Commit Graph

30611 Commits

Author SHA1 Message Date
Craig Topper 36e04d14e9 [PowerPC] Remove the SPE4RC register class and instead add f32 to the GPRC register class.
Summary:
Since the SPE4RC register class contains an identical set of registers
and an identical spill size to the GPRC class its slightly confusing
the tablegen emitter. It's preventing the GPRC_and_GPRC_NOR0 synthesized
register class from inheriting VTs and AltOrders from GPRC or GPRC_NOR0.
This is because SPE4C is found first in the super register class list
when inheriting these properties and it doesn't set the VTs or
AltOrders the same way as GPRC or GPRC_NOR0.

This patch replaces all uses of GPE4RC with GPRC and allows GPRC and
GPRC_NOR0 to contain f32.

The test changes here are because the AltOrders are being inherited
to GPRC_NOR0 now.

Found while trying to determine if getCommonSubClass needs to take
a VT argument. It was originally added to support fp128 on x86-64,
I've changed some things about that so that it might be needed
anymore. But a PowerPC test crashed without it and I think its
due to this subclass issue.

Reviewers: jhibbits, nemanjai, kbarton, hfinkel

Subscribers: wuzish, nemanjai, mehdi_amini, hiraditya, kbarton, MaskRay, dexonsmith, jsji, shchenz, steven.zhang, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67513

llvm-svn: 371779
2019-09-12 22:07:35 +00:00
Craig Topper efe6724b9f [DAGCombiner][X86] Pass the CmpOpVT to reduceSelectOfFPConstantLoads so X86 can exclude fp128 compares.
The X86 decision assumes the compare will produce a result in an XMM
register, but that can't happen for an fp128 compare since those
go to a libcall the returns an i32. Pass the VT so X86 can check
the type.

llvm-svn: 371775
2019-09-12 21:30:18 +00:00
Petar Avramovic ff6ac1eb5f [MIPS GlobalISel] Select indirect branch
Select G_BRINDIRECT for MIPS32.

Differential Revision: https://reviews.llvm.org/D67441

llvm-svn: 371730
2019-09-12 11:44:36 +00:00
Petar Avramovic 646e1f7b7f [MIPS GlobalISel] Lower G_DYN_STACKALLOC
IRTranslator creates G_DYN_STACKALLOC instruction during expansion of
alloca when argument that tells number of elements to allocate on stack
is a virtual register. Use default lowering for MIPS32.

Differential Revision: https://reviews.llvm.org/D67440

llvm-svn: 371728
2019-09-12 11:39:50 +00:00
Petar Avramovic 75e43a607c [MIPS GlobalISel] Select G_IMPLICIT_DEF
G_IMPLICIT_DEF is used for both integer and floating point implicit-def.
Handle G_IMPLICIT_DEF as ambiguous opcode in MipsRegisterBankInfo.
Select G_IMPLICIT_DEF for MIPS32.

Differential Revision: https://reviews.llvm.org/D67439

llvm-svn: 371727
2019-09-12 11:32:38 +00:00
Tim Northover f1c2892912 AArch64: support arm64_32, an ILP32 slice for watchOS.
This is the main CodeGen patch to support the arm64_32 watchOS ABI in LLVM.
FastISel is mostly disabled for now since it would generate incorrect code for
ILP32.

llvm-svn: 371722
2019-09-12 10:22:23 +00:00
Kai Luo cfaf2b6cfa [PowerPC][MCP][NFC] Pre-commit test cases for https://reviews.llvm.org/D65267
llvm-svn: 371717
2019-09-12 09:00:44 +00:00
Qiu Chaofan b7fb5d0f6f [DAGCombiner] Improve division estimation of floating points.
Current implementation of estimating divisions loses precision since it
estimates reciprocal first and does multiplication.  This patch is to re-order
arithmetic operations in the last iteration in DAGCombiner to improve the
accuracy.

Reviewed By: Sanjay Patel, Jinsong Ji

Differential Revision: https://reviews.llvm.org/D66050

llvm-svn: 371713
2019-09-12 07:51:24 +00:00
Craig Topper 635d383fad [X86] Enable -mprefer-vector-width=256 by default for Skylake-avx512 and later Intel CPUs.
AVX512 instructions can cause a frequency drop on these CPUs. This
can negate the performance gains from using wider vectors. Enabling
prefer-vector-width=256 will prevent generation of zmm registers
unless explicit 512 bit operations are used in the original source
code.

I believe gcc and icc both do something similar to this by default.

