Summary:
This patch adjusts the patterns to make the result type of the broadcast node vXf64/vXi64. Then adds a bitcast to vXi32 after that. Intrinsic lowering was also adjusted to generate this new pattern.
Fixes PR34357
We should probably just drop the intrinsic entirely and use native IR, but I'll leave that for a future patch.
Any idea what instruction we should be lowering the floating point 128-bit result version of this pattern to? There's a 128-bit v2i32 integer broadcast but not an fp one.
Reviewers: aymanmus, zvi, igorb
Reviewed By: aymanmus
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D37286
llvm-svn: 312101
This enables the use of a smaller encoding by using a VEX instruction when possible.
Differential Revision: https://reviews.llvm.org/D37092
llvm-svn: 312100
Currently we start applying this on Haswell and newer. I don't believe anything changed in the Haswell architecture to make this the right cutoff point. The partial flag handling around this has been roughly the same since Sandybridge.
Differential Revision: https://reviews.llvm.org/D37250
llvm-svn: 312099
Summary:
Currently we determine if macro fusion is supported based on the AVX flag as a proxy for the processor being Sandy Bridge".
This is really strange as now AMD supports AVX. It also means if user explicitly disables AVX we disable macro fusion.
This patch adds an explicit macro fusion feature. I've also enabled for the generic 64-bit CPU (which doesn't have AVX)
This is probably another candidate for being in the MI layer, but for now I at least wanted to correct the overloading of the AVX feature.
Reviewers: spatel, chandlerc, RKSimon, zvi
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D37280
llvm-svn: 312097
We don't have an intrinsic implemented for this instruction yet, but it looked odd that we were missing the accessor method from the subtarget.
llvm-svn: 312064
Summary: Knights Landing, because it is Atom derived, has slow two memory operand instructions. Mark the Knights Landing CPU model accordingly.
Patch by David Zarzycki.
Reviewers: craig.topper
Reviewed By: craig.topper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D37224
llvm-svn: 311979
EXTRACT_SUBVECTOR was marked Custom solely so we could combine it with BUILD_VECTOR operations to create smaller BUILD_VECTORS during Legalization. But that sort of combining should really be done by the DAG combiner.
This patch adds the last piece of needed supported DAG combine to handle this. Once that's done we can make the EXTRACT_SUBVECTOR operations Legal.
Differential Revision: https://reviews.llvm.org/D37197
llvm-svn: 311893
Differential Revision: https://reviews.llvm.org/D36788
M lib/Target/X86/Disassembler/X86DisassemblerDecoder.cpp
M lib/Target/X86/Disassembler/X86DisassemblerDecoder.h
A test/MC/Disassembler/X86/prefixes-i386.s
A test/MC/Disassembler/X86/prefixes-x86_64.s
M test/MC/Disassembler/X86/prefixes.txt
llvm-svn: 311882
This patch completely replaces the instruction scheduling information for the Haswell architecture target by modifying the file X86SchedHaswell.td located under the X86 Target.
We used the scheduling information retrieved from the Haswell architects in order to replace and modify the existing scheduling.
The patch continues the scheduling replacement effort started with the SNB target in r307529 and r310792.
Information includes latency, number of micro-Ops and used ports by each HSW instruction.
Please expect some performance fluctuations due to code alignment effects.
Reviewers: RKSimon, zvi, aymanmus, craig.topper, m_zuckerman, igorb, dim, chandlerc, aaboud
Differential Revision: https://reviews.llvm.org/D36663
llvm-svn: 311879
We used to do a late DAG combine to move the bitcasts out of the way, but I'm starting to think that it's better to canonicalize extract_subvector's type to match the type of its input. I've seen some cases where we've formed two different extract_subvector from the same node where one had a bitcast and the other didn't.
Add some more test cases to ensure we've also got most of the zero masking covered too.
llvm-svn: 311837
to instructions.
These can't be reasonably matched in tablegen due to the handling of
flags, so we have to do this in C++ code. We only did it for `inc` and
`dec` historically, this starts fleshing that out to more interesting
instructions. Notably, this handles transfering operands to `add` and
`sub`.
