This patch implements analysis for new-format TBAA access tags
with aggregate types as their final access types.
Differential Revision: https://reviews.llvm.org/D41501
llvm-svn: 324092
Summary:
This change is part of step five in the series of changes to remove alignment argument from
memcpy/memmove/memset in favour of alignment attributes. In particular, this changes the Lint
analysis to cease using the old getAlignment() API of MemoryIntrinsic in favour of getting
source & dest specific alignments through the new API.
Steps:
Step 1) Remove alignment parameter and create alignment parameter attributes for
memcpy/memmove/memset. ( rL322965, rC322964, rL322963 )
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments. ( rL323597 )
Step 3) Update Clang to use the new IRBuilder API. ( rC323617 )
Step 4) Update Polly to use the new IRBuilder API. ( rL323618 )
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use [get|set]DestAlignment()
and [get|set]SourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reference
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.htmlhttp://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
llvm-svn: 323886
We're getting bug reports:
https://bugs.llvm.org/show_bug.cgi?id=35807https://bugs.llvm.org/show_bug.cgi?id=35840https://bugs.llvm.org/show_bug.cgi?id=36045
...where we blow up the stack in value tracking because other passes are sending
in selects that have an operand that is itself the select.
We don't currently have a reliable way to avoid analyzing dead code that may take
non-standard forms, so bail out when things go too far.
This mimics the recursion depth limitations in other parts of value tracking.
Unfortunately, this pushes the underlying problems for other passes (jump-threading,
simplifycfg, correlated-propagation) into hiding. If someone wants to uncover those
again, the first draft of this patch on Phab would do that (it would assert rather
than bail out).
Differential Revision: https://reviews.llvm.org/D42442
llvm-svn: 323331
An alternative (and probably better) fix would be that of
making `Scale` an APInt, and there's a patch floating around
to do this. As we're still discussing it, at least stop crashing
in the meanwhile (added bonus, we now have a regression test for
this situation).
Fixes PR35843.
Thanks to Eli for suggesting the fix and Simon for reporting and
reducing the bug.
llvm-svn: 322467
Summary:
See D37528 for a previous (non-deferred) version of this
patch and its description.
Preserves dominance in a deferred manner using a new class
DeferredDominance. This reduces the performance impact of
updating the DominatorTree at every edge insertion and
deletion. A user may call DDT->flush() within JumpThreading
for an up-to-date DT. This patch currently has one flush()
at the end of runImpl() to ensure DT is preserved across
the pass.
LVI is also preserved to help subsequent passes such as
CorrelatedValuePropagation. LVI is simpler to maintain and
is done immediately (not deferred). The code to perform the
preversation was minimally altered and simply marked as
preserved for the PassManager to be informed.
This extends the analysis available to JumpThreading for
future enhancements such as threading across loop headers.
Reviewers: dberlin, kuhar, sebpop
Reviewed By: kuhar, sebpop
Subscribers: mgorny, dmgreen, kuba, rnk, rsmith, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D40146
llvm-svn: 322401
Summary:
There are few oddities that occur due to v1i1, v8i1, v16i1 being legal without v2i1 and v4i1 being legal when we don't have VLX. Particularly during legalization of v2i32/v4i32/v2i64/v4i64 masked gather/scatter/load/store. We end up promoting the mask argument to these during type legalization and then have to widen the promoted type to v8iX/v16iX and truncate it to get the element size back down to v8i1/v16i1 to use a 512-bit operation. Since need to fill the upper bits of the mask we have to fill with 0s at the promoted type.
It would be better if we could just have the v2i1/v4i1 types as legal so they don't undergo any promotion. Then we can just widen with 0s directly in a k register. There are no real v4i1/v2i1 instructions anyway. Everything is done on a larger register anyway.
This also fixes an issue that we couldn't implement a masked vextractf32x4 from zmm to xmm properly.
We now have to support widening more compares to 512-bit to get a mask result out so new tablegen patterns got added.
I had to hack the legalizer for widening the operand of a setcc a bit so it didn't try create a setcc returning v4i32, extract from it, then try to promote it using a sign extend to v2i1. Now we create the setcc with v4i1 if the original setcc's result type is v2i1. Then extract that and don't sign extend it at all.
There's definitely room for improvement with some follow up patches.
Reviewers: RKSimon, zvi, guyblank
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41560
llvm-svn: 321967
Summary:
See D37528 for a previous (non-deferred) version of this
patch and its description.
Preserves dominance in a deferred manner using a new class
DeferredDominance. This reduces the performance impact of
updating the DominatorTree at every edge insertion and
deletion. A user may call DDT->flush() within JumpThreading
for an up-to-date DT. This patch currently has one flush()
at the end of runImpl() to ensure DT is preserved across
the pass.
LVI is also preserved to help subsequent passes such as
CorrelatedValuePropagation. LVI is simpler to maintain and
is done immediately (not deferred). The code to perfom the
preversation was minimally altered and was simply marked
as preserved for the PassManager to be informed.
This extends the analysis available to JumpThreading for
future enhancements. One example is loop boundary threading.
Reviewers: dberlin, kuhar, sebpop
Reviewed By: kuhar, sebpop
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D40146
llvm-svn: 321825
Summary:
When using byval, the data is effectively copied as part of the call
anyway, so we aren't actually passing the pointer and thus there is no
reason to issue a warning.
Reviewers: rnk
Reviewed By: rnk
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D40118
llvm-svn: 321478
This is fix for the crash caused by ScalarEvolution::getTruncateExpr.
It expects that if it checked the condition that SCEV is not in UniqueSCEVs cache in
the beginning that it will not be there inside this method.
However during recursion and transformation/simplification for sub expression,
it is possible that these modifications will end up with the same SCEV as we started from.
So we must always check whether SCEV is in cache and do not insert item if it is already there.
Reviewers: sanjoy, mkazantsev, craig.topper
Reviewed By: sanjoy
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41380
llvm-svn: 321472
Summary:
Make MemorySSA allow reordering of two loads that may alias, when one is volatile.
This makes MemorySSA less conservative and behaving the same as the AliasSetTracker.
For more context, see D16875.
LLVM language reference: "The optimizers must not change the number of volatile operations or change their order of execution relative to other volatile operations. The optimizers may change the order of volatile operations relative to non-volatile operations. This is not Java’s “volatile” and has no cross-thread synchronization behavior."
Reviewers: george.burgess.iv, dberlin
Subscribers: sanjoy, reames, hfinkel, llvm-commits, Prazek
Differential Revision: https://reviews.llvm.org/D41525
llvm-svn: 321382
Summary:
Add an additional bit to ModRefInfo, ModRefInfo::Must, to be cleared for known must aliases.
Shift existing Mod/Ref/ModRef values to include an additional most
significant bit. Update wrappers that modify ModRefInfo values to
reflect the change.
Notes:
* ModRefInfo::Must is almost entirely cleared in the AAResults methods, the remaining changes are trying to preserve it.
* Only some small changes to make custom AA passes set ModRefInfo::Must (BasicAA).
* GlobalsModRef already declares a bit, who's meaning overlaps with the most significant bit in ModRefInfo (MayReadAnyGlobal). No changes to shift the value of MayReadAnyGlobal (see AlignedMap). FunctionInfo.getModRef() ajusts most significant bit so correctness is preserved, but the Must info is lost.
* There are cases where the ModRefInfo::Must is not set, e.g. 2 calls that only read will return ModRefInfo::NoModRef, though they may read from exactly the same location.
Reviewers: dberlin, hfinkel, george.burgess.iv
Subscribers: llvm-commits, sanjoy
Differential Revision: https://reviews.llvm.org/D38862
llvm-svn: 321309
Summary:
As suggested by Eli Friedman, don't try to handle array allocas here,
because of possible overflows, instead rely on instcombine converting
them to allocations of array types.
Reviewers: efriedma
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41398
llvm-svn: 321159
Enhance LVI to analyze the ‘ashr’ binary operation. This leverages the infrastructure in ConstantRange for the ashr operation.
Patch by Surya Kumari Jangala!
Differential Revision: https://reviews.llvm.org/D40886
llvm-svn: 320983
Based on the names of the check lines, features seems more appropriate that cpu.
Spotted while prototyping my patch to make 512-bit vectors illegal on SKX sometimes.
llvm-svn: 320959
Summary:
For byval arguments, the number of dereferenceable bytes is equal to
the size of the pointee, not the pointer.
Reviewers: hfinkel, rnk
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41305
llvm-svn: 320939
Summary:
See D37528 for a previous (non-deferred) version of this
patch and its description.
