Commit Graph

117665 Commits

Author SHA1 Message Date
Kostya Serebryany 2ea204e645 [lib/Fuzzer] make assertions more informative and update comments for the user-supplied mutator
llvm-svn: 238658
2015-05-30 17:33:13 +00:00
Benjamin Kramer 977d598d78 [MC] Reorder MCSymbol members to reduce padding.
sizeof(MCSymbol) goes from 72 to 64 bytes on x86_64.

llvm-svn: 238655
2015-05-30 13:52:30 +00:00
Simon Pilgrim f19ef9f741 Stripped trailing whitespace. NFC.
llvm-svn: 238654
2015-05-30 13:01:42 +00:00
Renato Golin 5d78c9ce58 Comment change. NFC
That comment misleads the current discussions in mentioned bug. Leave
the discussions to the bug. Also, adding a future change FIXME.

llvm-svn: 238653
2015-05-30 10:44:07 +00:00
Chandler Carruth cb58910ce8 [x86] Unify the horizontal adding used for popcount lowering taking the
best approach of each.

For vNi16, we use SHL + ADD + SRL pattern that seem easily the best.

For vNi32, we use the PUNPCK + PSADBW + PACKUSWB pattern. In some cases
there is a huge improvement with this in IACA's estimated throughput --
over 2x higher throughput!!!! -- but the measurements are too good to be
true. In one narrow case, the SHL + ADD + SHL + ADD + SRL pattern looks
slightly faster, but I'm not sure I believe any of the measurements at
this point. Both are the exact same uops though. Hard to be confident of
anything past that.

If anyone wants to collect very detailed (Agner-level) timings with the
result of this patch, or with the i32 case replaced with SHL + ADD + SHl
+ ADD + SRL, I'd be very interested. Note that you'll need to test it on
both Ivybridge and Haswell, with both SSE3, SSSE3, and AVX selected as
I saw unique behavior in each of these buckets with IACA all of which
should be checked against measured performance.

But this patch is still a useful improvement by dropping duplicate work
and getting the much nicer PSADBW lowering for v2i64.

I'd still like to rephrase this in terms of generic horizontal sum. It's
a bit lame to have a special case of that just for popcount.

llvm-svn: 238652
2015-05-30 10:35:03 +00:00
Renato Golin 230d298320 [ARMTargetParser] Move IAS arch ext parser. NFC
The plan was to move the whole table into the already existing ArchExtNames
but some fields depend on a table-generated file, and we don't yet have this
feature in the generic lib/Support side.

Once the minimum target-specific table-generated files are available in a
generic fashion to these libraries, we'll have to keep it in the ASM parser.

llvm-svn: 238651
2015-05-30 10:30:02 +00:00
Chandler Carruth 11e6f8fed1 [x86] Split out the horizontal byte sum lowering component of the LUT
lowering into a helper function.

NFC.

llvm-svn: 238650
2015-05-30 09:46:16 +00:00
Craig Topper 15864f1518 [TableGen] Merge RecTy::typeIsConvertibleTo and RecTy::baseClassOf. NFC
typeIsConvertibleTo was just calling baseClassOf(this) on the argument passed to it, but there weren't different signatures for baseClassOf so passing 'this' didn't really do anything interesting. typeIsConvertibleTo could have just been a non-virtual method in RecTy. But since that would be kind of a silly method, I instead re-distributed the logic from baseClassOf into typeIsConvertibleTo.

llvm-svn: 238648
2015-05-30 07:36:01 +00:00
Craig Topper 974ed6d3e7 Fix indentation. NFC.
llvm-svn: 238647
2015-05-30 07:35:21 +00:00
Craig Topper 9581906983 [TableGen] Remove all the variations of RecTy::convertValue and just handle the conversions in convertInitializerTo directly. This saves a bunch of vtable entries. NFC
llvm-svn: 238646
2015-05-30 07:34:51 +00:00
Chandler Carruth 3bedf4407b [x86] Update the order of instructions after I switched to a bitcast
helper that skips creating a cast when it isn't necessary.

It's really somewhat concerning that this was caused by the the presence
of a no-op bitcast, but...

llvm-svn: 238642
2015-05-30 06:02:37 +00:00
David Majnemer 4eecd30d19 [WinCOFF] Add support for the .safeseh directive
.safeseh adds an entry to the .sxdata section to register all the
appropriate functions which may handle an exception.  This entry is not
a relocation to the symbol but instead the symbol table index of the
function.

llvm-svn: 238641
2015-05-30 04:56:02 +00:00
Chandler Carruth 9cc2516676 [x86] Replace the long spelling of getting a bitcast with the *much*
shorter one. NFC.

