Summary:
This fixes most of the scheduling info for SKX vector operations.
I had to split a lot of the YMM/ZMM classes into separate classes for YMM and ZMM.
The before/after llvm-exegesis analysis are in the phabricator diff.
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D47721
llvm-svn: 334407
It's been reported
<http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20180611/559616.html>
that template argument deduction for RetryAfterSignal fails if open is
not prefixed with "::".
This should help us build correctly on those platforms and explicitly
specifying the namespace is more correct anyway.
llvm-svn: 334403
Summary:
This kind of functionality is useful to other project apart from clang.
LLDB works with version numbers a lot, but it does not have a convenient
abstraction for this. Moving this class to a lower level library allows
it to be freely used within LLDB.
Since this class is used in a lot of places in clang, and it used to be
in the clang namespace, it seemed appropriate to add it to the list of
adopted classes in LLVM.h to avoid prefixing all uses with "llvm::".
Also, I didn't find any tests specific for this class, so I wrote a
couple of quick ones for the more interesting bits of functionality.
Reviewers: zturner, erik.pilkington
Subscribers: mgorny, cfe-commits, llvm-commits
Differential Revision: https://reviews.llvm.org/D47887
llvm-svn: 334399
Summary: In preparation for D47721. HSW and SNB still define unsupported
classes as they are used by KNL and generic models respectively.
Reviewers: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D47763
llvm-svn: 334389
Summary: When compiling with -fpic, in contrast to -fPIC, use only the
immediate field to index into the GOT. This saves space if the GOT is
known to be small. The linker will warn if the GOT is too large for
this method.
Reviewers: jyknight, venkatra
Reviewed By: jyknight
Subscribers: brad, fedor.sergeev, jrtc27, llvm-commits
Differential Revision: https://reviews.llvm.org/D47136
llvm-svn: 334383
Codeview references to unnamed structs and unions are expected to refer to the
complete type definition instead of a forward reference so Visual Studio can
resolve the type properly.
Differential Revision: https://reviews.llvm.org/D32498
llvm-svn: 334382
This patch started off much more general and ambitious, but it's been a nightmare
seeing all the ways x86 vector codegen can go wrong.
So the code is still structured to allow extending easily, but it's currently
limited in several ways:
1. Only handle cases with an extending load.
2. Only handle cases with a zero constant compare.
3. Ignore setcc with vector bitmask (SetCCWidth != 1) - so AVX512 should be unaffected.
The motivating case from PR37427:
https://bugs.llvm.org/show_bug.cgi?id=37427
...is the 1st test, and that shows the expected win - we eliminated the unnecessary
intermediate cast.
There's a clear regression in the last test (sgt_zero_fp_select) because we longer
recognize a 'SHRUNKBLEND' opportunity. I think that general problem is also present
in sgt_zero, so I'll try to fix that in a follow-up. We need to match a sign-bit
setcc from a sign-extended operand and remove it.
Differential Revision: https://reviews.llvm.org/D47330
llvm-svn: 334378
I took some liberties and quoted fewer characters than before,
based on an article from MSDN which says that only certain characters
cause an arg to require quoting. This seems to be incorrect, though,
and worse it seems to be a difference in Windows version. The bot
that fails is Windows 7, and I can't reproduce the failure on Win
10. But it's definitely related to quoting and special characters,
because both tests that fail have a * in the argument, which is one
of the special characters that would cause an argument to be quoted
before but not any longer after the new patch.
Since I don't have Win 7, all I can do is just guess that I need to
restore the old quoting rules. So this patch does that in hopes that
it fixes the problem on Windows 7.
llvm-svn: 334375
We currently support them only in AArch64. The NEON Reference,
however, says they are 'ARMv7, ARMv8' intrinsics.
Differential Revision: https://reviews.llvm.org/D47447
llvm-svn: 334361
This reverts commit 65243b6d19143cb7a03f68df0169dcb63e8b4632.
Seems like it's not a flake. It might have something to do with
the '*' character being in a command line.
llvm-svn: 334356
There were a few linux compilation failures, but other than that
I think this was just a flake that caused the tests to fail. I'm
going to resubmit and see if the failures go away, if not I'll
revert again.
llvm-svn: 334355
This reverts commit 10d2e88e87150a35dc367ba30716189d2af26774.
