Vector 'getelementptr' with scalar base is an opportunity for gather/scatter intrinsic to generate a better sequence.
While looking for uniform base, we want to use the scalar base pointer of GEP, if exists.
Differential Revision: http://reviews.llvm.org/D11121
llvm-svn: 246622
The code introduced in r244314 assumed that EXTRACT_VECTOR_ELT only
takes constant indices, but it does accept variables.
Bail out for those: we can't use them, as the shuffles we want to
reconstruct do require constant masks.
llvm-svn: 246594
This matches the ARM behavior. In both cases, the register is part
of the optional Performance Monitors extension, so, add the feature,
and enable it for the A-class processors we support.
Differential Revision: http://reviews.llvm.org/D12425
llvm-svn: 246555
Summary:
Interleaved access lowering removes a memory operation and a
sequence of vector shuffles and replaces it with a series of
memory operations. This should be always beneficial.
This pass in only enabled on ARM/AArch64.
Reviewers: rengolin
Subscribers: aemerson, llvm-commits, rengolin
Differential Revision: http://reviews.llvm.org/D12145
llvm-svn: 246540
Currently, when edge weights are assigned to edges that are created when lowering switch statement, the weight on the edge to default statement (let's call it "default weight" here) is not considered. We need to distribute this weight properly. However, without value profiling, we have no idea how to distribute it. In this patch, I applied the heuristic that this weight is evenly distributed to successors.
For example, given a switch statement with cases 1,2,3,5,10,11,20, and every edge from switch to each successor has weight 10. If there is a binary search tree built to test if n < 10, then its two out-edges will have weight 4x10+10/2 = 45 and 3x10 + 10/2 = 35 respectively (currently they are 40 and 30 without considering the default weight). Each distribution (which is 5 here) will be stored in each SwitchWorkListItem for further distribution.
There are some exceptions:
For a jump table header which doesn't have any edge to default statement, we don't distribute the default weight to it.
For a bit test header which covers a contiguous range and hence has no edges to default statement, we don't distribute the default weight to it.
When the branch checks a single value or a contiguous range with no edge to default statement, we don't distribute the default weight to it.
In other cases, the default weight is evenly distributed to successors.
Differential Revision: http://reviews.llvm.org/D12418
llvm-svn: 246522
SETCC is one of those special node types for which operation actions (legality,
etc.) is keyed off of an operand type, not the node's value type. This makes
sense because the value type of a legal SETCC node is determined by its
operands' value type (via the TLI function getSetCCResultType). When the
SDAGBuilder creates SETCC nodes, it either creates them with an MVT::i1 value
type, or directly with the value type provided by TLI.getSetCCResultType.
The first problem being fixed here is that DAGCombine had several places
querying TLI.isOperationLegal on SETCC, but providing the return of
getSetCCResultType, instead of the operand type directly. This does not mean
what the author thought, and "luckily", most in-tree targets have SETCC with
Custom lowering, instead of marking them Legal, so these checks return false
anyway.
The second problem being fixed here is that two of the DAGCombines could create
SETCC nodes with arbitrary (integer) value types; specifically, those that
would simplify:
(setcc a, b, op1) and|or (setcc a, b, op2) -> setcc a, b, op3
(which is possible for some combinations of (op1, op2))
If the operands of the and|or node are actual setcc nodes, then this is not an
issue (because the and|or must share the same type), but, the relevant code in
DAGCombiner::visitANDLike and DAGCombiner::visitORLike actually calls
DAGCombiner::isSetCCEquivalent on each operand, and that function will
recognise setcc-like select_cc nodes with other return types. And, thus, when
creating new SETCC nodes, we need to be careful to respect the value-type
constraint. This is even true before type legalization, because it is quite
possible for the SELECT_CC node to have a legal type that does not happen to
match the corresponding TLI.getSetCCResultType type.
To be explicit, there is nothing that later fixes the value types of SETCC
nodes (if the type is legal, but does not happen to match
TLI.getSetCCResultType). Creating SETCCs with an MVT::i1 value type seems to
work only because, either MVT::i1 is not legal, or it is what
TLI.getSetCCResultType returns if it is legal. Fixing that is a larger change,
however. For the time being, restrict the relevant transformations to produce
only SETCC nodes with a value type matching TLI.getSetCCResultType (or MVT::i1
prior to type legalization).
