Summary:
The syncthreads MI is modeled as mayread/maywrite -- convergence doesn't
even come into play here. Nonetheless this property is highly implicit
in the tablegen files, so a test seems appropriate.
Reviewers: jingyue
Subscribers: llvm-commits, jholewinski
Differential Revision: http://reviews.llvm.org/D17319
llvm-svn: 261114
Summary:
Otherwise we'll try to do unsafe optimizations on these MIs, such as
sinking loads below calls.
(I suspect that this is not the only bug in the NVPTX instruction
tablegen files; I need to comb through them.)
Reviewers: jholewinski, tra
Subscribers: jingyue, jhen, llvm-commits
Differential Revision: http://reviews.llvm.org/D17315
llvm-svn: 261113
Summary:
As previously written, only functions could be convergent. But calls
need to have a notion of convergence as well.
To see why this is important, consider an indirect call. We may or may
not want to disable optimizations around it and behave as though we're
calling a convergent function -- it depends on the semantics of the
language we're compiling. Thus the need for this attr on the call.
Reviewers: jingyue, joker.eph
Subscribers: llvm-commits, tra, jhen, arsenm, chandlerc, hfinkel, resistor
Differential Revision: http://reviews.llvm.org/D17314
llvm-svn: 261111
The dynamic table is also an array of a fixed structure, so it can be
represented with a DynReginoInfo.
No major functionality change. The extra error checking is covered by
existing tests with a broken dynamic program header.
Idea extracted from r260488. I did the extra cleanups.
llvm-svn: 261107
We are getting better at combining constant pshufb masks - use a real input instead of undef.
Add test for decoding multi-use bitcasted masks as well (actual support will come soon).
llvm-svn: 261101
We used to keep both a section and a pointer to the first symbol.
The oddity of keeping a section for dynamic symbols is because there is
a DT_SYMTAB but no DT_SYMTABZ, so to print the table we have to find the
size via a section table.
The reason for still keeping a pointer to the first symbol is because we
want to be able to print relocation tables even if the section table is
missing (it is mandatory only for files used in linking).
With this patch we keep just a DynRegionInfo. This then requires
changing a few places that were asking for a Elf_Shdr but actually just
needed the first symbol.
The test change is to delete the program header pointer.
Now that we use the information of both DT_SYMTAB and .dynsym, we don't
depend on the sh_entsize of .dynsym if we see DT_SYMTAB.
Note: It is questionable if it is worth it putting the effort to report
broken sh_entsize given that in files with no section table we have to
assume it is sizeof(Elf_Sym), but that is for another change.
Extracted from r260488.
llvm-svn: 261099
Bug description:
The bug was discovered when test was compiled with -O0.
In case scatter result is DAG root , VectorLegalizer failed (assert) due to LowerMSCATTER() return kmask as result.
Change LowerMSCATTER() to return chain as original node do.
Differential Revision: http://reviews.llvm.org/D17331
llvm-svn: 261090
This section is used for debug information and has no need to be
in memory at runtime. This patch also fixes an error when compiling
the Linux kernel. The error is that there are relocations within the
.pdr section in a VDSO. SHT_REL was removed as it is a section type
and not a section flag, therefore it does not make sense for it to
be there. With this patch, LLVM now emits the same flags as
the GNU assembler.
llvm-svn: 261083
AVX1 doesn't support the shuffling of 256-bit integer vectors. For 32/64-bit elements we get around this by shuffling as float/double but for 8/16-bit elements (assuming they can't widen) we currently just split, shuffle as 128-bit vectors and concatenate the results back.
This patch adds the ability to lower using the bit-blend patterns before defaulting to the splitting behaviour.
Part 2 of 2
Differential Revision: http://reviews.llvm.org/D17292
llvm-svn: 261082
AVX1 doesn't support the shuffling of 256-bit integer vectors. For 32/64-bit elements we get around this by shuffling as float/double but for 8/16-bit elements (assuming they can't widen) we currently just split, shuffle as 128-bit vectors and concatenate the results back.
