Summary:
Local common symbols were properly inserted into the .bss section.
However, putting external common symbols in the .bss section would give
them a strong definition.
Instead, encode them as undefined, external symbols who's symbol value
is equivalent to their size.
Reviewers: Bigcheese, rafael, rnk
CC: llvm-commits
Differential Revision: http://reviews.llvm.org/D3324
llvm-svn: 205811
:doc:`...` and :ref:`...` links help Sphinx keep track the dependencies
between documents and ensure that they are not pointing to nowhere.
Raw HTML links work just fine and are easier for people less familiar
with reST/Sphinx. They are easy to change over to the :doc:/:ref: style
after the fact so this is not a problem.
This commit doesn't fix all of them.
llvm-svn: 205792
This implements the target-hooks for ARM64 to enable constant hoisting.
This fixes <rdar://problem/14774662> and <rdar://problem/16381500>.
llvm-svn: 205791
Until r197284, the entry frequency was constant -- i.e., set to 2^14.
Although current ToT still has a constant entry frequency, since r197284
that has been an implementation detail (which is soon going to change).
- r204690 made the wrong assumption for the CSRCost metric. Adjust
callee-saved register cost based on entry frequency.
- r185393 made the wrong assumption (although it was valid at the
time). Update SpillPlacement.cpp::Threshold to be relative to the
entry frequency.
Since ToT still has 2^14 entry frequency, this should have no observable
functionality change.
<rdar://problem/14292693>
llvm-svn: 205789
PPC::isVSLDOIShuffleMask should return -1, not false, when the shuffle
predicate should be false.
Noticed by inspection; no test case (yet).
llvm-svn: 205787
Summary:
This adds support in 'opt' to filter pass remarks emitted by
optimization passes. A new flag -pass-remarks specifies which
passes should emit a diagnostic when LLVMContext::emitOptimizationRemark
is invoked.
This will allow the front end to simply pass along the regular
expression from its own -Rpass flag when launching the backend.
Depends on D3227.
Reviewers: qcolombet
CC: llvm-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D3291
llvm-svn: 205775
Summary:
This patch adds backend support for -Rpass=, which indicates the name
of the optimization pass that should emit remarks stating when it
made a transformation to the code.
Pass names are taken from their DEBUG_NAME definitions.
When emitting an optimization report diagnostic, the lack of debug
information causes the diagnostic to use "<unknown>:0:0" as the
location string.
This is the back end counterpart for
http://llvm-reviews.chandlerc.com/D3226
Reviewers: qcolombet
CC: llvm-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D3227
llvm-svn: 205774
Confusingly, the NEON fmla instructions put the accumulator first but the
scalar versions put it at the end (like the fma lib function & LLVM's
intrinsic).
This should fix PR19345, assuming there's only one issue.
llvm-svn: 205758
indirectly requires a function analysis.
This bug was reported by Jason Kim. He included a test case here:
http://reviews.llvm.org/D3312
llvm-svn: 205753
Before, we would have conditional operators where one side of the
operator would be of type RelocationTypeAMD64 and the other is of type
RelocationTypeI386. GCC would noisly warn with -Wenum-compare
diagnostic.
Instead, refactor the code so it is more like the X86 ELF object writer.
llvm-svn: 205752
The IO normalizer would essentially lump I386 and AMD64 relocations
together. Relocation types with the same numeric value would then get
mapped in appropriately.
For example:
IMAGE_REL_AMD64_ADDR64 and IMAGE_REL_I386_DIR16 both have a numeric
value of one. We would see IMAGE_REL_I386_DIR16 in obj2yaml conversions
of object files with a machine type of IMAGE_FILE_MACHINE_AMD64.
llvm-svn: 205746
Fixes PR16365 - Extremely slow compilation in -O1 and -O2.
The SD scheduler has a quadratic implementation of load clustering
which absolutely blows up compile time for large blocks with constant
pool loads. The MI scheduler has a better implementation of load
clustering. However, we have not done the work yet to completely
eliminate the SD scheduler. Some benchmarks still seem to benefit from
early load clustering, although maybe by chance.
As an intermediate term fix, I just put a nice limit on the number of
DAG users to search before finding a match. With this limit there are no
binary differences in the LLVM test suite, and the PR16365 test case
does not suffer any compile time impact from this routine.
llvm-svn: 205738
Moving these patterns from TableGen files to PerformDAGCombine()
should allow us to generate better code by eliminating unnecessary
shifts and extensions earlier.
This also fixes a bug where the MAD pattern was calling
SimplifyDemandedBits with a 24-bit mask on the first operand
even when the full pattern wasn't being matched. This occasionally
resulted in some instructions being incorrectly deleted from the
program.
v2:
- Fix bug with 64-bit mul
llvm-svn: 205731
Using this file would result in an odr violation: it defines an llvm::Interval
class that conflicts with the one in Analysis/Interval.h.
llvm-svn: 205726
into a constant size alloca by inlining.
Ran a run over the testsuite, no results out of the noise, fixes
the testcase in the PR.
PR19115.
llvm-svn: 205710
cygwin has llvm-dwarfdump problems and isn't paying attention to the
specific xfail there.
s390x isn't matching for an unknown reason.
llvm-svn: 205708
- take->release: LLVM has moved to C++11. MockWrapper became an instance of unique_ptr.
- method symbol_iterator::increment disappeared recently, in this revision:
r200442 | rafael | 2014-01-29 20:49:50 -0600 (Wed, 29 Jan 2014) | 9 lines
Simplify the handling of iterators in ObjectFile.
None of the object file formats reported error on iterator increment. In
retrospect, that is not too surprising: no object format stores symbols or
sections in a linked list or other structure that requires chasing pointers.
As a consequence, all error checking can be done on begin() and end().
This reduces the text segment of bin/llvm-readobj in my machine from 521233 to
518526 bytes.
My change mimics the change that the revision made to lib/DebugInfo/DWARFContext.cpp .
- const_cast: Shut up a warning from gcc.
I ran unittests/ExecutionEngine/JIT/Debug+Asserts/JITTests to make sure it worked.
- Arch
llvm-svn: 205689
It affected callee's stack pop in x86. It is one of devergences between cygwin and mingw since mingw-gcc-4.6.
