In D41587, @mssimpso discovered that the order of some patterns for
AArch64 was sub-optimal. I thought a bit about how we could avoid that
case in the future. I do not think there is a need for evaluating all
patterns for now. But this patch adds an extra (expensive) check, that
evaluates the latencies of all patterns, and ensures that the latency
saved decreases for subsequent patterns.
This catches the sub-optimal order fixed in D41587, but I am not
entirely happy with the check, as it only applies to sub-optimal
patterns seen while building with EXPENSIVE_CHECKS on. It did not
discover any other sub-optimal pattern ordering.
Reviewers: Gerolf, spatel, mssimpso
Reviewed By: Gerolf, mssimpso
Differential Revision: https://reviews.llvm.org/D41766
llvm-svn: 323873
Summary:
When calculating the RootLatency, we add up all the latencies of the
deleted instructions. But for NewRootLatency we only add the latency of
the new root instructions, ignoring the latencies of the other
instructions inserted. This leads the combiner to underestimate the cost
of patterns which add multiple instructions. This patch fixes that by
summing up the latencies of all new instructions. For NewRootNode, the
more complex getLatency function is used.
Note that we may be slightly more precise than just summing up
all latencies. For example, consider a pattern like
r1 = INS1 ..
r2 = INS2 ..
r3 = INS3 r1, r2
I think in some other places, the total latency of the pattern would be
estimated as lat(INS3) + max(lat(INS1), lat(INS2)). If you consider
that worth changing, I think it would be best to do in a follow-up
patch.
Reviewers: Gerolf, sebpop, spop, fhahn
Reviewed By: fhahn
Subscribers: evandro, llvm-commits
Differential Revision: https://reviews.llvm.org/D40307
llvm-svn: 319951
All these headers already depend on CodeGen headers so moving them into
CodeGen fixes the layering (since CodeGen depends on Target, not the
other way around).
llvm-svn: 318490
This header includes CodeGen headers, and is not, itself, included by
any Target headers, so move it into CodeGen to match the layering of its
implementation.
llvm-svn: 317647
Summary:
Fixes a bogus iterator resulting from the removal of a block's first instruction at the point that incremental update is enabled.
Patch by Paul Walker.
Reviewers: fhahn, Gerolf, efriedma, MatzeB
Reviewed By: fhahn
Subscribers: aemerson, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D38734
llvm-svn: 315502
This version of the patch fixes an off-by-one error causing PR34596. We
do not need to use std::next(BlockIter) when calling updateDepths, as
BlockIter already points to the next element.
Original commit message:
> For large basic blocks with lots of combinable instructions, the
> MachineTraceMetrics computations in MachineCombiner can dominate the compile
> time, as computing the trace information is quadratic in the number of
> instructions in a BB and it's relevant successors/predecessors.
> In most cases, knowing the instruction depth should be enough to make
> combination decisions. As we already iterate over all instructions in a basic
> block, the instruction depth can be computed incrementally. This reduces the
> cost of machine-combine drastically in cases where lots of instructions
> are combined. The major drawback is that AFAIK, computing the critical path
> length cannot be done incrementally. Therefore we only compute
> instruction depths incrementally, for basic blocks with more
> instructions than inc_threshold. The -machine-combiner-inc-threshold
> option can be used to set the threshold and allows for easier
> experimenting and checking if using incremental updates for all basic
> blocks has any impact on the performance.
>
> Reviewers: sanjoy, Gerolf, MatzeB, efriedma, fhahn
>
> Reviewed By: fhahn
>
> Subscribers: kiranchandramohan, javed.absar, efriedma, llvm-commits
>
> Differential Revision: https://reviews.llvm.org/D36619
llvm-svn: 313751
This caused PR34596.
> [MachineCombiner] Update instruction depths incrementally for large BBs.
>
> Summary:
> For large basic blocks with lots of combinable instructions, the
> MachineTraceMetrics computations in MachineCombiner can dominate the compile
> time, as computing the trace information is quadratic in the number of
> instructions in a BB and it's relevant successors/predecessors.
>
> In most cases, knowing the instruction depth should be enough to make
> combination decisions. As we already iterate over all instructions in a basic
> block, the instruction depth can be computed incrementally. This reduces the
> cost of machine-combine drastically in cases where lots of instructions
> are combined. The major drawback is that AFAIK, computing the critical path
> length cannot be done incrementally. Therefore we only compute
> instruction depths incrementally, for basic blocks with more
> instructions than inc_threshold. The -machine-combiner-inc-threshold
> option can be used to set the threshold and allows for easier
> experimenting and checking if using incremental updates for all basic
> blocks has any impact on the performance.
>
> Reviewers: sanjoy, Gerolf, MatzeB, efriedma, fhahn
>
> Reviewed By: fhahn
>
> Subscribers: kiranchandramohan, javed.absar, efriedma, llvm-commits
>
> Differential Revision: https://reviews.llvm.org/D36619
llvm-svn: 313213
Summary:
For large basic blocks with lots of combinable instructions, the
MachineTraceMetrics computations in MachineCombiner can dominate the compile
time, as computing the trace information is quadratic in the number of
instructions in a BB and it's relevant successors/predecessors.