Differential Revision: https://reviews.llvm.org/D67259

llvm-svn: 371694
2019-09-11 23:54:36 +00:00
Amara Emerson 55d86f04c7 [AArch64][GlobalISel] Fall back on attempts to allocate split types on the stack.
First we were asserting that the ValNo of a VA was the wrong value. It doesn't actually
make a difference for us in CallLowering but fix that anyway to silence the assert.

The bigger issue was that after fixing the assert we were generating invalid MIR
because the merging/unmerging of values split across multiple registers wasn't
also implemented for memory locs. This happens when we run out of registers and
have to pass the split types like i128 -> i64 x 2 on the stack. This is do-able, but
for now just fall back.

llvm-svn: 371693
2019-09-11 23:53:23 +00:00
Jessica Paquette e297ad1bd9 [GlobalISel][AArch64] Check caller for swifterror params in tailcall eligibility
Before, we only checked the callee for swifterror. However, we should also be
checking the caller to see if it has a swifterror parameter.

Since we don't currently handle outgoing arguments, this didn't show up in the
swifterror.ll testcase.

Also, remove the swifterror checks from call-translator-tail-call.ll, since
they are covered by the existing swifterror testing. Better to have it all in
one place.

Differential Revision: https://reviews.llvm.org/D67465

llvm-svn: 371692
2019-09-11 23:44:16 +00:00
Reid Kleckner ff45955fc8 [X86] Fix latent bugs in 32-bit CMPXCHG8B inserter
I found three issues:
1. the loop over E[ABCD]X copies run over BB start
2. the direct address of cmpxchg8b could be a frame index
3. the displacement of cmpxchg8b could be a global instead of an
   immediate

These were all introduced together in r287875, and should be fixed with
this change.

Issue reported by Zachary Turner.

llvm-svn: 371678
2019-09-11 21:56:17 +00:00
Craig Topper 5278b0a04e [X86] Add test case for v16i64->v16i32 truncate on min-legal-vector-width=256.
I think this case would crash before I added back the -x86-experimental-vector-widening command line option. Adding this test case to prevent breaking it again when we remove the option.

llvm-svn: 371673
2019-09-11 21:30:42 +00:00
Craig Topper 08474ca091 [X86] Move x86_64 fp128 conversion to libcalls from type legalization to DAG legalization
fp128 is considered a legal type for a register, but has almost no legal operations so everything needs to be converted to a libcall. Previously this was implemented by tricking type legalization into softening the operations with various checks for "is legal in hardware register" to change the behavior to still use f128 as the resulting type instead of converting to i128.

This patch abandons this approach and instead moves the libcall conversions to LegalizeDAG. This is the approach taken by AArch64 where they also have a legal fp128 type, but no legal operations. I think this is more in spirit with how SelectionDAG's phases are supposed to work.

I had to make some hacks for STRICT_FP_ROUND because some of the strict FP handling checks if ISD::FP_ROUND is Legal for a given result type, but I had to make ISD::FP_ROUND Custom to allow making a libcall when the input is f128. For all other types the Custom handler just returns the original node. These hacks are incomplete and don't work for a strict truncate from f128, but I don't think it worked before either since LegalizeFloatTypes doesn't know about strict ops yet. I've also raised PR43209 against AArch64 which currently crashes on a strict ftrunc from f64->f32 because of FP_ROUND being marked Custom for the same reason there.

Differential Revision: https://reviews.llvm.org/D67128

llvm-svn: 371672
2019-09-11 21:30:09 +00:00
Austin Kerbow 666af6714c AMDGPU: Move m0 initializations earlier
Summary:
After hoisting and merging m0 initializations schedule them as early as
possible in the MBB. This helps the scheduler avoid hazards in some
cases.

Reviewers: rampitec, arsenm

Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, arphaman, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67450

llvm-svn: 371671
2019-09-11 21:28:41 +00:00
Michael Liao 7957d4c015 [AMDGPU] Fix crash in phi-elimination hook.
Summary: - Pre-check in case there's just a single PHI insn.

