Add an ability to specify the max full unroll count for LoopUnrollPass pass
in pass options.
Reviewers: fhahn, fedor.sergeev
Reviewed By: fedor.sergeev
Subscribers: hiraditya, zzheng, dmgreen, llvm-commits
Differential Revision: https://reviews.llvm.org/D67701
llvm-svn: 372305
We use `< UP.Threshold` later on, so we should use LoopSize + 1, to
allow unrolling if the result won't exceed to loop size.
Fixes PR43305.
Reviewers: efriedma, dmgreen, paquette
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D67594
llvm-svn: 372084
Summary:
When reconstructing the CFG of the loop after unrolling,
LoopUnroll could in some cases remove the phi operands of
loop-carried values instead of preserving them, resulting
in undef phi values after loop unrolling.
When doing this reconstruction, avoid removing incoming
phi values for phis in the successor blocks if the successor
is the block we are jumping to anyway.
Patch-by: ebevhan
Reviewers: fhahn, efriedma
Reviewed By: fhahn
Subscribers: bjope, lebedev.ri, zzheng, dmgreen, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66334
llvm-svn: 369886
We already supported rewriting loop exit values for multiple exit loops, but if any of the loop exits were not computable, we gave up on all loop exit values. This patch generalizes the existing code to handle individual computable loop exits where possible.
As discussed in the review, this is a starting point for figuring out a better API. The code is a bit ugly, but getting it in lets us test as we go.
Differential Revision: https://reviews.llvm.org/D65544
llvm-svn: 368898
Due to the nature of the beat system in the MVE architecture, along with tail
predication and low-overhead loops, unrolling has less benefit compared to
normal loops. You can not, for example, hide the latency of a load with other
instructions as you can for scalar code. Preventing unrolling also makes the
code easier to read and reason about.
So if a loop contains vector code, don't enable the runtime unrolling. At least
for the time being.
Differential Revision: https://reviews.llvm.org/D65803
llvm-svn: 368530
This patch adds an ability to disable profile based peeling
causing the peeling of all iterations and as a result prohibits
further unroll/peeling attempts on that loop.
The motivation to get an ability to separate peeling usage in
pipeline where in the first part we peel only separate iterations if needed
and later in pipeline we apply the full peeling which will prohibit further peeling.
Reviewers: reames, fhahn
Reviewed By: reames
Subscribers: hiraditya, zzheng, dmgreen, llvm-commits
Differential Revision: https://reviews.llvm.org/D64983
llvm-svn: 367668
Current peeling cost model can decide to peel off not all iterations
but only some of them to eliminate conditions on phi. At the same time
if any peeling happens the door for further unroll/peel optimizations on that
loop closes because the part of the code thinks that if peeling happened
it is profile based peeling and all iterations are peeled off.
To resolve this inconsistency the patch provides the flag which states whether
the full peeling basing on profile is enabled or not and peeling cost model
is able to modify this field like it does not PeelCount.
In a separate patch I will introduce an option to allow/disallow peeling basing
on profile.
To avoid infinite loop peeling the patch tracks the total number of peeled iteration
through llvm.loop.peeled.count loop metadata.
Reviewers: reames, fhahn
Reviewed By: reames
Subscribers: hiraditya, zzheng, dmgreen, llvm-commits
Differential Revision: https://reviews.llvm.org/D64972
llvm-svn: 367647
We'd like to determine the idom of exit block after peeling one iteration.
Let Exit is exit block.
Let ExitingSet - is a set of predecessors of Exit block. They are exiting blocks.
Let Latch' and ExitingSet' are copies after a peeling.
We'd like to find an idom'(Exit) - idom of Exit after peeling.
It is an evident that idom'(Exit) will be the nearest common dominator of ExitingSet and ExitingSet'.
idom(Exit) is a nearest common dominator of ExitingSet.
idom(Exit)' is a nearest common dominator of ExitingSet'.
Taking into account that we have a single Latch, Latch' will dominate Header and idom(Exit).
So the idom'(Exit) is nearest common dominator of idom(Exit)' and Latch'.
All these basic blocks are in the same loop, so what we find is
(nearest common dominator of idom(Exit) and Latch)'.
Reviewers: reames, fhahn
Reviewed By: reames
Subscribers: hiraditya, zzheng, llvm-commits
Differential Revision: https://reviews.llvm.org/D65292
llvm-svn: 367044
Current algorithm to update branch weights of latch block and its copies is
based on the assumption that number of peeling iterations is approximately equal
to trip count.
However it is not correct. According to profitability check in one case we can decide to peel
in case it helps to reduce the number of phi nodes. In this case the number of peeled iteration
can be less then estimated trip count.
This patch introduces another way to set the branch weights to peeled of branches.
Let F is a weight of the edge from latch to header.
Let E is a weight of the edge from latch to exit.
F/(F+E) is a probability to go to loop and E/(F+E) is a probability to go to exit.
Then, Estimated TripCount = F / E.
For I-th (counting from 0) peeled off iteration we set the the weights for
the peeled latch as (TC - I, 1). It gives us reasonable distribution,
The probability to go to exit 1/(TC-I) increases. At the same time
the estimated trip count of remaining loop reduces by I.
As a result after peeling off N iteration the weights will be
(F - N * E, E) and trip count of loop becomes
F / E - N or TC - N.
The idea is taken from the review of the patch D63918 proposed by Philip.
Reviewers: reames, mkuper, iajbar, fhahn
Reviewed By: reames
Subscribers: hiraditya, zzheng, llvm-commits
Differential Revision: https://reviews.llvm.org/D64235
llvm-svn: 366665
Summary:
There is currently a correctness issue when unrolling loops containing
callbr's where their indirect targets are being updated correctly to the
newly created labels, but their operands are not. This manifests in
unrolled loops where the second and subsequent copies of callbr
instructions have blockaddresses of the label from the first instance of
the unrolled loop, which would result in nonsensical runtime control
flow.
For now, conservatively do not unroll the loop. In the future, I think
we can pursue unrolling such loops provided we transform the cloned
callbr's operands correctly.
Such a transform and its legalities are being discussed in:
https://reviews.llvm.org/D64101
Link: https://bugs.llvm.org/show_bug.cgi?id=42489
Link: https://groups.google.com/forum/#!topic/clang-built-linux/z-hRWP9KqPI
Reviewers: fhahn, hfinkel, efriedma
Reviewed By: fhahn, hfinkel, efriedma
Subscribers: efriedma, hiraditya, zzheng, dmgreen, llvm-commits, pirama, kees, nathanchance, E5ten, craig.topper, chandlerc, glider, void, srhines
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64368
llvm-svn: 366130
It is possible that loop exit has two predecessors in a loop body.
In this case after the peeling the iDom of the exit should be a clone of
iDom of original exit but no a clone of a block coming to this exit.
Reviewers: reames, fhahn
Reviewed By: reames
Subscribers: hiraditya, zzheng, llvm-commits
Differential Revision: https://reviews.llvm.org/D64618
llvm-svn: 366050
This CL enables peeling of the loop with multiple exits where
one exit should be from latch and others are basic blocks with
call to deopt.
The peeling is enabled under the flag which is false by default.
Reviewers: reames, mkuper, iajbar, fhahn
Reviewed By: reames
Subscribers: xbolva00, hiraditya, zzheng, llvm-commits
Differential Revision: https://reviews.llvm.org/D63923
llvm-svn: 366048
This patch generalizes the UnrollLoop utility to support loops that exit
from the header instead of the latch. Usually, LoopRotate would take care
of must of those cases, but in some cases (e.g. -Oz), LoopRotate does
not kick in.
Codesize impact looks relatively neutral on ARM64 with -Oz + LTO.
Program master patch diff
External/S.../CFP2006/447.dealII/447.dealII 629060.00 627676.00 -0.2%
External/SPEC/CINT2000/176.gcc/176.gcc 1245916.00 1244932.00 -0.1%
MultiSourc...Prolangs-C/simulator/simulator 86100.00 86156.00 0.1%
MultiSourc...arks/Rodinia/backprop/backprop 66212.00 66252.00 0.1%
MultiSourc...chmarks/Prolangs-C++/life/life 67276.00 67312.00 0.1%
MultiSourc...s/Prolangs-C/compiler/compiler 69824.00 69788.00 -0.1%
MultiSourc...Prolangs-C/assembler/assembler 86672.00 86696.00 0.0%
Reviewers: efriedma, vsk, paquette
Reviewed By: paquette
Differential Revision: https://reviews.llvm.org/D61962
llvm-svn: 364398
Summary:
Bug: https://bugs.llvm.org/show_bug.cgi?id=39024
The bug reports that a vectorized loop is stepped through 4 times and each step through the loop seemed to show a different path. I found two problems here:
A) An incorrect line number on a preheader block (for.body.preheader) instruction causes a step into the loop before it begins.
B) Instructions in the middle block have different line numbers which give the impression of another iteration.
In this patch I give all of the middle block instructions the line number of the scalar loop latch terminator branch. This seems to provide the smoothest debugging experience because the vectorized loops will always end on this line before dropping into the scalar loop. To solve problem A I have altered llvm::SplitBlockPredecessors to accommodate loop header blocks.
I have set up a separate review D61933 for a fix which is required for this patch.
Reviewers: samsonov, vsk, aprantl, probinson, anemet, hfinkel, jmorse
Reviewed By: hfinkel, jmorse
Subscribers: jmorse, javed.absar, eraman, kcc, bjope, jmellorcrummey, hfinkel, gbedwell, hiraditya, zzheng, llvm-commits
Tags: #llvm, #debug-info
Differential Revision: https://reviews.llvm.org/D60831
> llvm-svn: 363046
llvm-svn: 363786
Summary:
Bug: https://bugs.llvm.org/show_bug.cgi?id=39024
The bug reports that a vectorized loop is stepped through 4 times and each step through the loop seemed to show a different path. I found two problems here:
A) An incorrect line number on a preheader block (for.body.preheader) instruction causes a step into the loop before it begins.
B) Instructions in the middle block have different line numbers which give the impression of another iteration.
In this patch I give all of the middle block instructions the line number of the scalar loop latch terminator branch. This seems to provide the smoothest debugging experience because the vectorized loops will always end on this line before dropping into the scalar loop. To solve problem A I have altered llvm::SplitBlockPredecessors to accommodate loop header blocks.
I have set up a separate review D61933 for a fix which is required for this patch.