Fixes PR24636.
llvm-svn: 246507
Summary: This handles all load/store operations that WebAssembly defines, and handles those necessary for C++ such as i1. I left a FIXME for outstanding features which aren't required for now.
Reviewers: sunfish
Subscribers: jfb, llvm-commits, dschuff
llvm-svn: 246500
Also delete and simplify a lot of MachineModuleInfo code that used to be
needed to handle personalities on landingpads. Now that the personality
is on the LLVM Function, we no longer need to track it this way on MMI.
Certainly it should not live on LandingPadInfo.
llvm-svn: 246478
The ISelLowering code turned insertion turned the element for the
lowest lane of a BUILD_VECTOR into an INSERT_SUBREG, this prohibited
the patterns for SCALAR_TO_VECTOR(Load) to match later. Restrict this
to cases without a load argument.
Reported in rdar://22223823
Differential Revision: http://reviews.llvm.org/D12467
llvm-svn: 246462
AggressiveAntiDepBreaker was doing some EarlyClobber checking, but was not
checking that the register being potentially renamed was defined by an
early-clobber def where there was also a use, in that instruction, of the
register being considered as the target of the rename. Fixes PR24014.
llvm-svn: 246423
There were really two problems here. The first was that we had the truth tables
for signed i1 comparisons backward. I imagine these are not very common, but if
you have:
setcc i1 x, y, LT
this has the '0 1' and the '1 0' results flipped compared to:
setcc i1 x, y, ULT
because, in the signed case, '1 0' is really '-1 0', and the answer is not the
same as in the unsigned case.
The second problem was that we did not have patterns (at all) for the unsigned
comparisons select_cc nodes for i1 comparison operands. This was the specific
cause of PR24552. These had to be added (and a missing Altivec promotion added
as well) to make sure these function for all types. I've added a bunch more
test cases for these patterns, and there are a few FIXMEs in the test case
regarding code-quality.
Fixes PR24552.
llvm-svn: 246400
Add support for MIR serialization of PowerPC-specific operand target flags
(based on the generic infrastructure added in r244185 and r245383).
I won't even pretend that this is good test coverage, but this includes the
regression test associated with r246372. Adding an MIR test for that fix is far
superior to adding an IR-level test because particular instruction-scheduling
decisions are necessary in order to expose the bug, and using an MIR test we
can start the pipeline post-scheduling.
llvm-svn: 246373
This is especially visible in softfp mode, for example in the implementation of libm fabs/fneg functions. If we have:
%1 = vmovdrr r0, r1
%2 = fabs %1
then move the fabs before the vmovdrr:
%1 = and r1, #0x7FFFFFFF
%2 = vmovdrr r0, r1
This is never a lose, and could be a serious win because the vmovdrr may be followed by a vmovrrd, which would enable us to remove the conversion into FPRs completely.
We already do this for f32, but not for f64. Tests are added for both.
llvm-svn: 246360
The VOP3 encoding of these allows any SGPR pair for the i1
output, but this was forced before to always use vcc.
This doesn't yet try to use this, but does add the operand
to the definitions so the main change is adding vcc to the
output of the VOP2 encoding.
llvm-svn: 246358
Without a memory operand, mayLoad or mayStore instructions
are treated as hasUnorderedMemRef, which results in much worse
scheduling.
We really should have a verifier check that any
non-side effecting mayLoad or mayStore has a memory operand.
There are a few instructions (interp and images) which I'm
not sure what / where to add these.
llvm-svn: 246356
I'm working on adding !dbg attachments to functions (PR23367), which
we'll use to determine the canonical subprogram for a function (instead
of the `subprograms:` array in the compile units). This updates a few
old tests in preparation.
Transforms/Mem2Reg/ConvertDebugInfo2.ll had an old-style grep+count
based test that would start to fail because I've added an extra line
with `!dbg`. Instead, explicitly `CHECK` for what I think the test
actually cares about.
