If we have more then 2 shuffle ops to combine, try to use combineX86ShuffleChainWithExtract to see if some are from the same super vector.
llvm-svn: 365050
iff the number of elements doesn't change.
This gets around an issue with combineX86ShuffleChain not being able to hint which domain is preferred for shuffles that can be done with either.
Fixes regression introduced in rL365041
llvm-svn: 365044
This better accounts for the cost/benefit of removing extract_subvectors from the shuffle and will be more useful in future patches.
The vpermq predicate regression will be fixed shortly.
llvm-svn: 365041
Summary:
This is the backend part of [[ https://bugs.llvm.org/show_bug.cgi?id=42457 | PR42457 ]].
In middle-end, we'd want to prefer the form with two adds - D63992,
but as this diff shows, not every target will prefer that pattern.
Out of 4 targets for which i added tests all seem to be ok with inc-of-add for scalars,
but only X86 prefer that same pattern for vectors.
Here i'm adding a new TLI hook, always defaulting to the inc-of-add,
but adding AArch64,ARM,PowerPC overrides to prefer inc-of-add only for scalars.
Reviewers: spatel, RKSimon, efriedma, t.p.northover, hfinkel
Reviewed By: efriedma
Subscribers: nemanjai, javed.absar, kristof.beyls, kbarton, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64090
llvm-svn: 365010
Mac Catalyst is a new MachO platform in macOS Catalina.
It always uses the build_version MachO load command.
Differential Revision: https://reviews.llvm.org/D64107
llvm-svn: 364981
Don't use APInt::getZExtValue() if you can avoid it - eventually someone will call it with i128 or something that doesn't fit into 64-bits.
In this case it was completely superfluous as we'd moved the rest of the code to always use APInt.
Fixes the <1 x i128> addition bug in PR42486
llvm-svn: 364953
Similar for (V)MOVSD. Ultimately, I'd like to see about folding
scalar_to_vector+load to vzload. Which would select as (V)MOVSSrm
so this is closer to that.
llvm-svn: 364948
I initially committed it with --check-prefix instead of --check-prefixes
(again, shame on me, and utils/update_*.py not complaining!)
and did not have a moment to understand the failure,
so i reverted it initially in rL64939.
llvm-svn: 364945
As it is pointed out in https://reviews.llvm.org/D63992,
before we get to pick canonical variant in middle-end
we should ensure best codegen in backend.
llvm-svn: 364930
These instructions only read 64-bits of memory so we shouldn't
allow a full vector width load to be pattern matched in case it
is marked volatile.
Instead allow vzload or scalar_to_vector+load.
Also add a DAG combine to turn full vector loads into vzload when
used by one of these instructions if the load isn't volatile.
This fixes another case for PR42079
llvm-svn: 364838
The function findPotentialBlockers may consider debug info instructions as
potential blockers and may stop searching for a store-load pair prematurely.
This patch corrects this and tests the cases where the store is separated
from the load by more than InspectionLimit debug instructions.
Patch by Chris Dawson.
Differential Revision: https://reviews.llvm.org/D62408
llvm-svn: 364829
We had a bunch of vector size legality checks for the source type
based on feature flags, but we didn't check the destination type at
all beyond ensuring that it was a "simple" type. But this allowed
the destination to be i128 which isn't legal.
This commit changes the code to use TLI's isTypeLegal logic in
place of the all the subtarget checks. Then additionally checks
that the source and dest are vectors.
Fixes 42452
llvm-svn: 364729
But only when the load isn't volatile.
This improves load folding during isel where we only have vzload
and scalar_to_vector+load patterns. We can't have full vector load
isel patterns for the same volatile load issue.
Also add some missing masked cvtsi2fp/cvtui2fp with vzload patterns.
llvm-svn: 364728
We already had patterns that used scalar_to_vector+load. But we can
also have a vzload.
Found while investigating combining scalar_to_vector+load to vzload.
llvm-svn: 364726
We were requiring that both shuffle operands were EXTRACT_SUBVECTORs, but we can relax this to only require one of them to be.
Also, we shouldn't bother attempting this if both operands are from the lowest subvector (or not EXTRACT_SUBVECTOR at all).
llvm-svn: 364644
Summary:
I'm submitting a new revision since i don't understand how to reclaim/reopen/take over the existing one, D50222.
There is no such action in "Add Action" menu...