Reviewers: samsonov, vsk, aprantl, probinson, anemet, hfinkel, jmorse
Reviewed By: hfinkel, jmorse
Subscribers: jmorse, javed.absar, eraman, kcc, bjope, jmellorcrummey, hfinkel, gbedwell, hiraditya, zzheng, llvm-commits
Tags: #llvm, #debug-info
Differential Revision: https://reviews.llvm.org/D60831
llvm-svn: 363046
This option allows loops with small max trip counts to be fully unrolled. This
can help with code like the remainder loops from manually unrolled loops like
those that appear in the cmsis dsp library. We would apparently previously
runtime unroll them with the default unroll count (4).
Differential Revision: https://reviews.llvm.org/D63064
llvm-svn: 362928
For some reason multiple places need to do this, and the variant the
loop unroller and inliner use was not handling it.
Also, introduce a new wrapper to be slightly more precise, since on
AMDGPU some addrspacecasts are free, but not no-ops.
llvm-svn: 362436
Those two subtarget features were awkward because their semantics are
reversed: each one indicates the _lack_ of support for something in
the architecture, rather than the presence. As a consequence, you
don't get the behavior you want if you combine two sets of feature
bits.
Each SubtargetFeature for an FP architecture version now comes in four
versions, one for each combination of those options. So you can still
say (for example) '+vfp2' in a feature string and it will mean what
it's always meant, but there's a new string '+vfp2d16sp' meaning the
version without those extra options.
A lot of this change is just mechanically replacing positive checks
for the old features with negative checks for the new ones. But one
more interesting change is that I've rearranged getFPUFeatures() so
that the main FPU feature is appended to the output list *before*
rather than after the features derived from the Restriction field, so
that -fp64 and -d32 can override defaults added by the main feature.
Reviewers: dmgreen, samparker, SjoerdMeijer
Subscribers: srhines, javed.absar, eraman, kristof.beyls, hiraditya, zzheng, Petar.Avramovic, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D60691
llvm-svn: 361845
Summary:
Bug: https://bugs.llvm.org/show_bug.cgi?id=39024
The bug reports that a vectorized loop is stepped through 4 times and each step through the loop seemed to show a different path. I found two problems here:
A) An incorrect line number on a preheader block (for.body.preheader) instruction causes a step into the loop before it begins.
B) Instructions in the middle block have different line numbers which give the impression of another iteration.
In this patch I give all of the middle block instructions the line number of the scalar loop latch terminator branch. This seems to provide the smoothest debugging experience because the vectorized loops will always end on this line before dropping into the scalar loop. To solve problem A I have altered llvm::SplitBlockPredecessors to accommodate loop header blocks.
Reviewers: samsonov, vsk, aprantl, probinson, anemet, hfinkel
Reviewed By: hfinkel
Subscribers: bjope, jmellorcrummey, hfinkel, gbedwell, hiraditya, zzheng, llvm-commits
Tags: #llvm, #debug-info
Differential Revision: https://reviews.llvm.org/D60831
llvm-svn: 360162
Summary:
In the following cases, unrolling can be beneficial, even when
optimizing for code size:
1) very low trip counts
2) potential to constant fold most instructions after fully unrolling.
We can unroll in those cases, by setting the unrolling threshold to the
loop size. This might highlight some cost modeling issues and fixing
them will have a positive impact in general.
Reviewers: vsk, efriedma, dmgreen, paquette
Reviewed By: paquette
Differential Revision: https://reviews.llvm.org/D60265
llvm-svn: 358586
As it's causing some bot failures (and per request from kbarton).
This reverts commit r358543/ab70da07286e618016e78247e4a24fcb84077fda.
llvm-svn: 358546
Summary:
Enable some of the existing size optimizations for cold code under PGO.
A ~5% code size saving in big internal app under PGO.
The way it gets BFI/PSI is discussed in the RFC thread
http://lists.llvm.org/pipermail/llvm-dev/2019-March/130894.html
Note it doesn't currently touch loop passes.
Reviewers: davidxl, eraman
Reviewed By: eraman
Subscribers: mgorny, javed.absar, smeenai, mehdi_amini, eraman, zzheng, steven_wu, dexonsmith, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59514
llvm-svn: 358422
The test case requires the peeled loop to be forgotten after peeling,
even though it does not have a parent. When called via the unroller,
SE->forgetTopmostLoop is also called, so the test case would also pass
without any SCEV invalidation, but peelLoop is exposed as utility
function. Also, in the test case, simplifyLoop will make changes,
removing the loop from SCEV, but it is better to not rely on this
behavior.
Reviewers: sanjoy, mkazantsev
Reviewed By: mkazantsev
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58192
llvm-svn: 354031
Summary:
This fixes the IDom for exit blocks and all blocks reachable from the exit blocks, when runtime unrolling under multiexit/exiting case.
We initially had a restrictive check that the IDom is only updated when
it is the header of the loop.
However, we also need to update the IDom to the correct one when the
IDom is any block within the original loop. See added test cases (which
fail dom tree verification without the patch).
Reviewers: reames, mzolotukhin, mkazantsev, hfinkel
Reviewed by: brzycki, kuhar
Subscribers: zzheng, dmgreen, llvm-commits
Differential Revision: https://reviews.llvm.org/D56284
llvm-svn: 350640
When using clang with `-fno-unroll-loops` (implicitly added with `-O1`),
the LoopUnrollPass is not not added to the (legacy) pass pipeline. This
also means that it will not process any loop metadata such as
llvm.loop.unroll.enable (which is generated by #pragma unroll or
WarnMissedTransformationsPass emits a warning that a forced
transformation has not been applied (see
https://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20181210/610833.html).
Such explicit transformations should take precedence over disabling
heuristics.
This patch unconditionally adds LoopUnrollPass to the optimizing
pipeline (that is, it is still not added with `-O0`), but passes a flag
indicating whether automatic unrolling is dis-/enabled. This is the same
approach as LoopVectorize uses.
The new pass manager's pipeline builder has no option to disable
unrolling, hence the problem does not apply.
Differential Revision: https://reviews.llvm.org/D55716
llvm-svn: 349509
When multiple loop transformation are defined in a loop's metadata, their order of execution is defined by the order of their respective passes in the pass pipeline. For instance, e.g.
#pragma clang loop unroll_and_jam(enable)
#pragma clang loop distribute(enable)
is the same as
#pragma clang loop distribute(enable)
#pragma clang loop unroll_and_jam(enable)
and will try to loop-distribute before Unroll-And-Jam because the LoopDistribute pass is scheduled after UnrollAndJam pass. UnrollAndJamPass only supports one inner loop, i.e. it will necessarily fail after loop distribution. It is not possible to specify another execution order. Also,t the order of passes in the pipeline is subject to change between versions of LLVM, optimization options and which pass manager is used.
This patch adds 'followup' attributes to various loop transformation passes. These attributes define which attributes the resulting loop of a transformation should have. For instance,
!0 = !{!0, !1, !2}
!1 = !{!"llvm.loop.unroll_and_jam.enable"}
!2 = !{!"llvm.loop.unroll_and_jam.followup_inner", !3}
!3 = !{!"llvm.loop.distribute.enable"}
defines a loop ID (!0) to be unrolled-and-jammed (!1) and then the attribute !3 to be added to the jammed inner loop, which contains the instruction to distribute the inner loop.
Currently, in both pass managers, pass execution is in a fixed order and UnrollAndJamPass will not execute again after LoopDistribute. We hope to fix this in the future by allowing pass managers to run passes until a fixpoint is reached, use Polly to perform these transformations, or add a loop transformation pass which takes the order issue into account.
For mandatory/forced transformations (e.g. by having been declared by #pragma omp simd), the user must be notified when a transformation could not be performed. It is not possible that the responsible pass emits such a warning because the transformation might be 'hidden' in a followup attribute when it is executed, or it is not present in the pipeline at all. For this reason, this patche introduces a WarnMissedTransformations pass, to warn about orphaned transformations.
Since this changes the user-visible diagnostic message when a transformation is applied, two test cases in the clang repository need to be updated.
To ensure that no other transformation is executed before the intended one, the attribute `llvm.loop.disable_nonforced` can be added which should disable transformation heuristics before the intended transformation is applied. E.g. it would be surprising if a loop is distributed before a #pragma unroll_and_jam is applied.
With more supported code transformations (loop fusion, interchange, stripmining, offloading, etc.), transformations can be used as building blocks for more complex transformations (e.g. stripmining+stripmining+interchange -> tiling).
Reviewed By: hfinkel, dmgreen
Differential Revision: https://reviews.llvm.org/D49281
Differential Revision: https://reviews.llvm.org/D55288
llvm-svn: 348944
Unlike its legacy counterpart new pass manager's LoopUnrollPass does
not provide any means to select which flavors of unroll to run
(runtime, peeling, partial), relying on global defaults.
In some cases having ability to run a restricted LoopUnroll that
does more than LoopFullUnroll is needed.
Introduced LoopUnrollOptions to select optional unroll behaviors.
Added 'unroll<peeling>' to PassRegistry mainly for the sake of testing.
Reviewers: chandlerc, tejohnson
Differential Revision: https://reviews.llvm.org/D53440
llvm-svn: 345723
This mirrors what we already do for AArch64 as the cores are similar.
As discussed in the review, enabling the machine scheduler causes
more variations in performance changes so it is not enabled for now.
This patch improves LNT scores by a geomean of 1.57% at -O3.
Differential Revision: https://reviews.llvm.org/D53562
llvm-svn: 345272
In this patch, I'm adding an extra check to the Latch's terminator in llvm::UnrollRuntimeLoopRemainder,
similar to how it is already done in the llvm::UnrollLoop.
The compiler would crash if this function is called with a malformed loop.
Patch by Rodrigo Caetano Rocha!
Differential Revision: https://reviews.llvm.org/D51486
llvm-svn: 342958
We now only add +64bit to the CPU string for "generic" CPU. All other CPU names are assumed to have the feature flag already set if they support 64-bit. I've remove the implies from CMPXCHG8 so that Feature64Bit only comes in via CPUs or user passing -mattr=+64bit.
I've changed the assert to a report_fatal_error so it's not lost in Release builds.
The test updates are to fix things that tripped the new error.
Differential Revision: https://reviews.llvm.org/D51231
llvm-svn: 341022
I'm not sure why the code here is skipping calls since
TTI does try to do something for general calls, but it
at least should allow intrinsics.
Skip intrinsics that should not be omitted as calls, which
is by far the most common case on AMDGPU.
llvm-svn: 335645
In order to set breakpoints on labels and list source code around
labels, we need collect debug information for labels, i.e., label
name, the function label belong, line number in the file, and the
address label located. In order to keep these information in LLVM
IR and to allow backend to generate debug information correctly.