Added testcases to llvm/test/CodeGen/X86/win32_sret.ll for cygwin.
llvm-svn: 205688
I really should read the spec more often (and test GCC more often too).
I just assumed that namespace aliases would be the same as using
directives, except with a name. But apparently that's not how the DWARF
standards suggests they be implemented. DWARF4 provides an example and
other non-normative text suggesting that namespace aliases be
implemented by named imported declarations intsead of named imported
modules.
So be it.
llvm-svn: 205685
Also update a few null pointers in this function to be consistent with
new null pointers being added.
Patch by Robert Matusewicz!
Differential Revision: http://reviews.llvm.org/D3123
llvm-svn: 205682
This adds a warning when linker_private or linker_private_weak is provided and
we handle it in a compatible manner.
Suggested by Chris Lattner!
llvm-svn: 205681
Member functions defined within a class definition are implicitly
'inline' for linkage purposes. Compilers might slightly favor inlining
functions explicitly marked 'inline', but LLVM doesn't make a stylistic
habit of doing this generally.
llvm-svn: 205679
This consolidates the duplicated MachO checks in the directive parsing for
various directives that are unsupported for Mach-O. The error message change is
unimportant as this restores the behaviour to that prior to the addition of the
new directive handling. Furthermore, use a more direct check for MachO
targeting rather than an indirect feature check of the assembler.
Also simplify the test execution command to avoid temporary files. Further more,
perform the check in both object and assembly emission.
Whether all non-applicable directives are handled is another question. .fnstart
is marked as being unsupported, however, the complementary .fnend is not. The
additional unwinding directives are also still honoured. This change does not
change that, though, it would be good to validate and mark them as being
unsupported if they are unsupported for the MachO emission.
llvm-svn: 205678
This avoids an extra copy during decompression and avoids the use of
MemoryBuffer which is a weirdly esoteric device that includes unrelated
concepts like "file name" (its rather generic name is a bit misleading).
Similar refactoring of zlib::compress coming up.
llvm-svn: 205676
This restores the linker_private and linker_private_weak lexemes to permit
translation of the deprecated lexmes. The behaviour is identical to the bitcode
handling: linker_private and linker_private_weak are handled as if private had
been specified. This enables compatibility with IR generated by LLVM 3.4.
Reported on IRC by ki9a!
llvm-svn: 205675
This provides more realistic costs for the insert/extractelement instructions
(which are load/store pairs), accounts for the cheap unaligned Altivec load
sequence, and for unaligned VSX load/stores.
Bad news:
MultiSource/Applications/sgefa/sgefa - 35% slowdown (this will require more investigation)
SingleSource/Benchmarks/McGill/queens - 20% slowdown (we no longer vectorize this, but it was a constant store that was scalarized)
MultiSource/Benchmarks/FreeBench/pcompress2/pcompress2 - 2% slowdown
Good news:
SingleSource/Benchmarks/Shootout/ary3 - 54% speedup
SingleSource/Benchmarks/Shootout-C++/ary - 40% speedup
MultiSource/Benchmarks/Ptrdist/ks/ks - 35% speedup
MultiSource/Benchmarks/FreeBench/neural/neural - 30% speedup
MultiSource/Benchmarks/TSVC/Symbolics-flt/Symbolics-flt - 20% speedup
Unfortunately, estimating the costs of the stack-based scalarization sequences
is hard, and adjusting these costs is like a game of whac-a-mole :( I'll
revisit this again after we have better codegen for vector extloads and
truncstores and unaligned load/stores.
llvm-svn: 205658
This patch adds the Octeon cnMips instructions seqi/snei and v3mulu/vmm0/vmulu.
It is only for the assembler. Test case is included.
Reviewed by: Daniel.Sanders@imgtec.com
llvm-svn: 205631
gcc inline asm supports specifying "cc" as a clobber of all condition
registers. Add just enough modeling of the full register to make this work.
Fixed PR19326.
llvm-svn: 205630
Summary:
They behave in accordance with the Has2008 and ABS2008 configuration bits of the
processor which are used to select between the 1985 and 2008 versions of IEEE
754. In 1985 mode, these instructions are arithmetic (i.e. they raise invalid
operation exceptions when given NaN), in 2008 mode they are non-arithmetic
(i.e. they are copies).
nmadd.[ds], and nmsub.[ds] are still subject to -enable-no-nans-fp-math because
the ISA spec does not explicitly state that they obey Has2008 and ABS2008.
Reviewers: matheusalmeida
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D3274
llvm-svn: 205628
When LLVM sees something like (v1iN (vselect v1i1, v1iN, v1iN)) it can
decide that the result is OK (v1i64 is legal on AArch64, for example)
but it still need scalarising because of that v1i1. There was no code
to do this though.
AArch64 and ARM64 have DAG combines to produce efficient code and
prevent that occuring in *most* such situations, but there are edge
cases that they miss. This adds a legalization to cope with that.
llvm-svn: 205626
There were several overlapping problems here, and this solution is
closely inspired by the one adopted in AArch64 in r201381.
Firstly, scalarisation of v1i1 setcc operations simply fails if the
input types are legal. This is fixed in LegalizeVectorTypes.cpp this
time, and allows AArch64 code to be simplified slightly.
Second, vselect with such a setcc feeding into it ends up in
ScalarizeVectorOperand, where it's not handled. I experimented with an
implementation, but found that whatever DAG came out was rather
horrific. I think Hao's DAG combine approach is a good one for
quality, though there are edge cases it won't catch (to be fixed
separately).
Should fix PR19335.
llvm-svn: 205625
Removed "GNU Assembler extension (compatibility)" definitions from ARMInstrInfo.td
Fixed ARMAsmParser::ParseInstruction GNU compatability branch, so it also works for thumb mode from now.
Added new tests.
llvm-svn: 205622
Sorry for the breakage.
For now, it will fail in two ways:
1. To fail for targeting x86_64-mingw32.
<stdin>:131:8: note: possible intended match here
0x30830a0100000002 3 0 1 0 0 is_stmt
2. To fail not to find the target x86.
llc: : error: unable to get target for 'x86_64-unknown-unknown',
see --version and --triple.
llvm-svn: 205621
The previous patterns directly inserted FMOV or INS instructions into
the DAG for scalar_to_vector & bitconvert patterns. This is horribly
inefficient and can generated lots more GPR <-> FPR register traffic
than necessary.