Preserves dominance in a deferred manner using a new class
DeferredDominance. This reduces the performance impact of
updating the DominatorTree at every edge insertion and
deletion. A user may call DDT->flush() within JumpThreading
for an up-to-date DT. This patch currently has one flush()
at the end of runImpl() to ensure DT is preserved across
the pass.
LVI is also preserved to help subsequent passes such as
CorrelatedValuePropagation. LVI is simpler to maintain and
is done immediately (not deferred). The code to perfom the
preversation was minimally altered and was simply marked
as preserved for the PassManager to be informed.
This extends the analysis available to JumpThreading for
future enhancements. One example is loop boundary threading.
Reviewers: dberlin, kuhar, sebpop
Reviewed By: kuhar, sebpop
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D40146
llvm-svn: 320612
This reverts part of r300656, which caused a regression in
propagateMassToSuccessors by counting edges n^2 times, where n is the
number of edges from the source basic block to the same successor basic
block. The result was both incorrect and very slow to compute for large
values of n (e.g. switches with multiple cases that go to the same basic
block).
Patch by Andrew Scheidecker!
llvm-svn: 320208
In this method, we invoke `SimplifyICmpOperands` which takes the `Cond` predicate
by reference and may change it along with `LHS` and `RHS` SCEVs. But then we invoke
`computeShiftCompareExitLimit` with Values from which the SCEVs have been derived,
these Values have not been modified while `Cond` could be.
One of possible outcomes of this is that we may falsely prove that an infinite loop ends
within some finite number of iterations.
In this patch, we save the original `Cond` and pass it along with original operands.
This logic may be removed in future once `computeShiftCompareExitLimit` works
with SCEVs instead of value operands.
Reviewed By: sanjoy
Differential Revision: https://reviews.llvm.org/D40953
llvm-svn: 320142
Given loops `L1` and `L2` with AddRecs `AR1` and `AR2` varying in them respectively.
When identifying loop disposition of `AR2` w.r.t. `L1`, we only say that it is varying if
`L1` contains `L2`. But there is also a possible situation where `L1` and `L2` are
consecutive sibling loops within the parent loop. In this case, `AR2` is also varying
w.r.t. `L1`, but we don't correctly identify it.
It can lead, for exaple, to attempt of incorrect folding. Consider:
AR1 = {a,+,b}<L1>
AR2 = {c,+,d}<L2>
EXAR2 = sext(AR1)
MUL = mul AR1, EXAR2
If we incorrectly assume that `EXAR2` is invariant w.r.t. `L1`, we can end up trying to
construct something like: `{a * {c,+,d}<L2>,+,b * {c,+,d}<L2>}<L1>`, which is incorrect
because `AR2` is not available on entrance of `L1`.
Both situations "`L1` contains `L2`" and "`L1` preceeds sibling loop `L2`" can be handled
with one check: "header of `L1` dominates header of `L2`". This patch replaces the old
insufficient check with this one.
Differential Revision: https://reviews.llvm.org/D39453
llvm-svn: 318819
Summary:
Add the following heuristics for irreducible loop metadata:
- When an irreducible loop header is missing the loop header weight metadata,
give it the minimum weight seen among other headers.
- Annotate indirectbr targets with the loop header weight metadata (as they are
likely to become irreducible loop headers after indirectbr tail duplication.)
These greatly improve the accuracy of the block frequency info of the Python
interpreter loop (eg. from ~3-16x off down to ~40-55% off) and the Python
performance (eg. unpack_sequence from ~50% slower to ~8% faster than GCC) due to
better register allocation under PGO.
Reviewers: davidxl
Reviewed By: davidxl
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D39980
llvm-svn: 318693
llvm.invariant.group.barrier may accept pointers to arbitrary address space.
This patch let it accept pointers to i8 in any address space and returns
pointer to i8 in the same address space.
Differential Revision: https://reviews.llvm.org/D39973
llvm-svn: 318413
This patch contains more accurate cost of interelaved load\store of stride 2 for the types int64\double on AVX2.
Reviewers: delena, RKSimon, craig.topper, dorit
Reviewed By: dorit
Differential Revision: https://reviews.llvm.org/D40008
llvm-svn: 318385
Summary:
This fixes PR35241.
When using byval, the data is effectively copied as part of the call
anyway, so the pointer returned by the alloca will not be leaked to the
callee and thus there is no reason to issue a warning.
Reviewers: rnk
Reviewed By: rnk
Subscribers: Ka-Ka, llvm-commits
Differential Revision: https://reviews.llvm.org/D40009
llvm-svn: 318279
Summary:
If a compare instruction is same or inverse of the compare in the
branch of the loop latch, then return a constant evolution node.
This shall facilitate computations of loop exit counts in cases
where compare appears in the evolution chain of induction variables.
Will fix PR 34538
Reviewers: sanjoy, hfinkel, junryoungju
Reviewed By: sanjoy, junryoungju
Subscribers: javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D38494
llvm-svn: 318050
Recommit:
This patch contains update of the costs of interleaved loads of v8f32 of stride 3 and 8.
fixed the location of the lit test it works with make check-all.
Differential Revision: https://reviews.llvm.org/D39403
llvm-svn: 317471
reverted my changes will be committed later after fixing the failure
This patch contains update of the costs of interleaved loads of v8f32 of stride 3 and 8.
Differential Revision: https://reviews.llvm.org/D39403
llvm-svn: 317433
This patch contains update of the costs of interleaved loads of v8f32 of stride 3 and 8.
Differential Revision: https://reviews.llvm.org/D39403
llvm-svn: 317432
Summary:
Currently the block frequency analysis is an approximation for irreducible
loops.
The new irreducible loop metadata is used to annotate the irreducible loop
headers with their header weights based on the PGO profile (currently this is
approximated to be evenly weighted) and to help improve the accuracy of the
block frequency analysis for irreducible loops.
This patch is a basic support for this.
Reviewers: davidxl
Reviewed By: davidxl
Subscribers: mehdi_amini, llvm-commits, eraman
Differential Revision: https://reviews.llvm.org/D39028
llvm-svn: 317278
Summary:
Compute the strongly connected components of the CFG and fall back to
use these for blocks that are in loops that are not detected by
LoopInfo when computing loop back-edge and exit branch probabilities.
Reviewers: dexonsmith, davidxl
Subscribers: mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D39385
llvm-svn: 317094
Max backedge taken count is always expected to be a constant; and this is
usually true by construction -- it is a SCEV expression with constant inputs.
However, if the max backedge expression ends up being computed to be a udiv with
a constant zero denominator[0], SCEV does not fold the result to a constant
since there is no constant it can fold it to (SCEV has no representation for
"infinity" or "undef").
However, in computeMaxBECountForLT we already know the denominator is positive,
and thus at least 1; and we can use this fact to avoid dividing by zero.
[0]: We can end up with a constant zero denominator if the signed range of the
stride is more precise than the unsigned range.
llvm-svn: 316615
Summary:
Got asserts in llvm::CastInst::getCastOpcode saying:
`DestBits == SrcBits && "Illegal cast to vector (wrong type or size)"' failed.
Problem seemed to be that llvm::ConstantFoldCastInstruction did
not handle ptrtoint cast of a getelementptr returning a vector
correctly. I assume such situations are quite rare, since the
GEP needs to be considered as a constant value (base pointer
being null).
The solution used here is to simply avoid the constant fold
of ptrtoint when the value is a vector. It is not supported,
and by bailing out we do not fail on assertions later on.
Reviewers: craig.topper, majnemer, davide, filcab, efriedma
Reviewed By: efriedma
Subscribers: efriedma, filcab, llvm-commits
Differential Revision: https://reviews.llvm.org/D38546
llvm-svn: 316430
This patch adds accurate instructions cost.
The formula presents two cases(stride 3 and stride 4) and calculates the cost according to the VF and stride.
Reviewers:
1. delena
2. Farhana
3. zvi
4. dorit
5. Ayal
Differential Revision: https://reviews.llvm.org/D38762
Change-Id: If4cfbd4ac0e63694e8144cb78c7fa34850647ff7
llvm-svn: 316072
Summary:
If a compare instruction is same or inverse of the compare in the
branch of the loop latch, then return a constant evolution node.
Currently scope of evaluation is limited to SCEV computation for
PHI nodes.
This shall facilitate computations of loop exit counts in cases
where compare appears in the evolution chain of induction variables.
Will fix PR 34538
Reviewers: sanjoy, hfinkel, junryoungju
Reviewed By: junryoungju
Subscribers: javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D38494
llvm-svn: 316054
Summary:
This patch teaches SCEV to calculate the maxBECount when the end bound
of the loop can vary. Note that we cannot calculate the exactBECount.
This will only be done when both conditions are satisfied:
1. the loop termination condition is strictly LT.