We create a new kind of metadata for labels, DILabel. The format
of DILabel is
!DILabel(scope: !1, name: "foo", file: !2, line: 3)
We hope to keep debug information as much as possible even the
code is optimized. So, we create a new kind of intrinsic for label
metadata to avoid the metadata is eliminated with basic block.
The intrinsic will keep existing if we keep it from optimized out.
The format of the intrinsic is
llvm.dbg.label(metadata !1)
It has only one argument, that is the DILabel metadata. The
intrinsic will follow the label immediately. Backend could get the
label metadata through the intrinsic's parameter.
We also create DIBuilder API for labels to be used by Frontend.
Frontend could use createLabel() to allocate DILabel objects, and use
insertLabel() to insert llvm.dbg.label intrinsic in LLVM IR.
Differential Revision: https://reviews.llvm.org/D45024
Patch by Hsiangkai Wang.
llvm-svn: 331841
If a predicate does not become known after peeling, peeling is unlikely
to be beneficial.
Reviewers: mcrosier, efriedma, mkazantsev, junbuml
Reviewed By: mkazantsev
Differential Revision: https://reviews.llvm.org/D44983
llvm-svn: 330250
For Hexagon, peeling loops with small runtime trip count is beneficial for our
benchmarks. We set PeelCount in HexagonTargetInfo.cpp and we use PeelCount set
by the target for computing the desired peel count.
Differential Revision: https://reviews.llvm.org/D44880
llvm-svn: 329042
For Hexagon, peeling loops with small runtime trip count is beneficial for our
benchmarks. We set PeelCount in HexagonTargetInfo.cpp and we use PeelCount set
by the target for computing the desired peel count.
Differential Revision: https://reviews.llvm.org/D44880
llvm-svn: 328854
Current logic of loop SCEV invalidation in Loop Unroller implicitly relies on
fact that exit count of outer loops cannot rely on exiting blocks of
inner loops, which is true in current implementation of backedge taken count
calculation but is wrong in general. As result, when we only forget the loop that
we have just unrolled, we may still have cached data for its outer loops (in particular,
exit counts) which keeps references on blocks of inner loop that could have been
changed or even deleted.
The attached test demonstrates a situaton when after unrolling of innermost loop
the outermost loop contains a dangling pointer on non-existant block. The problem
shows up when we apply patch https://reviews.llvm.org/D44677 that makes SCEV
smarter about exit count calculation. I am not sure if the bug exists without this patch,
it appears that now it is accidentally correct just because in practice exact backedge
taken count for outer loops with complex control flow inside is never calculated.
But when SCEV learns to do so, this problem shows up.
This patch replaces existing logic of SCEV loop invalidation with a correct one, which
happens to be invalidation of outermost loop (which also leads to invalidation of all
loops inside of it). It is the only way to ensure that no outer loop keeps dangling pointers
on removed blocks, or just outdated information that has changed after unrolling.
Differential Revision: https://reviews.llvm.org/D44818
Reviewed By: samparker
llvm-svn: 328483
Loop peeling also has an impact on the induction variables, so we should
benefit from induction variable simplification after peeling too.
Reviewers: sanjoy, bogner, mzolotukhin, efriedma
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D43878
llvm-svn: 328301
If the loop body contains conditions of the form IndVar < #constant, we
can remove the checks by peeling off #constant iterations.
This improves codegen for PR34364.
Reviewers: mkuper, mkazantsev, efriedma
Reviewed By: mkazantsev
Differential Revision: https://reviews.llvm.org/D43876
llvm-svn: 327671
Summary:
Before this patch call graph is like this in the LoopUnrollPass:
tryToUnrollLoop
ApproximateLoopSize
collectEphemeralValues
/* Use collected ephemeral values */
computeUnrollCount
analyzeLoopUnrollCost
/* Bail out from the analysis if loop contains CallInst */
This patch moves collection of the ephemeral values to the tryToUnrollLoop
function and passes the collected values into both ApproximateLoopsize (as
before) and additionally starts using them in analyzeLoopUnrollCost:
tryToUnrollLoop
collectEphemeralValues
ApproximateLoopSize(EphValues)
/* Use EphValues */
computeUnrollCount(EphValues)
analyzeLoopUnrollCost(EphValues)
/* Ignore ephemeral values - they don't contribute to the final cost */
/* Bail out from the analysis if loop contains CallInst */
Reviewers: mzolotukhin, evstupac, sanjoy
Reviewed By: evstupac
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D43931
llvm-svn: 327617
Currently when AllowRemainder is disabled, pragma unroll count is not
respected even though there is no remainder. This bug causes a loop
fully unrolled in many cases even though the user specifies a unroll
count. Especially it affects OpenCL/CUDA since in many cases a loop
contains convergent instructions and currently AllowRemainder is
disabled for such loops.
Differential Revision: https://reviews.llvm.org/D43826
llvm-svn: 326585
The commit rL308422 introduces a restriction for folding unconditional
branches. Specifically if empty block with unconditional branch leads to
header of the loop then elimination of this basic block is prohibited.
However it seems this condition is redundantly strict.
If elimination of this basic block does not introduce more back edges
then we can eliminate this block.
The patch implements this relax of restriction.
The test profile/Linux/counter_promo_nest.c in compiler-rt project
is updated to meet this change.
Reviewers: efriedma, mcrosier, pacxx, hsung, davidxl
Reviewed By: pacxx
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D42691
llvm-svn: 324572
The patch causes the failure of the test
compiler-rt/test/profile/Linux/counter_promo_nest.c
To unblock buildbot, revert the patch while investigation is in progress.
Differential Revision: https://reviews.llvm.org/D42691
llvm-svn: 324214
The commit rL308422 introduces a restriction for folding unconditional
branches. Specifically if empty block with unconditional branch leads to
header of the loop then elimination of this basic block is prohibited.
However it seems this condition is redundantly strict.
If elimination of this basic block does not introduce more back edges
then we can eliminate this block.
The patch implements this relax of restriction.
Reviewers: efriedma, mcrosier, pacxx, hsung, davidxl
Reviewed By: pacxx
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D42691
llvm-svn: 324208
The optimisation remarks for loop unrolling with an unrolled remainder looks something like:
test.c:7:18: remark: completely unrolled loop with 3 iterations [-Rpass=loop-unroll]
C[i] += A[i*N+j];
^
test.c:6:9: remark: unrolled loop by a factor of 4 with run-time trip count [-Rpass=loop-unroll]
for(int j = 0; j < N; j++)
^
This removes the first of the two messages.
Differential revision: https://reviews.llvm.org/D38725
llvm-svn: 316986
Before, loop unrolling was only enabled for loops with a single
block. This restriction has been removed and replaced by:
- allow a maximum of two exiting blocks,
- a four basic block limit for cores with a branch predictor.
Differential Revision: https://reviews.llvm.org/D38952
llvm-svn: 316313
(recommit #2 after checking for timeout issue).
The original patch was an improvement to IR ValueTracking on
non-negative integers. It has been checked in to trunk (D18777,
r284022). But was disabled by default due to performance regressions.
Perf impact has improved. The patch would be enabled by default.
Reviewers: reames, hfinkel
Differential Revision: https://reviews.llvm.org/D34101
Patch by: Olga Chupina <olga.chupina@intel.com>
llvm-svn: 316208
Summary:
And now that we no longer have to explicitly free() the Loop instances, we can
(with more ease) use the destructor of LoopBase to do what LoopBase::clear() was
doing.
Reviewers: chandlerc
Subscribers: mehdi_amini, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D38201
llvm-svn: 314375
Summary:
With this change:
- Methods in LoopBase trip an assert if the receiver has been invalidated
- LoopBase::clear frees up the memory held the LoopBase instance
This change also shuffles things around as necessary to work with this stricter invariant.
Reviewers: chandlerc
Subscribers: mehdi_amini, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D38055
llvm-svn: 313708
Add a profitability heuristic to enable runtime unrolling of multi-exit
loop: There can be atmost two unique exit blocks for the loop and the
second exit block should be a deoptimizing block. Also, there can be one
other exiting block other than the latch exiting block. The reason for
the latter is so that we limit the number of branches in the unrolled
code to being at most the unroll factor. Deoptimizing blocks are rarely
taken so these additional number of branches created due to the
unrolling are predictable, since one of their target is the deopt block.
Reviewers: apilipenko, reames, evstupac, mkuper
Subscribers: llvm-commits
Reviewed by: reames
Differential Revision: https://reviews.llvm.org/D35380
llvm-svn: 313363
During runtime unrolling on loops with multiple exits, we update the
exit blocks with the correct phi values from both original and remainder
loop.
In this process, we lookup the VMap for the mapped incoming phi values,
but did not update the VMap if a default entry was generated in the VMap
during the lookup. This default value is generated when constants or
values outside the current loop are looked up.
This patch fixes the assertion failure when null entries are present in
the VMap because of this lookup. Added a testcase that showcases the
problem.
llvm-svn: 313358
Debug information can be, and was, corrupted when the runtime
remainder loop was fully unrolled. This is because a !null node can
be created instead of a unique one describing the loop. In this case,
the original node gets incorrectly updated with the NewLoopID
metadata.
In the case when the remainder loop is going to be quickly fully
unrolled, there isn't the need to add loop metadata for it anyway.
Differential Revision: https://reviews.llvm.org/D37338
llvm-svn: 312471
I forgot to specify -unroll-loop-peel, making this test not
really effective. While here, adjust some details (naming and
run line). Thanks to Sanjoy and Michael Z. for pointing out in
their post-commit reviews.
llvm-svn: 312015
When peeling kicks in, it updates the loop preheader.
Later, a successful full unroll of the loop needs to update a PHI
which i-th argument comes from the loop preheader, so it'd better look
at the correct block. Fixes PR33437.
Differential Revision: https://reviews.llvm.org/D37153
llvm-svn: 311922
Store operation takes 2 UOps on X86 processors. The exact cost calculation affects several optimization passes including loop unroling.
This change compensates performance degradation caused by https://reviews.llvm.org/D34458 and shows improvements on some benchmarks.
Differential Revision: https://reviews.llvm.org/D35888
llvm-svn: 311285
- Set the default runtime unroll count to 4 and use the newly added
UnrollRemainder option.
- Create loop cost and force unroll for a cost less than 12.
- Disable unrolling on Thumb1 only targets.
Differential Revision: https://reviews.llvm.org/D36134
llvm-svn: 310997
On some targets, the penalty of executing runtime unrolling checks
and then not the unrolled loop can be significantly detrimental to
performance. This results in the need to be more conservative with
the unroll count, keeping a trip count of 2 reduces the overhead as
well as increasing the chance of the unrolled body being executed. But
being conservative leaves performance gains on the table.
