Age | Commit message (Collapse) | Author |
|
These will be using inline asm to ensure we have coverage that we're unlikely to get from lowering of basic ir.
Currently waiting for D39728 to land to add support for scheduler comments for inline asm.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317698 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
instructions. Remove bad pattern that had vf432 vcvtps2ph storing 128-bits.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317662 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Rely on EVEX->VEX to convert back.
Missed store folding opportunities will be fixed in a subsequent commit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317661 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
visibility.
Differential Revision: https://reviews.llvm.org/D39625
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317639 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Reland r317100 with minor fix regarding ComputeCommonTailLength function in
BranchFolding.cpp. Skipping top CFI instructions block needs to executed on
several more return points in ComputeCommonTailLength().
Original r317100 message:
"Correct dwarf unwind information in function epilogue for X86"
This patch aims to provide correct dwarf unwind information in function
epilogue for X86.
It consists of two parts. The first part inserts CFI instructions that set
appropriate cfa offset and cfa register in emitEpilogue() in
X86FrameLowering. This part is X86 specific.
The second part is platform independent and ensures that:
- CFI instructions do not affect code generation
- Unwind information remains correct when a function is modified by
different passes. This is done in a late pass by analyzing information
about cfa offset and cfa register in BBs and inserting additional CFI
directives where necessary.
Changed CFI instructions so that they:
- are duplicable
- are not counted as instructions when tail duplicating or tail merging
- can be compared as equal
Added CFIInstrInserter pass:
- analyzes each basic block to determine cfa offset and register valid at
its entry and exit
- verifies that outgoing cfa offset and register of predecessor blocks match
incoming values of their successors
- inserts additional CFI directives at basic block beginning to correct the
rule for calculating CFA
Having CFI instructions in function epilogue can cause incorrect CFA
calculation rule for some basic blocks. This can happen if, due to basic
block reordering, or the existence of multiple epilogue blocks, some of the
blocks have wrong cfa offset and register values set by the epilogue block
above them.
CFIInstrInserter is currently run only on X86, but can be used by any target
that implements support for adding CFI instructions in epilogue.
Patch by Violeta Vukobrat.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317579 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317571 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Summary:
Calls using invoke in funclet based functions are assumed to clobber
all registers, which causes the stack adjustment using pops to consider
all registers not defined by the call to be undefined, which can
unfortunately include the base pointer, if one is needed.
To prevent this (and possibly other hazards), skip reserved registers
when looking for candidate registers.
This fixes issue #45034 in the Rust compiler.
Reviewers: mkuper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D39636
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317551 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317548 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Disable the peephole pass to prove that the pattern is working.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317547 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
The instruction only loads 64-bits, but we should be able to fold a wider load and let it be narrowed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317546 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
shouldn't be required for load folding.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317545 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
intrinsics.
Looks like there's some missed load folding opportunities for i64 loads.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317544 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
opportunities for the legacy intrinsics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317543 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
COPY_TO_REGCLASS.
ExeDepsFix pass should take care of making the registers match.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317542 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
The EVEX to VEX pass is already assuming this is true under AVX512VL. We had special patterns to use zmm instructions if VLX and F16C weren't available.
Instead just make AVX512 imply F16C to make the EVEX to VEX behavior explicitly legal and remove the extra patterns.
All known CPUs with AVX512 have F16C so this should safe for now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317521 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Summary:
Print %subreg.<subregidxname> instead of just the subregister
index when printing immediate operands corresponding to subreg
indices in INSERT_SUBREG, EXTRACT_SUBREG, SUBREG_TO_REG and
REG_SEQUENCE.
Reviewers: qcolombet, MatzeB
Reviewed By: MatzeB
Subscribers: nhaehnle, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D39696
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317513 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Added TESTM and TESTNM to the list of instructions that already zeroing unused upper bits
and does not need the redundant shift left and shift right instructions afterwards.
Added a pattern for TESTM and TESTNM in iselLowering, so now icmp(neq,and(X,Y), 0) goes folds into TESTM
and icmp(eq,and(X,Y), 0) goes folds into TESTNM
This commit is a preparation for lowering the test and testn X86 intrinsics to IR.
Differential Revision: https://reviews.llvm.org/D38732
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317465 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Summary:
Try to lower a BUILD_VECTOR composed of extract-extract chains that can be
reasoned to be a permutation of a vector by indices in a non-constant vector.
We saw this pattern created by ISPC, which resolts to creating it due to the
requirement that shufflevector's mask operand be a *constant* vector.
I didn't check this but we could possibly use this pattern for lowering the X86 permute
C-instrinsics instead of llvm.x86 instrinsics.
This change can be followed by more improvements:
1. Handle vectors with undef elements.
2. Utilize pshufb and zero-mask-blending to support more effiecient
construction of vectors with constant-0 elements.
3. Use smaller-element vectors of same width, and "interpolate" the indices,
when no native operation available.
Reviewers: RKSimon, craig.topper
Reviewed By: RKSimon
Subscribers: chandlerc, DavidKreitzer
Differential Revision: https://reviews.llvm.org/D39126
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317463 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This patch, together with a matching clang patch (https://reviews.llvm.org/D38683), implements the lowering of X86 broadcastm intrinsics to IR.
Differential Revision: https://reviews.llvm.org/D38684
Change-Id: I709ac0b34641095397e994c8ff7e15d1315b3540
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317458 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317454 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Some of these demonstrate a missed EVEX to VEX compression because we aren't prefering EVEX instructions during isel.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317452 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
-show-mc-encoding.