In most cases, knowing the instruction depth should be enough to make
combination decisions. As we already iterate over all instructions in a basic
block, the instruction depth can be computed incrementally. This reduces the
cost of machine-combine drastically in cases where lots of instructions
are combined. The major drawback is that AFAIK, computing the critical path
length cannot be done incrementally. Therefore we only compute
instruction depths incrementally, for basic blocks with more
instructions than inc_threshold. The -machine-combiner-inc-threshold
option can be used to set the threshold and allows for easier
experimenting and checking if using incremental updates for all basic
blocks has any impact on the performance.
Reviewers: sanjoy, Gerolf, MatzeB, efriedma, fhahn
Reviewed By: fhahn
Subscribers: kiranchandramohan, javed.absar, efriedma, llvm-commits
Differential Revision: https://reviews.llvm.org/D36619
llvm-svn: 312719
Rename the DEBUG_TYPE to match the names of corresponding passes where
it makes sense. Also establish the pattern of simply referencing
DEBUG_TYPE instead of repeating the passname where possible.
llvm-svn: 303921
Before this patch compile time was about 21s (see below). After this patch
we have less than 2s (see bellow).
Intel(R) Xeon(R) CPU E5-2676 v3 @ 2.40GHz
DAGCombiner - trunk
time ./llc spill_fdiv.ll -o /dev/null -enable-unsafe-fp-math
real 0m1.685s
DAGCombiner + Speed patch
time ./llc spill_fdiv.ll -o /dev/null -enable-unsafe-fp-math
real 0m1.655s
MachineCombiner w/o Speed patch
time ./llc spill_fdiv.ll -o /dev/null -enable-unsafe-fp-math
real 0m21.614s
MachineCombiner + Speed patch
time ./llc spill_fdiv.ll -o /dev/null -enable-unsafe-fp-math
real 0m1.593s
The test spill_fdiv.ll is attached to D29627
D29627 should be closed.
llvm-svn: 294936
The primary use of the dump() functions in LLVM is for use in a
debugger. Unfortunately lldb does not seem to handle default arguments
so using `p SomeMI.dump()` fails and you have to type the longer `p
SomeMI.dump(nullptr)`. Remove the paramter to make the most common use
easy. (You can always construct something like `p
SomeMI.print(dbgs(),MyTII)` if you need more features).
Differential Revision: https://reviews.llvm.org/D29241
llvm-svn: 293440
we used to print UNKNOWN instructions when the instruction to be printer was not
yet inserted in any BB: in that case the pretty printer would not be able to
compute a TII as the instruction does not belong to any BB or function yet.
This patch explicitly passes the TII to the pretty-printer.
Differential Revision: https://reviews.llvm.org/D27645
llvm-svn: 290228
We have found that -- when the selected subarchitecture has a scheduling model
and we are not optimizing for size -- the machine-instruction combiner uses a
too-simple algorithm to compute the cost of one of the two alternatives [before
and after running a combining pass on a section of code], and therefor it throws
away the combination results too often.
This fix has the potential to help any ISA with the potential to combine
instructions and for which at least one subarchitecture has a scheduling model.
As of now, this is only known to definitely affect AArch64 subarchitectures with
a scheduling model.
Regression tested on AMD64/GNU-Linux, new test case tested to fail on an
unpatched compiler and pass on a patched compiler.
Patch by Abe Skolnik and Sebastian Pop.
llvm-svn: 289399
The original patch caused crashes because it could derefence a null pointer
for SelectionDAGTargetInfo for targets that do not define it.
Evaluates fmul+fadd -> fmadd combines and similar code sequences in the
machine combiner. It adds support for float and double similar to the existing
integer implementation. The key features are:
- DAGCombiner checks whether it should combine greedily or let the machine
combiner do the evaluation. This is only supported on ARM64.
- It gives preference to throughput over latency: the heuristic used is
to combine always in loops. The targets decides whether the machine
combiner should optimize for throughput or latency.
- Supports for fmadd, f(n)msub, fmla, fmls patterns
- On by default at O3 ffast-math
llvm-svn: 267328
Evaluates fmul+fadd -> fmadd combines and similar code sequences in the
machine combiner. It adds support for float and double similar to the existing
integer implementation. The key features are:
- DAGCombiner checks whether it should combine greedily or let the machine
combiner do the evaluation. This is only supported on ARM64.
- It gives preference to throughput over latency: the heuristic used is
to combine always in loops. The targets decides whether the machine
combiner should optimize for throughput or latency.
- Supports for fmadd, f(n)msub, fmla, fmls patterns
- On by default at O3 ffast-math
llvm-svn: 267098
Removed some unused headers, replaced some headers with forward class declarations.