2. the IV is proven to not overflow.
This provides more information to users of SCEV and can be used to
improve identification of finite loops.
Reviewers: sanjoy, mkazantsev, silviu.baranga, atrick
Reviewed by: mkazantsev
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D38825
llvm-svn: 315683
Significantly reduces performancei (~30%) of gipfeli
(https://github.com/google/gipfeli)
I have not yet managed to reproduce this regression with the open-source
version of the benchmark on github, but will work with others to get a
reproducer to you later today.
llvm-svn: 315680
Summary:
If the pointer width is 32 bits and the calculated GEP offset is
negative, we call APInt::getLimitedValue(), which does a
*zero*-extension of the offset. That's wrong -- we should do an sext.
Fixes a bug introduced in rL314362 and found by Evgeny Astigeevich.
Reviewers: efriedma
Subscribers: sanjoy, javed.absar, llvm-commits, eastig
Differential Revision: https://reviews.llvm.org/D38557
llvm-svn: 314935
Function isLoweredToCall can only accept non-null function pointer, but a function pointer can be null for indirect function call. So check it before calling isLoweredToCall from getInstructionLatency.
Differential Revision: https://reviews.llvm.org/D38204
llvm-svn: 314927
Recommitting r314517 with the fix for handling ConstantExpr.
Original commit message:
Currently, getGEPCost() returns TCC_FREE whenever a GEP is a legal addressing
mode in the target. However, since it doesn't check its actual users, it will
return FREE even in cases where the GEP cannot be folded away as a part of
actual addressing mode. For example, if an user of the GEP is a call
instruction taking the GEP as a parameter, then the GEP may not be folded in
isel.
llvm-svn: 314923
Summary:
When checking if a constant expression is a noop cast we fetched the
IntPtrType by doing DL->getIntPtrType(V->getType())). However, there can
be cases where V doesn't return a pointer, and then getIntPtrType()
triggers an assertion.
Now we pass DataLayout to isNoopCast so the method itself can determine
what the IntPtrType is.
Reviewers: arsenm
Reviewed By: arsenm
Subscribers: wdng, llvm-commits
Differential Revision: https://reviews.llvm.org/D37894
llvm-svn: 314763
This came out of a recent discussion on llvm-dev
(https://reviews.llvm.org/D38042). Currently the Verifier will strip
the debug info metadata from a module if it finds the dbeug info to be
malformed. This feature is very valuable since it allows us to improve
the Verifier by making it stricter without breaking bcompatibility,
but arguable the Verifier pass should not be modifying the IR. This
patch moves the stripping of broken debug info into AutoUpgrade
(UpgradeDebugInfo to be precise), which is a much better location for
this since the stripping of malformed (i.e., produced by older, buggy
versions of Clang) is a (harsh) form of AutoUpgrade.
This change is mostly NFC in nature, the one big difference is the
behavior when LLVM module passes are introducing malformed debug
info. Prior to this patch, a NoAsserts build would have printed a
warning and stripped the debug info, after this patch the Verifier
will report a fatal error. I believe this behavior is actually more
desirable anyway.
Differential Revision: https://reviews.llvm.org/D38184
llvm-svn: 314699
Summary:
Currently, getGEPCost() returns TCC_FREE whenever a GEP is a legal addressing mode in the target.
However, since it doesn't check its actual users, it will return FREE even in cases
where the GEP cannot be folded away as a part of actual addressing mode.
For example, if an user of the GEP is a call instruction taking the GEP as a parameter,
then the GEP may not be folded in isel.
Reviewers: hfinkel, efriedma, mcrosier, jingyue, haicheng
Reviewed By: hfinkel
Subscribers: javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D38085
llvm-svn: 314517
JumpThreading now preserves dominance and lazy value information across the
entire pass. The pass manager is also informed of this preservation with
the goal of DT and LVI being recalculated fewer times overall during
compilation.
This change prepares JumpThreading for enhanced opportunities; particularly
those across loop boundaries.
Patch by: Brian Rzycki <b.rzycki@samsung.com>,
Sebastian Pop <s.pop@samsung.com>
Differential revision: https://reviews.llvm.org/D37528
llvm-svn: 314435
Summary:
This avoids C++ UB if the GEP is weird and the calculation overflows
int64_t, and it's also observable in the cost model's results.
Such GEPs are almost surely not valid pointers, but LLVM nonetheless
generates them sometimes.
Reviewers: sanjoy
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D38337
llvm-svn: 314362
Usually an intrinsic is a simple target instruction, it should have a small latency. A real function call has much larger latency. So handle the intrinsic call in function getInstructionLatency().
Differential Revision: https://reviews.llvm.org/D38104
llvm-svn: 314003
Static alloca usually doesn't generate any machine instructions, so it has 0 cost.
Differential Revision: https://reviews.llvm.org/D37879
llvm-svn: 313410
For instructions that unlikely generate machine instructions, they should also have 0 latency.
Differential Revision: https://reviews.llvm.org/D37833
llvm-svn: 313288
Summary:
LAA can only emit run-time alias checks for pointers with affine AddRec
SCEV expressions. However, non-AddRecExprs can be now be converted to
affine AddRecExprs using SCEV predicates.
This change tries to add the minimal set of SCEV predicates in order
to enable run-time alias checking.
Reviewers: anemet, mzolotukhin, mkuper, sanjoy, hfinkel
Reviewed By: hfinkel
Subscribers: mssimpso, Ayal, dorit, roman.shirokiy, mzolotukhin, llvm-commits
Differential Revision: https://reviews.llvm.org/D17080
llvm-svn: 313012
Current TargetTransformInfo can support throughput cost model and code size model, but sometimes we also need instruction latency cost model in different optimizations. Hal suggested we need a single public interface to query the different cost of an instruction. So I proposed following interface:
enum TargetCostKind {
TCK_RecipThroughput, ///< Reciprocal throughput.
TCK_Latency, ///< The latency of instruction.
TCK_CodeSize ///< Instruction code size.
};
int getInstructionCost(const Instruction *I, enum TargetCostKind kind) const;
All clients should mainly use this function to query the cost of an instruction, parameter <kind> specifies the desired cost model.
This patch also provides a simple default implementation of getInstructionLatency.
The default getInstructionLatency provides latency numbers for only small number of instruction classes, those latency numbers are only reasonable for modern OOO processors. It can be extended in following ways:
Add more detail into this function.
Add getXXXLatency function and call it from here.
Implement target specific getInstructionLatency function.
Differential Revision: https://reviews.llvm.org/D37170
llvm-svn: 312832
Summary:
Add patterns for
fptoui <16 x float> to <16 x i8>
fptoui <16 x float> to <16 x i16>
Reviewers: igorb, delena, craig.topper
Reviewed By: craig.topper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D37505
llvm-svn: 312704
In LLVM IR the following code:
%r = urem <ty> %t, %b
is equivalent to
%q = udiv <ty> %t, %b
%s = mul <ty> nuw %q, %b
%r = sub <ty> nuw %t, %q ; (t / b) * b + (t % b) = t
As UDiv, Mul and Sub are already supported by SCEV, URem can be implemented
with minimal effort using that relation:
%r --> (-%b * (%t /u %b)) + %t
We implement two special cases:
- if %b is 1, the result is always 0
- if %b is a power-of-two, we produce a zext/trunc based expression instead
That is, the following code:
%r = urem i32 %t, 65536
Produces:
%r --> (zext i16 (trunc i32 %a to i16) to i32)
Note that while this helps get a tighter bound on the range analysis and the
known-bits analysis, this exposes some normalization shortcoming of SCEVs:
%div = udim i32 %a, 65536
%mul = mul i32 %div, 65536
%rem = urem i32 %a, 65536
%add = add i32 %mul, %rem
Will usually not be reduced.
llvm-svn: 312329
Summary:
This patch teaches PostDominatorTree about infinite loops. It is built on top of D29705 by @dberlin which includes a very detailed motivation for this change.
What's new is that the patch also teaches the incremental updater how to deal with reverse-unreachable regions and how to properly maintain and verify tree roots. Before that, the incremental algorithm sometimes ended up preserving reverse-unreachable regions after updates that wouldn't appear in the tree if it was constructed from scratch on the same CFG.
This patch makes the following assumptions:
- A sequence of updates should produce the same tree as a recalculating it.
- Any sequence of the same updates should lead to the same tree.
- Siblings and roots are unordered.
The last two properties are essential to efficiently perform batch updates in the future.
When it comes to the first one, we can decide later that the consistency between freshly built tree and an updated one doesn't matter match, as there are many correct ways to pick roots in infinite loops, and to relax this assumption. That should enable us to recalculate postdominators less frequently.
