| Commit message (Collapse) | Author | Age | Files | Lines | 
| ... |  | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
r zero scale SMULFIX, expand into MUL which produces better code for X86.
For vector arguments, expand into MUL if SMULFIX is provided with a zero scale.
Otherwise, expand into MULH[US] or [US]MUL_LOHI.
Differential Revision: https://reviews.llvm.org/D56987
llvm-svn: 352783
 | 
| | 
| 
| 
| 
| 
|  | 
This is causing a failure in chromium
llvm-svn: 352782
 | 
| | 
| 
| 
| 
| 
| 
| 
|  | 
This ensures that if we make it to the backend w/o lowering widenable_conditions first, that we generate correct code. Doing it in CGP - instead of isel - let's us fold control flow before hitting block local instruction selection.
Differential Revision: https://reviews.llvm.org/D57473
llvm-svn: 352779
 | 
| | 
| 
| 
|  | 
llvm-svn: 352775
 | 
| | 
| 
| 
| 
| 
|  | 
Differential Revision: https://reviews.llvm.org/D57514
llvm-svn: 352774
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
bitcast(insert_subvector(v,s,c2))
Similar to what we already do in DAGCombiner, but this version also handles bitcasts from types with different scalar sizes, which x86 is better at handling.
Differential Revision: https://reviews.llvm.org/D57514
llvm-svn: 352773
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
Reviewers: chandlerc
Reviewed By: chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D57494
llvm-svn: 352771
 | 
| | 
| 
| 
| 
| 
| 
| 
|  | 
leader"
Recommit of r352763 with fix for use after free.
llvm-svn: 352770
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
This reverts commit r352763.
Causing a couple bot failures, root cause pointed to by sanitizer bot:
http://lab.llvm.org:8011/builders/sanitizer-x86_64-linux-fast/builds/28909/steps/annotate/logs/stdio
Use after free. I understand the issue but will revert and test with fix
before recommitting.
llvm-svn: 352768
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
Summary:
COFF requires that COMDAT name match that of the leader. When we promote
and rename an internal leader in ThinLTO due to an import, ensure we
subsequently rename the associated COMDAT. Similar to D31963 which did
this during ThinLTO module splitting.
Fixes PR40414.
Reviewers: pcc, inglorion
Subscribers: mehdi_amini, dexonsmith, dmajor, llvm-commits
Differential Revision: https://reviews.llvm.org/D57395
llvm-svn: 352763
 | 
| | 
| 
| 
|  | 
llvm-svn: 352751
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
In order to make an option value truly optional, both the ValueOptional
and an empty-named value are required. This empty-named value appears in
the command-line help text, which is not ideal.
This change improves the help text for these sort of options in a number
of ways:
1) ValueOptional options with an empty-named value now print their help
text twice: both without and then with '=<value>' after the name. The
latter version then lists the allowed values after it.
2) Empty-named values with no help text in ValueOptional options are not
listed in the permitted values.
3) Otherwise empty-named options are printed as =<empty> rather than
simply '='.
4) Option values without help text do not have the '-' separator
printed.
It also tweaks the llvm-symbolizer -functions help text to not print a
trailing ':' as that looks bad combined with 1) above.
Reviewed by: thopre, ruiu
Differential Revision: https://reviews.llvm.org/D57030
llvm-svn: 352750
 | 
| | 
| 
| 
| 
| 
|  | 
Fixes regression introduced by rL352743
llvm-svn: 352745
 | 
| | 
| 
| 
| 
| 
| 
| 
|  | 
Enables 32/64-bit scalar load broadcasts on AVX1 targets
The extractelement-load.ll regression will be fixed shortly in a followup commit.
llvm-svn: 352743
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
broadcast(x)
If we're not inserting the broadcast into the lowest subvector then we can avoid the insertion by just performing a larger broadcast.
Avoids a regression when we enable AVX1 broadcasts in shuffle combining
llvm-svn: 352742
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
Introduces a pass that provides default lowering strategy for the
`experimental.widenable.condition` intrinsic, replacing all its uses with
`i1 true`.
Differential Revision: https://reviews.llvm.org/D56096
Reviewed By: reames
llvm-svn: 352739
 | 
| | 
| 
| 
|  | 
llvm-svn: 352738
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
Constants can also be materialised using the negated value and a MVN, and this
case seem to have been missed for Thumb2. To check the constant materialisation
costs, we now call getT2SOImmVal twice, once for the original constant and then
also for its negated value, and this function checks if the constant can both
be splatted or rotated.
This was revealed by a test that optimises for minsize: instead of a LDR
literal pool load and having a literal pool entry, just a MVN with an immediate
is smaller (and also faster).