Reviewers: alex-t, rampitec, arsenm

Subscribers: kzhuravl, jvesely, wdng, nhaehnle, dstuttard, tpr, t-tye, hiraditya, llvm-commits, yaxunl

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67451

llvm-svn: 371649
2019-09-11 19:55:20 +00:00
Matt Arsenault 81196a595c LiveIntervals: Split live intervals on multiple dead defs
If there are multiple dead defs of the same virtual register, these
are required to be split into multiple virtual registers with separate
live intervals to avoid a verifier error.

llvm-svn: 371640
2019-09-11 17:59:21 +00:00
Guillaume Chatelet 48904e9452 [Alignment] Use llvm::Align in MachineFunction and TargetLowering - fixes mir parsing
Summary:
This catches malformed mir files which specify alignment as log2 instead of pow2.
See https://reviews.llvm.org/D65945 for reference,

This is patch is part of a series to introduce an Alignment type.
See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html
See this patch for the introduction of the type: https://reviews.llvm.org/D64790

Reviewers: courbet

Subscribers: MatzeB, qcolombet, dschuff, arsenm, sdardis, nemanjai, jvesely, nhaehnle, hiraditya, kbarton, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, MaskRay, zzheng, edward-jones, atanasyan, rogfer01, MartinMosbeck, brucehoult, the_o, PkmX, jocewei, jsji, Petar.Avramovic, asbirlea, s.egerton, pzheng, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67433

llvm-svn: 371608
2019-09-11 11:16:48 +00:00
Simon Atanasyan d811d9115b [mips][msa] Fix infinite loop for mips.nori.b intrinsic
When value of immediate in `mips.nori.b` is 255 (which has all ones in
binary form as 8bit integer) DAGCombiner and Legalizer would fall in an
infinite loop. DAGCombiner would try to simplify `or %value, -1` by
turning `%value` into UNDEF. Legalizer will turn it back into `Constant<0>`
which would then be again turned into UNDEF by DAGCombiner. To avoid this
loop we make UNDEF legal for MSA int types on Mips.

Patch by Mirko Brkusanin.

Differential Revision: https://reviews.llvm.org/D67280

llvm-svn: 371607
2019-09-11 11:16:06 +00:00
Sam Parker 17ea9b463c [NFC][ARM] Add and modify tests
Add test for ParallelDSP.

llvm-svn: 371594
2019-09-11 08:17:48 +00:00
Jessica Paquette 469d42fcf6 [GlobalISel] When a tail call is emitted in a block, stop translating it
This fixes a crash in tail call translation caused by assume and lifetime_end
intrinsics.

It's possible to have instructions other than a return after a tail call which
will still have `Analysis::isInTailCallPosition` return true. (Namely,
lifetime_end and assume intrinsics.)

If we emit a tail call, we should stop translating instructions in the block.
Otherwise, we can end up emitting an extra return, or dead instructions in
general. This makes the verifier unhappy, and is generally unfortunate for
codegen.

This also removes the code from AArch64CallLowering that checks if we have a
tail call when lowering a return. This is covered by the new code now.

Also update call-translator-tail-call.ll to show that we now properly tail call
in the presence of lifetime_end and assume.

Differential Revision: https://reviews.llvm.org/D67415

llvm-svn: 371572
2019-09-10 23:34:45 +00:00
Jessica Paquette 2af5b193d5 [AArch64][GlobalISel] Support sibling calls with mismatched calling conventions
Add support for sibcalling calls whose calling convention differs from the
caller's.

- Port over `CCState::resultsCombatible` from CallingConvLower.cpp into
  CallLowering. This is used to verify that the way the caller and callee CC
  handle incoming arguments matches up.

- Add `CallLowering::analyzeCallResult`. This is basically a port of
  `CCState::AnalyzeCallResult`, but using `ArgInfo` rather than `ISD::InputArg`.

- Add `AArch64CallLowering::doCallerAndCalleePassArgsTheSameWay`. This checks
  that the calling conventions are compatible, and that the caller and callee
  preserve the same registers.

For testing:

- Update call-translator-tail-call.ll to show that we can now handle this.

- Add a GISel line to tailcall-ccmismatch.ll to show that we will not tail call
  when the regmasks don't line up.

Differential Revision: https://reviews.llvm.org/D67361

llvm-svn: 371570
2019-09-10 23:25:12 +00:00
Sanjay Patel 4d2b4077e7 [x86] add test for false dependency with AVX; NFC
Goes with D67363

llvm-svn: 371551
2019-09-10 20:04:10 +00:00
Matt Arsenault 4a23ae5e78 GlobalISel/TableGen: Handle REG_SEQUENCE patterns
The scalar f64 patterns don't work yet because they fail on multiple
results from the unused implicit def of scc in the result bit
operation.

llvm-svn: 371542
2019-09-10 17:57:33 +00:00
Guozhi Wei b329e0728b [BPI] Adjust the probability for floating point unordered comparison
Since NaN is very rare in normal programs, so the probability for floating point unordered comparison should be extremely small. Current probability is 3/8, it is too large, this patch changes it to a tiny number.