This patch is pretty conservative when it comes to incremental updates on reverse-unreachable regions and ends up recalculating the whole tree in many cases. It should be possible to improve the performance in many cases, if we decide that it's important enough.
That being said, my experiments showed that reverse-unreachable are very rare in the IR emitted by clang when bootstrapping clang. Here are the statistics I collected by analyzing IR between passes and after each removePredecessor call:
```
# functions: 52283
# samples: 337609
# reverse unreachable BBs: 216022
# BBs: 247840796
Percent reverse-unreachable: 0.08716159869015269 %
Max(PercRevUnreachable) in a function: 87.58620689655172 %
# > 25 % samples: 471 ( 0.1395104988314885 % samples )
... in 145 ( 0.27733680163724345 % functions )
```
Most of the reverse-unreachable regions come from invalid IR where it wouldn't be possible to construct a PostDomTree anyway.
I would like to commit this patch in the next week in order to be able to complete the work that depends on it before the end of my internship, so please don't wait long to voice your concerns :).
Reviewers: dberlin, sanjoy, grosser, brzycki, davide, chandlerc, hfinkel
Reviewed By: dberlin
Subscribers: nhaehnle, javed.absar, kparzysz, uabelho, jlebar, hiraditya, llvm-commits, dberlin, david2050
Differential Revision: https://reviews.llvm.org/D35851
llvm-svn: 310940
ValueTracking has to strike a balance when attempting to propagate information
backwards from assumes, because if the information is trivially propagated
backwards, it can appear to LLVM that the assumption is known to be true, and
therefore can be removed.
This is sound (because an assumption has no semantic effect except for causing
UB), but prevents the assume from allowing further optimizations.
The isEphemeralValueOf check exists to try and prevent this issue by not
removing the source of an assumption. This tries to make it a little bit more
general to handle the case of side-effectful instructions, such as in
%0 = call i1 @get_val()
%1 = xor i1 %0, true
call void @llvm.assume(i1 %1)
Patch by Ariel Ben-Yehuda, thanks!
Differential Revision: https://reviews.llvm.org/D36590
llvm-svn: 310859
causing compile time issues.
Moreover, the patch *deleted* the flag in addition to changing the
default, and links to a code review that doesn't even discuss the flag
and just has an update to a Clang test case.
I've followed up on the commit thread to ask for numbers on compile time
at this point, leaving the flag in place until things stabilize, and
pointing at specific code that seems to exhibit excessive compile time
with this patch.
Original commit message for r310583:
"""
[ValueTracking] Enabling ValueTracking patch by default (recommit). Part 2.
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.
""""
llvm-svn: 310816
Add missing SK_PermuteSingleSrc costs for AVX2 targets and earlier, also added some of the simpler SK_PermuteTwoSrc costs to support splitting of SK_PermuteSingleSrc shuffles
llvm-svn: 310632
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: 310583
Pushes the sext onto the operands of a Sub if NSW is present.
Also adds support for propagating the nowrap flags of the
llvm.ssub.with.overflow intrinsic during analysis.
Differential Revision: https://reviews.llvm.org/D35256
llvm-svn: 310117
The patch rL309080 was reverted because it did not clean up the cache on "forgetValue"
method call. This patch re-enables this change, adds the missing check and introduces
two new unit tests that make sure that the cache is cleaned properly.
Differential Revision: https://reviews.llvm.org/D36087
llvm-svn: 309925
This reverts commit r309080. The patch needs to clear out the
ScalarEvolution::ExitLimits cache in forgetMemoizedResults.
I've replied on the commit thread for the patch with more details.
llvm-svn: 309357
This patch adds a cache for computeExitLimit to save compilation time. A lot of examples of
tests that take extensive time to compile are attached to the bug 33494.
Differential Revision: https://reviews.llvm.org/D35827
llvm-svn: 309080
When SCEV calculates product of two SCEVAddRecs from the same loop, it
tries to combine them into one big AddRecExpr. If the sizes of the initial
SCEVs were `S1` and `S2`, the size of their product is `S1 + S2 - 1`, and every
operand of the resulting SCEV is combined from operands of initial SCEV and
has much higher complexity than they have.
As result, if we try to calculate something like:
%x1 = {a,+,b}
%x2 = mul i32 %x1, %x1
%x3 = mul i32 %x2, %x1
%x4 = mul i32 %x3, %x2
...
The size of such SCEVs grows as `2^N`, and the arguments
become more and more complex as we go forth. This leads
to long compilation and huge memory consumption.
This patch sets a limit after which we don't try to combine two
`SCEVAddRecExpr`s into one. By default, max allowed size of the
resulting AddRecExpr is set to 16.
Differential Revision: https://reviews.llvm.org/D35664
llvm-svn: 308847
This adds support for the new 32-bit vector float instructions of z14.
This includes:
- Enabling the instructions for the assembler/disassembler.
- CodeGen for the instructions, including new LLVM intrinsics.
- Scheduler description support for the instructions.
- Update to the vector cost function calculations.
In general, CodeGen support for the new v4f32 instructions closely
matches support for the existing v2f64 instructions.
llvm-svn: 308195
Summary:
NetBSD shell sh(1) does not support ">& /dev/null" construct.
This is bashism. The portable and POSIX solution is to use:
"> /dev/null 2>&1".
This change fixes 22 Unexpected Failures on NetBSD/amd64
for the "check-llvm" target.
Sponsored by <The NetBSD Foundation>
Reviewers: joerg, dim, rnk
Reviewed By: joerg, rnk
Subscribers: rnk, davide, llvm-commits
Differential Revision: https://reviews.llvm.org/D35277
llvm-svn: 307789
The patch was reverted due to a bug. The bug was that if the IV is the 2nd operand of the icmp
instruction, then the "Pred" variable gets swapped and differs from the instruction's predicate.
In this patch we use the original predicate to do the transformation.
Also added a test case that exercises this situation.
Differentian Revision: https://reviews.llvm.org/D35107
llvm-svn: 307477
It seems that the patch was reverted by mistake. Clang testing showed failure of the
MathExtras.SaturatingMultiply test, however I was unable to reproduce the issue on the
fresh code base and was able to confirm that the transformation introduced by the change
does not happen in the said test. This gives a strong confidence that the actual reason of
the failure of the initial patch was somewhere else, and that problem now seems to be
fixed. Re-submitting the change to confirm that.
llvm-svn: 307244
The dependence analysis was returning incorrect information when using the GEPs
to compute dependences. The analysis uses the GEP indices under certain
conditions, but was doing it incorrectly when the base objects of the GEP are
aliases, but pointing to different locations in the same array.
This patch adds another check for the base objects. If the base pointer SCEVs
are not equal, then the dependence analysis should fall back on the path
that uses the whole SCEV for the dependence check. This fixes PR33567.
Differential Revision: https://reviews.llvm.org/D34702
llvm-svn: 307203
This patch seems to cause failures of test MathExtras.SaturatingMultiply on
multiple buildbots. Reverting until the reason of that is clarified.
Differential Revision: https://reviews.llvm.org/rL307126
llvm-svn: 307135
-If there is a IndVar which is known to be non-negative, and there is a value which is also non-negative,
then signed and unsigned comparisons between them produce the same result. Both of those can be
seen in the same loop. To allow other optimizations to simplify them, we turn all instructions like
%c = icmp slt i32 %iv, %b
to
%c = icmp ult i32 %iv, %b
if both %iv and %b are known to be non-negative.
Differential Revision: https://reviews.llvm.org/D34979
llvm-svn: 307126
this patch updates the cost of addq\subq (add\subtract of vectors of 64bits)
based on the performance numbers of SLM arch.
Differential Revision: https://reviews.llvm.org/D33983
llvm-svn: 306974
In rL300494 there was an attempt to deal with excessive compile time on
invocations of getSign/ZeroExtExpr using local caching. This approach only
helps if we request the same SCEV multiple times throughout recursion. But
in the bug PR33431 we see a case where we request different values all the time,
so caching does not help and the size of the cache grows enormously.
In this patch we remove the local cache for this methods and add the recursion
depth limit instead, as we do for arithmetics. This gives us a guarantee that the
invocation sequence is limited and reasonably short.
Differential Revision: https://reviews.llvm.org/D34273
llvm-svn: 306785
Summary:
DFS InOut numbers currently get eagerly computer upon DomTree construction. They are only needed to answer dome dominance queries and they get invalidated by updates and recalculations. Because of that, it is faster in practice to compute them lazily when they are actually needed.
Clang built without this patch takes 6m 45s to boostrap on my machine, and with the patch applied 6m 38s.