It's much better to emit instructions the register allocator
understands so it can coalesce the copies when appropriate.
It led to at least one ISelLowering hack to avoid the problems, which
was incorrect for v1i64 (FPR64 has no dsub). It can now be removed
entirely.
This should also fix PR19331.
llvm-svn: 205616
Without this change, the llvm_unreachable kicked in. The code pattern
being spotted is rather non-canonical for 128-bit MLAs, but it can
happen and there's no point in generating sub-optimal code for it just
because it looks odd.
Should fix PR19332.
llvm-svn: 205615
recoloring cut-offs are encountered and register allocation failed.
This is related to PR18747
Patch by MAYUR PANDEY <mayur.p@samsung.com>.
llvm-svn: 205601
Removes unnecessary casts from non-generic address spaces to the generic address
space for certain code patterns.
Patch by Jingyue Wu.
llvm-svn: 205571
When rematerializing through truncates, the coalescer may produce instructions
with dead defs, but live implicit-defs of subregs:
E.g.
%X1<def,dead> = MOVi64imm 2, %W1<imp-def>; %X1:GPR64, %W1:GPR32
These instructions are live, and their definitions should not be rewritten.
Fixes <rdar://problem/16492408>
llvm-svn: 205565
Acording to AMD documentation, the correct opcode for
BFE_INT is 0x5, not 0x4
Fixes Arithm/Absdiff.Mat/3 OpenCV test
Patch by: Bruno Jiménez
llvm-svn: 205562
these is very much off and is more than just the branch
from this bug incorrect:
Address Line Column File ISA Discriminator Flags
------------------ ------ ------ ------ --- ------------- -------------
0x30830a0100000002 3 0 1 0 0 is_stmt
0x30830a0100000008 3 0 1 0 0 is_stmt end_sequence
llvm-svn: 205551
More updating of tests to be explicit about the target triple rather than
relying on the default target triple supporting ARM mode.
Indicate to lit that object emission is not yet available for Windows on ARM.
llvm-svn: 205545
This changes the tests that were targeting ARM EABI to explicitly specify the
environment rather than relying on the default. This breaks with the new
Windows on ARM support when running the tests on Windows where the default
environment is no longer EABI.
Take the opportunity to avoid a pointless redirect (helps when trying to debug
with providing a command line invocation which can be copy and pasted) and
removing a few greps in favour of FileCheck.
llvm-svn: 205541
Implementing this via ComputeMaskedBits has two advantages:
+ It actually works. DAGISel doesn't deal with the chains properly
in the previous pattern-based solution, so they never trigger.
+ The information can be used in other DAG combines, as well as the
trivial "get rid of truncs". For example if the trunc is in a
different basic block.
rdar://problem/16227836
llvm-svn: 205540
Summary:
test/MC/Mips/<isa1>/invalid-<isa2>.s
Test that <isa1> does not support <isa2>'s instructions.
test/MC/Mips/<isa1>/invalid-<isa2>-xfail.s
Things that should be invalid but currently aren't. Will XPASS if any
become invalid.
Reviewers: matheusalmeida
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D3262
llvm-svn: 205538
The terminal barrier of a cmpxchg expansion will be either Acquire or
SequentiallyConsistent. In either case it can be skipped if the
operation has Monotonic requirements on failure.
rdar://problem/15996804
llvm-svn: 205535
Summary:
Adds the 'mips4' processor and a simple test of the ELF e_flags.
Patch by David Chisnall
His work was sponsored by: DARPA, AFRL
I made one small change to the testcase so that it uses
mips64-unknown-linux instead of mips4-unknown-linux.
This patch indirectly adds FeatureCondMov to FeatureMips64. This is ok
because it's supposed to be there anyway and it turns out that
FeatureCondMov is not a predicate of any instructions at the moment
(this is a bug that hasn't been noticed because there are no targets
without the conditional move instructions yet).
CC: theraven
Differential Revision: http://llvm-reviews.chandlerc.com/D3244
llvm-svn: 205530
llc doesn't generate nodes for unconditional fall-through branches for targets
without FastISel implementation (X86 has it, but can be disabled by
"-fast-isel=false") in SelectionDAGBuilder::visitBr().
So for line 4 in the following testcase
1: void foo(int i){
2: switch(i){
3: default:
4: break;
5: }
6: return;
7: }
there is no corresponding line in .debug_line section, and a debugger
cannot set a breakpoint at line 4.
Fix this by always emitting a branch when we're not optimizing and add a
testcase to ensure that there's code on every line we'd want to break.
Patch by Daniil Fukalov.
llvm-svn: 205529
The previous situation where ATOMIC_LOAD_WHATEVER nodes were expanded
at MachineInstr emission time had grown to be extremely large and
involved, to account for the subtly different code needed for the
various flavours (8/16/32/64 bit, cmpxchg/add/minmax).
Moving this transformation into the IR clears up the code
substantially, and makes future optimisations much easier:
1. an atomicrmw followed by using the *new* value can be more
efficient. As an IR pass, simple CSE could handle this
efficiently.
2. Making use of cmpxchg success/failure orderings only has to be done
in one (simpler) place.
3. The common "cmpxchg; did we store?" idiom can be exposed to
optimisation.
I intend to gradually improve this situation within the ARM backend
and make sure there are no hidden issues before moving the code out
into CodeGen to be shared with (at least ARM64/AArch64, though I think
PPC & Mips could benefit too).
llvm-svn: 205525
The trouble as in ARMAsmParser, in ParseInstruction method. It assumes that ARM::R12 + 1 == ARM::SP.
It is wrong, since ARM::<Register> codes are generated by tablegen and actually could be any random numbers.
llvm-svn: 205524
add operation since extract_vector_elt can perform an extend operation. Get the input lane
type from the vector on which we're performing the vpaddl operation on and extend or
truncate it to the output type of the original add node.
llvm-svn: 205523
%highest(sym1 - sym2 + const) relocations. Remove "ABS_" from VK_Mips_HI
and VK_Mips_LO enums in MipsMCExpr, to be consistent with VK_Mips_HIGHER
and VK_Mips_HIGHEST.
