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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@294936 91177308-0d34-0410-b5e6-96231b3b80d8
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@293440 91177308-0d34-0410-b5e6-96231b3b80d8
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290228 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289399 91177308-0d34-0410-b5e6-96231b3b80d8
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@267328 91177308-0d34-0410-b5e6-96231b3b80d8
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@267098 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@261511 91177308-0d34-0410-b5e6-96231b3b80d8
Pass non-null arguments by reference in MachineTraceMetrics::Trace,
simplifying future work to remove implicit iterator => pointer
conversions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@261509 91177308-0d34-0410-b5e6-96231b3b80d8
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@252616 91177308-0d34-0410-b5e6-96231b3b80d8
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).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@252196 91177308-0d34-0410-b5e6-96231b3b80d8
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).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@244020 91177308-0d34-0410-b5e6-96231b3b80d8
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243994 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242277 91177308-0d34-0410-b5e6-96231b3b80d8
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@240361 91177308-0d34-0410-b5e6-96231b3b80d8
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!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@240137 91177308-0d34-0410-b5e6-96231b3b80d8
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()
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@229208 91177308-0d34-0410-b5e6-96231b3b80d8
This removes static initializers from the backends which generate this data, and also makes this struct match the other Tablegen generated structs in behaviour
Reviewed by Andy Trick and Chandler C
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216919 91177308-0d34-0410-b5e6-96231b3b80d8
This is a cleaner solution to the problem described in r215431.
When instructions are combined a dangling DBG_VALUE is removed.
This resolves bug 20598.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@215587 91177308-0d34-0410-b5e6-96231b3b80d8
Re-commit of r214832,r21469 with a work-around that
avoids the previous problem with gcc build compilers
The work-around is to use SmallVector instead of ArrayRef
of basic blocks in preservesResourceLen()/MachineCombiner.cpp
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@215151 91177308-0d34-0410-b5e6-96231b3b80d8
GCC 4.8.2 objects to the tautological condition in the assert as the unsigned
value is guaranteed to be >= 0. Simplify the assertion by dropping the
tautological condition.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214671 91177308-0d34-0410-b5e6-96231b3b80d8
sequence - target independent framework
When the DAGcombiner selects instruction sequences
it could increase the critical path or resource len.
For example, on arm64 there are multiply-accumulate instructions (madd,
msub). If e.g. the equivalent multiply-add sequence is not on the
crictial path it makes sense to select it instead of the combined,
single accumulate instruction (madd/msub). The reason is that the
conversion from add+mul to the madd could lengthen the critical path
by the latency of the multiply.
But the DAGCombiner would always combine and select the madd/msub
instruction.
This patch uses machine trace metrics to estimate critical path length
and resource length of an original instruction sequence vs a combined
instruction sequence and picks the faster code based on its estimates.
This patch only commits the target independent framework that evaluates
and selects code sequences. The machine instruction combiner is turned
off for all targets and expected to evolve over time by gradually
handling DAGCombiner pattern in the target specific code.
This framework lays the groundwork for fixing
rdar://16319955
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214666 91177308-0d34-0410-b5e6-96231b3b80d8