Differential Revision: https://reviews.llvm.org/D65303

llvm-svn: 371541
2019-09-10 17:25:11 +00:00
Matt Arsenault e1895aba3d AMDGPU/GlobalISel: Select G_FABS/G_FNEG
f64 doesn't work yet because tablegen currently doesn't handlde
REG_SEQUENCE.

This does regress some multi use VALU fneg cases since now the
immediate remains in an SGPR, and more moves are used for legalizing
the xor. This is a SIFixSGPRCopies deficiency.

llvm-svn: 371540
2019-09-10 17:19:46 +00:00
Matt Arsenault 7df5b3fd26 AMDGPU/GlobalISel: Select cvt pk intrinsics
llvm-svn: 371539
2019-09-10 17:17:05 +00:00
Matt Arsenault 37d1bda4f6 AMDGPU/GlobalISel: Select llvm.amdgcn.sffbh
llvm-svn: 371538
2019-09-10 17:16:59 +00:00
Matt Arsenault da027275c6 AMDGPU/GlobalISel: RegBankSelect for G_ZEXTLOAD/G_SEXTLOAD
llvm-svn: 371536
2019-09-10 16:42:37 +00:00
Matt Arsenault ad6a8b83cd AMDGPU/GlobalISel: Legalize constant 32-bit loads
Legalize by casting to a 64-bit constant address. This isn't how the
DAG implements it, but it should.

llvm-svn: 371535
2019-09-10 16:42:31 +00:00
Sam Elliott d57de491be [RISCV] Support llvm-objdump -M no-aliases and -M numeric
Summary:
Now that llvm-objdump allows target-specific options, we match the
`no-aliases` and `numeric` options for RISC-V, as supported by GNU objdump.

This is done by overriding the variables used for the command-line options, so
that the command-line options are still supported.

This patch updates all tests using `llvm-objdump -riscv-no-aliases` to use
`llvm-objdump -M no-aliases`.

Reviewers: luismarques, asb

Reviewed By: luismarques, asb

Subscribers: pzheng, hiraditya, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, kito-cheng, shiva0217, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, Jim, s.egerton, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D66139

llvm-svn: 371534
2019-09-10 16:24:03 +00:00
Matt Arsenault c0ceca5883 AMDGPU/GlobalISel: First pass at attempting to legalize load/stores
There's still a lot more to do, but this handles decomposing due to
alignment. I've gotten it to the point where nothing crashes or
infinite loops the legalizer.

llvm-svn: 371533
2019-09-10 16:20:14 +00:00
Sanjay Patel 8812157b11 [x86] add a test for BreakFalseDeps; NFC
As discussed in D67363

llvm-svn: 371528
2019-09-10 15:42:22 +00:00
Sanjay Patel d2434e65fa [ARM] add test for BreakFalseDeps with minsize attribute; NFC
llvm-svn: 371526
2019-09-10 14:29:02 +00:00
Simon Pilgrim 937ca68157 [X86] Add AVX partial dependency tests as noted on D67363
llvm-svn: 371525
2019-09-10 14:28:29 +00:00
Sanjay Patel 3b0b3def86 [ARM] auto-generate complete test checks; NFC
llvm-svn: 371524
2019-09-10 14:26:25 +00:00
Alexander Timofeev c2d292f839 [AMDGPU]: PHI Elimination hooks added for custom COPY insertion.
Reviewers: rampitec, vpykhtin

  Differential Revision: https://reviews.llvm.org/D67101

llvm-svn: 371508
2019-09-10 10:58:57 +00:00
Dmitri Gribenko 2bf8d77453 Revert "Reland "r364412 [ExpandMemCmp][MergeICmps] Move passes out of CodeGen into opt pipeline.""
This reverts commit r371502, it broke tests
(clang/test/CodeGenCXX/auto-var-init.cpp).

llvm-svn: 371507
2019-09-10 10:39:09 +00:00
Clement Courbet 612c260ec3 Reland "r364412 [ExpandMemCmp][MergeICmps] Move passes out of CodeGen into opt pipeline."
With a fix for sanitizer breakage (see explanation in D60318).