Currently this forces them into a register. The next patch will add
support for keeping immediate operands as immediates. Then I'll extend
this beyond just `add` and `sub`.
I'm not super thrilled by the repeated switches in the code but
everything else I tried was really ugly or problematic.
Many thanks to Craig Topper for the suggestions about where to even
begin here and how to make this stuff work.
Differential Revision: https://reviews.llvm.org/D37130
llvm-svn: 311806
to handle other x86 pseudos that carry flags and thus can't be matched
by our ISel patterns with fused memory accesses.
Differential Revision: https://reviews.llvm.org/D37088
llvm-svn: 311749
This extracts the code out of a giant switch in preparation for expanding it to
handle operations other thin `inc` and `dec`. Add a FIXME indicating what's
coming here.
Differential Revision: https://reviews.llvm.org/D37045
llvm-svn: 311748
FeatureSlowUAMem32.
The idea was to mark things that are slow on widely available processors
as slow in the generic CPU so that the code generated for that CPU would
be fast across those processors. However, for this feature that doesn't
work out very well at all.
The problem here is that you can very easily enable AVX or AVX2 on top
of this generic CPU. For example, this can happen just by using AVX2
intrinsics from Clang within a region of code guarded by a dynamic CPU
feature test. When you do that, the generated code with SlowUAMem32 set
is ... amazingly slower. The problem is that there really aren't very
good alternatives to the unaligned loads, and so our vector codegen
regresses significantly.
The other issue is that there are plenty of AMD CPUs with AVX1 that
don't set FeatureSlowUAMem32 and so we shouldn't just check for AVX2
instead of this special feature. =/
It would be nice to have the target attriute logic be able to
enable/disable more than just one feature at a time and control this in
a more fine grained and useful way, but that doesn't seem easy. Given
that it is only Sandybridge and Ivybridge that set this feature, for now
I'm just backing it out of the generic CPU. That has the additional
advantage of going back to the previous state that people seemed vaguely
happy with.
llvm-svn: 311740
The comment for this code indicated that it should work similar to our
handling of add lowering above: if we see uses of an instruction other
than flag usage and store usage, it tries to avoid the specialized
X86ISD::* nodes that are designed for flag+op modeling and emits an
explicit test.
Problem is, only the add case actually did this. In all the other cases,
the logic was incomplete and inverted. Any time the value was used by
a store, we bailed on the specialized X86ISD node. All of this appears
to have been historical where we had different logic here. =/
Turns out, we have quite a few patterns designed around these nodes. We
should actually form them. I fixed the code to match what we do for add,
and it has quite a positive effect just within some of our test cases.
The only thing close to a regression I see is using:
notl %r
testl %r, %r
instead of:
xorl -1, %r
But we can add a pattern or something to fold that back out. The
improvements seem more than worth this.
I've also worked with Craig to update the comments to no longer be
actively contradicted by the code. =[ Some of this still remains
a mystery to both Craig and myself, but this seems like a large step in
the direction of consistency and slightly more accurate comments.
Many thanks to Craig for help figuring out this nasty stuff.
Differential Revision: https://reviews.llvm.org/D37096
llvm-svn: 311737
This goes back to a discussion about IR canonicalization. We'd like to preserve and convert
more IR to 'select' than we currently do because that's likely the best choice in IR:
http://lists.llvm.org/pipermail/llvm-dev/2016-September/105335.html
...but that's often not true for codegen, so we need to account for this pattern coming in
to the backend and transform it to better DAG ops.
Steps in this patch:
1. Add an EVT param to the existing convertSelectOfConstantsToMath() TLI hook to more finely
enable this transform. Other targets will probably want that anyway to distinguish scalars
from vectors. We're using that here to exclude AVX512 targets, but it may not be necessary.
2. Convert a vselect to ext+add. This eliminates a constant load/materialization, and the
vector ext is often free.
Implementing a more general fold using xor+and can be a follow-up for targets that don't have
a legal vselect. It's also possible that we can remove the TLI hook for the special case fold
implemented here because we're eliminating a constant, but it needs to be tested on other
targets.