This patch adds the ability to lower using the bit-mask patterns before defaulting to the splitting behaviour. In some cases this ends up matching what AVX2 would do anyhow or what AVX1 does on the split vectors.
Part 1 of 2
Differential Revision: http://reviews.llvm.org/D17292
llvm-svn: 261081
Avoid reuse of operand variables, keep them local to a particular lowering - the operand collection is unique to each case anyhow.
Renamed from V to Ops to more closely match their purpose.
llvm-svn: 261078
This patch detects vector reductions before instruction selection. Vector
reductions are vectorized reduction operations, and for such operations we have
freedom to reorganize the elements of the result as long as the reduction of them
stay unchanged. This will enable some reduction pattern recognition during
instruction combine such as SAD/dot-product on X86. A flag is added to
SDNodeFlags to mark those vector reduction nodes to be checked during instruction
combine.
To detect those vector reductions, we search def-use chains starting from the
given instruction, and check if all uses fall into two categories:
1. Reduction with another vector.
2. Reduction on all elements.
in which 2 is detected by recognizing the pattern that the loop vectorizer
generates to reduce all elements in the vector outside of the loop, which
includes several ShuffleVector and one ExtractElement instructions.
Differential revision: http://reviews.llvm.org/D15250
llvm-svn: 261070
This reverts commit r261030 and r261036.
(The revision was marked "approved" on phabricator, but some concerns
were raised on the mailing list. Thanks D. Blaikie for notifying me.)
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 261055
This fixes very slow compilation on
test/CodeGen/Generic/2010-11-04-BigByval.ll . Note that MaxStoresPerMemcpy
and friends are not yet carefully tuned so the cutoff point is currently
somewhat arbitrary. However, it's important that there be a cutoff point
so that we don't emit unbounded quantities of loads and stores.
llvm-svn: 261050
reference-edge SCCs.
This essentially builds a more normal call graph as a subgraph of the
"reference graph" that was the old model. This allows both to exist and
the different use cases to use the aspect which addresses their needs.
Specifically, the pass manager and other *ordering* constrained logic
can use the reference graph to achieve conservative order of visit,
while analyses reasoning about attributes and other properties derived
from reachability can reason about the direct call graph.
Note that this isn't necessarily complete: it doesn't model edges to
declarations or indirect calls. Those can be found by scanning the
instructions of the function if desirable, and in fact every user
currently does this in order to handle things like calls to instrinsics.
If useful, we could consider caching this information in the call graph
to save the instruction scans, but currently that doesn't seem to be
important.
An important realization for why the representation chosen here works is
that the call graph is a formal subset of the reference graph and thus
both can live within the same data structure. All SCCs of the call graph
are necessarily contained within an SCC of the reference graph, etc.
The design is to build 'RefSCC's to model SCCs of the reference graph,
and then within them more literal SCCs for the call graph.
The formation of actual call edge SCCs is not done lazily, unlike
reference edge 'RefSCC's. Instead, once a reference SCC is formed, it
directly builds the call SCCs within it and stores them in a post-order
sequence. This is used to provide a consistent platform for mutation and
update of the graph. The post-order also allows for very efficient
updates in common cases by bounding the number of nodes (and thus edges)
considered.
There is considerable common code that I'm still looking for the best
way to factor out between the various DFS implementations here. So far,
my attempts have made the code harder to read and understand despite
reducing the duplication, which seems a poor tradeoff. I've not given up
on figuring out the right way to do this, but I wanted to wait until
I at least had the system working and tested to continue attempting to
factor it differently.
This also requires introducing several new algorithms in order to handle
all of the incremental update scenarios for the more complex structure
involving two edge colorings. I've tried to comment the algorithms
sufficiently to make it clear how this is expected to work, but they may
still need more extensive documentation.
I know that there are some changes which are not strictly necessarily
coupled here. The process of developing this started out with a very
focused set of changes for the new structure of the graph and
algorithms, but subsequent changes to bring the APIs and code into
consistent and understandable patterns also ended up touching on other
aspects. There was no good way to separate these out without causing
*massive* merge conflicts. Ultimately, to a large degree this is
a rewrite of most of the core algorithms in the LCG class and so I don't
think it really matters much.