This implements an optimization described in Hacker's Delight 10-17: when `C` is constant,
the result of `X % C == 0` can be computed more cheaply without actually calculating the remainder.
The motivation is discussed here: https://bugs.llvm.org/show_bug.cgi?id=35479.
This is a recommit, the original commit rL364563 was reverted in rL364568
because test-suite detected miscompile - the new comparison constant 'Q'
was being computed incorrectly (we divided by `D0` instead of `D`).
Original patch D50222 by @hermord (Dmytro Shynkevych)
Notes:
- In principle, it's possible to also handle the `X % C1 == C2` case, as discussed on bugzilla.
This seems to require an extra branch on overflow, so I refrained from implementing this for now.
- An explicit check for when the `REM` can be reduced to just its LHS is included:
the `X % C` == 0 optimization breaks `test1` in `test/CodeGen/X86/jump_sign.ll` otherwise.
I hadn't managed to find a better way to not generate worse output in this case.
- The `test/CodeGen/X86/jump_sign.ll` regresses, and is being fixed by a followup patch D63390.
Reviewers: RKSimon, craig.topper, spatel, hermord, xbolva00
Reviewed By: RKSimon, xbolva00
Subscribers: dexonsmith, kristina, xbolva00, javed.absar, llvm-commits, hermord
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63391
llvm-svn: 364600
The fold (D63391) uses multiplicativeInverse(),
but it is not guaranteed to always succeed,
and '100' appears to be one of the problematic values.
llvm-svn: 364578
Summary:
I'm submitting a new revision since i don't understand how to reclaim/reopen/take over the existing one, D50222.
There is no such action in "Add Action" menu...
Original patch D50222 by @hermord (Dmytro Shynkevych)
This implements an optimization described in Hacker's Delight 10-17: when `C` is constant,
the result of `X % C == 0` can be computed more cheaply without actually calculating the remainder.
The motivation is discussed here: https://bugs.llvm.org/show_bug.cgi?id=35479.
Original patch author: @hermord (Dmytro Shynkevych)!
Notes:
- In principle, it's possible to also handle the `X % C1 == C2` case, as discussed on bugzilla.
This seems to require an extra branch on overflow, so I refrained from implementing this for now.
- An explicit check for when the `REM` can be reduced to just its LHS is included:
the `X % C` == 0 optimization breaks `test1` in `test/CodeGen/X86/jump_sign.ll` otherwise.
I hadn't managed to find a better way to not generate worse output in this case.
- The `test/CodeGen/X86/jump_sign.ll` regresses, and is being fixed by a followup patch D63390.
Reviewers: RKSimon, craig.topper, spatel, hermord, xbolva00
Reviewed By: RKSimon, xbolva00
Subscribers: xbolva00, javed.absar, llvm-commits, hermord
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63391
llvm-svn: 364563
While lowering calls, collect info about registers that forward arguments
into following function frame. We store such info into the MachineFunction
of the call. This is used very late when dumping DWARF info about
call site parameters.
([9/13] Introduce the debug entry values.)
Co-authored-by: Ananth Sowda <asowda@cisco.com>
Co-authored-by: Nikola Prica <nikola.prica@rt-rk.com>
Co-authored-by: Ivan Baev <ibaev@cisco.com>
Differential Revision: https://reviews.llvm.org/D60715
llvm-svn: 364516
This patch rewrites the loop iteration to only visit every other element starting with element 0. And we work on the "even" element and "next" element at the same time. The "First" logic has been moved to the bottom of the loop and doesn't run on every element. I believe it could create dangling nodes previously since we didn't check if we were going to use SCALAR_TO_VECTOR for the first insertion. I got rid of the "First" variable and just do a null check on V which should be equivalent. We also no longer use undef as the starting V for vectors with no zeroes to avoid false dependencies. This matches v8i16.
I've changed all the extends and OR operations to use MVT::i32 since that's what they'll be promoted to anyway. I've tried to use zero_extend only when necessary and use any_extend otherwise. This resulted in some improvements in tests where we are now able to promote aligned (i32 (extload i8)) to a 32-bit load.
Differential Revision: https://reviews.llvm.org/D63702
llvm-svn: 364469
Create a per-byte shuffle mask based on the computeKnownBits from each operand - if for each byte we have a known zero (or both) then it can be safely blended.
Fixes PR41545
llvm-svn: 364458
Summary:
The one thing of note here is that the 'bitwidth' constant (32/64) was previously pessimistic.