In addition to being much shorter to type and requiring fewer arguments,
this change saves over 30 lines from this one file, all wasted on total
boilerplate...

llvm-svn: 238640
2015-05-30 04:23:13 +00:00
Chandler Carruth 060cdca996 [x86] Replace the long spelling of getting a bitcast with the new short
spelling. NFC.

llvm-svn: 238639
2015-05-30 04:19:57 +00:00
Chandler Carruth 502b23a7a9 [sdag] Add the helper I most want to the DAG -- building a bitcast
around a value using its existing SDLoc.

Start using this in just one function to save omg lines of code.

llvm-svn: 238638
2015-05-30 04:14:10 +00:00
Chandler Carruth 2599da3cfd [x86] Restore the bitcasts I removed when refactoring this to avoid
shifting vectors of bytes as x86 doesn't have direct support for that.

This removes a bunch of redundant masking in the generated code for SSE2
and SSE3.

In order to avoid the really significant code size growth this would
have triggered, I also factored the completely repeatative logic for
shifting and masking into two lambdas which in turn makes all of this
much easier to read IMO.

llvm-svn: 238637
2015-05-30 04:05:11 +00:00
Chandler Carruth 6ba9730a4e [x86] Implement a faster vector population count based on the PSHUFB
in-register LUT technique.

Summary:
A description of this technique can be found here:
http://wm.ite.pl/articles/sse-popcount.html

The core of the idea is to use an in-register lookup table and the
PSHUFB instruction to compute the population count for the low and high
nibbles of each byte, and then to use horizontal sums to aggregate these
into vector population counts with wider element types.

On x86 there is an instruction that will directly compute the horizontal
sum for the low 8 and high 8 bytes, giving vNi64 popcount very easily.
Various tricks are used to get vNi32 and vNi16 from the vNi8 that the
LUT computes.

The base implemantion of this, and most of the work, was done by Bruno
in a follow up to D6531. See Bruno's detailed post there for lots of
timing information about these changes.

I have extended Bruno's patch in the following ways:

0) I committed the new tests with baseline sequences so this shows
   a diff, and regenerated the tests using the update scripts.

1) Bruno had noticed and mentioned in IRC a redundant mask that
   I removed.

2) I introduced a particular optimization for the i32 vector cases where
   we use PSHL + PSADBW to compute the the low i32 popcounts, and PSHUFD
   + PSADBW to compute doubled high i32 popcounts. This takes advantage
   of the fact that to line up the high i32 popcounts we have to shift
   them anyways, and we can shift them by one fewer bit to effectively
   divide the count by two. While the PSHUFD based horizontal add is no
   faster, it doesn't require registers or load traffic the way a mask
   would, and provides more ILP as it happens on different ports with
   high throughput.

3) I did some code cleanups throughout to simplify the implementation
   logic.

4) I refactored it to continue to use the parallel bitmath lowering when
   SSSE3 is not available to preserve the performance of that version on
   SSE2 targets where it is still much better than scalarizing as we'll
   still do a bitmath implementation of popcount even in scalar code
   there.

With #1 and #2 above, I analyzed the result in IACA for sandybridge,
ivybridge, and haswell. In every case I measured, the throughput is the
same or better using the LUT lowering, even v2i64 and v4i64, and even
compared with using the native popcnt instruction! The latency of the
LUT lowering is often higher than the latency of the scalarized popcnt
instruction sequence, but I think those latency measurements are deeply
misleading. Keeping the operation fully in the vector unit and having
many chances for increased throughput seems much more likely to win.

With this, we can lower every integer vector popcount implementation
using the LUT strategy if we have SSSE3 or better (and thus have
PSHUFB). I've updated the operation lowering to reflect this. This also
fixes an issue where we were scalarizing horribly some AVX lowerings.

Finally, there are some remaining cleanups. There is duplication between
the two techniques in how they perform the horizontal sum once the byte
population count is computed. I'm going to factor and merge those two in
a separate follow-up commit.