Many thanks to the careful review by Sanjoy Das!
Differential Revision: http://reviews.llvm.org/D16802
llvm-svn: 261040
__chkstk clobbers EAX. If EAX is live across the prologue, then we have
to take extra steps to save it. We already had code to do this if EAX
was a register parameter. This change adapts it to work when shrink
wrapping is used.
llvm-svn: 261039
Summary: Loading IR with debug info improves MDString::get() from 19ms to 10ms.
Reviewers: dexonsmith
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D16597
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 261030
Summary:
On the contrary to Full LTO, ThinLTO can afford to shift compile time
from the frontend to the linker: both phases are parallel (even if
it is not totally "free": projects like clang are reusing product
from the "compile phase" for multiple link, think about
libLLVMSupport reused for opt, llc, etc.).
This pipeline is based on the proposal in D13443 for full LTO. We
didn't move forward on this proposal because the LTO link was far too
long after that. We believe that we can afford it with ThinLTO.
The ThinLTO pipeline integrates in the regular O2/O3 flow:
- The compile phase perform the inliner with a somehow lighter
function simplification. (TODO: tune the inliner thresholds here)
This is intendend to simplify the IR and get rid of obvious things
like linkonce_odr that will be inlined.
- The link phase will run the pipeline from the start, extended with
some specific passes that leverage the augmented knowledge we have
during LTO. Especially after the inliner is done, a sequence of
globalDCE/globalOpt is performed, followed by another run of the
"function simplification" passes. It is not clear if this part
of the pipeline will stay as is, as the split model of ThinLTO
does not allow the same benefit as FullLTO without added tricks.
The measurements on the public test suite as well as on our internal
suite show an overall net improvement. The binary size for the clang
executable is reduced by 5%. We're still tuning it with the bringup
of ThinLTO and it will evolve, but this should provide a good starting
point.
Reviewers: tejohnson
Differential Revision: http://reviews.llvm.org/D17115
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 261029
It is intended to contains the passes run over a function after the
inliner is done with a function and before it moves to its callers.
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 261028
Currently, we sometimes miscompile this vector pattern:
(c ? -v : v)
We lower it to (because "c" is <4 x i1>, lowered as a vector mask):
(~c & v) | (c & -v)
When we have SSSE3, we incorrectly lower that to PSIGN, which does:
(c < 0 ? -v : c > 0 ? v : 0)
in other words, when c is either all-ones or all-zero:
(c ? -v : 0)
While this is an old bug, it rarely triggers because the PSIGN combine
is too sensitive to operand order. This will be improved separately.
Note that the PSIGN tests are also incorrect. Consider:
%b.lobit = ashr <4 x i32> %b, <i32 31, i32 31, i32 31, i32 31>
%sub = sub nsw <4 x i32> zeroinitializer, %a
%0 = xor <4 x i32> %b.lobit, <i32 -1, i32 -1, i32 -1, i32 -1>
%1 = and <4 x i32> %a, %0
%2 = and <4 x i32> %b.lobit, %sub
%cond = or <4 x i32> %1, %2
ret <4 x i32> %cond
if %b is zero:
%b.lobit = <4 x i32> zeroinitializer
%sub = sub nsw <4 x i32> zeroinitializer, %a
%0 = <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
%1 = <4 x i32> %a
%2 = <4 x i32> zeroinitializer
%cond = or <4 x i32> %a, zeroinitializer
ret <4 x i32> %a
whereas we currently generate:
psignd %xmm1, %xmm0
retq
which returns 0, as %xmm1 is 0.
Instead, use a pure logic sequence, as described in:
https://graphics.stanford.edu/~seander/bithacks.html#ConditionalNegate
Fixes PR26110.
Differential Revision: http://reviews.llvm.org/D17181
llvm-svn: 261023
We're going to stop generating PSIGN, so calling a test "psign"
isn't ideal. Instead, call these tests what they really are:
variable blends using logic.
Also add a test to exhibit a case we're currently missing in
the PSIGN combine.
llvm-svn: 261022
When emitting the source filename, the encoding of the string
was checked against the name instead of the filename.