This change also deletes test file test/MC/Mips/higher_highest.ll and moves
its CHECK's to the new test file test/MC/Mips/higher-highest-addressing.s.
The deleted file tests that R_MIPS_HIGHER and R_MIPS_HIGHEST relocations are
emitted in the .o file. Since it uses -force-mips-long-branch option, it was
created when MipsLongBranch's implementation was emitting R_MIPS_HIGHER and
R_MIPS_HIGHEST relocations in the .o file. It was disabled when MipsLongBranch
started to directly calculate offsets.
Differential Revision: http://llvm-reviews.chandlerc.com/D3230
llvm-svn: 205522
Switching between i32 and i64 based on the LHS type is a good idea in
theory, but pre-legalisation uses i64 regardless of our choice,
leading to potential ISel errors.
Should fix PR19294.
llvm-svn: 205519
While we were encoding 64 bit values (data8) in the subrange itself,
using a 32 bit type for the subrange was still confusing the gdb. Oh,
and make it unsigned too.
As the comment points out, this could be pushed into the frontend so
that it would be 32 or 64 bit as appropriate, etc.
llvm-svn: 205512
I should have read that comment a little more carefully. ;)
Regression test in the works, committing in the mean time to un-break people.
llvm-svn: 205511
This has the following advantages:
* Less code.
* The old ELF implementation was wrong for non-relocatable objects.
* The old ELF implementation (and I think MachO) was wrong for thumb.
No current testcase since this is only used from MCJIT and it only uses
relocatable objects and I don't think it supports thumb yet.
llvm-svn: 205508
When a vector type legalizes to a larger vector type, and the target does not
support the associated extending load (or truncating store), then legalization
will scalarize the load (or store) resulting in an associated scalarization
cost. BasicTTI::getMemoryOpCost needs to account for this.
Between this, and r205487, PowerPC on the P7 with VSX enabled shows:
MultiSource/Benchmarks/PAQ8p/paq8p: 43% speedup
SingleSource/Benchmarks/BenchmarkGame/puzzle: 51% speedup
SingleSource/UnitTests/Vectorizer/gcc-loops 28% speedup
(some of these are new; some of these, such as PAQ8p, just reverse regressions
that VSX support would trigger)
llvm-svn: 205495
This reverts commit r205479.
It turns out that nm does use addresses, it is just that every reasonable
relocatable ELF object has sections with address 0. I have no idea if those
exist in reality, but it at least it shows that llvm-nm should use the name
address.
The added test was includes an unusual .o file with non 0 section addresses. I
created it by hacking ELFObjectWriter.cpp.
Really sorry for the churn.
llvm-svn: 205493
TargetInstrInfo::findCommutedOpIndices to enable VFMA*231 commutation, rather
than abusing commuteInstruction.
Thanks very much for the suggestion guys!
llvm-svn: 205489
For an cast (extension, etc.), the currently logic predicts a low cost if the
associated operation (keyed on the destination type) is legal (or promoted).
This is not true when the number of values required to legalize the type is
changing. For example, <8 x i16> being sign extended by <8 x i32> is not
generically cheap on PPC with VSX, even though sign extension to v4i32 is
legal, because two output v4i32 values are required compared to the single
v8i16 input value, and without custom logic in the target, this conversion will
scalarize.
llvm-svn: 205487
What llvm-nm prints depends on the file format. On ELF for example, if the
file is relocatable, it prints offsets. If it is not, it prints addresses.
Since it doesn't really need to care what it is that it is printing, use the
generic term value.
Fix or implement getSymbolValue to keep llvm-nm working.
llvm-svn: 205479
PPCTTI::getMemoryOpCost will now make use of BasicTTI::getMemoryOpCost to
calculate the base cost of the memory access, and then adjust on top of that.
There is no functionality change from this modification, but it will become
important so that PPCTTI can take advantage of scalarization information for which
BasicTTI::getMemoryOpCost will account in the near future.
llvm-svn: 205476
on FMA3 memory operands. FMA3 instructions are VEX encoded, so they can load
from unaligned memory.
Testcase to follow, along with related patch.
<rdar://problem/16478629>
llvm-svn: 205472
This changes the tests that were targeting ARM EABI to explicitly specify the
environment rather than relying on the default. This breaks with the new
Windows on ARM support when running the tests on Windows where the default
environment is no longer EABI.
Take the opportunity to avoid a pointless redirect (helps when trying to debug
with providing a command line invocation which can be copy and pasted) and
removing a few greps in favour of FileCheck.
llvm-svn: 205465
Just pass a MachineInstr reference rather than an MBB iterator.
Creating a MachineInstr& is the first thing every implementation did
anyway.
llvm-svn: 205453
Unlike other v6+ processors, cortex-m0 never supports unaligned accesses.
From the v6m ARM ARM:
"A3.2 Alignment support: ARMv6-M always generates a fault when an unaligned
access occurs."
rdar://16491560
llvm-svn: 205452
Adds the instructions ext/ext32/cins/cins32.
It also changes pop/dpop to accept the two operand version and
adds a simple pattern to generate baddu.
Tests for the two operand versions (including baddu/dmul/dpop/pop)
and the code generation pattern for baddu are included.
Reviewed by: Daniel.Sanders@imgtec.com
llvm-svn: 205449
and ContiguousBlobAccumulator classes. Pass ContiguousBlobAccumulator to
the handleSymtabSectionHeader function directly.
No functional changes.
llvm-svn: 205431
Weak symbols cannot use the small code model's usual ADRP sequences since the
instruction simply may not be able to encode a value of 0.