Differential Revision: http://reviews.llvm.org/D10084

llvm-svn: 238636
2015-05-30 03:20:59 +00:00
Chandler Carruth c2e400de83 [x86] Restructure the parallel bitmath lowering of popcount into
a separate routine, generalize it to work for all the integer vector
sizes, and do general code cleanups.

This dramatically improves lowerings of byte and short element vector
popcount, but more importantly it will make the introduction of the
LUT-approach much cleaner.

The biggest cleanup I've done is to just force the legalizer to do the
bitcasting we need. We run these iteratively now and it makes the code
much simpler IMO. Other changes were minor, and mostly naming and
splitting things up in a way that makes it more clear what is going on.

The other significant change is to use a different final horizontal sum
approach. This is the same number of instructions as the old method, but
shifts left instead of right so that we can clear everything but the
final sum with a single shift right. This seems likely better than
a mask which will usually have to read the mask from memory. It is
certaily fewer u-ops. Also, this will be temporary. This and the LUT
approach share the need of horizontal adds to finish the computation,
and we have more clever approaches than this one that I'll switch over
to.

llvm-svn: 238635
2015-05-30 03:20:55 +00:00
Jim Grosbach 13760bd152 MC: Clean up MCExpr naming. NFC.
llvm-svn: 238634
2015-05-30 01:25:56 +00:00
Filipe Cabecinhas 14e686774d [BitcodeReader] Change an assert to a call to a call to Error()
It's reachable from user input.

Bug found with AFL fuzz.

llvm-svn: 238633
2015-05-30 00:17:20 +00:00
Fiona Glaser b82e33106b SelectionDAG: fix logic for promoting shift types
r238503 fixed the problem of too-small shift types by promoting them
during legalization, but the correct solution is to promote only the
operands that actually demand promotion.

This fixes a crash on an out-of-tree target caused by trying to
promote an operand that can't be promoted.

llvm-svn: 238632
2015-05-29 23:37:22 +00:00
Reid Kleckner e6531a5588 [WinEH] Adjust the 32-bit SEH prologue to better match reality
It turns out that _except_handler3 and _except_handler4 really use the
same stack allocation layout, at least today. They just make different
choices about encoding the LSDA.

This is in preparation for lowering the llvm.eh.exceptioninfo().

llvm-svn: 238627
2015-05-29 22:57:46 +00:00
Jingyue Wu 2cfd9d574d [docs] fix the declarations of the llvm.nvvm.ptr.gen.to.* intrinsics
Summary:
These intrinsics should take a generic input address space and outputs a
non-generic address space.

Test Plan: no

Reviewers: jholewinski, eliben

Reviewed By: eliben

Subscribers: eliben, jholewinski, llvm-commits

Differential Revision: http://reviews.llvm.org/D10132

llvm-svn: 238620
2015-05-29 22:18:03 +00:00
Reid Kleckner 173a72524f Disable FP elimination in funcs using 32-bit MSVC EH personalities
The value in 'ebp' acts as an implicit argument to the outlined
handlers, and is recovered with frameaddress(1).

llvm-svn: 238619
2015-05-29 21:58:11 +00:00
Rafael Espindola 4d37b2a259 Remove getData.
This completes the mechanical part of merging MCSymbol and MCSymbolData.

llvm-svn: 238617
2015-05-29 21:45:01 +00:00
Reid Kleckner 5b8ebfbc25 Only add the EH state insertion pass on 32-bit Windows
llvm-svn: 238612
2015-05-29 20:43:10 +00:00
Rafael Espindola beb6060a51 Remove the MCSymbolData typedef.
The getData member function is next.

llvm-svn: 238611
2015-05-29 20:41:47 +00:00
Rafael Espindola e45f0c1609 Merge MCSymbol and MCSymbolData.
As a transition hack leave MCSymbolData as a typedef of MCSymbol. I will be
removing that in a second.

llvm-svn: 238609
2015-05-29 20:31:23 +00:00
Kostya Serebryany 3fe7682fb0 [lib/Fuzzer] relax an assertion
llvm-svn: 238608
2015-05-29 20:31:17 +00:00
Rafael Espindola b5d316bfc3 Rename getOrCreateSymbolData to registerSymbol and return void.
Another step in merging MCSymbol and MCSymbolData.

llvm-svn: 238607
2015-05-29 20:21:02 +00:00
Benjamin Kramer f5e2fc474d Replace push_back(Constructor(foo)) with emplace_back(foo) for non-trivial types
If the type isn't trivially moveable emplace can skip a potentially
expensive move. It also saves a couple of characters.