This patch enables the unrolling of the remainder loop introduced by
runtime unrolling. This can help reduce the overhead of misunrolled
loops because the cost of non-taken branches is much less than the
cost of the backedge that would normally be executed in the remainder
loop. This allows larger unroll factors to be used without suffering
performance loses with smaller iteration counts.
Differential Revision: https://reviews.llvm.org/D36309
llvm-svn: 310824
results when a loop is completely removed.
This is very hard to manifest as a visible bug. You need to arrange for
there to be a subsequent allocation of a 'Loop' object which gets the
exact same address as the one which the unroll deleted, and you need the
LoopAccessAnalysis results to be significant in the way that they're
stale. And you need a million other things to align.
But when it does, you get a deeply mysterious crash due to actually
finding a stale analysis result. This fixes the issue and tests for it
by directly checking we successfully invalidate things. I have not been
able to get *any* test case to reliably trigger this. Changes to LLVM
itself caused the only test case I ever had to cease to crash.
I've looked pretty extensively at less brittle ways of fixing this and
they are actually very, very hard to do. This is a somewhat strange and
unusual case as we have a pass which is deleting an IR unit, but is not
running within that IR unit's pass framework (which is what handles this
cleanly for the normal loop unroll). And where there isn't a definitive
way to clear *all* of the stale cache entries. And where the pass *is*
updating the core analysis that provides the IR units!
For example, we don't have any of these problems with Function analyses
because it is easy to clear out function analyses when the functions
themselves may have been deleted -- we clear an entire module's worth!
But that is too heavy of a hammer down here in the LoopAnalysisManager
layer.
A better long-term solution IMO is to require that AnalysisManager's
make their keys durable to this kind of thing. Specifically, when
caching an analysis for one IR unit that is conceptually "owned" by
a higher level IR unit, the AnalysisManager should incorporate this into
its data structures so that we can reliably clear these results without
having to teach each and every pass to do so manually as we do here. But
that is a change for another day as it will be a fairly invasive change
to the AnalysisManager infrastructure. Until then, this fortunately
seems to be quite rare.
llvm-svn: 310333
Summary:
Detect when the working set size of a profiled application is huge,
by comparing the number of counts required to reach the hot percentile
in the profile summary to a large threshold*.
When the working set size is determined to be huge, disable peeling
to avoid bloating the working set further.
*Note that the selected threshold (15K) is significantly larger than the
largest working set value in SPEC cpu2006 (which is gcc at around 11K).
Reviewers: davidxl
Subscribers: mehdi_amini, mzolotukhin, eraman, llvm-commits
Differential Revision: https://reviews.llvm.org/D36288
llvm-svn: 310005
Summary:
Peeling should not occur during the full unrolling invocation early
in the pipeline, but rather later with partial and runtime loop
unrolling. The later loop unrolling invocation will also eventually
utilize profile summary and branch frequency information, which
we would like to use to control peeling. And for ThinLTO we want
to delay peeling until the backend (post thin link) phase, just as
we do for most types of unrolling.
Ensure peeling doesn't occur during the full unrolling invocation
by adding a parameter to the shared implementation function, similar
to the way partial and runtime loop unrolling are disabled.
Performance results for ThinLTO suggest this has a neutral to positive
effect on some internal benchmarks.
Reviewers: chandlerc, davidxl
Subscribers: mzolotukhin, llvm-commits, mehdi_amini
Differential Revision: https://reviews.llvm.org/D36258
llvm-svn: 309966
Summary:
This is largely NFC*, in preparation for utilizing ProfileSummaryInfo
and BranchFrequencyInfo analyses. In this patch I am only doing the
splitting for the New PM, but I can do the same for the legacy PM as
a follow-on if this looks good.
*Not NFC since for partial unrolling we lose the updates done to the
loop traversal (adding new sibling and child loops) - according to
Chandler this is not very useful for partial unrolling, but it also
means that the debugging flag -unroll-revisit-child-loops no longer
works for partial unrolling.
Reviewers: chandlerc
Subscribers: mehdi_amini, mzolotukhin, eraman, llvm-commits
Differential Revision: https://reviews.llvm.org/D36157
llvm-svn: 309886
Enable runtime and partial loop unrolling of simple loops without
calls on M-class cores. The thresholds are calculated based on
whether the target is Thumb or Thumb-2.
Differential Revision: https://reviews.llvm.org/D34619
llvm-svn: 308956
Summary:
When simplifying unconditional branches from empty blocks, we pre-test if the
BB belongs to a set of loop headers and keep the block to prevent passes from
destroying canonical loop structure. However, the current algorithm fails if
the destination of the branch is a loop header. Especially when such a loop's
latch block is folded into loop header it results in additional backedges and
LoopSimplify turns it into a nested loop which prevent later optimizations
from being applied (e.g., loop unrolling and loop interleaving).
This patch augments the existing algorithm by further checking if the
destination of the branch belongs to a set of loop headers and defer
eliminating it if yes to LateSimplifyCFG.
Fixes PR33605: https://bugs.llvm.org/show_bug.cgi?id=33605
Reviewers: efriedma, mcrosier, pacxx, hsung, davidxl
Reviewed By: efriedma
Subscribers: ashutosh.nema, gberry, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D35411
llvm-svn: 308422
Summary:
When we runtime unroll with multiple exit blocks, we also need to update the
immediate dominators of the immediate successors of the exit blocks.
Reviewers: reames, mkuper, mzolotukhin, apilipenko
Reviewed by: mzolotukhin
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D35304
llvm-svn: 307909
Refactored the code and separated out a function
`canSafelyUnrollMultiExitLoop` to reduce redundant checks and make it
easier to add profitability heuristics later.
Added tests to runtime unrolling to make sure that unrolling for
multi-exit loops is not done unless the option
-unroll-runtime-multi-exit is true.
llvm-svn: 307843
The loop structure for the outer loop does not contain the epilog
preheader when we try to unroll inner loop with multiple exits and
epilog code is generated. For now, we just bail out in such cases.
Added a test case that shows the problem. Without this bailout, we would
trip on assert saying LCSSA form is incorrect for outer loop.
llvm-svn: 307676
When unrolling under multiple exits which is under off-by-default option,
the assert that checks for VMap entry in loop exit values is too strong.
(assert if VMap entry did not exist, the value should be a
constant). However, values derived from
constants or from values outside loop, does not have a VMap entry too.
Removed the assert and added a testcase showcasing the property for
non-constant values.
llvm-svn: 307542
With the NFC refactoring in rL307417 (git SHA 987dd01), all the logic
is in place to support multiple exit/exiting blocks when prolog
remainder is generated.
This patch removed the assert that multiple exit blocks unrolling is only
supported when epilog remainder is generated.
Also, added test runs and checks with PROLOG prefix in
runtime-loop-multiple-exits.ll test cases.
llvm-svn: 307435
Currently, we do not support multiple exiting blocks to the
latch exit block. However, this bailout wasn't triggered when we had a
unique exit block (which is the latch exit), with multiple exiting
blocks to that unique exit.
Moved the bailout so that it's triggered in both cases and added
testcase.
llvm-svn: 307291
Summary:
Runtime unrolling is done for loops with a single exit block and a
single exiting block (and this exiting block should be the latch block).
This patch adds logic to support unrolling in the presence of multiple exit
blocks (which also means multiple exiting blocks).
Currently this is under an off-by-default option and is supported when
epilog code is generated. Support in presence of prolog code will be in
a future patch (we just need to add more tests, and update comments).
This patch is essentially an implementation patch. I have not added any
heuristic (in terms of branches added or code size) to decide when
this should be enabled.
Reviewers: mkuper, sanjoy, reames, evstupac
Reviewed by: reames
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D33001
llvm-svn: 306846
The current Loop Unroll implementation works with loops having a
single latch that contains a conditional branch to a block outside
the loop (the other successor is, by defition of latch, the header).
If this precondition doesn't hold, avoid unrolling the loop as
the code is not ready to handle such circumstances.
Differential Revision: https://reviews.llvm.org/D32261
llvm-svn: 301239
This patch is a generalization of the improvement introduced in rL296898.
Previously, we were able to peel one iteration of a loop to get rid of a Phi that becomes
an invariant on the 2nd iteration. In more general case, if a Phi becomes invariant after
N iterations, we can peel N times and turn it into invariant.
In order to do this, we for every Phi in loop's header we define the Invariant Depth value
which is calculated as follows:
Given %x = phi <Inputs from above the loop>, ..., [%y, %back.edge].
If %y is a loop invariant, then Depth(%x) = 1.
If %y is a Phi from the loop header, Depth(%x) = Depth(%y) + 1.
Otherwise, Depth(%x) is infinite.
Notice that if we peel a loop, all Phis with Depth = 1 become invariants,
and all other Phis with finite depth decrease the depth by 1.
Thus, peeling N first iterations allows us to turn all Phis with Depth <= N
into invariants.
Reviewers: reames, apilipenko, mkuper, skatkov, anna, sanjoy
Reviewed By: sanjoy
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D31613
llvm-svn: 300446
When peeling loops basing on phis becoming invariants, we make a wrong loop size check.
UP.Threshold should be compared against the total numbers of instructions after the transformation,
which is equal to 2 * LoopSize in case of peeling one iteration.
We should also check that the maximum allowed number of peeled iterations is not zero.
Reviewers: sanjoy, anna, reames, mkuper
Reviewed By: mkuper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D31753
llvm-svn: 300441
Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
calling convention can be changed to a non-kernel.
Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'
on the relevant test directories (and undoing in one place that actually
wanted a non-kernel).
llvm-svn: 298444
Summary:
We should check if loop size allows us to peel at least one iteration
before we do so.
Patch by Max Kazantsev!
Reviewers: sanjoy, mkuper, efriedma
Reviewed By: mkuper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D30632
llvm-svn: 297122
Summary:
If a loop contains a Phi node which has an invariant input from back
edge, it is profitable to peel such loops (rather than unroll them) to
use the advantage that this Phi is always invariant starting from 2nd
iteration. After the 1st iteration is peeled, other optimizations can
potentially simplify calculations with this invariant.
Patch by Max Kazantsev!
Reviewers: sanjoy, apilipenko, igor-laevsky, anna, mkuper, reames
Reviewed By: mkuper
Subscribers: mkuper, mzolotukhin, llvm-commits
Differential Revision: https://reviews.llvm.org/D30161
llvm-svn: 296898
Summary:
Extend -unroll-partial-threshold to 200 for runtime-loop3.ll test
as epilogue unroll initially add 1 more IV to the loop.