Differential Revision: https://reviews.llvm.org/D36840
llvm-svn: 311731
Summary:
We add the precise cache sizes and associativity for the following Intel
architectures:
- Penry
- Nehalem
- Westmere
- Sandy Bridge
- Ivy Bridge
- Haswell
- Broadwell
- Skylake
- Kabylake
Polly uses since several months a performance model for BLAS computations that
derives optimal cache and register tile sizes from cache and latency
information (based on ideas from "Analytical Modeling Is Enough for High-Performance BLIS", by Tze Meng Low published at TOMS 2016).
While bootstrapping this model, these target values have been kept in Polly.
However, as our implementation is now rather mature, it seems time to teach
LLVM itself about cache sizes.
Interestingly, L1 and L2 cache sizes are pretty constant across
micro-architectures, hence a set of architecture specific default values
seems like a good start. They can be expanded to more target specific values,
in case certain newer architectures require different values. For now a set
of Intel architectures are provided.
Just as a little teaser, for a simple gemm kernel this model allows us to
improve performance from 1.2s to 0.27s. For gemm kernels with less optimal
memory layouts even larger speedups can be reported.
Reviewers: Meinersbur, bollu, singam-sanjay, hfinkel, gareevroman, fhahn, sebpop, efriedma, asb
Reviewed By: fhahn, asb
Subscribers: lsaba, asb, pollydev, llvm-commits
Differential Revision: https://reviews.llvm.org/D37051
llvm-svn: 311647
This patch is intended to enable the use of basic double letter constraints used in GCC extended inline asm {Yi Y2 Yz Y0 Ym Yt}.
Supersedes D35204
Clang counterpart: D36371
Differential Revision: https://reviews.llvm.org/D36369
llvm-svn: 311644
Some refactoring to X86AsmParser, mostly regarding the way rewrites are conducted.
Mainly, we try to concentrate all the rewrite effort under one hood, so it'll hopefully be less of a mess and easier to maintain and understand.
naturally, some frontend tests were affected: D36794
Differential Revision: https://reviews.llvm.org/D36793
llvm-svn: 311639
G_PHI has the same semantics as PHI but also has types.
This lets us verify that the types in the G_PHI are consistent.
This also allows specifying legalization actions for G_PHIs.
https://reviews.llvm.org/D36990
llvm-svn: 311596
There are no 512-bit blend instructions so we shouldn't create SHRUNKBLEND for them.
On a side note, it looks like there may be a missed opportunity for constant folding TESTM when LHS and RHS are equal.
This fixes PR34139.
Differential Revision: https://reviews.llvm.org/D36992
llvm-svn: 311572
There's no reason to have a target specific node with the same semantics as a target independent opcode.
This should simplify D36335 so that it doesn't need to touch X86ISelDAGToDAG.cpp
Differential Revision: https://reviews.llvm.org/D36983
llvm-svn: 311568
Summary:
This change achieves two things:
- Redefine the Custom Event handling instrumentation points emitted by
the compiler to not require dynamic relocation of references to the
__xray_CustomEvent trampoline.
- Remove the synthetic reference we emit at the end of a function that
we used to keep auxiliary sections alive in favour of SHF_LINK_ORDER
associated with the section where the function is defined.
To achieve the custom event handling change, we've had to introduce the
concept of sled versioning -- this will need to be supported by the
runtime to allow us to understand how to turn on/off the new version of
the custom event handling sleds. That change has to land first before we
change the way we write the sleds.
To remove the synthetic reference, we rely on a relatively new linker
feature that preserves the sections that are associated with each other.
This allows us to limit the effects on the .text section of ELF
binaries.
Because we're still using absolute references that are resolved at
runtime for the instrumentation map (and function index) maps, we mark
these sections write-able. In the future we can re-define the entries in
the map to use relative relocations instead that can be statically
determined by the linker. That change will be a bit more invasive so we
defer this for later.
Depends on D36816.
Reviewers: dblaikie, echristo, pcc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36615
llvm-svn: 311525
This partially reverts r311429 in favor of making ISD::isConstantSplatVector do something not confusing. Turns out the only other user of it was also having to deal with the weird property of it returning a smaller size.
So rather than continue to deal with this quirk everywhere, just make the interface do something sane.