Reviewers: sanjoy, dberlin, chandlerc
Reviewed By: dberlin
Subscribers: davide, llvm-commits
Differential Revision: https://reviews.llvm.org/D34296
llvm-svn: 306778
In LLVM IR the following code:
%r = urem <ty> %t, %b
is equivalent to:
%q = udiv <ty> %t, %b
%s = mul <ty> nuw %q, %b
%r = sub <ty> nuw %t, %q ; (t / b) * b + (t % b) = t
As UDiv, Mul and Sub are already supported by SCEV, URem can be
implemented with minimal effort this way.
Note: While SRem and SDiv are also related this way, SCEV does not
provides SDiv yet.
llvm-svn: 306695
The cost of an interleaved access was only implemented for AVX512. For other
X86 targets an overly conservative Base cost was returned, resulting in
avoiding vectorization where it is actually profitable to vectorize.
This patch starts to add costs for AVX2 for most prominent cases of
interleaved accesses (stride 3,4 chars, for now).
Note1: Improvements of up to ~4x were observed in some of EEMBC's rgb
workloads; There is also a known issue of 15-30% degradations on some of these
workloads, associated with an interleaved access followed by type
promotion/widening; the resulting shuffle sequence is currently inefficient and
will be improved by a series of patches that extend the X86InterleavedAccess pass
(such as D34601 and more to follow).
Note 2: The costs in this patch do not reflect port pressure penalties which can
be very dominant in the case of interleaved accesses since most of the shuffle
operations are restricted to a single port. Further tuning, that may incorporate
these considerations, will be done on top of the upcoming improved shuffle
sequences (that is, along with the abovementioned work to extend
X86InterleavedAccess pass).
Differential Revision: https://reviews.llvm.org/D34023
llvm-svn: 306238
Using various methods, BasicAA tries to determine whether two
GetElementPtr memory locations alias when its base pointers are known
to be equal. When none of its heuristics are applicable, it falls back
to PartialAlias to, according to a comment, protect TBAA making a wrong
decision in case of unions and malloc. PartialAlias is not correct,
because a PartialAlias result implies that some, but not all, bytes
overlap which is not necessarily the case here.
AAResults returns the first analysis result that is not MayAlias.
BasicAA is always the first alias analysis. When it returns
PartialAlias, no other analysis is queried to give a more exact result
(which was the intention of returning PartialAlias instead of MayAlias).
For instance, ScopedAA could return a more accurate result.
The PartialAlias hack was introduced in r131781 (and re-applied in
r132632 after some reverts) to fix llvm.org/PR9971 where TBAA returns a
wrong NoAlias result due to a union. A test case for the malloc case
mentioned in the comment was not provided and I don't think it is
affected since it returns an omnipotent char anyway.
Since r303851 (https://reviews.llvm.org/D33328) clang does emit specific
TBAA for unions anymore (but "omnipotent char" instead). Hence, the
PartialAlias workaround is not required anymore.
This patch passes the test-suite and check-llvm/check-clang of a
self-hoisted build on x64.
Reviewed By: hfinkel
Differential Revision: https://reviews.llvm.org/D34318
llvm-svn: 305938
Summary:
After a single predecessor is merged into a basic block, we need to invalidate
the LVI information for the new merged block, when LVI is not provably true for
all of instructions in the new block.
The test cases added show the correct LVI information using the LVI printer
pass.
Reviewers: reames, dberlin, davide, sanjoy
Reviewed by: dberlin, davide
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34108
llvm-svn: 305699
This is a fix for PR33292 that shows a case of extremely long compilation
of a single .c file with clang, with most time spent within SCEV.
We have a mechanism of limiting recursion depth for getAddExpr to avoid
long analysis in SCEV. However, there are calls from getAddExpr to getMulExpr
and back that do not propagate the info about depth. As result of this, a chain
getAddExpr -> ... .> getAddExpr -> getMulExpr -> getAddExpr -> ... -> getAddExpr
can be extremely long, with every segment of getAddExpr's being up to max depth long.
This leads either to long compilation or crash by stack overflow. We face this situation while
analyzing big SCEVs in the test of PR33292.
This patch applies the same limit on max expression depth for getAddExpr and getMulExpr.
Differential Revision: https://reviews.llvm.org/D33984
llvm-svn: 305463
The zero heuristic assumes that integers are more likely positive than negative,
but this also has the effect of assuming that strcmp return values are more
likely positive than negative. Given that for nonzero strcmp return values it's
the ordering of arguments that determines the sign of the result there's no
reason to assume that's true.
Fix this by inspecting the LHS of the compare and using TargetLibraryInfo to
decide if it's strcmp-like, and if so only assume that nonzero is more likely
than zero i.e. strings are more often different than the same. This causes a
slight code generation change in the spec2006 benchmark 403.gcc, but with no
noticeable performance impact. The intent of this patch is to allow better
optimisation of dhrystone on Cortex-M cpus, but currently it won't as there are
also some changes that need to be made to if-conversion.
Differential Revision: https://reviews.llvm.org/D33934
llvm-svn: 304970
Summary:
LVIPrinter pass was previously relying on the LVICache. We now directly call the
the LVI functions which solves the value if the LVI information is not already
available in the cache. This has 2 benefits over the printing of LVI cache:
1. higher coverage (i.e. catches errors) in LVI code when cache value is
invalidated.
2. relies on the core functions, and not dependent on the LVI cache (which may
be scrapped at some point).
It would still catch any cache invalidation errors, since we first go through
the cache.
Reviewers: reames, dberlin, sanjoy
Reviewed by: reames
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D32135
llvm-svn: 304819
Thanks to Galina Kistanova for finding the missing break!
When trying to make a test for this, I realized our logic for handling
extractvalue/insertvalue/... is somewhat broken. This makes constructing
a test-case for this missing break nontrivial.
llvm-svn: 304275
The optimistic delinearization implemented in LLVM detects array sizes by
looking for non-linear products between parameters and induction variables.
In OpenCL code, such products often look like:
A[get_global_id(0) * N + get_global_id(1)]
Hence, the IV is hidden in the get_global_id() call and consequently
delinearization would fail as no induction variable is available that helps
us to identify N as array size parameter.
We now use a very simple heuristic to change this. We assume that each parameter
that comes directly from a function call is a hidden induction variable. As
a result, we can delinearize the access above to:
A[get_global_id(0)][get_global_id(1]
llvm-svn: 304073
The patch rL303730 was reverted because test lsr-expand-quadratic.ll failed on
many non-X86 configs with this patch. The reason of this is that the patch
makes a correctless fix that changes optimizer's behavior for this test.
Without the change, LSR was making an overconfident simplification basing on a
wrong SCEV. Apparently it did not need the IV analysis to do this. With the
change, it chose a different way to simplify (that wasn't so confident), and
this way required the IV analysis. Now, following the right execution path,
LSR tries to make a transformation relying on IV Users analysis. This analysis
is target-dependent due to this code:
// LSR is not APInt clean, do not touch integers bigger than 64-bits.
// Also avoid creating IVs of non-native types. For example, we don't want a
// 64-bit IV in 32-bit code just because the loop has one 64-bit cast.
uint64_t Width = SE->getTypeSizeInBits(I->getType());
if (Width > 64 || !DL.isLegalInteger(Width))
return false;
To make a proper transformation in this test case, the type i32 needs to be
legal for the specified data layout. When the test runs on some non-X86
configuration (e.g. pure ARM 64), opt gets confused by the specified target
and does not use it, rejecting the specified data layout as well. Instead,
it uses some default layout that does not treat i32 as a legal type
(currently the layout that is used when it is not specified does not have
legal types at all). As result, the transformation we expect to happen does
not happen for this test.
This re-enabling patch does not have any source code changes compared to the
original patch rL303730. The only difference is that the failing test is
moved to X86 directory and now has requirement of running on x86 only to comply
with the specified target triple and data layout.
Differential Revision: https://reviews.llvm.org/D33543
llvm-svn: 303971
When folding arguments of AddExpr or MulExpr with recurrences, we rely on the fact that
the loop of our base recurrency is the bottom-lost in terms of domination. This assumption
may be broken by an expression which is treated as invariant, and which depends on a complex
Phi for which SCEVUnknown was created. If such Phi is a loop Phi, and this loop is lower than
the chosen AddRecExpr's loop, it is invalid to fold our expression with the recurrence.
Another reason why it might be invalid to fold SCEVUnknown into Phi start value is that unlike
other SCEVs, SCEVUnknown are sometimes position-bound. For example, here:
for (...) { // loop
phi = {A,+,B}
}
X = load ...