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 261019
This apparently comes up when the register allocator decides that a
variable will become undef along a certain path.
Also improve the error message we emit when we can't map from LLVM
register number to CV register number.
llvm-svn: 261016
The register stackifier currently checks for intervening stores (and
loads that may alias them) but doesn't account for the fact that the
instruction being moved may affect intervening loads.
Differential Revision: http://reviews.llvm.org/D17298
llvm-svn: 261014
Summary:
I thought -Xlinker -mllvm -Xlinker -stats worked at some point but maybe
it never did.
For clang, I believe that stats are printed from cc1_main. This patch
also prints them for LTO, specifically right after codegen happens.
I only looked at the C API for LTO briefly to see if this is a good
place. Probably there are still cases where this wouldn't be printed
but it seems to be working for the common case. I also experimented
putting this in the LTOCodeGenerator destructor but that didn't trigger
for me because ld64 does not destroy the LTOCodeGenerator.
Reviewers: dexonsmith, joker.eph
Subscribers: rafael, joker.eph, llvm-commits
Differential Revision: http://reviews.llvm.org/D17302
llvm-svn: 261013
The usual way to get a 32-bit relocation is to use a constant extender which doubles the size of the instruction, 4 bytes to 8 bytes.
Another way is to put a .word32 and mix code and data within a function. The disadvantage is it's not a valid instruction encoding and jumping over it causes prefetch stalls inside the hardware.
This relocation packs a 23-bit value in to an "r0 = add(rX, #a)" instruction by overwriting the source register bits. Since r0 is the return value register, if this instruction is placed after a function call which return void, r0 will be filled with an undefined value, the prefetch won't be confused, and the callee can access the constant value by way of the link register.
llvm-svn: 261006
Summary:
This change will add a pass to remove unnecessary zero copies in target blocks
of cbz/cbnz instructions. E.g., the copy instruction in the code below can be
removed because the cbz jumps to BB1 when x0 is zero :
BB0:
cbz x0, .BB1
BB1:
mov x0, xzr
Jun
Reviewers: gberry, jmolloy, HaoLiu, MatzeB, mcrosier
Subscribers: mcrosier, mssimpso, haicheng, bmakam, llvm-commits, aemerson, rengolin
Differential Revision: http://reviews.llvm.org/D16203
llvm-svn: 261004
Original message:
Get rid of the ifdefs in TargetLowering.
Introduce a new API used only by GlobalISel: CallLowering.
This API will contain target hooks dedicated to call lowering.
llvm-svn: 260998
CopyToReg nodes don't support FrameIndex operands. Other targets select
the FI to some LEA-like instruction, but since we don't have that, we
need to insert some kind of instruction that can take an FI operand and
produces a value usable by CopyToReg (i.e. in a vreg). So insert a dummy
copy_local between Op and its FI operand. This results in a redundant
copy which we should optimize away later (maybe in the post-FI-lowering
peephole pass).
Differential Revision: http://reviews.llvm.org/D17213
llvm-svn: 260987
Summary: This change renames output operand for VOP instructions from dst to vdst. This is needed to enable decoding named operands for disassembler.
Reviewers: vpykhtin, tstellarAMD, arsenm
Subscribers: arsenm, llvm-commits, nhaustov
Projects: #llvm-amdgpu-spb
Differential Revision: http://reviews.llvm.org/D16920
llvm-svn: 260986
The root issue appears to be a confusion around what makeNoWrapRegion actually does. It seems likely we need two versions of this function with slightly different semantics.
llvm-svn: 260981
WebAssembly doesn't require full RPO; topological sorting is sufficient and
can preserve more of the MachineBlockPlacement ordering. Unfortunately, this
still depends a lot on heuristics, because while we use the
MachineBlockPlacement ordering as a guide, we can't use it in places where
it isn't topologically ordered. This area will require further attention.
llvm-svn: 260978
This avoids some complications updating LiveIntervals to be aware of the new
register lifetimes, because we can just compute new intervals from scratch
rather than describe how the old ones have been changed.
llvm-svn: 260971
Original commit message:
[readobj] Dump DT_JMPREL relocations when outputting dynamic relocations.