Differential Revision: https://reviews.llvm.org/D37039
llvm-svn: 311510
ISD::isConstantSplatVector can shrink to the smallest splat width. But we don't check the size of the resulting APInt at all. This can cause us to misinterpret the results.
This patch just adds a flag to prevent the APInt from changing width.
Fixes PR34271.
Differential Revision: https://reviews.llvm.org/D36996
llvm-svn: 311429
Summary: With masked operations, its possible for the operation node like fadd, fsub, etc. to be used by multiple different vselects. Since the pattern matching will start at the vselect, we need to make sure the operation node itself is only used once before we can fold a load. Otherwise we'll end up folding the same load into multiple instructions.
Reviewers: RKSimon, spatel, zvi, igorb
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36938
llvm-svn: 311342
widely used processors.
This occured to me when I saw that we were generating 'inc' and 'dec'
when for Haswell and newer we shouldn't. However, there were a few "X is
slow" things that we should probably just set.
I've avoided any of the "X is fast" features because most of those would
be pretty serious regressions on processors where X isn't actually fast.
The slow things are likely to be negligible costs on processors where
these aren't slow and a significant win when they are slow.
In retrospect this seems somewhat obvious. Not sure why we didn't do
this a long time ago.
Differential Revision: https://reviews.llvm.org/D36947
llvm-svn: 311318
rather than doing a separate comparison.
This both saves an explicit comparision and avoids the use of `xadd`
which introduces register constraints and other challenges to the
generated code.
The motivating case is from atomic reference counts where `1` is the
sentinel rather than `0` for whatever reason. This can and should be
lowered efficiently on x86 by just using a different flag, however the
x86 code only handled the `0` case.
There remains some further opportunities here that are currently hidden
due to canonicalization. I've included test cases that show these and
FIXMEs. However, I don't at the moment have any production use cases and
they seem substantially harder to address.
Differential Revision: https://reviews.llvm.org/D36945
llvm-svn: 311317
There's no functional difference between the AVX512DQ instructions if we're not masking.
This change unifies test checks and removes extra isel entries. Similar was done for subvector insert and extracts recently.
llvm-svn: 311308
Store operation takes 2 UOps on X86 processors. The exact cost calculation affects several optimization passes including loop unroling.
This change compensates performance degradation caused by https://reviews.llvm.org/D34458 and shows improvements on some benchmarks.
Differential Revision: https://reviews.llvm.org/D35888
llvm-svn: 311285
Summary: Support call ABI. For now only Linux C and X86_64_SysV calling conventions supported. Variadic function not supported.
Reviewers: zvi, guyblank, oren_ben_simhon
Reviewed By: oren_ben_simhon
Subscribers: rovka, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D34602
llvm-svn: 311279
We can load the memory VT and check for natural alignment. This also adds a new preferNonTemporalLoad helper that checks the correct subtarget feature based on the load size.
This shrinks the isel table by at least 5000 bytes by allowing more reordering and combining to occur.
llvm-svn: 311266
The primary thing that this accomplishes is to allow future re-use of
these routines in more contexts and clarify the behavior w.r.t. loops.
For example, if handling outer loops is desirable, doing so in
a inside-out order becomes straight forward because it walks the loop
nest itself (rather than walking the function's basic blocks) and
de-couples the CMOV rewriting from the loop structure as there isn't
actually anything loop-specific about this transformation.
This patch should be essentially a no-op. It potentially changes the
order in which we visit the inner loops, but otherwise should merely set
the stage for subsequent changes.
Differential Revision: https://reviews.llvm.org/D36783
llvm-svn: 311225
There's really no reason to do this we should just let isel pick the integer version and let the execution dependency fixing pass take care of moving to FP if necessary.
It's not very reliable to look for bitcasts at the edges of patterns. If for some reason one input was bitcasted and the other wasn't, or if one was a v4f32 bitcast and one was a v2f64 bitcast, we would have fallen back to the integer pattern anyway.
llvm-svn: 311138
There's no reason to switch instructions with and without DQI. It just creates extra isel patterns and test divergences.
There is however value in enabling the masked version of the instructions with DQI.
This required introducing some new multiclasses to enabling this splitting.
Differential Revision: https://reviews.llvm.org/D36661
llvm-svn: 311091
Summary: Just like the FIXME says, there is no alignment requirement for MMX.