All three testcases have subprograms with a valid `function:` reference
-- which means my upgrade script will add a `!dbg` attachment -- but
that aren't referenced from any compile unit. I suspect these testcases
were handreduced over-zealously (or have bitrotted?). Add a reference
from the compile unit so that upcoming Verifier checks won't fail here.
llvm-svn: 246351
As a follow-up to r246098, require `DISubprogram` definitions
(`isDefinition: true`) to be 'distinct'. Specifically, add an assembler
check, a verifier check, and bitcode upgrading logic to combat testcase
bitrot after the `DIBuilder` change.
While working on the testcases, I realized that
test/Linker/subprogram-linkonce-weak-odr.ll isn't relevant anymore. Its
purpose was to check for a corner case in PR22792 where two subprogram
definitions match exactly and share the same metadata node. The new
verifier check, requiring that subprogram definitions are 'distinct',
precludes that possibility.
I updated almost all the IR with the following script:
git grep -l -E -e '= !DISubprogram\(.* isDefinition: true' |
grep -v test/Bitcode |
xargs sed -i '' -e 's/= \(!DISubprogram(.*, isDefinition: true\)/= distinct \1/'
Likely some variant of would work for out-of-tree testcases.
llvm-svn: 246327
When combiner AA is enabled, look at stores on the same chain.
Non-aliasing stores are moved to the same chain so the existing
code fails because it expects to find an adajcent store on a consecutive
chain.
Because of how DAGCombiner tries these store combines,
MergeConsecutiveStores doesn't see the correct set of stores on the chain
when it visits the other stores. Each store individually has its chain
fixed before trying to merge consecutive stores, and then tries to merge
stores from that point before the other stores have been processed to
have their chains fixed. To fix this, attempt to use FindBetterChain
on any possibly neighboring stores in visitSTORE.
Suppose you have 4 32-bit stores that should be merged into 1 vector
store. One store would be visited first, fixing the chain. What happens is
because not all of the store chains have yet been fixed, 2 of the stores
are merged. The other 2 stores later have their chains fixed,
but because the other stores were already merged, they have different
memory types and merging the two different sized stores is not
supported and would be more difficult to handle.
llvm-svn: 246307
Summary:
Change the coloring algorithm in WinEHPrepare to visit a funclet's exits
in its parents' contexts and so properly classify the continuations of
nested funclets.
Also change the placement of cloned blocks to be deterministic and to
maintain the relative order of each funclet's blocks.
Add a lit test showing various patterns that require cloning, the last
several of which don't have CHECKs yet because they require cloning
entire funclets which is NYI.
Reviewers: rnk, andrew.w.kaylor, majnemer
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D12353
llvm-svn: 246245
more than 2 instructions.
I introduced this regression a while back and did not noticed it because I
somehow forgot to push the initial test cases for the pass!
Fix that as well!
llvm-svn: 246239
We can now run 32-bit programs with empty catch bodies. The next step
is to change PEI so that we get funclet prologues and epilogues.
llvm-svn: 246235
Fixes PR24602: r245689 introduced an unguarded use of
SelectionDAG::FoldConstantArithmetic, which returns 0 when it fails
because of opaque (hoisted) constants.
llvm-svn: 246217
This is a one-line-change patch that moves the update to UnhandledWeights to the correct position: it should be updated for all clusters instead of just range clusters.
Differential Revision: http://reviews.llvm.org/D12391
llvm-svn: 246129
Summary:
Let NVPTX backend detect integer min and max patterns during isel and emit intrinsics that enable hardware support.
Reviewers: jholewinski, meheff, jingyue
Subscribers: arsenm, llvm-commits, meheff, jingyue, eliben, jholewinski
Differential Revision: http://reviews.llvm.org/D12377
llvm-svn: 246107
Currently, when lowering switch statement and a new basic block is built for jump table / bit test header, the edge to this new block is not assigned with a correct weight. This patch collects the edge weight from all its successors and assign this sum of weights to the edge (and also the other fall-through edge). Test cases are adjusted accordingly.
Differential Revision: http://reviews.llvm.org/D12166#fae6eca7
llvm-svn: 246104
Things of note:
- Other linkage types aren't handled yet. We'll figure it out with dynamic linking.
- Special LLVM globals are either ignored, or error out for now.
- TLS isn't supported yet (WebAssembly will have threads later).
- There currently isn't a syntax for alignment, I left it in a comment so it's easy to hook up.
- Undef is convereted to whatever the type's appropriate null value is.