Call sites were found with the ASTMatcher + some semi-automated cleanup.

memberCallExpr(
    argumentCountIs(1), callee(methodDecl(hasName("push_back"))),
    on(hasType(recordDecl(has(namedDecl(hasName("emplace_back")))))),
    hasArgument(0, bindTemporaryExpr(
                       hasType(recordDecl(hasNonTrivialDestructor())),
                       has(constructExpr()))),
    unless(isInTemplateInstantiation()))

No functional change intended.

llvm-svn: 238602
2015-05-29 19:43:39 +00:00
Rafael Espindola 2229d33a9c Move Flags from MCSymbolData to MCSymbol.
llvm-svn: 238598
2015-05-29 19:07:51 +00:00
Rafael Espindola d31c0e2673 Fix build without asserts.
llvm-svn: 238597
2015-05-29 19:04:38 +00:00
Rafael Espindola e3b2acf274 Pass MCSymbols to the helper functions in MCELF.h.
llvm-svn: 238596
2015-05-29 18:47:23 +00:00
Chris Bieneman 7c445dd6c7 [CMake] Bug 23468 - LLVM_OPTIMIZED_TABLEGEN does not work with Visual Studio
Summary: Multi-configuration builds put their binaries into ${CMAKE_BINARY_DIR}/Release/bin/. The table-gen cross-compilation support needs to take that into account.

Reviewers: yaron.keren

Reviewed By: yaron.keren

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D10102

llvm-svn: 238592
2015-05-29 18:34:41 +00:00
Rafael Espindola e19faeed71 Use an explicitly defaulted constructor.
llvm-svn: 238591
2015-05-29 18:31:17 +00:00
Rafael Espindola ece40ca43d Pass a MCSymbol to needsRelocateWithSymbol.
llvm-svn: 238589
2015-05-29 18:26:09 +00:00
Matthias Braun 165d467125 MachineCopyPropagation: Remove the copies instead of using KILL instructions.
For some history here see the commit messages of r199797 and r169060.

The original intent was to fix cases like:

%EAX<def> = COPY %ECX<kill>, %RAX<imp-def>
%RCX<def> = COPY %RAX<kill>

where simply removing the copies would have RCX undefined as in terms of
machine operands only the ECX part of it is defined. The machine
verifier would complain about this so 169060 changed such COPY
instructions into KILL instructions so some super-register imp-defs
would be preserved. In r199797 it was finally decided to always do this
regardless of super-register defs.

But this is wrong, consider:
R1 = COPY R0
...
R0 = COPY R1
getting changed to:
R1 = KILL R0
...
R0 = KILL R1

It now looks like R0 dies at the first KILL and won't be alive until the
second KILL, while in reality R0 is alive and must not change in this
part of the program.

As this only happens after register allocation there is not much code
still performing liveness queries so the issue was not noticed.  In fact
I didn't manage to create a testcase for this, without unrelated changes
I am working on at the moment.

The fix is simple: As of r223896 the MachineVerifier allows reads from
partially defined registers, so the whole transforming COPY->KILL thing
is not necessary anymore. This patch also changes a similar (but more
benign case as the def and src are the same register) case in the
VirtRegRewriter.

Differential Revision: http://reviews.llvm.org/D10117

llvm-svn: 238588
2015-05-29 18:19:25 +00:00
Frederic Riss 3733c03d3b YAML traits need to be in the llvm::yaml namespace.
Hope this fixes the bits, eg:
http://lab.llvm.org:8011/builders/clang-hexagon-elf/builds/27147

llvm-svn: 238586
2015-05-29 18:14:55 +00:00
Frederic Riss 4939e6a1b8 [YAMLIO] Make line-wrapping configurable and test it.
Summary:
We would wrap flow mappings and sequences when they go over a hardcoded 70
characters limit. Make the wrapping column configurable (and default to 70
co the change should be NFC for current users). Passing 0 allows to completely
suppress the wrapping which makes it easier to handle in tools like FileCheck.