The bits of r260488 it depends on have been committed.
llvm-svn: 260970
This requires making an error message a bit more generic, but that seems
a reasonable tradeoff.
Extracted from r260488 but simplified a bit.
llvm-svn: 260967
Original messages:
Revert "[readobj] Handle ELF files with no section table or with no program headers."
Revert "[readobj] Dump DT_JMPREL relocations when outputting dynamic relocations."
r260489 depends on r260488 and among other issues r260488 deleted error
handling code.
llvm-svn: 260962
Once a pointer is turned into a reference it cannot be nullptr, clang
rightfully warns about this assert being a tautology. Put the assert
before the reference is created.
llvm-svn: 260949
Summary:
Extending findExistingExpansion can use existing value in ExprValueMap.
This patch gives 0.3~0.5% performance improvements on
benchmarks(test-suite, spec2000, spec2006, commercial benchmark)
Reviewers: mzolotukhin, sanjoy, zzheng
Differential Revision: http://reviews.llvm.org/D15559
llvm-svn: 260938
r260925 introduced a version of the *trim methods which is preferable
when trimming a single kind of character. Update all users in llvm.
llvm-svn: 260926
Add support for trimming a single kind of character from a StringRef.
This makes the common case of trimming null bytes much neater. It's also
probably a bit speedier too, since it avoids creating a std::bitset in
find_{first,last}_not_of.
llvm-svn: 260925
Summary: The name is confusing as it matche another method on the module.
Reviewers: joker.eph, Wallbraker, echristo
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D17283
llvm-svn: 260920
This patch avoids the initial memset at the cost of making iterators
slightly more complex. This should be beneficial as most SmallPtrSets
hold no or only a few elements, while iterating over them is less
common.
Differential Revision: http://reviews.llvm.org/D16672
llvm-svn: 260913
We always clear the unused bits in the most signifant word so there is
no need to mask them out in countLeadingZerosSlowCase().
Differential Revision: http://reviews.llvm.org/D16621
llvm-svn: 260911
This is an updated version which fixes a bug that happened with
uses tied to an earlyclobber operand which end at an unusual slotindex.
If two definitions write to independent subregisters then they can be
put in any order. LiveIntervalAnalysis::handleMove() did not support
this previously because it looks like moving a definition of a vreg past
another one.
This is a modified version of a patch proposed (two years ago) by
Vincent Lejeune! This version does not touch the read-undef flags and is
extended for the case of moving a subregister def behind all uses - this
can happen for subregister defs that are completely unused.
Differential Revision: http://reviews.llvm.org/D9067
llvm-svn: 260906
This function was basically useless, since volatile memacesses or MIs with
unmodelled sideffects become global memory objects, and the other little
checks are also done elsewhere.
Reviewed by Andy Trick
http://reviews.llvm.org/D16881
llvm-svn: 260899
Summary:
In order to pass the tests, this required marking R_MIPS_16 relocations
as needing to point to the symbol and not the section.
Reviewers: vkalintiris, dsanders
Subscribers: dsanders, llvm-commits
Differential Revision: http://reviews.llvm.org/D17200
llvm-svn: 260896
Summary:
While shrinking types according to the required bits, we can
encounter insert/extract element instructions. This will cause us to
reach an llvm_unreachable statement.
This change adds support for truncating insert/extract element
operations, and adds a regression test.
Reviewers: jmolloy
Subscribers: mzolotukhin, llvm-commits
Differential Revision: http://reviews.llvm.org/D17078
llvm-svn: 260893
LICM starts with an *empty* AST, and then merges in each sub-loop. While the
add code is appropriate for sub-loop 2 and up, it's utterly unnecessary for
sub-loop 1. If the AST starts off empty, we can just clone/move the contents
of the subloop into the containing AST.