Given `x & (-1 >> (C - z))`, we were taking `C` to be `bitwidth(x)`, but in reality
we want `(-1 >> (C - z))` pattern to mean "low z bits must be all-ones".
And for that, `C` should be `bitwidth(-1 >> (C - z))`, i.e. of the shift operation itself.
Last pattern D does not seem to exhibit any of these truncation issues.
Although it has the opposite problem - if we extract low bits (no shift) from i64,
and then truncate to i32, then we fail to shrink this 64-bit extraction into 32-bit extraction.
Reviewers: RKSimon, craig.topper, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62806
llvm-svn: 364419
Summary:
(Not so) boringly identical to pattern a (D62786)
Not yet sure how do deal with the last pattern c.
Reviewers: RKSimon, craig.topper, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62793
llvm-svn: 364418
Summary:
Finally tying up loose ends here.
The problem is quite simple:
If we have pattern `(x >> start) & (1 << nbits) - 1`,
and then truncate the result, that truncation will be propagated upwards,
into the `and`. And that isn't currently handled.
I'm only fixing pattern `a` here,
the same fix will be needed for patterns `b`/`c` too.
I *think* this isn't missing any extra legality checks,
since we only look past truncations. Similary, i don't think
we can get any other truncation there other than i64->i32.
Reviewers: craig.topper, RKSimon, spatel
Reviewed By: craig.topper
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62786
llvm-svn: 364417
This allows later passes (in particular InstCombine) to optimize more
cases.
One that's important to us is `memcmp(p, q, constant) < 0` and memcmp(p, q, constant) > 0.
llvm-svn: 364412
Ideally this needs to be a generic combine in DAGCombiner::visitEXTRACT_SUBVECTOR but there's some nasty regressions in aarch64 due to neon shuffles not handling bitcasts at all.....
llvm-svn: 364407
truncateVectorWithPACK is often used in conjunction with ComputeNumSignBits which struggles when peeking through bitcasts.
This fix tries to avoid bitcast(shuffle(bitcast())) patterns in the 256-bit 64-bit sublane shuffles so we can still see through at least until lowering when the shuffles will need to be bitcasted to widen the shuffle type.
llvm-svn: 364401
Peephole opt has a one use limitation which appears to be accidental. The function being used was incorrectly documented as returning whether the def had one *user*, but instead returned true only when there was one *use*. Add a corresponding hasOneNonDbgUser helper, and adjust peephole-opt to use the appropriate one.
All of the actual folding code handles multiple uses within a single instruction. That codepath is well exercised through instruction selection.
Differential Revision: https://reviews.llvm.org/D63656
llvm-svn: 364336
We currently have some isel patterns for treating vzmovl+load the same as vzload, but that shrinks the load which we shouldn't do if the load is volatile.
Rather than adding isel checks for volatile. This patch removes the patterns and teachs DAG combine to merge them into vzload when its legal to do so.
Differential Revision: https://reviews.llvm.org/D63665
llvm-svn: 364333
Change the generic ctpop expansion to more efficiently handle a
check for not-a-power-of-two value:
(ctpop x) != 1 --> (x == 0) || ((x & x-1) != 0)
This is the inverted predicate sibling pattern that was added with:
D63004
This should have been done before I changed IR canonicalization to
favor this form with:
rL364246
...so if this requires revert/changing, the earlier commit may also
need to modified.
llvm-svn: 364319
Simplify ZERO_EXTEND_VECTOR_INREG if the extended bits are not required.
Matches what we already do for ZERO_EXTEND.
Reapplies rL363850 but now with legality checks added at rL364290
llvm-svn: 364303
Simplify SIGN_EXTEND_VECTOR_INREG if the extended bits are not required/known zero.
Matches what we already do for SIGN_EXTEND.
Reapplies rL363802 but now with legality checks added at rL364290
llvm-svn: 364299
As part of the fix for rL364264 + rL364272 - limit the *_EXTEND conversion to !TLO.LegalOperations || isOperationLegal cases.
We'll improve X86 legality in future commits.
llvm-svn: 364290
Summary:
This addresses the regression that is being exposed by D50222 in `test/CodeGen/X86/jump_sign.ll`
The missing fold, at least partially, looks trivial:
https://rise4fun.com/Alive/Zsln
i.e. if we are comparing with zero, and comparing the `urem`-by-non-power-of-two,
and the `urem` is of something that may at most have a single bit set (or no bits set at all),
the `urem` is not needed.