From: Evgeny Stupachenko <evstupac@gmail.com>
llvm-svn: 296803
This enables peeling of loops with low dynamic iteration count by default,
when profile information is available.
Differential Revision: https://reviews.llvm.org/D27734
llvm-svn: 295796
Exit loop analysis early if suitable private access found.
Do not account for GEPs which are invariant to loop induction variable.
Do not account for Allocas which are too big to fit into register file anyway.
Add option for tuning: -amdgpu-unroll-threshold-private.
Differential Revision: https://reviews.llvm.org/D29473
llvm-svn: 293991
factory functions for the two modes the loop unroller is actually used
in in-tree: simplified full-unrolling and the entire thing including
partial unrolling.
I've also wired these up to nice names so you can express both of these
being in a pipeline easily. This is a precursor to actually enabling
these parts of the O2 pipeline.
Differential Revision: https://reviews.llvm.org/D28897
llvm-svn: 293136
Even when we don't create a remainder loop (that is, when we unroll by 2), we
may duplicate nested loops into the remainder. This is complicated by the fact
the remainder may itself be either inserted into an outer loop, or at the top
level. In the latter case, we may need to create new top-level loops.
Differential Revision: https://reviews.llvm.org/D29156
llvm-svn: 293124
loops.
We do this by reconstructing the newly added loops after the unroll
completes to avoid threading pass manager details through all the mess
of the unrolling infrastructure.
I've enabled some extra assertions in the LPM to try and catch issues
here and enabled a bunch of unroller tests to try and make sure this is
sane.
Currently, I'm manually running loop-simplify when needed. That should
go away once it is folded into the LPM infrastructure.
Differential Revision: https://reviews.llvm.org/D28848
llvm-svn: 293011
With this change dominator tree remains in sync after each step of loop
peeling.
Differential Revision: https://reviews.llvm.org/D29029
llvm-svn: 292895
Running non-LCSSA-preserving LoopSimplify followed by LCSSA on (roughly) the
same loop is incorrect, since LoopSimplify may break LCSSA arbitrarily higher
in the loop nest. Instead, run LCSSA first, and then run LCSSA-preserving
LoopSimplify on the result.
This fixes PR31718.
Differential Revision: https://reviews.llvm.org/D29055
llvm-svn: 292854
Summary: Partial unrolling should have separate threshold with full unrolling.
Reviewers: efriedma, mzolotukhin
Reviewed By: efriedma, mzolotukhin
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28831
llvm-svn: 292293
Summary:
Regardless how the loop body weight is distributed, we should preserve
total loop body weight. i.e. we should have same weight reaching the body of the loop
or its duplicates in peeled and unpeeled case.
Reviewers: mkuper, davidxl, anemet
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28179
llvm-svn: 290833
Summary:
The current loop complete unroll algorithm checks if unrolling complete will reduce the runtime by a certain percentage. If yes, it will apply a fixed boosting factor to the threshold (by discounting cost). The problem for this approach is that the threshold abruptly. This patch makes the boosting factor a function of runtime reduction percentage, capped by a fixed threshold. In this way, the threshold changes continuously.
The patch also simplified the code by reducing one parameter in UP.
The patch only affects code-gen of two speccpu2006 benchmark:
445.gobmk binary size decreases 0.08%, no performance change.
464.h264ref binary size increases 0.24%, no performance change.
Reviewers: mzolotukhin, chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D26989
llvm-svn: 290737
This implements PGO-driven loop peeling.
The basic idea is that when the average dynamic trip-count of a loop is known,
based on PGO, to be low, we can expect a performance win by peeling off the
first several iterations of that loop.
Unlike unrolling based on a known trip count, or a trip count multiple, this
doesn't save us the conditional check and branch on each iteration. However,
it does allow us to simplify the straight-line code we get (constant-folding,
etc.). This is important given that we know that we will usually only hit this
code, and not the actual loop.
This is currently disabled by default.
Differential Revision: https://reviews.llvm.org/D25963
llvm-svn: 288274
Summary:
For flat loop, even if it is hot, it is not a good idea to unroll in runtime, thus we set a lower partial unroll threshold.
For hot loop, we set a higher unroll threshold and allows expensive tripcount computation to allow more aggressive unrolling.
Reviewers: davidxl, mzolotukhin
Subscribers: sanjoy, mehdi_amini, llvm-commits
Differential Revision: https://reviews.llvm.org/D26527
llvm-svn: 287186
When we have a loop with a known upper bound on the number of iterations, and
furthermore know that either the number of iterations will be either exactly
that upper bound or zero, then we can fully unroll up to that upper bound
keeping only the first loop test to check for the zero iteration case.
Most of the work here is in plumbing this 'max-or-zero' information from the
part of scalar evolution where it's detected through to loop unrolling. I've
also gone for the safe default of 'false' everywhere but howManyLessThans which
could probably be improved.
Differential Revision: https://reviews.llvm.org/D25682
llvm-svn: 284818
Reappy r284044 after revert in r284051. Krzysztof fixed the error in r284049.
The original summary:
This patch tries to fully unroll loops having break statement like this
for (int i = 0; i < 8; i++) {
if (a[i] == value) {
found = true;
break;
}
}
GCC can fully unroll such loops, but currently LLVM cannot because LLVM only
supports loops having exact constant trip counts.
The upper bound of the trip count can be obtained from calling
ScalarEvolution::getMaxBackedgeTakenCount(). Part of the patch is the
refactoring work in SCEV to prevent duplicating code.
The feature of using the upper bound is enabled under the same circumstance
when runtime unrolling is enabled since both are used to unroll loops without
knowing the exact constant trip count.
llvm-svn: 284053
This patch tries to fully unroll loops having break statement like this
for (int i = 0; i < 8; i++) {
if (a[i] == value) {
found = true;
break;
}
}
GCC can fully unroll such loops, but currently LLVM cannot because LLVM only
supports loops having exact constant trip counts.
The upper bound of the trip count can be obtained from calling
ScalarEvolution::getMaxBackedgeTakenCount(). Part of the patch is the
refactoring work in SCEV to prevent duplicating code.
The feature of using the upper bound is enabled under the same circumstance
when runtime unrolling is enabled since both are used to unroll loops without
knowing the exact constant trip count.
Differential Revision: https://reviews.llvm.org/D24790
llvm-svn: 284044
Summary: Debug info should *not* affect optimization decisions. This patch updates loop unroller cost model to make it not affected by debug info.
Reviewers: davidxl, mzolotukhin
Subscribers: haicheng, llvm-commits, mzolotukhin
Differential Revision: https://reviews.llvm.org/D25098
llvm-svn: 282894
Summary:
When cloning blocks for prologue/epilogue we need to replicate the loop
structure from the original loop. It wasn't a problem for the innermost
loops, but it led to an incorrect loop info when we unrolled a loop with
a child loop - in this case created prologue-loop had a child loop, but
loop info didn't reflect that.
This fixes PR28888.
Reviewers: chandlerc, sanjoy, hfinkel
Subscribers: llvm-commits, silvas
Differential Revision: https://reviews.llvm.org/D24203
llvm-svn: 280901
As agreed in post-commit review of r265388, I'm switching the flag to
its original value until the 90% runtime performance regression on
SingleSource/Benchmarks/Stanford/Bubblesort is addressed.
llvm-svn: 277524
LoopUnroll is a loop pass, so the analysis of OptimizationRemarkEmitter
is added to the common function analysis passes that loop passes
depend on.
The BFI and indirectly BPI used in this pass is computed lazily so no
overhead should be observed unless -pass-remarks-with-hotness is used.
This is how the patch affects the O3 pipeline:
Dominator Tree Construction
Natural Loop Information
Canonicalize natural loops
Loop-Closed SSA Form Pass
Basic Alias Analysis (stateless AA impl)
Function Alias Analysis Results
Scalar Evolution Analysis
+ Lazy Branch Probability Analysis
+ Lazy Block Frequency Analysis
+ Optimization Remark Emitter
Loop Pass Manager
Rotate Loops
Loop Invariant Code Motion
Unswitch loops
Simplify the CFG
Dominator Tree Construction
Basic Alias Analysis (stateless AA impl)
Function Alias Analysis Results
Combine redundant instructions
Natural Loop Information
Canonicalize natural loops
Loop-Closed SSA Form Pass
Scalar Evolution Analysis
+ Lazy Branch Probability Analysis
+ Lazy Block Frequency Analysis
+ Optimization Remark Emitter
Loop Pass Manager
Induction Variable Simplification
Recognize loop idioms
Delete dead loops
Unroll loops
...
llvm-svn: 277203
We just set PreserveLCSSA to always true since we don't have an
analogous method `mustPreserveAnalysisID(LCSSA)`.
Also port LoopInfo verifier pass to test LoopUnrollPass.
llvm-svn: 276063
When simplifying a load we need to make sure that the type of the
simplified value matches the type of the instruction we're processing.
In theory, we can handle casts here as we deal with constant data, but
since it's not implemented at the moment, we at least need to bail out.
This fixes PR28262.
llvm-svn: 273562
The way we elide max expressions when computing trip counts is incorrect
-- it breaks cases like this:
```
static int wrapping_add(int a, int b) {
return (int)((unsigned)a + (unsigned)b);
}
void test() {
volatile int end_buf = 2147483548; // INT_MIN - 100
int end = end_buf;
unsigned counter = 0;
for (int start = wrapping_add(end, 200); start < end; start++)
counter++;
print(counter);
}
```
Note: the `NoWrap` variable that was being tested has little to do with
the values flowing into the max expression; it is a property of the
induction variable.
test/Transforms/LoopUnroll/nsw-tripcount.ll was added to solely test
functionality I'm reverting in this change, so I've deleted the test
fully.
llvm-svn: 273079
We do not support splitting cleanuppad or catchswitches. This is
problematic for passes which assume that a loop is in loop simplify
form (the loop would have a dedicated exit block instead of sharing it).
While it isn't great that we don't support this for cleanups, we still
cannot make loop-simplify form an assertable precondition because
indirectbr will also disable these sorts of CFG cleanups.
This fixes PR28132.
llvm-svn: 272739
with user specified count has been applied.
Summary:
Previously SetLoopAlreadyUnrolled() set the disable pragma only if
there was some loop metadata.
Now it set the pragma in all cases. This helps to prevent multiple
unroll when -unroll-count=N is given.