Reviewed-by: Philip Reames <listmail@philipreames.com>
Differential Revision: http://reviews.llvm.org/D16753
llvm-svn: 260892
Summary:
This section is used for debug information and has no need to be
in memory at runtime. With this patch, LLVM now emits the same flags as
the GNU assembler. This patch also fixes an error when compiling
the Linux kernel, The error is that there are relocations within the
.pdr section in a VDSO.
Reviewers: vkalintiris, dsanders
Subscribers: llvm-commits, dsanders
Differential Revision: http://reviews.llvm.org/D17199
llvm-svn: 260879
If KMOVB not supported (require AVX512DQ) only KMOVW can be used so store size should be 2 bytes.
Differential Revision: http://reviews.llvm.org/D17138
llvm-svn: 260878
This ensures that all of the various pieces are working. The next patch
will wire up commandline-driven alias analysis chain building and allow
BasicAA to work with the AAManager.
llvm-svn: 260838
into the new pass manager and fix the latent bugs there.
This lets everything live together nicely, but it isn't really useful
yet. I never finished wiring the AA layer up for the new pass manager,
and so subsequent patches will change this to do that wiring and get AA
stuff more fully integrated into the new pass manager. Turns out this is
necessary even to get functionattrs ported over. =]
llvm-svn: 260836
r180893 added an indirect include of llvm/Config/Targets.def to
llvm/Support/CodeGen.h, which in turn is included by things like
llvm/IR/Module.h. After a full build of LLVM and Clang, ninja had to
rebuild 1274 files after reconfiguring.
This commit strips CodeGen.h back down to just a pile of enums and moves
the expensive includes over to CodeGenCWrappers.h (which is only
included in two places). This gets ninja down to 88 files if you
reconfigure with, e.g., -DLLVM_TARGETS_TO_BUILD=X86.
llvm-svn: 260835
This patch attempts to represent a shuffle as a repeating shuffle (recognisable by is128BitLaneRepeatedShuffleMask) with the source input(s) in their original lanes, followed by a single permutation of the 128-bit lanes to their final destinations.
On AVX2 we can additionally attempt to match using 64-bit sub-lane permutation. AVX2 can also now match a similar 'broadcasted' repeating shuffle.
This patch has several benefits:
* Avoids prematurely matching with lowerVectorShuffleByMerging128BitLanes which can require both inputs to have their input lanes permuted before shuffling.
* Can replace PERMPS/PERMD instructions - although these are useful for cross-lane unary shuffling, they require their shuffle mask to be pre-loaded (and increase register pressure).
* Matching the repeating shuffle makes use of a lot of existing shuffle lowering.
There is an outstanding minor AVX1 regression (combine_unneeded_subvector1 in vector-shuffle-combining.ll) of a previously 128-bit shuffle + subvector splat being converted to a subvector splat + (2 instruction) 256-bit shuffle, I intend to fix this in a followup patch for review.
Differential Revision: http://reviews.llvm.org/D16537
llvm-svn: 260834
As shown in:
https://llvm.org/bugs/show_bug.cgi?id=23203
...we currently die because lowering believes that mfence is allowed without SSE2 on x86-64,
but the instruction def doesn't know that.
I don't know if allowing mfence without SSE is right, but if not, at least now it's consistently wrong. :)
Differential Revision: http://reviews.llvm.org/D17219
llvm-svn: 260828
than the SCC object, and have it scan the instruction stream directly
rather than relying on call records.
This makes the behavior of this routine consistent between libc routines
and LLVM intrinsics for libc routines. We can go and start teaching it
about those being norecurse, but we should behave the same for the
intrinsic and the libc routine rather than differently. I chatted with
James Molloy and the inconsistency doesn't seem intentional and likely
is due to intrinsic calls not being modelled in the call graph analyses.
This also fixes a bug where we would deduce norecurse on optnone
functions, when generally we try to handle optnone functions as-if they
were replaceable and thus unanalyzable.
llvm-svn: 260813
This requirement was a huge hack to keep LiveVariables alive because it
was optionally used by TwoAddressInstructionPass and PHIElimination.
However we have AnalysisUsage::addUsedIfAvailable() which we can use in
those passes.
llvm-svn: 260806
Justin Lebar