This redirects them to use the GOT, which hopefully linkers are able to cope
with even in the static relocation model.
llvm-svn: 205426
Some Intrinsics are overloaded to the extent that return type equality (all
that's been checked up to now) does not guarantee that the arguments are the
same. In these cases SLP vectorizer should not recurse into the operands, which
can be achieved by comparing them as "Function *" rather than simply the ID.
llvm-svn: 205424
Again, coalescing and other optimisations swiftly made the MachineInstrs
consistent again, but when compiled at -O0 a bad INSERT_SUBREGISTER was
produced.
llvm-svn: 205423
The previous attempt was fine with optimisations, but was actually rather
cavalier with its types. When compiled at -O0, it produced invalid COPY
MachineInstrs.
llvm-svn: 205422
ARM specific optimiztion, finding places in ARM machine code where 2 dmbs
follow one another, and eliminating one of them.
Patch by Reinoud Elhorst.
llvm-svn: 205409
and isTargetCygwin() to isTargetWindowsCygwin() to be consistent with the
four Windows environments in Triple.h.
Suggestion by Saleem Abdulrasool!
llvm-svn: 205393
For the purpose of calculating the cost of the loop at various vectorization
factors, we need to count dependencies of consecutive pointers as uniforms
(which means that the VF = 1 cost is used for all overall VF values).
For example, the TSVC benchmark function s173 has:
...
%3 = add nsw i64 %indvars.iv, 16000
%arrayidx8 = getelementptr inbounds %struct.GlobalData* @global_data, i64 0, i32 0, i64 %3
...
and we must realize that the add will be a scalar in order to correctly deduce
it to be profitable to vectorize this on PowerPC with VSX enabled. In fact, all
dependencies of a consecutive pointer must be a scalar (uniform), and so we
simply need to add all consecutive pointers to the worklist that currently
detects collects uniforms.
Fixes PR19296.
llvm-svn: 205387
I'm not sure the comment in the implementation really adds a lot of
value (it's clear that we emit zero when no symbol is provided, but it
doesn't explain why we would do that). Happy to iterate.
llvm-svn: 205386
This removes the magic-number-esque code creating/retrieving the same
label for a debug_loc entry from two places and removes the last small
piece of reusable logic from emitDebugLoc so that there will be less
duplication when refactoring it into two functions (one for debug_loc,
the other for debug_loc.dwo).
llvm-svn: 205382
Seems we didn't have any test coverage for merging... awesome. So I
added some - but hit an llvm-objdump bug while I was there. I'm choosing
not to shave that yak right now.
Code review feedback/bug catch by Adrian Prantl in r205360.
llvm-svn: 205373
No test case (this would invoke UB by examining uninitialized members,
etc, at best - and this code is apparently untested anyway - I'm about
to fix that)
Code review feedback from Adrian Prantl on r205360.
llvm-svn: 205367
This provides an initial implementation of getUnrollingPreferences for x86.
getUnrollingPreferences is used by the generic (concatenation) unroller, which
is distinct from the unrolling done by the loop vectorizer. Many modern x86
cores have some kind of uop cache and loop-stream detector (LSD) used to
efficiently dispatch small loops, and taking full advantage of this requires
unrolling small loops (small here means 10s of uops).
These caches also have limits on the number of taken branches in the loop, and
so we also cap the loop unrolling factor based on the maximum "depth" of the
loop. This is currently calculated with a partial DFS traversal (partial
because it will stop early if the path length grows too much). This is still an
approximation, and one that is both conservative (because it does not account
for branches eliminated via block placement) and optimistic (because it is only
recording the maximum depth over minimum paths). Nevertheless, because the
loops that fit in these uop caches are so small, it is not clear how much the
details matter.
The original set of patches posted for review produced the following test-suite
performance results (from the TSVC benchmark) at that time:
ControlLoops-dbl - 13% speedup
ControlLoops-flt - 15% speedup
Reductions-dbl - 7.5% speedup
llvm-svn: 205348
In preparation for an upcoming commit implementing unrolling preferences for
x86, this adds additional fields to the UnrollingPreferences structure:
- PartialThreshold and PartialOptSizeThreshold - Like Threshold and
OptSizeThreshold, but used when not fully unrolling. These are necessary
because we need different thresholds for full unrolling from those used when
partially unrolling (the full unrolling thresholds are generally going to be
larger).
- MaxCount - A cap on the unrolling factor when partially unrolling. This can
be used by a target to prevent the unrolled loop from exceeding some
resource limit independent of the loop size (such as number of branches).
There should be no functionality change for any in-tree targets.
llvm-svn: 205347
The implementation of getUserCost had duplicated (and hard-coded) the default
logic in getGEPCost. Instead, it is better to use getGEPCost directly, which
limits the default logic to the implementation of one function, and allows
targets to override the behavior.
No functionality change intended.
llvm-svn: 205346
Identical to Win32 method except the GS segment register is used for TLS
instead of FS and pvArbitrary is at TEB offset 0x28 instead of 0x14.
llvm-svn: 205342
The Cyclone CPU is similar to swift for most LLVM purposes, but does have two
preferred instructions for zeroing a VFP register. This teaches LLVM about
them.
llvm-svn: 205309
This is for consistency with other functions. The Parse* functions consume
tokens and the Match* functions don't.
No functional change.
llvm-svn: 205305
Summary:
This should fix the issues the D3222 caused in lld. Testcase is based on
the one that failed in the buildbot.
Depends on D3233
Reviewers: matheusalmeida, vmedic
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D3234
llvm-svn: 205298
Summary:
Parsing registers no longer consume the $ token before it's confirmed whether it really has a register or not, therefore it's no longer impossible to match symbols if registers were tried first.
Depends on D3232
Reviewers: matheusalmeida, vmedic
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D3233
llvm-svn: 205297
Summary:
Highlights:
- Registers are resolved much later (by the render method).
Prior to that point, GPR32's/GPR64's are GPR's regardless of register
size. Similarly FGR32's/FGR64's/AFGR64's are FGR's regardless of register
size or FR mode. Numeric registers can be anything.
- All registers are parsed the same way everywhere (even when handling
symbol aliasing)
- One consequence is that all registers can be specified numerically
almost anywhere (e.g. $fccX, $wX). The exception is symbol aliasing
but that can be easily resolved.
- Removes the need for the hasConsumedDollar hack
- Parenthesis and Bracket suffixes are handled generically
- Micromips instructions are parsed directly instead of going through the
standard encodings first.