Differential Revision: https://reviews.llvm.org/D57327
llvm-svn: 352737
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
And instead just generate a libcall. My motivating example on ARM was a simple:
  
  shl i64 %A, %B
for which the code bloat is quite significant. For other targets that also
accept __int128/i128 such as AArch64 and X86, it is also beneficial for these
cases to generate a libcall when optimising for minsize. On these 64-bit targets,
the 64-bits shifts are of course unaffected because the SHIFT/SHIFT_PARTS
lowering operation action is not set to custom/expand.
Differential Revision: https://reviews.llvm.org/D57386
llvm-svn: 352736
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
functions
Summary: This patch enables folding following expressions under -ffast-math flag: exp(X) * exp(Y) -> exp(X + Y), exp2(X) * exp2(Y) -> exp2(X + Y). Motivation: https://bugs.llvm.org/show_bug.cgi?id=35594
Reviewers: hfinkel, spatel, efriedma, lebedev.ri
Reviewed By: spatel, lebedev.ri
Subscribers: lebedev.ri, llvm-commits
Differential Revision: https://reviews.llvm.org/D41342
llvm-svn: 352730
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
Currently SCEV attempts to limit transformations so that they do not work with
big SCEVs (that may take almost infinite compile time). But for this, it uses heuristics
such as recursion depth and number of operands, which do not give us a guarantee
that we don't actually have big SCEVs. This situation is still possible, though it is not
likely to happen. However, the bug PR33494 showed a bunch of simple corner case
tests where we still produce huge SCEVs, even not reaching big recursion depth etc.
This patch introduces a concept of 'huge' SCEVs. A SCEV is huge if its expression
size (intoduced in D35989) exceeds some threshold value. We prohibit optimizing
transformations if any of SCEVs we are dealing with is huge. This gives us a reliable
check that we don't spend too much time working with them.
As the next step, we can possibly get rid of old limiting mechanisms, such as recursion
depth thresholds.
Differential Revision: https://reviews.llvm.org/D35990
Reviewed By: reames
llvm-svn: 352728
 | 
| | 
| 
| 
|  | 
llvm-svn: 352725
 | 
| | 
| 
| 
| 
| 
| 
| 
|  | 
This change reverts r351626.
The changes in r351626 cause quadratic work in several cases. (See r351626 thread on llvm-commits for details.)
llvm-svn: 352722
 | 
| | 
| 
| 
|  | 
llvm-svn: 352720
 | 
| | 
| 
| 
|  | 
llvm-svn: 352719
 | 
| | 
| 
| 
|  | 
llvm-svn: 352718
 | 
| | 
| 
| 
| 
| 
|  | 
For AMDGPU the result is always 32-bit for 64-bit inputs.
llvm-svn: 352717
 | 
| | 
| 
| 
| 
| 
| 
| 
|  | 
Also fix an alignment bug getMachineMemOperand. If the
tracked value is null, the offset isn't tracked so the
base alignment needs to be reduced.
llvm-svn: 352716
 | 
| | 
| 
| 
|  | 
llvm-svn: 352712
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
Summary:
Fixes PR40267, in which the removed assertion was triggering on
perfectly valid IR. As far as I can tell, constant out of bounds
indices should be allowed when splitting extract_vector_elt, since
they will simply be propagated as out of bounds indices in the
resulting split vector and handled appropriately elsewhere.
Reviewers: aheejin
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya
Differential Revision: https://reviews.llvm.org/D57471
llvm-svn: 352702
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
default case of some type legalization handlers that can be reached with intrinsics with result or operands that aren't legal types.
These can be triggered by mistakenly using a 64-bit mode only intrinsics with a -mtriple=i686. Using report_fatal_error gives a better experience for this mistake in release builds instead of probably crashing.
We already do this for some of the vector type legalization handles.
llvm-svn: 352699
 | 
| | 
| 
| 
| 
| 
|  | 
I believe this was there to handle avx512bw intrinsics that returned i64 type in 32-bit mode. But all those intrinsics have since been changed to v64i1 results or replaced with generic IR.
llvm-svn: 352698
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
ELF sections allow 0 for the alignment, which is specified to
be the same as 1.  However many clients do not expect this and
will behave poorly in the presence of a 0-aligned section (for
example by trying to modulo something by the section alignment).
We can be more polite by making sure that we always pass a
non-zero value to clients.
Differential Revision: https://reviews.llvm.org/D57482
llvm-svn: 352694
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
This teaches the legalizer to handle G_FEXP in AArch64. As a result, it also
allows us to select G_FEXP.
It...