This is causing some test failures for some reason, reverting
while I investigate.
llvm-svn: 334354
This function was internal to Program.inc, but I've needed this
on several occasions when I've had to use CreateProcess without
llvm's sys::Execute functions. In doing so, I noticed that the
function was written using unsafe C-string access and was pretty
hard to understand / make sense of, so I've also re-written the
functions to use more modern LLVM constructs.
llvm-svn: 334353
This is a recommit of r333506, which was reverted in r333518.
The original commit message is below.
In r325551 many calls of malloc/calloc/realloc were replaces with calls of
their safe counterparts defined in the namespace llvm. There functions
generate crash if memory cannot be allocated, such behavior facilitates
handling of out of memory errors on Windows.
If the result of *alloc function were checked for success, the function was
not replaced with the safe variant. In these cases the calling function made
the error handling, like:
T *NewElts = static_cast<T*>(malloc(NewCapacity*sizeof(T)));
if (NewElts == nullptr)
report_bad_alloc_error("Allocation of SmallVector element failed.");
Actually knowledge about the function where OOM occurred is useless. Moreover
having a single entry point for OOM handling is convenient for investigation
of memory problems. This change removes custom OOM errors handling and
replaces them with calls to functions `llvm::safe_*alloc`.
Declarations of `safe_*alloc` are moved to a separate include file, to avoid
cyclic dependency in SmallVector.h
Differential Revision: https://reviews.llvm.org/D47440
llvm-svn: 334344
SmallSet forwards to SmallPtrSet for pointer types. SmallPtrSet supports iteration, but a normal SmallSet doesn't. So if it wasn't for the forwarding, this wouldn't work.
These places were found by hiding the begin/end methods in the SmallSet forwarding
llvm-svn: 334343
It looks like this got left in by accident in r289794; I can't think of
any reason this check would be necessary. (Maybe it was meant to be a
check that the AND has one use? But we check that a few lines earlier.)
Differential Revision: https://reviews.llvm.org/D47921
llvm-svn: 334322
An expression like
(zext i2 {(trunc i32 (1 + %B) to i2),+,1}<%while.body> to i32)
will become zero exactly when the nested value becomes zero in its type.
Strip injective operations from the input value in howFarToZero to make
the value simpler.
Differential Revision: https://reviews.llvm.org/D47951
llvm-svn: 334318
Summary:
If we can use comdats, then we can make it so that the global metadata
is thrown away if the prevailing definition of the global was
uninstrumented. I have only tested this on COFF targets, but in theory,
there is no reason that we cannot also do this for ELF.
This will allow us to re-enable string merging with ASan on Windows,
reducing the binary size cost of ASan on Windows.
Reviewers: eugenis, vitalybuka
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D47841
llvm-svn: 334313
Extension to D46954 (PR37426), this patch adds support for v8i16/v16i16 rotations in a similar manner - the conversion of the shift/rotate amount to a multiplication factor and the use of PMULLW to shift left and PMULHUW (ISD::MULHU) to shift the wrapped bits back around to be ORd together.
Differential Revision: https://reviews.llvm.org/D47822
llvm-svn: 334309
Summary: This patch originated from D46562 and is a proper subset, with some issues addressed for fsub.
Reviewers: spatel, hfinkel, wristow, arsenm
Reviewed By: spatel
Subscribers: wdng
Differential Revision: https://reviews.llvm.org/D47910
llvm-svn: 334306
This patch moves the recipe-creation functions out of
LoopVectorizationPlanner, which should do the high-level
orchestration of the transformations.
Reviewers: dcaballe, rengolin, hsaito, Ayal
Reviewed By: dcaballe
Differential Revision: https://reviews.llvm.org/D47595
llvm-svn: 334305
As detailed on Agner's Microarchitecture doc (21.8 AMD Bobcat and Jaguar pipeline - Dependency-breaking instructions), these instructions are dependency breaking and fast-path zero the destination register (and appropriate EFLAGS bits).
llvm-svn: 334303
AMDGPU inline assembler support i16, half and i128 typed variables in constraints, but they were reported as error.