llvm-svn: 371502
2019-09-10 09:18:00 +00:00
Craig Topper e8b432fa0e [LegalizeTypes] Teach SoftenFloatOp_SELECT_CC to handle operand 2 or 3 being softened.
This can only happen on X86 when fp128 is a legal type, but we
go through softening to generate libcalls. This causes fp128 to
be softened to fp128 instead of an integer type. This can be
removed if D67128 lands.

llvm-svn: 371493
2019-09-10 07:56:02 +00:00
Craig Topper 0e533ca4bb [X86] Add broadcast load unfolding support for VCMPPS/PD.
llvm-svn: 371487
2019-09-10 05:49:53 +00:00
Craig Topper 7c2fdf2779 [X86] Add broadcast load unfold tests for VCMPPS/PD.
llvm-svn: 371486
2019-09-10 05:49:48 +00:00
Kai Luo 73da43aeb3 [PowerPC][NFC] Update test assertions using update_llc_test_checks.py
Summary:
This patch is made due to https://reviews.llvm.org/rL371289 where typo
fixes failed.

Differential Revision: https://reviews.llvm.org/D67317

llvm-svn: 371483
2019-09-10 02:28:24 +00:00
Matt Arsenault a91f017ae3 AMDGPU/GlobalISel: Fix insert point when lowering fminnum/fmaxnum
llvm-svn: 371471
2019-09-09 23:30:11 +00:00
Reid Kleckner bf02399a85 [Windows] Replace TrapUnreachable with an int3 insertion pass
This is an alternative to D66980, which was reverted. Instead of
inserting a pseudo instruction that optionally expands to nothing, add a
pass that inserts int3 when appropriate after basic block layout.

Reviewers: hans

Differential Revision: https://reviews.llvm.org/D67201

llvm-svn: 371466
2019-09-09 23:04:25 +00:00
Philip Reames 48453bb8ed [Tests] Add anyextend tests for unordered atomics
Motivated by work on changing our representation of unordered atomics in SelectionDAG, but as an aside, all our lowerings for O3 are terrible.  Even the ones which ignore the atomicity.  

llvm-svn: 371449
2019-09-09 20:26:52 +00:00
Douglas Yung 4bd6eb8ff2 Relax opcode checks in test to check for only a number instead of a specific number.
llvm-svn: 371447
2019-09-09 20:12:29 +00:00
Philip Reames 20aafa3156 Introduce infrastructure for an incremental port of SelectionDAG atomic load/store handling
This is the first patch in a large sequence. The eventual goal is to have unordered atomic loads and stores - and possibly ordered atomics as well - handled through the normal ISEL codepaths for loads and stores. Today, there handled w/instances of AtomicSDNodes. The result of which is that all transforms need to be duplicated to work for unordered atomics. The benefit of the current design is that it's harder to introduce a silent miscompile by adding an transform which forgets about atomicity.  See the thread on llvm-dev titled "FYI: proposed changes to atomic load/store in SelectionDAG" for further context.

Note that this patch is NFC unless the experimental flag is set.

The basic strategy I plan on taking is:

    introduce infrastructure and a flag for testing (this patch)
    Audit uses of isVolatile, and apply isAtomic conservatively*
    piecemeal conservative* update generic code and x86 backedge code in individual reviews w/tests for cases which didn't check volatile, but can be found with inspection
    flip the flag at the end (with minimal diffs)
    Work through todo list identified in (2) and (3) exposing performance ops

(*) The "conservative" bit here is aimed at minimizing the number of diffs involved in (4). Ideally, there'd be none. In practice, getting it down to something reviewable by a human is the actual goal. Note that there are (currently) no paths which produce LoadSDNode or StoreSDNode with atomic MMOs, so we don't need to worry about preserving any behaviour there.

We've taken a very similar strategy twice before with success - once at IR level, and once at the MI level (post ISEL). 

Differential Revision: https://reviews.llvm.org/D66309

llvm-svn: 371441
2019-09-09 19:23:22 +00:00
Matt Arsenault a0933e6df7 AMDGPU/GlobalISel: Legalize G_BUILD_VECTOR v2s16
Handle it the same way as G_BUILD_VECTOR_TRUNC. Arguably only
G_BUILD_VECTOR_TRUNC should be legal for this, but G_BUILD_VECTOR will
probably be more convenient in most cases.

llvm-svn: 371440
2019-09-09 18:57:51 +00:00
Matt Arsenault 8bc05d7d60 AMDGPU: Make VReg_1 size be 1
This was getting chosen as the preferred 32-bit register class based
on how TableGen selects subregister classes.

llvm-svn: 371438
2019-09-09 18:43:29 +00:00