Reviewers: RKSimon, craig.topper, xbolva00, spatel
Reviewed By: xbolva00, spatel
Subscribers: xbolva00, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63390
llvm-svn: 364286
I've been trying to fix this, but hit some roadblocks. So I'm
committing the test case for now so we'll at least avoid
recreating that failure.
llvm-svn: 364272
This reverts the following patches.
"[TargetLowering] SimplifyDemandedBits SIGN_EXTEND_VECTOR_INREG -> ANY/ZERO_EXTEND_VECTOR_INREG"
"[TargetLowering] SimplifyDemandedBits ZERO_EXTEND_VECTOR_INREG -> ANY_EXTEND_VECTOR_INREG"
"[TargetLowering] SimplifyDemandedBits - add ANY_EXTEND_VECTOR_INREG support"
We can end up with an any_extend_vector_inreg with a 256 bit result type
and a 128 bit result type. This is allowed by the ISD opcode, but the
generic operation legalizer is only able to expand cases where the
total vector width is the same.
The X86 backend creates these mismatched cases for zext_vec_inreg/sext_vec_inreg.
The SimplifyDemandedBits changes are allowing those nodes to become
aext_vec_inreg. For the zext/sext cases, the X86 backend has Custom
handling and never lets them get to the generic legalizer. We need to do the same
for aext_vec_inreg.
llvm-svn: 364264
Widen vector result type for ctlz_zero_undef and cttz_zero_undef the same as
ctlz and cttz.
Differential Revision: https://reviews.llvm.org/D63463
llvm-svn: 364221
This patch does a few things to start cleaning up the isFNEG function.
-Remove the Op0/Op1 peekThroughBitcast calls that seem unnecessary. getTargetConstantBitsFromNode has its own peekThroughBitcast inside. And we have a separate peekThroughBitcast on the return value.
-Add a check of the scalar size after the first peekThroughBitcast to ensure we haven't changed the element size and just did something like f32->i32 or f64->i64.
-Remove an unnecessary check that Op1's type is floating point after the peekThroughBitcast. We're just going to look for a bit pattern from a constant. We don't care about its type.
-Add VT checks on several places that consume the return value of isFNEG. Due to the peekThroughBitcasts inside, the type of the return value isn't guaranteed. So its not safe to use it to build other nodes without ensuring the type matches the type being used to build the node. We might be able to replace these checks with bitcasts instead, but I don't have a test case so a bail out check seemed better for now.
Differential Revision: https://reviews.llvm.org/D63683
llvm-svn: 364206
This can occur under certain circumstances when undefs are created later on in the constant multipliers (e.g. in this case due to SimplifyDemandedVectorElts). Its better to let the shift by zero to occur and perform any cleanup afterward.
Fixes OSS Fuzz #15429
llvm-svn: 364179
Ideally we'd be able to represent this truncate as a any_extend to
v16i32 and a truncate, but SelectionDAG doens't know how to not
fold those together.
We have isel patterns to use a vpmovzxwd+vpdmovdb for the truncate,
but we aren't able to simultaneously fold the load and the store
from the isel pattern. By pulling the truncate into the store we
can successfully hide it from the DAG combiner. Then we can isel
pattern match the truncstore and load+any_extend separately.
llvm-svn: 364163
128/256 bit scalar_to_vectors are canonicalized to (insert_subvector undef, (scalar_to_vector), 0). We have isel patterns that try to match this pattern being used by a vzmovl to use a 128-bit instruction and a subreg_to_reg.
This patch detects the insert_subvector undef portion of this and pulls it through the vzmovl, creating a narrower vzmovl and an insert_subvector allzeroes. We can then match the insertsubvector into a subreg_to_reg operation by itself. Then we can fall back on existing (vzmovl (scalar_to_vector)) patterns.
Note, while the scalar_to_vector case is the motivating case I didn't restrict to just that case. I'm also wondering about shrinking any 256/512 vzmovl to an extract_subvector+vzmovl+insert_subvector(allzeros) but I fear that would have bad implications to shuffle combining.
I also think there is more canonicalization we can do with vzmovl with loads or scalar_to_vector with loads to create vzload.
Differential Revision: https://reviews.llvm.org/D63512
llvm-svn: 364095
We already use vmovq for v2i64/v2f64 vzmovl. But we were using a
blendpd+xorpd for v4i64/v4f64/v8i64/v8f64 under opt speed. Or
movsd+xorpd under optsize.