Reviewers: mzolotukhin
Differential Revision: http://reviews.llvm.org/D20765
From: Evgeny Stupachenko <evstupac@gmail.com>
llvm-svn: 272195
In some cases, when simplifying with SCEV, we might consider pointer values as
just usual integer values. Thus, we might get a different type from what we
had originally in the map of simplified values, and hence we need to check
types before operating on the values.
This fixes PR28015.
llvm-svn: 271931
Summary:
Unroll factor (Count) calculations moved to a new function.
Early exits on pragma and "-unroll-count" defined factor added.
New type of unrolling "Force" introduced (previously used implicitly).
New unroll preference "AllowRemainder" introduced and set "true" by default.
(should be set to false for architectures that suffers from it).
Reviewers: hfinkel, mzolotukhin, zzheng
Differential Revision: http://reviews.llvm.org/D19553
From: Evgeny Stupachenko <evstupac@gmail.com>
llvm-svn: 271071
Condition might be simplified to a Constant, but it doesn't have to be
ConstantInt, so we should dyn_cast, instead of cast.
This fixes PR27886.
llvm-svn: 270924
Summary:
This patch turns on LoopUnrollAnalyzer by default. To mitigate compile
time regressions, I chose very conservative thresholds for now. Later we
can make them more aggressive, but it might require being smarter in
which loops we're optimizing. E.g. currently the biggest issue is that
with more agressive thresholds we unroll many cold loops, which
increases compile time for no performance benefit (performance of those
loops is improved, but it doesn't matter since they are cold).
Test results for compile time(using 4 samples to reduce noise):
```
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes 5.19%
SingleSource/Benchmarks/Polybench/medley/reg_detect/reg_detect 4.19%
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow 3.39%
MultiSource/Applications/JM/lencod/lencod 1.47%
MultiSource/Benchmarks/Fhourstones-3_1/fhourstones3_1 -6.06%
```
I didn't see any performance changes in the testsuite, but it improves
some internal tests.
Reviewers: hfinkel, chandlerc
Subscribers: llvm-commits, mzolotukhin
Differential Revision: http://reviews.llvm.org/D20482
llvm-svn: 270478
Summary:
...loop after the last iteration.
This is really hard to do correctly. The core problem is that we need to
model liveness through the induction PHIs from iteration to iteration in
order to get the correct results, and we need to correctly de-duplicate
the common subgraphs of instructions feeding some subset of the
induction PHIs. All of this can be driven either from a side effect at
some iteration or from the loop values used after the loop finishes.
This patch implements this by storing the forward-propagating analysis
of each instruction in a cache to recall whether it was free and whether
it has become live and thus counted toward the total unroll cost. Then,
at each sink for a value in the loop, we recursively walk back through
every value that feeds the sink, including looping back through the
iterations as needed, until we have marked the entire input graph as
live. Because we cache this, we never visit instructions more than twice
-- once when we analyze them and put them into the cache, and once when
we count their cost towards the unrolled loop. Also, because the cache
is only two bits and because we are dealing with relatively small
iteration counts, we can store all of this very densely in memory to
avoid this from becoming an excessively slow analysis.
The code here is still pretty gross. I would appreciate suggestions
about better ways to factor or split this up, I've stared too long at
the algorithmic side to really have a good sense of what the design
should probably look at.
Also, it might seem like we should do all of this bottom-up, but I think
that is a red herring. Specifically, the simplification power is *much*
greater working top-down. We can forward propagate very effectively,
even across strange and interesting recurrances around the backedge.
Because we use data to propagate, this doesn't cause a state space
explosion. Doing this level of constant folding, etc, would be very
expensive to do bottom-up because it wouldn't be until the last moment
that you could collapse everything. The current solution is essentially
a top-down simplification with a bottom-up cost accounting which seems
to get the best of both worlds. It makes the simplification incremental
and powerful while leaving everything dead until we *know* it is needed.
Finally, a core property of this approach is its *monotonicity*. At all
times, the current UnrolledCost is a conservatively low estimate. This
ensures that we will never early-exit from the analysis due to exceeding
a threshold when if we had continued, the cost would have gone back
below the threshold. These kinds of bugs can cause incredibly hard to
track down random changes to behavior.
We could use a techinque similar (but much simpler) within the inliner
as well to avoid considering speculated code in the inline cost.
Reviewers: chandlerc
Subscribers: sanjoy, mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D11758
llvm-svn: 269388
Summary:
Currently we consider such instructions as simplified, which is incorrect,
because if their user isn't simplified, we can't actually simplify them too.
This biases our estimates of profitability: for instance the analyzer expects
much more gains from unrolling memcpy loops than there actually are.
Reviewers: hfinkel, chandlerc
Subscribers: mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D17365
llvm-svn: 269387
Before r268509, Clang would disable the loop unroll pass when optimizing
for size. That commit enabled it to be able to support unroll pragmas
in -Os builds. However, this regressed binary size in one of Chromium's
DLLs with ~100 KB.
This restores the original behaviour of no unrolling at -Os, but doing it
in LLVM instead of Clang makes more sense, and also allows the pragmas to
keep working.
Differential revision: http://reviews.llvm.org/D20115
llvm-svn: 269124
The unroll pass was disabled by clang in /Os. Those new test cases shows that the pass will behave correctly even if it is not fully disabled. This patch is related in some way to the clang commit (http://reviews.llvm.org/D19827), which re-enables the pass in /Os.
Differential Revision: http://reviews.llvm.org/D19870
llvm-svn: 268524
We were overly cautious in our analysis of loops which have invokes
which unwind to EH pads. The loop unroll transform is safe because it
only clones blocks in the loop body, it does not try to split critical
edges involving EH pads. Instead, move the necessary safety check to
LoopUnswitch.
N.B. The safety check for loop unswitch is covered by an existing test
which fails without it.
llvm-svn: 268357
Summary:
It is incorrect to compare TripCount (which is BECount + 1)
with extraiters (or Count) to check if we should enter unrolled
loop or not, because TripCount can potentially overflow
(when BECount is max unsigned integer).
While comparing BECount with (Count - 1) is overflow safe and
therefore correct.
Reviewer: hfinkel
Differential Revision: http://reviews.llvm.org/D19256
From: Evgeny Stupachenko <evstupac@gmail.com>
llvm-svn: 267662
Currently each Function points to a DISubprogram and DISubprogram has a
scope field. For member functions the scope is a DICompositeType. DIScopes
point to the DICompileUnit to facilitate type uniquing.
Distinct DISubprograms (with isDefinition: true) are not part of the type
hierarchy and cannot be uniqued. This change removes the subprograms
list from DICompileUnit and instead adds a pointer to the owning compile
unit to distinct DISubprograms. This would make it easy for ThinLTO to
strip unneeded DISubprograms and their transitively referenced debug info.
Motivation
----------
Materializing DISubprograms is currently the most expensive operation when
doing a ThinLTO build of clang.
We want the DISubprogram to be stored in a separate Bitcode block (or the
same block as the function body) so we can avoid having to expensively
deserialize all DISubprograms together with the global metadata. If a
function has been inlined into another subprogram we need to store a
reference the block containing the inlined subprogram.
Attached to https://llvm.org/bugs/show_bug.cgi?id=27284 is a python script
that updates LLVM IR testcases to the new format.
http://reviews.llvm.org/D19034
<rdar://problem/25256815>
llvm-svn: 266446
Updating dominators for exit-blocks of the unrolled loops is not enough,
as shown in PR27157. The proper way is to update dominators for all
dominance-children of original loop blocks.
llvm-svn: 265605
Summary:
Specifically, when we perform runtime loop unrolling of a loop that
contains a convergent op, we can only unroll k times, where k divides
the loop trip multiple.
Without this change, we'll happily unroll e.g. the following loop
for (int i = 0; i < N; ++i) {
if (i == 0) convergent_op();
foo();
}
into
int i = 0;
if (N % 2 == 1) {
convergent_op();
foo();
++i;
}
for (; i < N - 1; i += 2) {
if (i == 0) convergent_op();
foo();
foo();
}.
This is unsafe, because we've just added a control-flow dependency to
the convergent op in the prelude.
In general, runtime unrolling loops that contain convergent ops is safe
only if we don't have emit a prelude, which occurs when the unroll count
divides the trip multiple.
Reviewers: resistor
Subscribers: llvm-commits, mzolotukhin
Differential Revision: http://reviews.llvm.org/D17526
llvm-svn: 263509
Summary: As we now have unit-tests for UnrollAnalyzer, we can convert some existing tests to this format. It should make the tests more robust.
Reviewers: chandlerc, sanjoy
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D17904
llvm-svn: 263318
The issue was that we only required LCSSA rebuilding if the immediate
parent-loop had values used outside of it. The fix is to enaable the
same logic for all outer loops, not only immediate parent.
llvm-svn: 261575
Summary:
Extending findExistingExpansion can use existing value in ExprValueMap.
This patch gives 0.3~0.5% performance improvements on
benchmarks(test-suite, spec2000, spec2006, commercial benchmark)
Reviewers: mzolotukhin, sanjoy, zzheng
Differential Revision: http://reviews.llvm.org/D15559
llvm-svn: 260938
Currently we're unrolling loops more in minsize than in optsize, which
means -Oz will have a larger code size than -Os. That doesn't make any
sense.
This resolves the FIXME about this in LoopUnrollPass and extends the
optsize test to make sure we use the smaller threshold for minsize as
well.
llvm-svn: 257402
It's strange that LoopInfo mostly owns the Loop objects, but that it
defers deleting them to the loop pass manager. Instead, change the
oddly named "updateUnloop" to "markAsRemoved" and have it queue the
Loop object for deletion. We can't delete the Loop immediately when we
remove it, since we need its pointer identity still, so we'll mark the
object as "invalid" so that clients can see what's going on.
llvm-svn: 257191
noduplicate prevents unrolling of small loops that happen to have
barriers in them. If a loop has a barrier in it, it is OK to duplicate
it for the unroll.
llvm-svn: 256075
Summary:
Currently we always recompute LCSSA for outer loops after unrolling an
inner loop. That leads to compile time problem when we have big loop
nests, and we can solve it by avoiding unnecessary work. For instance,
if w eonly do partial unrolling, we don't break LCSSA, so we don't need
to rebuild it. Also, if all exits from the inner loop are inside the
enclosing loop, then complete unrolling won't break LCSSA either.
I replaced unconditional LCSSA recomputation with conditional recomputation +
unconditional assert and added several tests, which were failing when I
experimented with it.
Soon I plan to follow up with a similar patch for recalculation of dominators
tree.