- assert versus report_fatal_error: follow what other AsmPrinters do, and assert only on what should have been caught elsewhere.
llvm-svn: 246092
This was causing problems when some functions use a GuardReg and some
don't as can happen when mixing SelectionDAG and FastISel generated
functions.
llvm-svn: 246075
If you're going to realign %sp to get object alignment properly (which
the code does), and stack offsets and alignments are calculated going
down from %fp (which they are), then the total stack size had better
be a multiple of the alignment. LLVM did indeed ensure that.
And then, after aligning, the sparc frame code added 96 (for sparcv8)
to the frame size, making any requested alignment of 64-bytes or
higher *guaranteed* to be misaligned. The test case added with r245668
even tests this exact scenario, and asserted the incorrect behavior,
which I somehow failed to notice. D'oh.
This change fixes the frame lowering code to align the stack size
*after* adding the spill area, instead.
Differential Revision: http://reviews.llvm.org/D12349
llvm-svn: 246042
Summary:
This change makes the variable argument intrinsics, `llvm.va_start` and
`llvm.va_copy`, and the `va_arg` instruction behave as they do on Windows
inside a `CallingConv::X86_64_Win64` function. It's needed for a Clang patch
I have to add support for GCC's `__builtin_ms_va_list` constructs.
Reviewers: nadav, asl, eugenis
CC: llvm-commits
Differential Revision: http://llvm-reviews.chandlerc.com/D1622
llvm-svn: 245990
When lowering switch statement, if bit tests are used then LLVM will always generates a jump to the default statement in the last bit test. However, this is not necessary when all cases in bit tests cover a contiguous range. This is because when generating the bit tests header MBB, there is a range check that guarantees cases in bit tests won't go outside of [low, high], where low and high are minimum and maximum case values in the bit tests. This patch checks if this is the case and then doesn't emit jump to default statement and hence saves a bit test and a branch.
Differential Revision: http://reviews.llvm.org/D12249
llvm-svn: 245976
This is a follow-on from the discussion in http://reviews.llvm.org/D12154.
This change allows memset/memcpy to use SSE or AVX memory accesses for any chip that has
generally fast unaligned memory ops.
A motivating use case for this change is a clang invocation that doesn't explicitly set
the CPU, but does target a feature that we know only exists on a CPU that supports fast
unaligned memops. For example:
$ clang -O1 foo.c -mavx
This resolves a difference in lowering noted in PR24449:
https://llvm.org/bugs/show_bug.cgi?id=24449
Before this patch, we used different store types depending on whether the example can be
lowered as a memset or not.
Differential Revision: http://reviews.llvm.org/D12288
llvm-svn: 245950
This fixes two issues in x86 fptoui lowering.
1) Makes conversions from f80 go through the right path on AVX-512.
2) Implements an inline sequence for fptoui i64 instead of a library
call. This improves performance by 6X on SSE3+ and 3X otherwise.
Incidentally, it also removes the use of ftol2 for fptoui, which was
wrong to begin with, as ftol2 converts to a signed i64, producing
wrong results for values >= 2^63.
Patch by: mitch.l.bodart@intel.com
Differential Revision: http://reviews.llvm.org/D11316
llvm-svn: 245924
We might end up with a trivial copy as the addend, and if so, we should ignore
the corresponding FMA instruction. The trivial copy can be coalesced away later,
so there's nothing to do here. We should not, however, assert. Fixes PR24544.
llvm-svn: 245907
Summary: I forgot to squash git commits before doing an svn dcommit of D12219. Reverting, and re-submitting.
Subscribers: jfb, llvm-commits
Differential Revision: http://reviews.llvm.org/D12298
llvm-svn: 245886
This patch fixes PR24546, which demonstrates a segfault during the VSX
swap removal pass. The problem is that debug value instructions were
not excluded from the list of instructions to be analyzed for webs of
related computation. I've added the test case from the PR as a crash
test in test/CodeGen/PowerPC.
llvm-svn: 245862
The FP16_TO_FP node only uses the bottom 16 bits of its input, so the
following pattern can be optimised by removing the AND:
(FP16_TO_FP (AND op, 0xffff)) -> (FP16_TO_FP op)
This is a common pattern for ARM targets when functions have __fp16
arguments, as they are passed as floats (so that they get passed in the
correct registers), but then bitcast and truncated to ignore the top 16
bits.
llvm-svn: 245832
Summary:
WinEHPrepare is going to require that cleanuppad and catchpad produce values
of token type which are consumed by any cleanupret or catchret exiting the
pad. This change updates the signatures of those operators to require/enforce
that the type produced by the pads is token type and that the rets have an
appropriate argument.