Found using simple scripts like this one:
clear && ack --cpp -l '#include "llvm/ADT/IndexedMap.h"' | xargs grep -L 'IndexedMap[<]' | xargs grep -n --color=auto 'IndexedMap'
Patch by Eugene Kosov <claprix@yandex.ru>
Differential Revision: http://reviews.llvm.org/D19219
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 266595
This reverts commit r261510, effectively reapplying r261509. The
original commit missed a caller in AArch64ConditionalCompares.
Original commit message:
Pass non-null arguments by reference in MachineTraceMetrics::Trace,
simplifying future work to remove implicit iterator => pointer
conversions.
llvm-svn: 261511
Pass non-null arguments by reference in MachineTraceMetrics::Trace,
simplifying future work to remove implicit iterator => pointer
conversions.
llvm-svn: 261509
This is one of the problems noted in PR25016:
https://llvm.org/bugs/show_bug.cgi?id=25016
and:
http://lists.llvm.org/pipermail/llvm-dev/2015-October/090998.html
The spilling problem is independent and not addressed by this patch.
The MachineCombiner was doing reassociations that don't improve or even worsen the critical path.
This is caused by inclusion of the "slack" factor when calculating the critical path of the original
code sequence. If we don't add that, then we have a more conservative cost comparison of the old code
sequence vs. a new sequence. The more liberal calculation must be preserved, however, for the AArch64
MULADD patterns because benchmark regressions were observed without that.
The two failing test cases now have identical asm that does what we want:
a + b + c + d ---> (a + b) + (c + d)
Differential Revision: http://reviews.llvm.org/D13417
llvm-svn: 252616
Also, remove an enum hack where enum values were used as indexes into an array.
We may want to make this a real class to allow pattern-based queries/customization (D13417).
llvm-svn: 252196
In r242277, I updated the MachineCombiner to work with itineraries, but I
missed a call that is scheduling-model-only (the opcode-only form of
computeInstrLatency). Using the form that takes an MI* allows this to work with
itineraries (and should be NFC for subtargets with scheduling models).
llvm-svn: 244020
Create wrapper methods in the Function class for the OptimizeForSize and MinSize
attributes. We want to hide the logic of "or'ing" them together when optimizing
just for size (-Os).
Currently, we are not consistent about this and rely on a front-end to always set
OptimizeForSize (-Os) if MinSize (-Oz) is on. Thus, there are 18 FIXME changes here
that should be added as follow-on patches with regression tests.
This patch is NFC-intended: it just replaces existing direct accesses of the attributes
by the equivalent wrapper call.
Differential Revision: http://reviews.llvm.org/D11734
llvm-svn: 243994
MachineCombiner predicated its use of scheduling-based metrics on
hasInstrSchedModel(), but useful conclusions can be drawn from pipeline
itineraries as well. Almost all of the logic (except for resource tracking in
preservesResourceLen) can be used if we have an itinerary, so enable it in that
case as well.
This will be used by the PowerPC backend in an upcoming commit.
llvm-svn: 242277
Currently ( D10321, http://reviews.llvm.org/rL239486 ), we can use the machine combiner pass
to reassociate the following sequence to reduce the critical path:
A = ? op ?
B = A op X
C = B op Y
-->
A = ? op ?
B = X op Y
C = A op B
'op' is currently limited to x86 AVX scalar FP adds (with fast-math on), but in theory, it could
be any associative math/logic op (see TODO in code comment).
This patch generalizes the pattern match to ignore the instruction that defines 'A'. So instead of
a sequence of 3 adds, we now only need to find 2 dependent adds and decide if it's worth
reassociating them.
This generalization has a compile-time cost because we can now match more instruction sequences
and we rely more heavily on the machine combiner to discard sequences where reassociation doesn't
improve the critical path.
For example, in the new test case:
A = M div N
B = A add X
C = B add Y
We'll match 2 reassociation patterns, but this transform doesn't reduce the critical path:
A = M div N
B = A add Y
C = B add X
We need the combiner to reject that pattern but select this:
A = M div N
B = X add Y
C = B add A
Differential Revision: http://reviews.llvm.org/D10460
llvm-svn: 240361
The patch is generated using this command:
tools/clang/tools/extra/clang-tidy/tool/run-clang-tidy.py -fix \
-checks=-*,llvm-namespace-comment -header-filter='llvm/.*|clang/.*' \
llvm/lib/
Thanks to Eugene Kosov for the original patch!
llvm-svn: 240137
Canonicalize access to function attributes to use the simpler API.
getAttributes().getAttribute(AttributeSet::FunctionIndex, Kind)
=> getFnAttribute(Kind)
getAttributes().hasAttribute(AttributeSet::FunctionIndex, Kind)
=> hasFnAttribute(Kind)
Also, add `Function::getFnStackAlignment()`, and canonicalize:
getAttributes().getStackAlignment(AttributeSet::FunctionIndex)
=> getFnStackAlignment()
llvm-svn: 229208
Andrew V. Tischenko