Folding phi + X into {A+X,+,B}<loop> actually makes no sense, because X does not exist and cannot
exist while we are iterating in loop (this memory can be even not allocated and not filled by this moment).
It is only valid to make such folding if X is defined before the loop. In this case the recurrence {A+X,+,B}<loop>
may be existant.
This patch prohibits folding of SCEVUnknown (and those who use them) into the start value of an AddRecExpr,
if this instruction is dominated by the loop. Merging the dominating unknown values is still valid. Some tests that
relied on the fact that some SCEVUnknown should be folded into AddRec's are changed so that they no longer
expect such behavior.
llvm-svn: 303730
This is a re-application of a r303497 that was reverted in r303498.
I thought it had broken a bot when it had not (the breakage did not
go away with the revert).
This change makes the split between the "exact" backedge taken count
and the "maximum" backedge taken count a bit more obvious. Both of
these are upper bounds on the number of times the loop header
executes (since SCEV does not account for most kinds of abnormal
control flow), but the latter is guaranteed to be a constant.
There were a few places where the max backedge taken count *was* a
non-constant; I've changed those to compute constants instead.
At this point, I'm not sure if the constant max backedge count can be
computed by calling `getUnsignedRange(Exact).getUnsignedMax()` without
losing precision. If it can, we can simplify even further by making
`getMaxBackedgeTakenCount` a thin wrapper around
`getBackedgeTakenCount` and `getUnsignedRange`.
llvm-svn: 303531
This change makes the split between the "exact" backedge taken count
and the "maximum" backedge taken count a bit more obvious. Both of
these are upper bounds on the number of times the loop header
executes (since SCEV does not account for most kinds of abnormal
control flow), but the latter is guaranteed to be a constant.
There were a few places where the max backedge taken count *was* a
non-constant; I've changed those to compute constants instead.
At this point, I'm not sure if the constant max backedge count can be
computed by calling `getUnsignedRange(Exact).getUnsignedMax()` without
losing precision. If it can, we can simplify even further by making
`getMaxBackedgeTakenCount` a thin wrapper around
`getBackedgeTakenCount` and `getUnsignedRange`.
llvm-svn: 303497
The probability of edge coming to unreachable block should be as low as possible.
The change reduces the probability to minimal value greater than zero.
The bug https://bugs.llvm.org/show_bug.cgi?id=32214 show the example when
the probability of edge coming to unreachable block is greater than for edge
coming to out of the loop and it causes incorrect loop rotation.
Please note that with this change the behavior of unreachable heuristic is a bit different
than others. Specifically, before this change the sum of probabilities
coming to unreachable blocks have the same weight for all branches
(it was just split over all edges of this block coming to unreachable blocks).
With this change it might be slightly different but not to much due to probability of
taken branch to unreachable block is really small.
Reviewers: chandlerc, sanjoy, vsk, congh, junbuml, davidxl, dexonsmith
Reviewed By: chandlerc, dexonsmith
Subscribers: reames, llvm-commits
Differential Revision: https://reviews.llvm.org/D30633
llvm-svn: 303327
The existing sorting order in defined CompareSCEVComplexity sorts AddRecExprs
by loop depth, but does not pay attention to dominance of loops. This can
lead us to the following buggy situation:
for (...) { // loop1
op1 = {A,+,B}
}
for (...) { // loop2
op2 = {A,+,B}
S = add op1, op2
}
In this case there is no guarantee that in operand list of S the op2 comes
before op1 (loop depth is the same, so they will be sorted just
lexicographically), so we can incorrectly treat S as a recurrence of loop1,
which is wrong.
This patch changes the sorting logic so that it places the dominated recs
before the dominating recs. This ensures that when we pick the first recurrency
in the operands order, it will be the bottom-most in terms of domination tree.
The attached test set includes some tests that produce incorrect SCEV
estimations and crashes with oldlogic.
Reviewers: sanjoy, reames, apilipenko, anna
Reviewed By: sanjoy
Subscribers: llvm-commits, mzolotukhin
Differential Revision: https://reviews.llvm.org/D33121
llvm-svn: 303148
Update a few tests to use llvm.masked.load/store instead of arm neon
vector loads and stores, and move the tests that are actually specific
to those arm intrinsics to their own files. This lets us mark the
tests that use target specific intrinsics as requiring those targets.
llvm-svn: 302972
This is a follow up patch for https://reviews.llvm.org/rL300440
to address a comment.
To make implementation to be consistent with other cases we just
ignore the remainder after distribution of remaining probability between
reachable edges.
If we reduced the probability of some edges coming to unreachable
blocks we should distribute the remaining part across other edges
coming to reachable blocks to satisfy the condition that sum of all
probabilities should be equal to one. If this remaining part is not
divided by number of "reachable" edges then we get this remainder.
This remainder probability should be pretty small. Other cases just ignore
if the sum of probabilities is not equal to one so we do the same.
Reviewers: chandlerc, sanjoy, vsk, junbuml, reames
Reviewed By: reames
Subscribers: reames, llvm-commits
Differential Revision: https://reviews.llvm.org/D32124
llvm-svn: 302883
The AArch64 instruction set has a few "widening" instructions (e.g., uaddl,
saddl, uaddw, etc.) that take one or more doubleword operands and produce
quadword results. The operands are automatically sign- or zero-extended as
appropriate. However, in LLVM IR, these extends are explicit. This patch
updates TTI to consider these widening instructions as single operations whose
cost is attached to the arithmetic instruction. It marks extends that are part
of a widening operation "free" and applies a sub-target specified overhead
(zero by default) to the arithmetic instructions.
Differential Revision: https://reviews.llvm.org/D32706
llvm-svn: 302582
Account for subvector extraction/insertion, helps prevent the vectorizers from selecting 256-bit vectors that will have to be split anyhow on AVX1 targets.
llvm-svn: 302378
Summary:
The existing implementation creates a symbolic SCEV expression every
time we analyze a phi node and then has to remove it, when the analysis
is finished. This is very expensive, and in most of the cases it's also
unnecessary. According to the data I collected, ~60-70% of analyzed phi
nodes (measured on SPEC) have the following form:
PN = phi(Start, OP(Self, Constant))
Handling such cases separately significantly speeds this up.
Reviewers: sanjoy, pete
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D32663
llvm-svn: 302096
Fixes PR31789 - When loop-vectorize tries to use these intrinsics for a
non-default address space pointer we fail with a "Calling a function with a
bad singature!" assertion. This patch solves this by adding the 'vector of
pointers' argument as an overloaded type which will determine the address
space.
Differential revision: https://reviews.llvm.org/D31490
llvm-svn: 302018
In cases where an instruction (a call site, say) is RAUW'ed with some
other value (this is possible via the `returned` attribute, for
instance), we want the slot in UnknownInsts to point to the original
Instruction we wanted to track, not the value it got replaced by.
Fixes PR32587.
This relands r301426.
llvm-svn: 301814
Summary:
programUndefinedIfPoison makes more sense, given what the function
does; and I'm about to add a function with a name similar to
isKnownNotFullPoison (so do the rename to avoid confusion).
Reviewers: broune, majnemer, bjarke.roune
Reviewed By: broune
Subscribers: mcrosier, llvm-commits, mzolotukhin
Differential Revision: https://reviews.llvm.org/D30444
llvm-svn: 301776
Commits were:
"Use WeakVH instead of WeakTrackingVH in AliasSetTracker's UnkownInsts"
"Add a new WeakVH value handle; NFC"
"Rename WeakVH to WeakTrackingVH; NFC"
The changes assumed pointers are 8 byte aligned on all architectures.
llvm-svn: 301429
Summary:
In cases where an instruction (a call site, say) is RAUW'ed with some
other value (this is possible via the `returned` attribute, amongst
other things), we want the slot in UnknownInsts to point to the
original Instruction we wanted to track, not the value it got replaced
by.
Fixes PR32587.
Reviewers: davide
Subscribers: mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D32268
llvm-svn: 301426
Summary:
In a previous change I changed SCEV's normalization / denormalization
to work with non-affine add recs. So the bailout in IVUsers can be
removed.
Reviewers: atrick, efriedma
Reviewed By: atrick
Subscribers: davide, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D32105
llvm-svn: 301298
There have been multiple reports of this causing problems: a
compile-time explosion on the LLVM testsuite, and a stack
overflow for an opencl kernel.
llvm-svn: 300928
Use haveNoCommonBitsSet to figure out whether an "or" instruction
is equivalent to addition. This handles more cases than just
checking for a constant on the RHS.
Differential Revision: https://reviews.llvm.org/D32239
llvm-svn: 300746
Metadata potentially is more precise than any heuristics we use, so
it makes sense to use first metadata info if it is available. However it makes
sense to examine it against other strong heuristics like unreachable one.