Use feature names instead of CPU names.
A future commit will add avx512vl command lines to demonstrate missed use of EVEX instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317451 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Fixes PR35161.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317445 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
missed in r317413.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317441 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Matching patterns that vectorizers should have created for us.
The experimental intrinsics should probably be added as well.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317439 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317424 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
SSE rcp/rsqrt intrinsics when AVX512 features are enabled.
Summary:
AVX512 added RCP14 and RSQRT instructions which improve accuracy over the legacy RCP and RSQRT instruction, but not enough accuracy to remove the need for a Newton Raphson refinement.
Currently we use these new instructions for the legacy packed SSE instrinics, but not the scalar instrinsics. And we use it for fast math optimization of division and reciprocal sqrt.
I think switching the legacy instrinsics maybe surprising to the user since it changes the answer based on which processor you're using regardless of any fastmath settings. It's also weird that we did something different between scalar and packed.
As far at the reciprocal estimation, I think it creates unnecessary deltas in our output behavior (and prevents EVEX->VEX). A little playing around with gcc and icc and godbolt suggest they don't change which instructions they use here.
This patch adds new X86ISD nodes for the RCP14/RSQRT14 and uses those for the new intrinsics. Leaving the old intrinsics to use the old instructions.
Going forward I think our focus should be on
-Supporting 512-bit vectors, which will have to use the RCP14/RSQRT14.
-Using RSQRT28/RCP28 to remove the Newton Raphson step on processors with AVX512ER
-Supporting double precision.
Reviewers: zvi, DavidKreitzer, RKSimon
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D39583
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317413 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317412 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
into VPERM2F128/VPERM2I128.
This recovers some of the tests that were changed by r317403.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317410 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This allows masked operations to be used and allows the register allocator to use YMM16-31 if necessary.
As a follow up I'll look into teaching EVEX->VEX how to turn this back into PERM2X128 if any of the additional features don't work out.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317403 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
make it possible to fold a load.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317382 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Differential Revision: https://reviews.llvm.org/D39546
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317330 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Fix undefined references: ExpandMemCmp belongs to CodeGen/, not Scalar/.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317318 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value.
We have to account for pre-SSE41 targets not supporting PACKUSDW
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317315 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
to isel patterns instead. Prefer 128-bit VALIGND/VALIGNQ over PALIGNR during lowering when possible.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317299 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Differential Revision: https://reviews.llvm.org/D39065
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317292 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
I thought we had gotten all these priority bugs worked out, but I guess not.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317283 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
undefined reference to `llvm::TargetPassConfig::ID' on
clang-ppc64le-linux-multistage
This reverts commit eea333c33fa73ad225ef28607795984829f65688.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317213 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Summary:
This is mostly a noop (most of the test diffs are renamed blocks).
There are a few temporary register renames (eax<->ecx) and a few blocks are
shuffled around.
See the discussion in PR33325 for more details.
Reviewers: spatel
Subscribers: mgorny
Differential Revision: https://reviews.llvm.org/D39456
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317211 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
When splitting a large load to smaller legally-typed loads, the last load should be padded to reach the size of the previous one so a CONCAT_VECTORS node could reunite them again.
The code currently pads the last load to reach the size of the first load (instead of the previous).
Differential Revision: https://reviews.llvm.org/D38495
Change-Id: Ib60b55ed26ce901fabf68108daf52683fbd5013f
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317206 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Change-Id: Iefcb0ec6b6aa1b530ce5358081f02e6e522a8e50
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317202 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
VXOR, VPERMILx, VBROADCASTx, etc.
PR32857 should be closed.
Differential Revision: https://reviews.llvm.org/D39227
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317196 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Test is failing due to the revert in r317136. Fix the test to make all
the bots happy.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317153 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This reverts r317100 as it introduced sanitizer-x86_64-linux-autoconf
buildbot failure (build #15606).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317136 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Similar to the existing code to lower to PACKSS, we can use PACKUS if the input vector's leading zero bits extend all the way to the packed/truncated value.
We have to account for pre-SSE41 targets not supporting PACKUSDW
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317128 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
VPALIGND/Q into VPALIGNR if the extended registers aren't being used.
This will enable us to prefer VALIGND/Q during shuffle lowering in order to get the extended register encoding space when BWI isn't available. But if we end up not using the extended registers we can switch VPALIGNR for the shorter VEX encoding.
Differential Revision: https://reviews.llvm.org/D39401
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317122 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
hasPartialRegUpdate.
This patch moves the check for opt size and hasPartialRegUpdate into the lower level implementation of foldMemoryOperandImpl to catch the entry point that fast isel uses.
We're still folding undef register instructions in AVX that we should also probably disable, but that's a problem for another patch.
Unfortunately, this requires reordering a bunch of functions which is why the diff is so large. I can do the function reordering separately if we want.
Differential Revision: https://reviews.llvm.org/D39402
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317112 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317107 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
X86FastISel::X86SelectSIToFP
Summary:
[X86] Teach fast isel to handle i64 sitofp with AVX.
For some reason we only handled i32 sitofp with AVX. But with SSE only we support i64 so we should do the same with AVX.
Also add i686 command lines for the 32-bit tests. 64-bit tests are in a separate file to avoid a fast-isel abort failure in 32-bit mode.
Reviewers: RKSimon, zvi
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D39450
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317102 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Differential Revision: https://reviews.llvm.org/D39059
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@317101 91177308-0d34-0410-b5e6-96231b3b80d8
|