I think the blend with 0 or movss/d is only needed for
vXi32 where we don't have an instruction that can move 32
bits from one xmm to another while zeroing upper bits.
movq is no worse than blendpd on any known CPUs.
llvm-svn: 364079
We sometimes get poor code size because constants of types < 32b are legalized
as 32 bit G_CONSTANTs with a truncate to fit. This works but means that the
localizer can no longer sink them (although it's possible to extend it to do so).
On AArch64 however s8 and s16 constants can be selected in the same way as s32
constants, with a mov pseudo into a W register. If we make s8 and s16 constants
legal then we can avoid unnecessary truncates, they can be CSE'd, and the
localizer can sink them as normal.
There is a caveat: if the user of a smaller constant has to widen the sources,
we end up with an anyext of the smaller typed G_CONSTANT. This can cause
regressions because of the additional extend and missed pattern matching. To
remedy this, there's a new artifact combiner to generate the wider G_CONSTANT
if it's legal for the target.
Differential Revision: https://reviews.llvm.org/D63587
llvm-svn: 364075
The sat add/sub tests still have unnecessary extract_subvector((vandnps ymm, ymm), 0) uses that should be split to (vandnps (extract_subvector(ymm, 0), extract_subvector(ymm, 0)), but its getting better.
llvm-svn: 364038
Summary:
BLSI sets the C flag is the input is not zero. So if its followed
by a TEST of the input where only the Z flag is consumed, we can
replace it with the opposite check of the C flag.
We should be able to do the same for BLSMSK and BLSR, but the
naive test case for those is being optimized to a subo by
CodeGenPrepare.
Reviewers: spatel, RKSimon
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63589
llvm-svn: 363957
This is an exception to the rule that we should prefer xmm ops to ymm ops.
As shown in PR42305:
https://bugs.llvm.org/show_bug.cgi?id=42305
...the store folding opportunity with vextractf128 may result in better
perf by reducing the instruction count.
Differential Revision: https://reviews.llvm.org/D63517
llvm-svn: 363853
We already do this for ZERO_EXTEND/ZERO_EXTEND_VECTOR_INREG - this just extends the pattern matcher to recognize cases where we don't need the zeros in the extension.
llvm-svn: 363841
Use matchBinaryPredicate instead of isConstOrConstSplat to let us handle non-uniform shift cases.
This requires us to tweak matchBinaryPredicate to allow it to (optionally) handle constants with different type widths.
llvm-svn: 363792
This allows targets to make more decisions about reserved registers
after isel. For example, now it should be certain there are calls or
stack objects in the frame or not, which could have been introduced by
legalization.
Patch by Matthias Braun
llvm-svn: 363757
Part of fixing the X86 regression noted in D63281 - I've split this into X86 and generic parts - the generic commit will be coming shortly and will fix the vector-reduce-mul-widen.ll regression introduced here.
llvm-svn: 363693
This adds vector splitting for vaarg instructions during type legalization
Committed on behalf of @luke (Luke Lau)
Differential Revision: https://reviews.llvm.org/D60762
llvm-svn: 363671
The isel patterns for these use a bitcast and load/store, but
DAG combine should have canonicalized those away.
For the purposes of the memory folding table these opcodes can be
replaced by the MOVSSrm_alt/MOVSDrm_alt and MOVSSmr/MOVSDmr opcodes.
llvm-svn: 363644
Rename the old versions that use FR32/FR64 to MOVSSrm_alt/MOVSDrm_alt.
Use the new versions in patterns that previously used a COPY_TO_REGCLASS
to VR128. These patterns expect the upper bits to be zero. The
current set up appears to work, but I'm not sure we should be
enforcing upper bits being zero through a COPY_TO_REGCLASS.
I wanted to flip the arrangement and use a COPY_TO_REGCLASS to
FR32/FR64 for the patterns that need an f32/f64 result, but that
complicated fastisel and globalisel.
I've been doing some experiments with reducing some isel patterns
and ended up in a situation where I had a
(SUBREG_TO_REG (COPY_TO_RECLASS (VMOVSSrm), VR128)) and our
post-isel peephole was unable to avoid using an instruction for
the SUBREG_TO_REG due to the COPY_TO_REGCLASS. Having a VR128
instruction removes the COPY_TO_REGCLASS that was breaking this.
llvm-svn: 363643
Simon Pilgrim