If edge coming to unreachable block has higher probability then it is expected
by unreachable heuristic then we use heuristic and remaining probability is
distributed among other reachable blocks equally.
An example where metadata might be more strong then unreachable heuristic is
as follows: it is possible that there are two branches and for the branch A
metadata says that its probability is (0, 2^25). For the branch B
the probability is (1, 2^25).
So the expectation is that first edge of B is hotter than first edge of A
because first edge of A did not executed at least once.
If first edge of A points to the unreachable block then using the unreachable
heuristics we'll set the probability for A to (1, 2^20) and now edge of A
becomes hotter than edge of B.
This is unexpected behavior.
This fixed the biggest part of https://bugs.llvm.org/show_bug.cgi?id=32214
Reviewers: sanjoy, junbuml, vsk, chandlerc
Reviewed By: chandlerc
Subscribers: llvm-commits, reames, davidxl
Differential Revision: https://reviews.llvm.org/D30631
llvm-svn: 300440
Summary:
* Add a bitreverse case in the demanded bits analysis pass.
* Add tests for the bitreverse (and bswap) intrinsic in the
demanded bits pass.
* Add a test case to the BDCE tests: that manipulations to
high-order bits are eliminated once the bits are reversed
and then right-shifted.
Reviewers: mkuper, jmolloy, hfinkel, trentxintong
Reviewed By: jmolloy
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D31857
llvm-svn: 300215
Summary:
Readnone attribute would cause CSE of two barriers with
the same argument, which is invalid by example:
struct Base {
virtual int foo() { return 42; }
};
struct Derived1 : Base {
int foo() override { return 50; }
};
struct Derived2 : Base {
int foo() override { return 100; }
};
void foo() {
Base *x = new Base{};
new (x) Derived1{};
int a = std::launder(x)->foo();
new (x) Derived2{};
int b = std::launder(x)->foo();
}
Here 2 calls of std::launder will produce @llvm.invariant.group.barrier,
which would be merged into one call, causing devirtualization
to devirtualize second call into Derived1::foo() instead of
Derived2::foo()
Reviewers: chandlerc, dberlin, hfinkel
Subscribers: llvm-commits, rsmith, amharc
Differential Revision: https://reviews.llvm.org/D31531
llvm-svn: 300101
getArithmeticInstrCost(), getShuffleCost(), getCastInstrCost(),
getCmpSelInstrCost(), getVectorInstrCost(), getMemoryOpCost(),
getInterleavedMemoryOpCost() implemented.
Interleaved access vectorization enabled.
BasicTTIImpl::getCastInstrCost() improved to check for legal extending loads,
in which case the cost of the z/sext instruction becomes 0.
Review: Ulrich Weigand, Renato Golin.
https://reviews.llvm.org/D29631
llvm-svn: 300052
Collection of PostDominatedByUnreachable and PostDominatedByColdCall have been
split out of heuristics itself. Update of the data happens now for each basic
block (before update for PostDominatedByColdCall might be skipped if
unreachable or matadata heuristic handled this basic block).
This separation allows re-ordering of heuristics without loosing
the post-domination information.
Reviewers: sanjoy, junbuml, vsk, chandlerc, reames
Reviewed By: chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D31701
llvm-svn: 300029
Analysis, it has Analysis passes, and once NewGVN is made an Analysis,
this removes the cross dependency from Analysis to Transform/Utils.
NFC.
llvm-svn: 299980
The patch rL298481 was reverted due to crash on clang-with-lto-ubuntu build.
The reason of the crash was type mismatch between either a or b and RHS in the following situation:
LHS = sext(a +nsw b) > RHS.
This is quite rare, but still possible situation. Normally we need to cast all {a, b, RHS} to their widest type.
But we try to avoid creation of new SCEV that are not constants to avoid initiating recursive analysis that
can take a lot of time and/or cache a bad value for iterations number. To deal with this, in this patch we
reject this case and will not try to analyze it if the type of sum doesn't match with the type of RHS. In this
situation we don't need to create any non-constant SCEVs.
This patch also adds an assertion to the method IsProvedViaContext so that we could fail on it and not
go further into range analysis etc (because in some situations these analyzes succeed even when the passed
arguments have wrong types, what should not normally happen).
The patch also contains a fix for a problem with too narrow scope of the analysis caused by wrong
usage of predicates in recursive invocations.
The regression test on the said failure: test/Analysis/ScalarEvolution/implied-via-addition.ll
Reviewers: reames, apilipenko, anna, sanjoy
Reviewed By: sanjoy
Subscribers: mzolotukhin, mehdi_amini, llvm-commits
Differential Revision: https://reviews.llvm.org/D31238
llvm-svn: 299205
The patch rL298481 was reverted due to crash on clang-with-lto-ubuntu build.
The reason of the crash was type mismatch between either a or b and RHS in the following situation:
LHS = sext(a +nsw b) > RHS.
This is quite rare, but still possible situation. Normally we need to cast all {a, b, RHS} to their widest type.
But we try to avoid creation of new SCEV that are not constants to avoid initiating recursive analysis that
can take a lot of time and/or cache a bad value for iterations number. To deal with this, in this patch we
reject this case and will not try to analyze it if the type of sum doesn't match with the type of RHS. In this
situation we don't need to create any non-constant SCEVs.
This patch also adds an assertion to the method IsProvedViaContext so that we could fail on it and not
go further into range analysis etc (because in some situations these analyzes succeed even when the passed
arguments have wrong types, what should not normally happen).
The patch also contains a fix for a problem with too narrow scope of the analysis caused by wrong
usage of predicates in recursive invocations.
The regression test on the said failure: test/Analysis/ScalarEvolution/implied-via-addition.ll
llvm-svn: 298690
Given below case:
%y = shl %x, n
%z = ashr %y, m
when n = m, SCEV models it as sext(trunc(x)). This patch tries to handle
the case where n > m by using sext(mul(trunc(x), 2^(n-m)))) as the SCEV
expression.
llvm-svn: 298631
Summary:
Adding a printer pass for printing the LVI cache values after transformations
that use LVI.
This will help us in identifying cases where LVI
invariants are violated, or transforms that leave LVI in an incorrect state.
Right now, I have added two test cases to show that the printer pass is working.
I will be adding more test cases in a later change, once this change is
checked in upstream.
Reviewers: reames, dberlin, sanjoy, apilipenko
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D30790
llvm-svn: 298542
This patch allows SCEV predicate analysis to prove implication of some expression predicates
from context predicates related to arguments of those expressions.
It introduces three new rules:
For addition:
(A >X && B >= 0) || (B >= 0 && A > X) ===> (A + B) > X.
For division:
(A > X) && (0 < B <= X + 1) ===> (A / B > 0).
(A > X) && (-B <= X < 0) ===> (A / B >= 0).
Using these rules, SCEV is able to prove facts like "if X > 1 then X / 2 > 0".
They can also be combined with the same context, to prove more complex expressions like
"if X > 1 then X/2 + 1 > 1".
Diffirential Revision: https://reviews.llvm.org/D30887
Reviewed by: sanjoy
llvm-svn: 298481
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
After the loop unroll threshold was increased in r295538, very
large constant expressions can be created. This prevents them
from having to be recursively scanned, leading to a compile
time blow-up.
Differential Revision: https://reviews.llvm.org/D30689
llvm-svn: 298356
If loop bound containing calculations like min(a,b), the Scalar
Evolution API getSmallConstantTripMultiple returns 4294967295 "-1"
as the trip multiple. The problem is that, SCEV use -1 * umax to
represent umin. The multiple constant -1 was returned, and the logic
of guarding against huge trip counts was skipped. Because -1 has 32
active bits.
The fix attempt to factor more general cases. First try to get the
greatest power of two divisor of trip count expression. In case
overflow happens, the trip count expression is still divisible by the
greatest power of two divisor returned. Returns 1 if not divisible by 2.
Patch by Huihui Zhang <huihuiz@codeaurora.org>
Differential Revision: https://reviews.llvm.org/D30840
llvm-svn: 298301
Summary:
This approach has two major advantages over the existing one:
1. We don't need to extend bitwidth in our computations. Extending
bitwidth is a big issue for compile time as we often end up working with
APInts wider than 64bit, which is a slow case for APInt.
2. When we zero extend a wrapped range, we lose some information (we
replace the range with [0, 1 << src bit width)). Thus, avoiding such
extensions better preserves information.
Correctness testing:
I ran 'ninja check' with assertions that the new implementation of
getRangeForAffineAR gives the same results as the old one (this
functionality is not present in this patch). There were several failures
- I inspected them manually and found out that they all are caused by
the fact that we're returning more accurate results now (see bullet (2)
above).