The catchpad argument of a `CatchReturnInst` must be a `CatchPadInst` (and
similarly for `CleanupReturnInst`/`CleanupPadInst`). To accommodate that
restriction, this change adds a notion of an operator constraint to both
LLParser and BitcodeReader, allowing appropriate sentinels to be constructed
for forward references and appropriate error messages to be emitted for
illegal inputs.
Also add a verifier rule (noted in LangRef) that a catchpad with a catchpad
predecessor must have no other predecessors; this ensures that WinEHPrepare
will see the expected linear relationship between sibling catches on the
same try.
Lastly, remove some superfluous/vestigial casts from instruction operand
setters operating on BasicBlocks.
Reviewers: rnk, majnemer
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D12108
llvm-svn: 245797
Summary:
__shared__ variable may now emit undef value as initializer, do not
throw error on that.
Test Plan: test/CodeGen/NVPTX/global-addrspace.ll
Patch by Xuetian Weng
Reviewers: jholewinski, tra, jingyue
Subscribers: llvm-commits, jholewinski
Differential Revision: http://reviews.llvm.org/D12242
llvm-svn: 245785
We can wait on either VM, EXP or LGKM.
The waits are independent.
Without this patch, a wait inserted because of one of them
would also wait for all the previous others.
This patch makes s_wait only wait for the ones we need for the next
instruction.
Here's an example of subtle perf reduction this patch solves:
This is without the patch:
buffer_load_format_xyzw v[8:11], v0, s[44:47], 0 idxen
buffer_load_format_xyzw v[12:15], v0, s[48:51], 0 idxen
s_load_dwordx4 s[44:47], s[8:9], 0xc
s_waitcnt lgkmcnt(0)
buffer_load_format_xyzw v[16:19], v0, s[52:55], 0 idxen
s_load_dwordx4 s[48:51], s[8:9], 0x10
s_waitcnt vmcnt(1)
buffer_load_format_xyzw v[20:23], v0, s[44:47], 0 idxen
The s_waitcnt vmcnt(1) is useless.
The reason it is added is because the last
buffer_load_format_xyzw needs s[44:47], which was issued
by the first s_load_dwordx4. It waits for all VM
before that call to have finished.
Internally after every instruction, 3 counters (for VM, EXP and LGTM)
are updated after every instruction. For example buffer_load_format_xyzw
will
increase the VM counter, and s_load_dwordx4 the LGKM one.
Without the patch, for every defined register,
the current 3 counters are stored, and are used to know
how long to wait when an instruction needs the register.
Because of that, the s[44:47] counter includes that to use the register
you need to wait for the previous buffer_load_format_xyzw.
Instead this patch stores only the counters that matter for the
register,
and puts zero for the other ones, since we don't need any wait for them.
Patch by: Axel Davy
Differential Revision: http://reviews.llvm.org/D11883
llvm-svn: 245755
When PPCVSXFMAMutate would look at the input addend register, it would get its
input value number. This would fail, however, if the register was undef,
causing a segfault. Don't segfault (just skip such FMA instructions).
Fixes the test case from PR24542 (although that may have been over-reduced).
llvm-svn: 245741
See discussion in D12154 ( http://reviews.llvm.org/D12154 ), AMD Software
Optimization Guides for 10H/12H/15H/16H, and Agner Fog's experimental data.
llvm-svn: 245733
This will confirm that the patch in D12154 is actually NFC.
It will also confirm that the proposed changes for the AMD chips
are behaving as expected.
llvm-svn: 245704
This is intended to improve code generation for GEPs, as the index value is
shifted by the element size and in GEPs of multi-dimensional arrays the index
of higher dimensions is multiplied by the lower dimension size.
Differential Revision: http://reviews.llvm.org/D12197
llvm-svn: 245689
Note: I do not implement a base pointer, so it's still impossible to
have dynamic realignment AND dynamic alloca in the same function.
