mi-counting.NumCMOV                |   24815 |   25731 |   916 |  3.69% |
| x86-mi-counting.NumVecBlend            |      17 |      17 |     0 |  0.00% |

We significantly decrease basic block count, notably decrease instruction count,
significantly decrease branch count and very significantly increase `cmov` count.

Performance-wise, unsurprisingly, this has great effect on
target RawSpeed benchmark. I'm seeing 5 **major** improvements:
```
Benchmark                                                                                             Time             CPU      Time Old      Time New       CPU Old       CPU New
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Samsung/NX3000/_3184416.SRW/threads:8/process_time/real_time_pvalue                                 0.0000          0.0000      U Test, Repetitions: 49 vs 49
Samsung/NX3000/_3184416.SRW/threads:8/process_time/real_time_mean                                  -0.3064         -0.3064      226.9913      157.4452      226.9800      157.4384
Samsung/NX3000/_3184416.SRW/threads:8/process_time/real_time_median                                -0.3057         -0.3057      226.8407      157.4926      226.8282      157.4828
Samsung/NX3000/_3184416.SRW/threads:8/process_time/real_time_stddev                                -0.4985         -0.4954        0.3051        0.1530        0.3040        0.1534
Kodak/DCS760C/86L57188.DCR/threads:8/process_time/real_time_pvalue                                  0.0000          0.0000      U Test, Repetitions: 49 vs 49
Kodak/DCS760C/86L57188.DCR/threads:8/process_time/real_time_mean                                   -0.1747         -0.1747       80.4787       66.4227       80.4771       66.4146
Kodak/DCS760C/86L57188.DCR/threads:8/process_time/real_time_median                                 -0.1742         -0.1743       80.4686       66.4542       80.4690       66.4436
Kodak/DCS760C/86L57188.DCR/threads:8/process_time/real_time_stddev                                 +0.6089         +0.5797        0.0670        0.1078        0.0673        0.1062
Sony/DSLR-A230/DSC08026.ARW/threads:8/process_time/real_time_pvalue                                 0.0000          0.0000      U Test, Repetitions: 49 vs 49
Sony/DSLR-A230/DSC08026.ARW/threads:8/process_time/real_time_mean                                  -0.1598         -0.1598      171.6996      144.2575      171.6915      144.2538
Sony/DSLR-A230/DSC08026.ARW/threads:8/process_time/real_time_median                                -0.1598         -0.1597      171.7109      144.2755      171.7018      144.2766
Sony/DSLR-A230/DSC08026.ARW/threads:8/process_time/real_time_stddev                                +0.4024         +0.3850        0.0847        0.1187        0.0848        0.1175
Canon/EOS 77D/IMG_4049.CR2/threads:8/process_time/real_time_pvalue                                  0.0000          0.0000      U Test, Repetitions: 49 vs 49
Canon/EOS 77D/IMG_4049.CR2/threads:8/process_time/real_time_mean                                   -0.0550         -0.0551      280.3046      264.8800      280.3017      264.8559
Canon/EOS 77D/IMG_4049.CR2/threads:8/process_time/real_time_median                                 -0.0554         -0.0554      280.2628      264.7360      280.2574      264.7297
Canon/EOS 77D/IMG_4049.CR2/threads:8/process_time/real_time_stddev                                 +0.7005         +0.7041        0.2779        0.4725        0.2775        0.4729
Canon/EOS 5DS/2K4A9929.CR2/threads:8/process_time/real_time_pvalue                                  0.0000          0.0000      U Test, Repetitions: 49 vs 49
Canon/EOS 5DS/2K4A9929.CR2/threads:8/process_time/real_time_mean                                   -0.0354         -0.0355      316.7396      305.5208      316.7342      305.4890
Canon/EOS 5DS/2K4A9929.CR2/threads:8/process_time/real_time_median                                 -0.0354         -0.0356      316.6969      305.4798      316.6917      305.4324
Canon/EOS 5DS/2K4A9929.CR2/threads:8/process_time/real_time_stddev                                 +0.0493         +0.0330        0.3562        0.3737        0.3563        0.3681
```

That being said, it's always best-effort, so there will likely
be cases where this worsens things.

Reviewers: efriedma, craig.topper, dmgreen, jmolloy, fhahn, Carrot, hfinkel, chandlerc

Reviewed By: jmolloy

Subscribers: xbolva00, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67318

llvm-svn: 372009
2019-09-16 16:18:24 +00:00
Hiroshi Yamauchi d842f2eec4 [PGO][CHR] Speed up following long, interlinked use-def chains.
Summary:
Avoid visiting an instruction more than once by using a map.

This is similar to https://reviews.llvm.org/rL361416.

Reviewers: davidxl

Reviewed By: davidxl

Subscribers: llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67198

llvm-svn: 371086
2019-09-05 16:56:55 +00:00
Hiroshi Yamauchi dfeb797455 [PGO][CHR] Speed up following long use-def chains.
Summary: Avoid visiting an instruction more than once by using a map.

Reviewers: davidxl

Reviewed By: davidxl

Subscribers: llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D62262

llvm-svn: 361416
2019-05-22 18:37:34 +00:00
Hiroshi Yamauchi 1620104034 [PGO][CHR] A bug fix.
Summary: Fix a transformation bug where two scopes share a common instrution to hoist.

Reviewers: davidxl

Reviewed By: davidxl

Subscribers: llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D61405

llvm-svn: 359736
2019-05-01 22:49:52 +00:00
Eric Christopher cee313d288 Revert "Temporarily Revert "Add basic loop fusion pass.""
The reversion apparently deleted the test/Transforms directory.

Will be re-reverting again.

llvm-svn: 358552
2019-04-17 04:52:47 +00:00
Eric Christopher a863435128 Temporarily Revert "Add basic loop fusion pass."
As it's causing some bot failures (and per request from kbarton).

This reverts commit r358543/ab70da07286e618016e78247e4a24fcb84077fda.

llvm-svn: 358546
2019-04-17 02:12:23 +00:00
Hiroshi Yamauchi 9775a620b0 [PGO] Control Height Reduction
Summary:
Control height reduction merges conditional blocks of code and reduces the
number of conditional branches in the hot path based on profiles.

if (hot_cond1) { // Likely true.
  do_stg_hot1();
}
if (hot_cond2) { // Likely true.
  do_stg_hot2();
}

->

if (hot_cond1 && hot_cond2) { // Hot path.
  do_stg_hot1();
  do_stg_hot2();
} else { // Cold path.
  if (hot_cond1) {
    do_stg_hot1();
  }
  if (hot_cond2) {
    do_stg_hot2();
  }
}

This speeds up some internal benchmarks up to ~30%.

Reviewers: davidxl

Reviewed By: davidxl

Subscribers: xbolva00, dmgreen, mehdi_amini, llvm-commits, mgorny

Differential Revision: https://reviews.llvm.org/D50591

llvm-svn: 341386
2018-09-04 17:19:13 +00:00