Needed to fix https://github.com/RadeonOpenCompute/ROCm/issues/341,
e.g. to be able to load with global_load_dwordx4 to a 128bit integer variable
Differential Revision: https://reviews.llvm.org/D44920
llvm-svn: 334301
Summary:
`%ret = add nuw i8 %x, C`
From [[ https://llvm.org/docs/LangRef.html#add-instruction | langref ]]:
nuw and nsw stand for “No Unsigned Wrap” and “No Signed Wrap”,
respectively. If the nuw and/or nsw keywords are present,
the result value of the add is a poison value if unsigned
and/or signed overflow, respectively, occurs.
So if `C` is `-1`, `%x` can only be `0`, and the result is always `-1`.
I'm not sure we want to use `KnownBits`/`LVI` here, because there is
exactly one possible value (all bits set, `-1`), so some other pass
should take care of replacing the known-all-ones with constant `-1`.
The `test/Transforms/InstCombine/set-lowbits-mask-canonicalize.ll` change *is* confusing.
What happening is, before this: (omitting `nuw` for simplicity)
1. First, InstCombine D47428/rL334127 folds `shl i32 1, %NBits`) to `shl nuw i32 -1, %NBits`
2. Then, InstSimplify D47883/rL334222 folds `shl nuw i32 -1, %NBits` to `-1`,
3. `-1` is inverted to `0`.
But now:
1. *This* InstSimplify fold `%ret = add nuw i32 %setbit, -1` -> `-1` happens first,
before InstCombine D47428/rL334127 fold could happen.
Thus we now end up with the opposite constant,
and it is all good: https://rise4fun.com/Alive/OA9https://rise4fun.com/Alive/sldC
Was mentioned in D47428 review.
Follow-up for D47883.
Reviewers: spatel, craig.topper
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D47908
llvm-svn: 334298
Summary:
The function `llvm::sys::commandLineFitsWithinSystemLimits` appears to be overestimating the system limits. This issue was discovered while attempting to enable response files in the Swift compiler. When the compiler submits its frontend jobs, those jobs are subjected to the system limits on command line length. `commandLineFitsWithinSystemLimits` is used to determine if the job's arguments need to be wrapped in a response file. There are some cases where the argument size for the job passes `commandLineFitsWithinSystemLimits`, but actually exceeds the real system limit, and the job fails.
`clang` also uses this function to decide whether or not to wrap it's job arguments in response files. See: https://github.com/llvm-mirror/clang/blob/master/lib/Driver/Driver.cpp#L1341. Clang will also fail for response files who's size falls within a certain range. I wrote a script that should find a failure point for `clang++`. All that is needed to run it is Python 2.7, and a simple "hello world" program for `test.cc`. It should run on Linux and on macOS. The script is available here: https://gist.github.com/dabelknap/71bd083cd06b91c5b3cef6a7f4d3d427. When it hits a failure point, you should see a `clang: error: unable to execute command: posix_spawn failed: Argument list too long`.
The proposed solution is to mirror the behavior of `xargs` in `commandLinefitsWithinSystemLimits`. `xargs` defaults to 128k for the command line length size (See: https://fossies.org/dox/findutils-4.6.0/buildcmd_8c_source.html#l00551). It adjusts this depending on the value of `ARG_MAX`.
Reviewers: alexfh
Reviewed By: alexfh
Subscribers: llvm-commits
Tags: #clang
Patch by Austin Belknap!
Differential Revision: https://reviews.llvm.org/D47795
llvm-svn: 334295
NFC here, this just raises some platform specific ifdef hackery
out of a class and creates proper platform-independent typedefs
for the relevant things. This allows these typedefs to be
reused in other places without having to reinvent this preprocessor
logic.
llvm-svn: 334294
O_CLOEXEC is the right default, but occasionally you don't
want this. This is especially true for tools like debuggers
where you might need to spawn the child process with specific
files already open, but it's occasionally useful in other
scenarios as well, like when you want to do some IPC between
parent and child.
llvm-svn: 334293
Simplify combineVectorTruncationWithPACKUS to mask the upper bits followed by calling truncateVectorWithPACK instead of duplicating with similar code.
This results in the codegen using (V)PACKUSDW on SSE41+ targets for vXi64/vXi32 inputs where before it always used PACKUSWB (along with a lot more bitcasting).