Reviewers: hfinkel, dexonsmith, bogner, joker.eph, chandlerc
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D14526
llvm-svn: 253126
Previously, subprograms contained a metadata reference to the function they
described. Because most clients need to get or set a subprogram for a given
function rather than the other way around, this created unneeded inefficiency.
For example, many passes needed to call the function llvm::makeSubprogramMap()
to build a mapping from functions to subprograms, and the IR linker needed to
fix up function references in a way that caused quadratic complexity in the IR
linking phase of LTO.
This change reverses the direction of the edge by storing the subprogram as
function-level metadata and removing DISubprogram's function field.
Since this is an IR change, a bitcode upgrade has been provided.
Fixes PR23367. An upgrade script for textual IR for out-of-tree clients is
attached to the PR.
Differential Revision: http://reviews.llvm.org/D14265
llvm-svn: 252219
Commit 251839 triggers miscompiles on some bots:
http://lab.llvm.org:8011/builders/perf-x86_64-penryn-O3-polly-fast/builds/13723
(The commit is listed in 13722, but due to an existing failure introduced in
13721 and reverted in 13723 the failure is only visible in 13723)
To verify r251839 is indeed the only change that triggered the buildbot failures
and to ensure the buildbots remain green while investigating I temporarily
revert this commit. At the current state it is unclear if this commit introduced
some miscompile or if it only exposed code to Polly that is subsequently
miscompiled by Polly.
llvm-svn: 251901
Summary:
This patch adds support to check if a loop has loop invariant conditions which lead to loop exits. If so, we know that if the exit path is taken, it is at the first loop iteration. If there is an induction variable used in that exit path whose value has not been updated, it will keep its initial value passing from loop preheader. We can therefore rewrite the exit value with
its initial value. This will help remove phis created by LCSSA and enable other optimizations like loop unswitch.
Reviewers: sanjoy
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D13974
llvm-svn: 251839
Summary:
This patch adds support to check if a loop has loop invariant conditions which lead to loop exits. If so, we know that if the exit path is taken, it is at the first loop iteration. If there is an induction variable used in that exit path whose value has not been updated, it will keep its initial value passing from loop preheader. We can therefore rewrite the exit value with
its initial value. This will help remove phis created by LCSSA and enable other optimizations like loop unswitch.
Reviewers: sanjoy
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D13974
llvm-svn: 251492
Apart from checking that GlobalVariable is a constant, we should check
that it's not a weak constant, in which case we can't propagate its
value.
llvm-svn: 248327
We only checked that a global is initialized with constants, which is
incorrect. We should be checking that GlobalVariable *is* a constant,
not just initialized with it.
llvm-svn: 247769
As a follow-up to r246098, require `DISubprogram` definitions
(`isDefinition: true`) to be 'distinct'. Specifically, add an assembler
check, a verifier check, and bitcode upgrading logic to combat testcase
bitrot after the `DIBuilder` change.
While working on the testcases, I realized that
test/Linker/subprogram-linkonce-weak-odr.ll isn't relevant anymore. Its
purpose was to check for a corner case in PR22792 where two subprogram
definitions match exactly and share the same metadata node. The new
verifier check, requiring that subprogram definitions are 'distinct',
precludes that possibility.
I updated almost all the IR with the following script:
git grep -l -E -e '= !DISubprogram\(.* isDefinition: true' |
grep -v test/Bitcode |
xargs sed -i '' -e 's/= \(!DISubprogram(.*, isDefinition: true\)/= distinct \1/'
Likely some variant of would work for out-of-tree testcases.
llvm-svn: 246327
This change adds the unroll metadata "llvm.loop.unroll.enable" which directs
the optimizer to unroll a loop fully if the trip count is known at compile time, and
unroll partially if the trip count is not known at compile time. This differs from
"llvm.loop.unroll.full" which explicitly does not unroll a loop if the trip count is not
known at compile time.
The "llvm.loop.unroll.enable" is intended to be added for loops annotated with
"#pragma unroll".
llvm-svn: 244466
through PHI nodes across iterations.
This patch teaches the new advanced loop unrolling heuristics to propagate
constants into the loop from the preheader and around the backedge after
simulating each iteration. This lets us brute force solve simple recurrances
that aren't modeled effectively by SCEV. It also makes it more clear why we
need to process the loop in-order rather than bottom-up which might otherwise
make much more sense (for example, for DCE).
This came out of an attempt I'm making to develop a principled way to account
for dead code in the unroll estimation. When I implemented
a forward-propagating version of that it produced incorrect results due to
failing to propagate *cost* between loop iterations through the PHI nodes, and
it occured to me we really should at least propagate simplifications across
those edges, and it is quite easy thanks to the loop being in canonical and
LCSSA form.
Differential Revision: http://reviews.llvm.org/D11706
llvm-svn: 243900
r243250 appeared to break clang/test/Analysis/dead-store.c on one of the build
slaves, but I couldn't reproduce this failure locally. Probably a false
positive as I saw this test was broken by r243246 or r243247 too but passed
later without people fixing anything.
llvm-svn: 243253
Summary:
This patch updates TargetTransformInfoImplCRTPBase::getGEPCost to consider
addressing modes. It now returns TCC_Free when the GEP can be completely folded
to an addresing mode.
I started this patch as I refactored SLSR. Function isGEPFoldable looks common
and is indeed used by some WIP of mine. So I extracted that logic to getGEPCost.
Furthermore, I noticed getGEPCost wasn't directly tested anywhere. The best
testing bed seems CostModel, but its getInstructionCost method invokes
getAddressComputationCost for GEPs which provides very coarse estimation. So
this patch also makes getInstructionCost call the updated getGEPCost for GEPs.
This change inevitably breaks some tests because the cost model changes, but
nothing looks seriously wrong -- if we believe the new cost model is the right
way to go, these tests should be updated.
This patch is not perfect yet -- the comments in some tests need to be updated.
I want to know whether this is a right approach before fixing those details.
Reviewers: chandlerc, hfinkel
Subscribers: aschwaighofer, llvm-commits, aemerson
Differential Revision: http://reviews.llvm.org/D9819
llvm-svn: 243250
Summary:
Resolving a branch allows us to ignore blocks that won't be executed, and thus make our estimate more accurate.
This patch is intended to be applied after D10205 (though it could be applied independently).
Reviewers: chandlerc
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D10206
llvm-svn: 243084
During estimation of unrolling effect we should be able to propagate
constants through casts.
Differential Revision: http://reviews.llvm.org/D10207
llvm-svn: 242257
Enable runtime unrolling for loops with unroll count metadata ("#pragma unroll N")
and a runtime trip count. Also, do not unroll loops with unroll full metadata if the
loop has a runtime loop count. Previously, such loops would be unrolled with a
very large threshold (pragma-unroll-threshold) if runtime unrolled happened to be
enabled resulting in a very large (and likely unwise) unroll factor.
llvm-svn: 242047
We would create a phi node with a zero initialized operand instead of
undef in the case where no value was originally available. This was
problematic for x86_mmx which has no null value.
llvm-svn: 241143
This improves debug locations in passes that do a lot of basic block
transformations. Important case is LoopUnroll pass, the test for correct
debug locations accompanies this change.
Test Plan: regression test suite
Reviewers: dblaikie, sanjoy
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D10367
llvm-svn: 239551
Summary:
canUnrollCompletely takes `unsigned` values for `UnrolledCost` and
`RolledDynamicCost` but is passed in `uint64_t`s that are silently
truncated. Because of this, when `UnrolledSize` is a large integer
that has a small remainder with UINT32_MAX, LLVM tries to completely
unroll loops with high trip counts.
Reviewers: mzolotukhin, chandlerc
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D10293
llvm-svn: 239218
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
On X86 (and similar OOO cores) unrolling is very limited, and even if the
runtime unrolling is otherwise profitable, the expense of a division to compute
the trip count could greatly outweigh the benefits. On the A2, we unroll a lot,
and the benefits of unrolling are more significant (seeing a 5x or 6x speedup
is not uncommon), so we're more able to tolerate the expense, on average, of a
division to compute the trip count.
llvm-svn: 237947
This is to cleanup some redundency generated by LoopUnroll pass. Such redundency may not be cleaned up by existing passes after LoopUnroll.
Differential Revision: http://reviews.llvm.org/D9777
llvm-svn: 237395
Summary:
This patch reimplements heuristic that tries to estimate optimization beneftis
from complete loop unrolling.
In this patch I kept the minimal changes - e.g. I removed code handling
branches and folding compares. That's a promising area, but now there
are too many questions to discuss before we can enable it.
Test Plan: Tests are included in the patch.
Reviewers: hfinkel, chandlerc
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D8816
llvm-svn: 237156
Summary:
Runtime unrolling of loops needs to emit an expression to compute the
loop's runtime trip-count. Avoid runtime unrolling if this computation
will be expensive.
Depends on D8993.
Reviewers: atrick
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D8994
llvm-svn: 234846
Clean up a predicate I added in r229731, fix the relevant comment and
add a test case. The earlier version is confusing to read and was also
buggy (probably not a coincidence) till Alexey fixed it in r233881.
llvm-svn: 234701
It's firstly committed at r231630, and reverted at r231635.
Function pass InstructionSimplifier is inserted as barrier to
make sure loop unroll pass won't affect on LICM pass.
llvm-svn: 232011
For inner one of nested loops, it is more likely to be a hot loop,
and the runtime check can be promoted out from patch 0001, so the
overhead is less, we can try a doubled threshold to unroll more loops.
llvm-svn: 231632
Runtime unrolling is an expensive optimization which can bring benefit
only if the loop is hot and iteration number is relatively large enough.
For some loops, we know they are not worth to be runtime unrolled.
The scalar loop from vectorization is one of the cases.
llvm-svn: 231631
Runtime unrollng will introduce a runtime check in loop prologue.
If the unrolled loop is a inner loop, then the proglogue will be inside
the outer loop. LICM pass can help to promote the runtime check out if
the checked value is loop invariant.
llvm-svn: 231630
Essentially the same as the GEP change in r230786.
A similar migration script can be used to update test cases, though a few more
test case improvements/changes were required this time around: (r229269-r229278)
import fileinput
import sys
import re
pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)")
for line in sys.stdin:
sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line))
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7649
llvm-svn: 230794
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
Don't spend the entire iteration space in the scalar loop prologue if
computing the trip count overflows. This change also gets rid of the
backedge check in the prologue loop and the extra check for
overflowing trip-count.