- rdhwr accepts all 32 registers, and the following instructions that previously
xfailed now work:
ddiv, ddivu, div, divu, cvt.l.[ds], se[bh], wsbh, floor.w.[ds], c.ngl.d,
c.sf.s, dsbh, dshd, madd.s, msub.s, nmadd.s, nmsub.s, swxc1
- Diagnostics involving registers point at the correct character (the $)
- There's only one kind of immediate in MipsOperand. LSA immediates are handled
by the predicate and renderer.
Lowlights:
- Hardcoded '$zero' in the div patterns is handled with a hack.
MipsOperand::isReg() will return true for a k_RegisterIndex token
with Index == 0 and getReg() will return ZERO for this case. Note that it
doesn't return ZERO_64 on isGP64() targets.
- I haven't cleaned up all of the now-unused functions.
Some more of the generic parser could be removed too (integers and relocs
for example).
- insve.df needed a custom decoder to handle the implicit fourth operand that
was needed to make it parse correctly. The difficulty was that the matcher
expected a Token<'0'> but gets an Imm<0>. Adding an implicit zero solved this.
Reviewers: matheusalmeida, vmedic
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D3222
llvm-svn: 205292
Making the new TableGen documentation official and marking the old file as
"Moved". Also, reverting the original LangRef as the normative formal
description of the language, while keeping the "new" LangRef as LangIntro
for the less inlcined to reading language grammars.
We should remove TableGenFundamentals.rst one day, but for now, just a
warning that it moved will have to do, while we make sure there are no more
links to it from elsewhere.
llvm-svn: 205289
This moves one case of raw text checking down into the MCStreamer
interfaces in the form of a virtual function, even if we ultimately end
up consolidating on the one-or-many line tables issue one day, this is
nicer in the interim. This just generally streamlines a bunch of use
cases into a common code path.
llvm-svn: 205287
I don't think this is reachable by any frontend (why would you transform
asm to asm+debug info?) but it helps tidy up some of this code, avoid
the weird special case of "emit the first CU, store the label, then emit
the rest" in MCDwarfLineTable::Emit by instead having the
DWARF-for-assembly case use the same codepath as DwarfDebug.cpp, by
registering the label of the debug_line section, thus causing it to be
emitted. (with a special case in asm output to just emit the label since
asm output uses the .loc directives, etc, rather than the debug_loc
directly)
llvm-svn: 205286
No other functionality changes, DIBuilder testcase is included in a paired
CFE commit.
This relaxes the assertion in isScopeRef to also accept subclasses of
DIScope.
llvm-svn: 205279
Cygwin is now a proper environment rather than an OS. This updates the MCJIT
tests to avoid execution on Cygwin. This fixes native cygwin tests.
llvm-svn: 205266
The generic (concatenation) loop unroller is currently placed early in the
standard optimization pipeline. This is a good place to perform full unrolling,
but not the right place to perform partial/runtime unrolling. However, most
targets don't enable partial/runtime unrolling, so this never mattered.
However, even some x86 cores benefit from partial/runtime unrolling of very
small loops, and follow-up commits will enable this. First, we need to move
partial/runtime unrolling late in the optimization pipeline (importantly, this
is after SLP and loop vectorization, as vectorization can drastically change
the size of a loop), while keeping the full unrolling where it is now. This
change does just that.
llvm-svn: 205264
Setting this parameter enables llvm-lit to run on source directories for
compiler-rt test suites that implement magic in their lit.cfg.
<rdar://problem/16458307>
llvm-svn: 205262
This reverts commit r205018.
Conflicts:
lib/Transforms/Vectorize/SLPVectorizer.cpp
test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
This is breaking libclc build.
llvm-svn: 205260
This commit updates the stackmap format to version 1 to indicate the
reorganizaion of several fields. This was done in order to align stackmap
entries to their natural alignment and to minimize padding.
Fixes <rdar://problem/16005902>
llvm-svn: 205254
A value of 5 means if we have a split or spill option that has a really
low cost (1 << 14 is the entry frequency), we will choose to spill
or split the really cold path before using a callee-saved register.
This gives us the performance benefit on SPECInt2k and is also conservative.
rdar://16162005
llvm-svn: 205248
This patch is to fix the following warning when compiled with MSVC 64 bit.
warning C4334: '<<' : result of 32-bit shift implicitly converted to 64
bits (was 64-bit shift intended?)
llvm-svn: 205245
This adds the ability to expand large (meaning with more than two unique
defined values) BUILD_VECTOR nodes in terms of SCALAR_TO_VECTOR and (legal)
vector shuffles. There is now no limit of the size we are capable of expanding
this way, although we don't currently do this for vectors with many unique
values because of the default implementation of TLI's
shouldExpandBuildVectorWithShuffles function.
There is currently no functional change to any existing targets because the new
capabilities are not used unless some target overrides the TLI
shouldExpandBuildVectorWithShuffles function. As a result, I've not included a
test case for the new functionality in this commit, but regression tests will
(at least) be added soon when I commit support for the PPC QPX vector
instruction set.
The benefit of committing this now is that it makes the
shouldExpandBuildVectorWithShuffles callback, which had to be added for other
reasons regardless, fully functional. I suspect that other targets will
also benefit from tuning the heuristic.
llvm-svn: 205243
If we have two unique values for a v2i64 build vector, this will always result
in two vector loads if we expand using shuffles. Only one is necessary.
llvm-svn: 205231
There are two general methods for expanding a BUILD_VECTOR node:
1. Use SCALAR_TO_VECTOR on the defined scalar values and then shuffle
them together.
2. Build the vector on the stack and then load it.
Currently, we use a fixed heuristic: If there are only one or two unique
defined values, then we attempt an expansion in terms of SCALAR_TO_VECTOR and
vector shuffles (provided that the required shuffle mask is legal). Otherwise,
always expand via the stack. Even when SCALAR_TO_VECTOR is not legal, this
can still be a good idea depending on what tricks the target can play when
lowering the resulting shuffle. If the target can't do anything special,
however, and if SCALAR_TO_VECTOR is expanded via the stack, this heuristic
leads to sub-optimal code (two stack loads instead of one).