Reviewers: RKSimon, zvi, igorb
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36815
llvm-svn: 311090
We used to have a separate multiclass for AVX2 and SSE/AVX. Now we have one multiclass and pass the relevant differences.
We were also missing load patterns, though we had them for the AVX-512 version.
llvm-svn: 311059
This reverts commit r310425, thus reapplying r310335 with a fix for link
issue of the AArch64 unittests on Linux bots when BUILD_SHARED_LIBS is ON.
Original commit message:
[GlobalISel] Remove the GISelAccessor API.
Its sole purpose was to avoid spreading around ifdefs related to
building global-isel. Since r309990, GlobalISel is not optional anymore,
thus, we can get rid of this mechanism all together.
NFC.
----
The fix for the link issue consists in adding the GlobalISel library in
the list of dependencies for the AArch64 unittests. This dependency
comes from the use of AArch64Subtarget that needs to know how
to destruct the GISel related APIs when being detroyed.
Thanks to Bill Seurer and Ahmed Bougacha for helping me reproducing and
understand the problem.
llvm-svn: 310969
According to the X86ISelLowering.h, UMUL results are low, high, and flags. But this place was treating result 1 or 2 as flags.
Differential Revision: https://reviews.llvm.org/D36654
llvm-svn: 310846
Summary:
The flag result is an i32 type. But its only really used for connectivity. I don't think anything even assumes a particular format. We don't ever do any real operations on it. So known bits don't help us optimize anything.
My main motivation is that the UMUL behavior is actually wrong. I was going to fix this in D36654, but then realized there was just no reason for it to be here.
Reviewers: RKSimon, zvi, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36657
llvm-svn: 310845
Summary: This looks to have been disconnected about 3 years ago in r219358.
Reviewers: gadi.haber, RKSimon, zvi
Reviewed By: gadi.haber
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36658
llvm-svn: 310844
Summary:
I don't think we need this code anymore. It only existed because i1 used to be legal.
There's probably more unneeded code in fast isel still.
Reviewers: guyblank, zvi
Reviewed By: guyblank
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36652
llvm-svn: 310843
Previously it would not return true for extracting either of the upper quarters of a 512-bit registers.
For mask registers we support extracting anything from index 0. And otherwise we only support extracting the upper half of a register.
Differential Revision: https://reviews.llvm.org/D36638
llvm-svn: 310794
Summary:
Without the SrcVT its hard to know what is really being asked for. For example if your target has 128, 256, and 512 bit vectors. Maybe extracting 128 from 256 is cheap, but maybe extracting 128 from 512 is not.
For x86 we do support extracting a quarter of a 512-bit register. But for i1 vectors we don't have isel patterns for extracting arbitrary pieces. So we need this to have a correct implementation of isExtractSubvectorCheap for mask vectors.
Reviewers: RKSimon, zvi, efriedma
Reviewed By: RKSimon
Subscribers: aemerson, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D36649
llvm-svn: 310793
This is a continuation patch for commit r307529 which completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target (see also https://reviews.llvm.org/D35019).
In this patch we added the scheduling information of additional SNB instructions that were missing from the patch commit r307529, fixed the scheduling of several resource groups that include only port0 instead of port05 (i.e., port0 OR port5) and fixed several incorrect instructions' scheduling in the r307529 commit.
The patch also includes the X87 instructions which were missing in previous patch commit r307529 as reported in bugzilla bug 34080.
Reviewers: zvi, RKSimon, chandlerc, igorb, m_zuckerman, craig.topper, aymanmus, dim
Differential Revision: https://reviews.llvm.org/D36388
llvm-svn: 310792
K0 isn't expected as a write-mask, so provide a detailed error here, instead of the more generic one (invalid op for insn)
Conforms with gas
Differential Revision: https://reviews.llvm.org/D36570
llvm-svn: 310789
Add an X86 combine for TESTM when one of the operands is a BUILD_VECTOR(0,0,...).
TESTM op0, BUILD_VECTOR(0,0,...) -> BUILD_VECTOR(0,0,...)
TESTM BUILD_VECTOR(0,0,...), op1 -> BUILD_VECTOR(0,0,...)