Reviewers: bogner

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D10109

llvm-svn: 238584
2015-05-29 17:56:28 +00:00
Rafael Espindola 14672508b1 Move common symbol related information from MCSectionData to MCSymbol.
llvm-svn: 238583
2015-05-29 17:48:04 +00:00
Rafael Espindola 66ccf49a0c Store MCSymbols in PendingLabels.
llvm-svn: 238582
2015-05-29 17:41:59 +00:00
Rafael Espindola 7c23cba65c Move SymbolSize from MCSymbolData to MCSymbol.
llvm-svn: 238580
2015-05-29 17:24:52 +00:00
Pete Cooper c5a7177772 Fix crash in MCExpr::print.
Symbols are no longer required to be named, but this leads to a crash here if an
unnamed symbol checks that its first character is '$'.

Change the code to first check for a name, then check its first character.

No test case i'm afraid as this is debugging code, but any test case with temp labels
and 'llc --debug --filetype=obj' would have crashed.

llvm-svn: 238579
2015-05-29 17:19:11 +00:00
Nemanja Ivanovic 376e17364f Add support for VSX FMA single-precision instructions to the PPC back end
This patch corresponds to review:
http://reviews.llvm.org/D9941

It adds the various FMA instructions introduced in the version 2.07 of
the ISA along with the testing for them. These are operations on single
precision scalar values in VSX registers.

llvm-svn: 238578
2015-05-29 17:13:25 +00:00
Alex Lorenz 09b832cac5 MIR Serialization: use correct line and column numbers for LLVM IR errors.
This commit translates the line and column numbers for LLVM IR
errors from the numbers in the YAML block scalar to the numbers 
in the MIR file so that the MIRParser users can report LLVM IR 
errors with the correct line and column numbers.

Reviewers: Duncan P. N. Exon Smith

Differential Revision: http://reviews.llvm.org/D10108

llvm-svn: 238576
2015-05-29 17:05:41 +00:00
Reid Kleckner 1d3d4adbb9 [WinEH] Emit EH tables for __CxxFrameHandler3 on 32-bit x86
Small (really small!) C++ exception handling examples work on 32-bit x86
now.

This change disables the use of .seh_* directives in WinException when
CFI is not in use. It also uses absolute symbol references in the tables
instead of imagerel32 relocations.

Also fixes a cache invalidation bug in MMI personality classification.

llvm-svn: 238575
2015-05-29 17:00:57 +00:00
Jingyue Wu 995dde2799 [NVPTXFavorNonGenericAddrSpaces] recursively trace into GEP and BitCast
Summary:
This patch allows NVPTXFavorNonGenericAddrSpaces to remove addrspacecast
from longer chains consisting of GEPs and BitCasts. For example, it can
now optimize

  %0 = addrspacecast [10 x float] addrspace(3)* @a to [10 x float]*
  %1 = gep [10 x float]* %0, i64 0, i64 %i
  %2 = bitcast float* %1 to i32*
  %3 = load i32* %2 ; emits ld.u32

to

  %0 = gep [10 x float] addrspace(3)* @a, i64 0, i64 %i
  %1 = bitcast float addrspace(3)* %0 to i32 addrspace(3)*
  %3 = load i32 addrspace(3)* %1 ; emits ld.shared.f32

Test Plan: @ld_int_from_global_float in access-non-generic.ll

Reviewers: broune, eliben, jholewinski, meheff

Subscribers: jholewinski, llvm-commits

Differential Revision: http://reviews.llvm.org/D10074

llvm-svn: 238574
2015-05-29 17:00:27 +00:00
Jingyue Wu a84feb1727 [DependenceAnalysis] Extend unifySubscriptType for handling coupled subscript groups.
Summary:
In continuation to an earlier commit to DependenceAnalysis.cpp by jingyue (r222100), the type for all subscripts in a coupled group need to be the same since constraints from one subscript may be propagated to another during testing. During testing, new SCEVs may be created and the operands for these need to be the same.
This patch extends unifySubscriptType() to work on lists of subscript pairs, ensuring a common extended type for all of them.

Test Plan:
Added a test case to NonCanonicalizedSubscript.ll which causes dependence analysis to crash without this fix.

All regression tests pass.

Reviewers: spop, sebpop, jingyue

Reviewed By: jingyue

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D9698

llvm-svn: 238573
2015-05-29 16:58:08 +00:00
Rafael Espindola f4b4430f8c Simplify now that symbols contain the correct section.
The complexity in here was because before r233995 variable symbols would report
the incorrect section.

llvm-svn: 238559
2015-05-29 15:07:27 +00:00