Differential Revision: http://reviews.llvm.org/D7715
llvm-svn: 229731
The issues with the new unroll analyzer are more fundamental than code
cleanup, algorithm, or data structure changes. I've sent an email to the
original commit thread with details and a proposal for how to redesign
things. I'm disabling this for now so that we don't spend time
debugging issues with it in its current state.
llvm-svn: 229064
Now that the way that the partial unrolling threshold for small loops is used
to compute the unrolling factor as been corrected, a slightly smaller threshold
is preferable. This is expected; other targets may need to re-tune as well.
llvm-svn: 225566
When we compute the size of a loop, we include the branch on the backedge and
the comparison feeding the conditional branch. Under normal circumstances,
these don't get replicated with the rest of the loop body when we unroll. This
led to the somewhat surprising behavior that really small loops would not get
unrolled enough -- they could be unrolled more and the resulting loop would be
below the threshold, because we were assuming they'd take
(LoopSize * UnrollingFactor) instructions after unrolling, instead of
(((LoopSize-2) * UnrollingFactor)+2) instructions. This fixes that computation.
llvm-svn: 225565
The P7 benefits from not have really-small loops so that we either have
multiple dispatch groups in the loop and/or the ability to form more-full
dispatch groups during scheduling. Setting the partial unrolling threshold to
44 seems good, empirically, for the P7. Compared to using no late partial
unrolling, this yields the following test-suite speedups:
SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding
-66.3253% +/- 24.1975%
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
-44.0169% +/- 29.4881%
SingleSource/Benchmarks/Misc/pi
-27.8351% +/- 12.2712%
SingleSource/Benchmarks/Stanford/Bubblesort
-30.9898% +/- 22.4647%
I've speculatively added a similar setting for the P8. Also, I've noticed that
the unroller does not quite calculate the unrolling factor correctly for really
tiny loops because it neglects to account for the fact that not every loop body
replicant contains an ending branch and counter increment. I'll fix that later.
llvm-svn: 225522
Propagate whether `MDNode`s are 'distinct' through the other types of IR
(assembly and bitcode). This adds the `distinct` keyword to assembly.
Currently, no one actually calls `MDNode::getDistinct()`, so these nodes
only get created for:
- self-references, which are never uniqued, and
- nodes whose operands are replaced that hit a uniquing collision.
The concept of distinct nodes is still not quite first-class, since
distinct-ness doesn't yet survive across `MapMetadata()`.
Part of PR22111.
llvm-svn: 225474
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
llvm-svn: 224257
Currently LoopUnroll generates a prologue loop before the main loop
body to execute first N%UnrollFactor iterations. Also, this loop is
used if trip-count can overflow - it's determined by a runtime check.
However, we've been mistakenly optimizing this loop to a linear code for
UnrollFactor = 2, not taking into account that it also serves as a safe
version of the loop if its trip-count overflows.
llvm-svn: 222451
In a case where we have a no {un,}signed wrap flag on the increment, if
RHS - Start is constant then we can avoid inserting a max operation bewteen
the two, since we can statically determine which is greater.
This allows us to unroll loops such as:
void testcase3(int v) {
for (int i=v; i<=v+1; ++i)
f(i);
}
llvm-svn: 220960
ScalarEvolution in the presence of multiple exits. Previously all
loops exits had to have identical counts for a loop trip count to be
considered computable. This pessimization was implemented by calling
getBackedgeTakenCount(L) rather than getExitCount(L, ExitingBlock)
inside of ScalarEvolution::getSmallConstantTripCount() (see the FIXME
in the comments of that function). The pessimization was added to fix
a corner case involving undefined behavior (pr/16130). This patch more
precisely handles the undefined behavior case allowing the pessimization
to be removed.
ControlsExit replaces IsSubExpr to more precisely track the case where
undefined behavior is expected to occur. Because undefined behavior is
tracked more precisely we can remove MustExit from ExitLimit. MustExit
was used to track the case where the limit was computed potentially
assuming undefined behavior even if undefined behavior didn't necessarily
occur.
llvm-svn: 219517
`LoopUnrollPass` says that it preserves `LoopInfo` -- make it so. In
particular, tell `LoopInfo` about copies of inner loops when unrolling
the outer loop.
Conservatively, also tell `ScalarEvolution` to forget about the original
versions of these loops, since their inputs may have changed.
Fixes PR20987.
llvm-svn: 219241
Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
if (extraiters == loopfactor) jump L1
if (extraiters == loopfactor-1) jump L2
...
L1: LoopBody;
L2: LoopBody;
...
if tripcount < loopfactor jump End
Loop:
...
End:
It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like
extraiters = tripcount % loopfactor
if (extraiters == 0) jump Loop:
else jump Prol
Prol: LoopBody;
extraiters -= 1 // Omitted if unroll factor is 2.
if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
if (tripcount < loopfactor) jump End
Loop:
...
End:
Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.
llvm-svn: 218604
The annotation instructions are dropped during codegen and have no
impact on size. In some cases, the annotations were preventing the
unroller from unrolling a loop because the annotation calls were
pushing the cost over the unrolling threshold.
Differential Revision: http://reviews.llvm.org/D5335
llvm-svn: 218525
This adds a set of utility functions for collecting 'ephemeral' values. These
are LLVM IR values that are used only by @llvm.assume intrinsics (directly or
indirectly), and thus will be removed prior to code generation, implying that
they should be considered free for certain purposes (like inlining). The
inliner's cost analysis, and a few other passes, have been updated to account
for ephemeral values using the provided functionality.
This functionality is important for the usability of @llvm.assume, because it
limits the "non-local" side-effects of adding llvm.assume on inlining, loop
unrolling, etc. (these are hints, and do not generate code, so they should not
directly contribute to estimates of execution cost).
llvm-svn: 217335
hint) the loop unroller replaces the llvm.loop.unroll.count metadata with
llvm.loop.unroll.disable metadata to prevent any subsequent unrolling
passes from unrolling more than the hint indicates. This patch fixes
an issue where loop unrolling could be disabled for other loops as well which
share the same llvm.loop metadata.
llvm-svn: 213900
[LLVM part]
These patches rename the loop unrolling and loop vectorizer metadata
such that they have a common 'llvm.loop.' prefix. Metadata name
changes:
llvm.vectorizer.* => llvm.loop.vectorizer.*
llvm.loopunroll.* => llvm.loop.unroll.*
This was a suggestion from an earlier review
(http://reviews.llvm.org/D4090) which added the loop unrolling
metadata.
Patch by Mark Heffernan.
llvm-svn: 211710
[This is resubmitting r210721, which was reverted due to suspected breakage
which turned out to be unrelated].
Some extra review comments were addressed. See D4090 and D4147 for more details.
The Clang change that produces this metadata was committed in r210667
Patch by Mark Heffernan.
llvm-svn: 211076
See http://reviews.llvm.org/D4090 for more details.
The Clang change that produces this metadata was committed in r210667
Patch by Mark Heffernan.
llvm-svn: 210721
During loop-unroll, loop exits from the current loop may end up in in different
outer loop. This requires to re-form LCSSA recursively for one level down from
the outer most loop where loop exits are landed during unroll. This fixes PR18861.
Differential Revision: http://reviews.llvm.org/D2976
llvm-svn: 209796
The old method used by X86TTI to determine partial-unrolling thresholds was
messy (because it worked by testing target features), and also would not
correctly identify the target CPU if certain target features were disabled.
After some discussions on IRC with Chandler et al., it was decided that the
processor scheduling models were the right containers for this information
(because it is often tied to special uop dispatch-buffer sizes).
This does represent a small functionality change:
- For generic x86-64 (which uses the SB model and, thus, will get some
unrolling).
- For AMD cores (because they still currently use the SB scheduling model)
- For Haswell (based on benchmarking by Louis Gerbarg, it was decided to bump
the default threshold to 50; we're working on a test case for this).
Otherwise, nothing has changed for any other targets. The logic, however, has
been moved into BasicTTI, so other targets may now also opt-in to this
functionality simply by setting LoopMicroOpBufferSize in their processor
model definitions.
llvm-svn: 208289
Otherwise we use the same threshold as for complete unrolling, which is
way too high. This made us unroll any loop smaller than 150 instructions
by 8 times, but only if someone specified -march=core2 or better,
which happens to be the default on darwin.
llvm-svn: 207940
This patch changes the vectorization remarks to also inform when
vectorization is possible but not beneficial.
Added tests to exercise some loop remarks.
llvm-svn: 207574
This provides an initial implementation of getUnrollingPreferences for x86.
getUnrollingPreferences is used by the generic (concatenation) unroller, which
is distinct from the unrolling done by the loop vectorizer. Many modern x86
cores have some kind of uop cache and loop-stream detector (LSD) used to
efficiently dispatch small loops, and taking full advantage of this requires
unrolling small loops (small here means 10s of uops).
These caches also have limits on the number of taken branches in the loop, and
so we also cap the loop unrolling factor based on the maximum "depth" of the
loop. This is currently calculated with a partial DFS traversal (partial
because it will stop early if the path length grows too much). This is still an
approximation, and one that is both conservative (because it does not account
for branches eliminated via block placement) and optimistic (because it is only
recording the maximum depth over minimum paths). Nevertheless, because the
loops that fit in these uop caches are so small, it is not clear how much the
details matter.
The original set of patches posted for review produced the following test-suite
performance results (from the TSVC benchmark) at that time:
ControlLoops-dbl - 13% speedup
ControlLoops-flt - 15% speedup
Reductions-dbl - 7.5% speedup
llvm-svn: 205348
The PowerPC A2 core greatly benefits from aggressive concatenation unrolling;
use the new getUnrollingPreferences to enable this by default when targeting
the PPC A2 core.
llvm-svn: 190549
- Instead of setting the suffixes in a bunch of places, just set one master
list in the top-level config. We now only modify the suffix list in a few
suites that have one particular unique suffix (.ml, .mc, .yaml, .td, .py).
- Aside from removing the need for a bunch of lit.local.cfg files, this enables
4 tests that were inadvertently being skipped (one in
Transforms/BranchFolding, a .s file each in DebugInfo/AArch64 and
CodeGen/PowerPC, and one in CodeGen/SI which is now failing and has been
XFAILED).
- This commit also fixes a bunch of config files to use config.root instead of
older copy-pasted code.
llvm-svn: 188513
This update was done with the following bash script:
find test/Transforms -name "*.ll" | \
while read NAME; do
echo "$NAME"
if ! grep -q "^; *RUN: *llc" $NAME; then
TEMP=`mktemp -t temp`
cp $NAME $TEMP
sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \
while read FUNC; do
sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP
done
mv $TEMP $NAME
fi
done
llvm-svn: 186268
Serguei Katkov