Differential Revision:
https://reviews.llvm.org/D36536
llvm-svn: 310787
Summary:
Previously we were creating the flag result with MVT::Other which is interpretted as a Chain node. If we used a memory form of the instruction we would end up with a copyToReg that consumed the chain result of the adcx instruction instead of the flag result.
Pretty sure we should be using MVT::i32 here, that's what we do other places we create these node types.
We should probably consider this for 5.0 as well.
Reviewers: RKSimon, zvi, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36645
llvm-svn: 310784
Summary:
Previously we would use these instructions if sse was disabled and fastmath was enabled.
As mentioned in D28335, this is a bad idea.
Reviewers: efriedma, scanon, DavidKreitzer
Reviewed By: DavidKreitzer
Subscribers: zvi, llvm-commits
Differential Revision: https://reviews.llvm.org/D36344
llvm-svn: 310762
When the access to a weak symbol is not a call, the access has to be
able to produce the value 0 at runtime.
We were sometimes producing code sequences where that was not possible
if the code was leaded more than 4g away from 0.
llvm-svn: 310756
Summary:
This autoupgrades most of the broadcast intrinsics. They've been unused in clang for some time.
This leaves the 32x2 intrinsics because they are still used in clang.
Reviewers: RKSimon, zvi, igorb
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36606
llvm-svn: 310725
Summary:
This teaches 512-bit shuffles to detect unused halfs in order to reduce shuffle size.
We may need to refine the 512-bit exit point. I couldn't remember if we had good cross lane shuffles for 8/16 bit with AVX-512 or not.
I believe this is step towards being able to handle D36454 without a special case.
From here we need to improve our ability to combine extract_subvector with insert_subvector and other extract_subvectors. And we need to support narrowing binary operations where we don't demand all elements. This may be improvements to DAGCombiner::narrowExtractedVectorBinOp(by recognizing an insert_subvector in addition to concat) or we may need a target specific combiner.
Reviewers: RKSimon, zvi, delena, jbhateja
Reviewed By: RKSimon, jbhateja
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36601
llvm-svn: 310724
The previous rev (r310208) failed to account for overflow when subtracting the
constants to see if they're suitable for shift/lea. This version add a check
for that and more test were added in r310490.
We can convert any select-of-constants to math ops:
http://rise4fun.com/Alive/d7d
For this patch, I'm enhancing an existing x86 transform that uses fake multiplies
(they always become shl/lea) to avoid cmov or branching. The current code misses
cases where we have a negative constant and a positive constant, so this is just
trying to plug that hole.
The DAGCombiner diff prevents us from hitting a terrible inefficiency: we can start
with a select in IR, create a select DAG node, convert it into a sext, convert it
back into a select, and then lower it to sext machine code.
Some notes about the test diffs:
1. 2010-08-04-MaskedSignedCompare.ll - We were creating control flow that didn't exist in the IR.
2. memcmp.ll - Choose -1 or 1 is the case that got me looking at this again. We could avoid the
push/pop in some cases if we used 'movzbl %al' instead of an xor on a different reg? That's a
post-DAG problem though.
3. mul-constant-result.ll - The trade-off between sbb+not vs. setne+neg could be addressed if
that's a regression, but those would always be nearly equivalent.
4. pr22338.ll and sext-i1.ll - These tests have undef operands, so we don't actually care about these diffs.
5. sbb.ll - This shows a win for what is likely a common case: choose -1 or 0.
6. select.ll - There's another borderline case here: cmp+sbb+or vs. test+set+lea? Also, sbb+not vs. setae+neg shows up again.
7. select_const.ll - These are motivating cases for the enhancement; replace cmov with cheaper ops.
Assembly differences between movzbl and xor to avoid a partial reg stall are caused later by the X86 Fixup SetCC pass.
Differential Revision: https://reviews.llvm.org/D35340
llvm-svn: 310717
Move store merge to happen after intrinsic lowering to allow lowered
stores to be merged.
Some regressions due in MergeConsecutiveStores to missing
insert_subvector that are addressed in follow up patch.
Reviewers: craig.topper, efriedma, RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34559
llvm-svn: 310710
Igor Breger