Without such assertions 'ninja check' works just fine, as well as
SPEC2006.
Compile time testing:
CTMark/Os:
- mafft/pairlocalalign -16.98%
- tramp3d-v4/tramp3d-v4 -12.72%
- lencod/lencod -11.51%
- Bullet/bullet -4.36%
- ClamAV/clamscan -3.66%
- 7zip/7zip-benchmark -3.19%
- sqlite3/sqlite3 -2.95%
- SPASS/SPASS -2.74%
- Average -5.81%
Performance testing:
The changes are expected to be neutral for runtime performance.
Reviewers: sanjoy, atrick, pete
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D30477
llvm-svn: 297992
getIntrinsicInstrCost() used to only compute scalarization cost based on types.
This patch improves this so that the actual arguments are checked when they are
available, in order to handle only unique non-constant operands.
Tests updates:
Analysis/CostModel/X86/arith-fp.ll
Transforms/LoopVectorize/AArch64/interleaved_cost.ll
Transforms/LoopVectorize/ARM/interleaved_cost.ll
The improvement in getOperandsScalarizationOverhead() to differentiate on
constants made it necessary to update the interleaved_cost.ll tests even
though they do not relate to intrinsics.
Review: Hal Finkel
https://reviews.llvm.org/D29540
llvm-svn: 297705
When the array indexes are all determined by GVN to be constants,
a call is made to constant-folding to optimize/simplify the address
computation.
The constant-folding, however, makes a mistake in that it sometimes reads
back stale Idxs instead of NewIdxs, that it re-computed in previous iteration.
This leads to incorrect addresses coming out of constant-folding to GEP.
A test case is included. The error is only triggered when indexes have particular
patterns that the stale/new index updates interplay matters.
Reviewers: Daniel Berlin
Differential Revision: https://reviews.llvm.org/D30642
llvm-svn: 297317
While working on improvements to region info analysis, this test case caused an
incorrect region bb2 => bb3 to be detected.
Reviewers: grosser
Contributed-by: Nandini Singhal <cs15mtech01004@iith.ac.in>
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D30652
llvm-svn: 297014
While working on improvements to the region info analysis, this test case caused
an incorrect region 1 => 2 to be detected. It is incorrect because entry has an
outgoing edge to 3. This is interesting because 1 dom 2 and 2 pdom 1, which
should have been enough to prevent incoming forward edges into the region and
outgoing forward edges from the region.
Reviewers: grosser
Subscribers: llvm-commits
Contributed-by: Nandini Singhal <cs15mtech01004@iith.ac.in>
Differential Revision: https://reviews.llvm.org/D30603
llvm-svn: 296988
and also "clang-format GenericDomTreeConstruction.h, since the current
formatting makes it look like their is a bug in the loop indentation, and there
is not"
This reverts commit r296535.
There are still some open design questions which I would like to discuss. I
revert this for Daniel (who gave the OK), as he is on vacation.
llvm-svn: 296812
Summary:
Currently, our post-dom tree tries to ignore and remove the effects of
infinite loops. It fails miserably at this, because it tries to do it
ahead of time, and thus can only detect self-loops, and any other type
of infinite loop, it pretends doesn't exist at all.
This can, in a bunch of cases, lead to wrong answers and a completely
empty post-dom tree.
Wrong answer:
```
declare void foo()
define internal void @f() {
entry:
br i1 undef, label %bb35, label %bb3.i
bb3.i:
call void @foo()
br label %bb3.i
bb35.loopexit3:
br label %bb35
bb35:
ret void
}
```
We get:
```
Inorder PostDominator Tree:
[1] <<exit node>> {0,7}
[2] %bb35 {1,6}
[3] %bb35.loopexit3 {2,3}
[3] %entry {4,5}
```
This is a trivial modification of the testcase for PR 6047
Note that we pretend bb3.i doesn't exist.
We also pretend that bb35 post-dominates entry.
While it's true that it does not exit in a theoretical sense, it's not
really helpful to try to ignore the effect and pretend that bb35
post-dominates entry. Worse, we pretend the infinite loop does
nothing (it's usually considered a side-effect), and doesn't even
exist, even when it calls a function. Sadly, this makes it impossible
to use when you are trying to move code safely. All compilers also
create virtual or real single exit nodes (including us), and connect
infinite loops there (which this patch does). In fact, others have
worked around our behavior here, to the point of building their own
post-dom trees:
https://zneak.github.io/fcd/2016/02/17/structuring.html and pointing
out the region infrastructure is near-useless for them with postdom in
this state :(
Completely empty post-dom tree:
```
define void @spam() #0 {
bb:
br label %bb1
bb1: ; preds = %bb1, %bb
br label %bb1
bb2: ; No predecessors!
ret void
}
```
Printing analysis 'Post-Dominator Tree Construction' for function 'foo':
=============================--------------------------------
Inorder PostDominator Tree:
[1] <<exit node>> {0,1}
:(
(note that even if you ignore the effects of infinite loops, bb2
should be present as an exit node that post-dominates nothing).
This patch changes post-dom to properly handle infinite loops and does
root finding during calculation to prevent empty tress in such cases.
We match gcc's (and the canonical theoretical) behavior for infinite
loops (find the backedge, connect it to the exit block).
Testcases coming as soon as i finish running this on a ton of random graphs :)
Reviewers: chandlerc, davide
Subscribers: bryant, llvm-commits
Differential Revision: https://reviews.llvm.org/D29705
llvm-svn: 296535
Summary:
Motivation: fix PR31181 without regression (the actual fix is still in
progress). However, the actual content of PR31181 is not relevant
here.
This change makes poison propagation more aggressive in the following
cases:
1. poision * Val == poison, for any Val. In particular, this changes
existing intentional and documented behavior in these two cases:
a. Val is 0
b. Val is 2^k * N
2. poison << Val == poison, for any Val
3. getelementptr is poison if any input is poison
I think all of these are justified (and are axiomatically true in the
new poison / undef model):
1a: we need poison * 0 to be poison to allow transforms like these:
A * (B + C) ==> A * B + A * C
If poison * 0 were 0 then the above transform could not be allowed
since e.g. we could have A = poison, B = 1, C = -1, making the LHS
poison * (1 + -1) = poison * 0 = 0
and the RHS
poison * 1 + poison * -1 = poison + poison = poison
1b: we need e.g. poison * 4 to be poison since we want to allow
A * 4 ==> A + A + A + A
If poison * 4 were a value with all of their bits poison except the
last four; then we'd not be able to do this transform since then if A
were poison the LHS would only be "partially" poison while the RHS
would be "full" poison.
2: Same reasoning as (1b), we'd like have the following kinds
transforms be legal:
A << 1 ==> A + A
Reviewers: majnemer, efriedma
Subscribers: mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D30185
llvm-svn: 295809
Newer ppc supports unaligned memory access, it reduces the cost of unaligned memory access significantly. This patch handles this case in PPCTTIImpl::getMemoryOpCost.
This patch fixes pr31492.
Differential Revision: https://reviews.llvm.org/D28630
This is resubmit of r292680, which was reverted by r293092. The internal application failures were actually caused by a source code bug.
llvm-svn: 295506
proven larger than the loop-count
This fixes PR31098: Try to resolve statically data-dependences whose
compile-time-unknown distance can be proven larger than the loop-count,
instead of resorting to runtime dependence checking (which are not always
possible).
For vectorization it is sufficient to prove that the dependence distance
is >= VF; But in some cases we can prune unknown dependence distances early,
and even before selecting the VF, and without a runtime test, by comparing
the distance against the loop iteration count. Since the vectorized code
will be executed only if LoopCount >= VF, proving distance >= LoopCount
also guarantees that distance >= VF. This check is also equivalent to the
Strong SIV Test.
Reviewers: mkuper, anemet, sanjoy
Differential Revision: https://reviews.llvm.org/D28044
llvm-svn: 294892
Make SolveLinEquationWithOverflow take the start as a SCEV, so we can
solve more cases. With that implemented, get rid of the special case
for powers of two.
The additional functionality probably isn't particularly useful,
but it might help a little for certain cases involving pointer
arithmetic.
Differential Revision: https://reviews.llvm.org/D28884
llvm-svn: 293576
This is fixing pr31761: BasicAA is deducing NoAlias
on the result of the GEP if the base pointer is itself NoAlias.
This is possible only if the NoAlias on the base pointer is
deduced with a non-sized query: this should guarantee that
the pointers are belonging to different memory allocation
and that the GEP can't legally jump from one to another.
Differential Revision: https://reviews.llvm.org/D29216
llvm-svn: 293293
Simon Pilgrim