This also moves the code for determining the frame index reference
into getFrameIndexReference, where it belongs, instead of inline in
eliminateFrameIndex.
[Begin long-winded screed]
Now, stack realignment for Sparc is actually a silly thing to support,
because the Sparc ABI has no need for it -- unlike the situation on
x86, the stack is ALWAYS aligned to the required alignment for the CPU
instructions: 8 bytes on sparcv8, and 16 bytes on sparcv9.
However, LLVM unfortunately implements user-specified overalignment
using stack realignment support, so for now, I'm going to go along
with that tradition. GCC instead treats objects which have alignment
specification greater than the maximum CPU-required alignment for the
target as a separate block of stack memory, with their own virtual
base pointer (which gets aligned). Doing it that way avoids needing to
implement per-target support for stack realignment, except for the
targets which *actually* have an ABI-specified stack alignment which
is too small for the CPU's requirements.
Further unfortunately in LLVM, the default canRealignStack for all
targets effectively returns true, despite that implementing that is
something a target needs to do specifically. So, the previous behavior
on Sparc was to silently ignore the user's specified stack
alignment. Ugh.
Yet MORE unfortunate, if a target actually does return false from
canRealignStack, that also causes the user-specified alignment to be
*silently ignored*, rather than emitting an error.
(I started looking into fixing that last, but it broke a bunch of
tests, because LLVM actually *depends* on having it silently ignored:
some architectures (e.g. non-linux i386) have smaller stack alignment
than spilled-register alignment. But, the fact that a register needs
spilling is not known until within the register allocator. And by that
point, the decision to not reserve the frame pointer has been frozen
in place. And without a frame pointer, stack realignment is not
possible. So, canRealignStack() returns false, and
needsStackRealignment() then returns false, assuming everyone can just
go on their merry way assuming the alignment requirements were
probably just suggestions after-all. Sigh...)
Differential Revision: http://reviews.llvm.org/D12208
llvm-svn: 245668
When producing conditional compare sequences for or operations we need
to negate the operands and the finally tested flags. The thing is if we negate
the finally tested flags this equals a logical negation of all previously
emitted expressions. There was a case missing where we have to order OR
expressions so they get emitted first.
This fixes http://llvm.org/PR24459
llvm-svn: 245641
Create CMP;CCMP sequences from and/or trees does not gain us anything if
the and/or tree is materialized to a GP register anyway. While most of
the code already checked for hasOneUse() there was one important case
missing.
llvm-svn: 245640
Fixes PR23464: one way to use the broadcast intrinsics is:
_mm256_broadcastw_epi16(_mm_cvtsi32_si128(*(int*)src));
We don't currently fold this, but now that we use native IR for
the intrinsics (r245605), we can look through one bitcast to find
the broadcast scalar.
Differential Revision: http://reviews.llvm.org/D10557
llvm-svn: 245613
Since r245605, the clang headers don't use these anymore.
r245165 updated some of the tests already; update the others, add
an autoupgrade, remove the intrinsics, and cleanup the definitions.
Differential Revision: http://reviews.llvm.org/D10555
llvm-svn: 245606
XVCMPEQDP is used for VSX v2f64 equality comparisons, but the value type needs
to be v2i64 (as that's the corresponding SETCC type).
Fixes PR24225.
llvm-svn: 245535
This DAGCombine was creating custom SDAG nodes with an illegal ppc_fp128
operand type because it was triggering on f64/f32 int2fp(fp2int(ppc_fp128 x)),
but shouldn't (it should only apply to f32/f64 types). The result was a crash.
llvm-svn: 245530
This commit modifies the serialization syntax so that the global IR values in
machine memory operands use the global value '@<name>' syntax instead of the
current '%ir.<name>' syntax.
The unnamed global IR values are handled by this commit as well, as the
existing global value parsing method can parse the unnamed globals already.
llvm-svn: 245527
The global IR values in machine memory operands should use the global value
'@<name>' syntax instead of the current '%ir.<name>' syntax.
However, the global value call entry pseudo source values use the global value
syntax already. Therefore, the syntax for the call entry pseudo source values
has to be changed so that the global values and call entry global value PSVs
can be parsed without ambiguities.
llvm-svn: 245526