Because only the target knows whether the SCALAR_TO_VECTORs and shuffles for a
build vector of a particular type are likely to be optimial, this adds a new
TLI function: shouldExpandBuildVectorWithShuffles which takes the vector type
and the count of unique defined values. If this function returns true, then
method (1) will be used, subject to the constraint that all of the necessary
shuffles are legal (as determined by isShuffleMaskLegal). If this function
returns false, then method (2) is always used.
This commit does not enhance the current code to support expanding a
build_vector with more than two unique values using shuffles, but I'll commit
an implementation of the more-general case shortly.
llvm-svn: 205230
Summary:
Highlights:
- Registers are resolved much later (by the render method).
Prior to that point, GPR32's/GPR64's are GPR's regardless of register
size. Similarly FGR32's/FGR64's/AFGR64's are FGR's regardless of register
size or FR mode. Numeric registers can be anything.
- All registers are parsed the same way everywhere (even when handling
symbol aliasing)
- One consequence is that all registers can be specified numerically
almost anywhere (e.g. $fccX, $wX). The exception is symbol aliasing
but that can be easily resolved.
- Removes the need for the hasConsumedDollar hack
- Parenthesis and Bracket suffixes are handled generically
- Micromips instructions are parsed directly instead of going through the
standard encodings first.
- rdhwr accepts all 32 registers, and the following instructions that previously
xfailed now work:
ddiv, ddivu, div, divu, cvt.l.[ds], se[bh], wsbh, floor.w.[ds], c.ngl.d,
c.sf.s, dsbh, dshd, madd.s, msub.s, nmadd.s, nmsub.s, swxc1
- Diagnostics involving registers point at the correct character (the $)
- There's only one kind of immediate in MipsOperand. LSA immediates are handled
by the predicate and renderer.
Lowlights:
- Hardcoded '$zero' in the div patterns is handled with a hack.
MipsOperand::isReg() will return true for a k_RegisterIndex token
with Index == 0 and getReg() will return ZERO for this case. Note that it
doesn't return ZERO_64 on isGP64() targets.
- I haven't cleaned up all of the now-unused functions.
Some more of the generic parser could be removed too (integers and relocs
for example).
- insve.df needed a custom decoder to handle the implicit fourth operand that
was needed to make it parse correctly. The difficulty was that the matcher
expected a Token<'0'> but gets an Imm<0>. Adding an implicit zero solved this.
Reviewers: matheusalmeida, vmedic
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D3222
llvm-svn: 205229
part of an asm .symver directive as being used. This prevents referenced
functions from being internalized and deleted.
Without the patch to LTOModule.cpp, the test case will produce the error:
LLVM ERROR: A @@ version cannot be undefined.
llvm-svn: 205221
This generalises the object file type parsing to all Windows environments. This
is used by cygwin as well as MSVC environments for MCJIT. This also makes the
triple more similar to Chandler's suggestion of a separate field for the object
file format.
llvm-svn: 205219
Now that r205212 was committed, r203483 is no longer necessary; it was a
temporary workaround that only handled a small number of the problematic cases.
llvm-svn: 205216
This is a more thorough fix for the issue than r203483. An IR pass will run
before NVPTX codegen to make sure there are no invalid symbol names that can't
be consumed by the ptxas assembler.
llvm-svn: 205212
%got_hi, %got_lo, %call_hi, %call_lo, %higher, and %highest are now recognised
by MipsAsmParser::getVariantKind().
To prevent future issues with missing entries in this StringSwitch, I've added
an assertion to the default case.
llvm-svn: 205200
Unlike my previous commit, don't try to remove the corresponding VK_Mips_GOT yet
even though it shares the same assembly text since that is used.
llvm-svn: 205196
Summary:
Where those ISA's are not currently supported, the test is run with the smallest
superset of that ISA.
Some instructions are valid but don't pass yet. These have been placed in the
valid-xfail.s's which will XPASS if _any_ instruction starts working.
The valid.s's do not verify the encoding yet. There are also no tests checking that instructions from neighbouring ISA's are not accepted.
Reviewers: matheusalmeida
Reviewed By: matheusalmeida
Differential Revision: http://llvm-reviews.chandlerc.com/D3214
llvm-svn: 205180
When the loop vectorizer vectorizes code that uses the loop induction variable,
we often end up with IR like this:
%b1 = insertelement <2 x i32> undef, i32 %v, i32 0
%b2 = shufflevector <2 x i32> %b1, <2 x i32> undef, <2 x i32> zeroinitializer
%i = add <2 x i32> %b2, <i32 2, i32 3>
If the add in this example is not legal (as is the case on PPC with VSX), it
will be scalarized, and we'll end up with a number of extract_vector_elt nodes
with the vector shuffle as the input operand, and that vector shuffle is fed by
one or more build_vector nodes. By the time that vector operations are
expanded, visitEXTRACT_VECTOR_ELT will not create new extract_vector_elt by
looking through the vector shuffle (to make sure that no illegal operations are
created), and so the extract_vector_elt -> vector shuffle -> build_vector is
never simplified to an operand of the build vector.
By looking at build_vectors through a shuffle we fix this particular situation,
preventing a vector from being built, only to be deconstructed again (for the
scalarized add) -- an expensive proposition when this all needs to be done via
the stack. We probably want a more comprehensive fix here where we look back
recursively through any shuffles to any build_vectors or scalar_to_vectors,
etc. but that can come later.
llvm-svn: 205179
While reviewing r204163, I noticed that the MIPS16 test only checked for a .ent
directive and didn't actually check the code emitted. Fixed this and added a
check for llvm.bswap.i32 on MIPS64 at the same time.
llvm-svn: 205177
Summary:
The FileHeader mapping now accepts an optional Flags sequence that accepts
the EF_<arch>_<flag> constants. When not given, Flags defaults to zero.
Reviewers: atanasyan
Reviewed By: atanasyan
CC: llvm-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D3213
llvm-svn: 205173
Previously, MinGW OS was Triple::MinGW and Cygwin was Triple::Cygwin
and now it is Triple::Win32 with Environment being GNU or Cygwin.