- Updates the legalizer-info tests
- Adds a test for legalizing exp
- Updates the existing fp tests to show that we can now select G_FEXP
https://reviews.llvm.org/D57483
llvm-svn: 352692
 | 
| | 
| 
| 
| 
| 
|  | 
No test as it's a preventative fix.
llvm-svn: 352691
 | 
| | 
| 
| 
| 
| 
|  | 
Differential Revision: https://reviews.llvm.org/D57439
llvm-svn: 352689
 | 
| | 
| 
| 
|  | 
llvm-svn: 352686
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
|  | 
This adds instruction selection support for G_FABS in AArch64. It also updates
the existing basic FP tests, adds a selection test for G_FABS.
https://reviews.llvm.org/D57418
llvm-svn: 352684
 | 
| | 
| 
| 
| 
| 
| 
| 
|  | 
Subscribers: dschuff, jgravelle-google, aheejin, sunfish, llvm-commits
Differential Revision: https://reviews.llvm.org/D57477
llvm-svn: 352683
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
Summary:
After the staack is unwound due to a thrown exxception,
`__stack_pointer` global can point to an invalid address. So
a `global.set` to restore `__stack_pointer` should be inserted right
after `catch` instruction.
But after r352598 the `global.set` instruction is inserted not right
after `catch` but after `block` - `br-on-exn` - `end_block` -
`extract_exception` sequence. This CL fixes it.
While doing that, we can actually move ReplacePhysRegs pass after
LateEHPrepare and merge EHRestoreStackPointer pass into LateEHPrepare,
and now placing `global.set` to `__stack_pointer` right after `catch` is
much easier. Otherwise it is hard to guarantee that `global.set` is
still right after `catch` and not touched with other transformations, in
which case we have to do something to hoist it.
Reviewers: dschuff
Subscribers: mgorny, sbc100, jgravelle-google, sunfish, llvm-commits
Differential Revision: https://reviews.llvm.org/D57421
llvm-svn: 352681
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
This extends the existing transform for:
add X, 0/1 --> sub X, 0/-1
...to allow the sibling subtraction fold.
This pattern could regress with the proposed change in D57401.
llvm-svn: 352680
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
This teaches GlobalISel to emit a RTLib call for @llvm.log2 when it encounters
it.
It updates the existing floating point tests to show that we don't fall back on
the intrinsic, and select the correct instructions. It also adds a legalizer
test for G_FLOG2.
https://reviews.llvm.org/D57357
llvm-svn: 352673
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
This teaches the legalizer about G_FSQRT in AArch64. Also adds a legalizer
test for G_FSQRT, a selection test for it, and updates existing floating point
tests.
https://reviews.llvm.org/D57361
llvm-svn: 352671
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
Follow-up commit to https://reviews.llvm.org/D57359. (r352668)
This adds IRTranslator support for recognising a @llvm.sqrt intrinsic and
translating it into a G_FSQRT.
https://reviews.llvm.org/D57360
llvm-svn: 352670
 | 
| | 
| 
| 
| 
| 
| 
| 
|  | 
causing
assertions on some buildbots.
llvm-svn: 352666
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
This is meant to be used with clang's __builtin_dynamic_object_size.
When 'true' is passed to this parameter, the intrinsic has the
potential to be folded into instructions that will be evaluated
at run time. When 'false', the objectsize intrinsic behaviour is
unchanged.
rdar://32212419
Differential revision: https://reviews.llvm.org/D56761
llvm-svn: 352664
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
This fixes the test case in PR35982 by preventing MMX instructions that read MM0-7 from being moved below EMMS/FEMMS by the post RA scheduler.
Though as discussed in bugzilla, this is not a complete fix. There is still the possibility of reordering in IR or by the pre-RA scheduler.
Differential Revision: https://reviews.llvm.org/D57298
llvm-svn: 352660
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
The point is that this simplifies integration of new intrinsics into SimplifiedDemandedVectorElts, and ensures we don't miss any existing ones.
This is intended to be NFC-ish, but as seen from the diffs, can produce slightly different output.  This is due to order of transforms w/in instcombine resulting in two slightly different fixed points.  That's something we should fix, but isn't a problem w/this patch per se.
Differential Revision: https://reviews.llvm.org/D57398
llvm-svn: 352653
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
| 
|  | 
The LiveDebugValues pass recognizes spills but not restores, which can 
cause large gaps in location information for some variables, depending
on control flow. This patch make LiveDebugValues recognize restores and
generate appropriate DBG_VALUE instructions. 
Reviewers: aprantl, NicolaPrica
Differential Revision: https://reviews.llvm.org/D57271
llvm-svn: 352642
 | 
| | 
| 
| 
| 
| 
| 
| 
| 
|  | 
I've repeatedly encountered bugs resulting from custom legalize
mutations returning nonsense legalize results, such as increasing the
number of elements for FewerElements. Add an assert function to make
sure the type to mutate to is consistent with the legalize action.
llvm-svn: 352636
 |