So,
TheTriple.getOS() == Triple::Win32
is replaced by
TheTriple.isWindowsMSVCEnvironment()
and
(TheTriple.getOS() == Triple::MinGW32 || TheTriple.getOS() == Triple::Cygwin)
is replaced by
TheTriple.isOSCygMing()
llvm-svn: 205170
is not a pattern to lower this with clever instructions that zero the
register, so restrict the zero immediate legality special case to f64
and f32 (the only two sizes which fmov seems to directly support). Fixes
backend errors when building code such as libxml.
llvm-svn: 205161
There is no direct AVX instruction to convert to unsigned. I have some ideas
how we may be able to do this with three vector instructions but the current
backend just bails on this to get it scalarized.
See the comment why we need to adjust the cost returned by BasicTTI.
The test is a bit roundabout (and checks assembly rather than bit code) because
I'd like it to work even if at some point we could vectorize this conversion.
Fixes <rdar://problem/16371920>
llvm-svn: 205159
When expanding EXTRACT_VECTOR_ELT and EXTRACT_SUBVECTOR using
SelectionDAGLegalize::ExpandExtractFromVectorThroughStack, we store the entire
vector and then load the piece we want. This is fine in isolation, but
generating a new store (and corresponding stack slot) for each extraction ends
up producing code of poor quality. When we scalarize a vector operation (using
SelectionDAG::UnrollVectorOp for example) we generate one EXTRACT_VECTOR_ELT
for each element in the vector. This used to generate one stored copy of the
vector for each element in the vector. Now we search the uses of the vector for
a suitable store before generating a new one, which results in much more
efficient scalarization code.
llvm-svn: 205153
sitofp from v2i32 to v2f64 ends up generating a SIGN_EXTEND_INREG v2i64 node
(and similarly for v2i16 and v2i8). Even though there are no sign-extension (or
algebraic shifts) for v2i64 types, we can handle v2i32 sign extensions by
converting two and from v2i64. The small trick necessary here is to shift the
i32 elements into the right lanes before the i32 -> f64 step. This is because
of the big Endian nature of the system, we need the i32 portion in the high
word of the i64 elements.
For v2i16 and v2i8 we can do the same, but we first use the default Altivec
shift-based expansion from v2i16 or v2i8 to v2i32 (by casting to v4i32) and
then apply the above procedure.
llvm-svn: 205146
parameters rather than runtime parameters.
There is only one user of these parameters and they are compile time for
that user. Making these compile time seems to better reflect their
intended usage as well.
llvm-svn: 205143
That causes references to them to be weak references which can collapse
to null if no definition is provided. We call these functions
unconditionally, so a definition *must* be provided. Make the
definitions provided in the .cpp file weak by re-declaring them as weak
just prior to defining them. This should keep compilers which cannot
attach the weak attribute to the definition happy while actually
resolving the symbols correctly during the link.
You might ask yourself upon reading this commit log: how did *any* of
this work before? Well, fun story. It turns out we have some code in
Support (BumpPtrAllocator) which both uses virtual dispatch and has
out-of-line vtables used by that virtual dispatch. If you move the
virtual dispatch into its header in *just* the right way, the optimizer
gets to devirtualize, and remove all references to the vtable. Then the
sad part: the references to this one vtable were the only strong symbol
uses in the support library for llvm-tblgen AFAICT. At least, after
doing something just like this, these symbols stopped getting their weak
definition and random calls to them would segfault instead.
Yay software.
llvm-svn: 205137
StringRef::lower() returns a std::string. Better yet, we can now stop
thinking about what it returns and write 'auto'. It does the right
thing. =]
llvm-svn: 205135
It was doing functional but highly suspect operations on bools due to
the more limited shifting operands supported by memory instructions.
Should fix some MSVC warnings.
llvm-svn: 205134
Actually, mostly only those in the top-level directory that already
had a "virtual" attached. But it's the thought that counts and it's
been a long day.
llvm-svn: 205131
If the environment is unknown and no object file is provided, then assume an
"MSVC" environment, otherwise, set the environment to the object file format.
In the case that we have a known environment but a non-native file format for
Windows (COFF) which is used for MCJIT, then append the custom file format to
the triple as an additional component.
This fixes the MCJIT tests on Windows.
llvm-svn: 205130
Patch by Tobias Güntner.
I tried to write a test, but the only difference is the Changed value that
gets returned. It can be tested with "opt -debug-pass=Executions -functionattrs,
but that doesn't seem worth it.
llvm-svn: 205121
This will fix cross-compiling buildbots (e.g. cygwin). This is in the same vein
as SVN r205070. Apply this to fix the cross-compiling scenario, even though the
preferred solution is to update the build system to normalize the embedded
triple rather than perform this at runtime every time. This is meant to tide us
over until that approach is fleshed out and applied.
llvm-svn: 205120
The ARM64 backend uses it only as a container to keep an MCLOHType and
Arguments around so give it its own little copy. The other functionality
isn't used and we had a crazy method specialization hack in place to
keep it working. Unfortunately that was incompatible with MSVC.
Also range-ify a couple of loops while at it.
llvm-svn: 205114
v2i64 is a legal type under VSX, however we don't have native vector
comparisons. We can handle eq/ne by casting it to an Altivec type, but
everything else must be expanded.
llvm-svn: 205106
When LLVM is not built with zlib, nocompression.s will test
for the error message. But this test case will cause breakage
because the exit code is non-zero. This commit fix this issue
by adding "not" to the command.
llvm-svn: 205102
The vector divide and sqrt instructions have high latencies, and the scalar
comparisons are like all of the others. On the P7, permutations take an extra
cycle over purely-simple vector ops.
llvm-svn: 205096
Issue subject: Crash using integrated assembler with immediate arithmetic
Fix description:
Expressions like 'cmp r0, #(l1 - l2) >> 3' could not be evaluated on asm parsing stage,
since it is impossible to resolve labels on this stage. In the end of stage we still have
expression (MCExpr).
Then, when we want to encode it, we expect it to be an immediate, but it still an expression.
Patch introduces a Fixup (MCFixup instance), that is processed after main encoding stage.
llvm-svn: 205094
no assert at all. ;] Some of these should probably be switched to
llvm_unreachable, but I didn't want to perturb the behavior in this
patch.
Found by -Wstring-conversion, which I'll try to turn on in CMake builds
at least as it is finding useful things.
llvm-svn: 205091
Craig Topper