I've raised PR37749 as until we avoid unnecessary concats back to 256-bit for bitwise ops, we can't avoid splitting the input value into 128-bit subvectors for masking.
llvm-svn: 334289
Currently the loop branch heuristic is applied before the invoke heuristic which makes us overestimate the probability of the unwind destination of invokes inside loops. This in turn makes us grossly underestimate the frequencies of loops with invokes.
Reviewed By: skatkov, vsk
Differential Revision: https://reviews.llvm.org/D47371
llvm-svn: 334285
This first step separates VPInstruction-based and VPRecipe-based
VPlan creation, which should make it easier to migrate to VPInstruction
based code-gen step by step.
Reviewers: Ayal, rengolin, dcaballe, hsaito, mkuper, mzolotukhin
Reviewed By: dcaballe
Subscribers: bollu, tschuett, rkruppe, llvm-commits
Differential Revision: https://reviews.llvm.org/D47477
llvm-svn: 334284
The instruction makes use of a previously ignored field in the fence
instruction. It is introduced in the version 2.3 draft of the RISC-V
specification after much work by the Memory Model Task Group.
As clarified here <https://github.com/riscv/riscv-isa-manual/issues/186>,
the fence.tso assembler mnemonic does not have operands.
llvm-svn: 334278
We have some combines/lowerings that attempt to use PACKSS-then-PACKUS and others that use PACKUS-then-PACKSS.
PACKUS is much easier to combine with if we know the upper bits are zero as ComputeKnownBits can easily see through BITCASTs etc. especially now that rL333995 and rL334007 have landed. It also effectively works at byte level which further simplifies shuffle combines.
The only (minor) annoyances are that ComputeKnownBits can sometimes take longer as it doesn't fail as quickly as ComputeNumSignBits (but I'm not seeing any actual regressions in tests) and PACKUSDW only became available after SSE41 so we have more codegen diffs between targets.
llvm-svn: 334276
There could be more than one PHIs in exit block using same loop recurrence.
Don't assume there is only one and fix each user.
Differential Revision: https://reviews.llvm.org/D47788
llvm-svn: 334271
While trying to propagate AND masks back to loads, we currently allow
one non-load node to be included as a leaf in chain. This fix now
limits that node to produce only a single data value.
Differential Revision: https://reviews.llvm.org/D47878
llvm-svn: 334268
The NumControlBits variable was definitely sketchy. I think that only worked because the expected value was 1 or 2 and the number of lanes was 2 or 4. Had their been 8 lanes the number of bits should have been 3 not 4 as the previous code would have given.
llvm-svn: 334258
This one allows much more flexibility than the standard
openFileForRead / openFileForWrite functions. Since there is now
just one "real" function that does the work, all other implementations
simply delegate to this one.
llvm-svn: 334246
Summary: This change uses fmf subflags to guard fma optimizations as well as unsafe. These changes originated from D46483 and have been simplified via getNode.
Reviewers: spatel, arsenm, hfinkel, javed.absar
Reviewed By: spatel
Subscribers: nemanjai, wdng
Differential Revision: https://reviews.llvm.org/D47388
llvm-svn: 334242
- Make code easier to maintain.
- Avoid generating waitcnts for VMEM if the address sppace does not involve VMEM.
- Add support to generate waitcnts for LDS and GDS memory.
Differential Revision: https://reviews.llvm.org/D47504
llvm-svn: 334241
Summary:
`%r = shl nuw i8 C, %x`
As per langref:
```
If the nuw keyword is present, then the shift produces
a poison value if it shifts out any non-zero bits.
```
Thus, if the sign bit is set on `C`, then `%x` can only be `0`,
which means that `%r` can only be `C`.
Or in other words, set sign bit means that the signed value
is negative, so the constant is `<= 0`.
https://rise4fun.com/Alive/WMkhttps://rise4fun.com/Alive/udv
Was mentioned in D47428 review.
We already handle the `0` constant, https://godbolt.org/g/UZq1sJ, so this only handles negative constants.
Could use computeKnownBits() / LazyValueInfo,
but the cost-benefit analysis (https://reviews.llvm.org/D47891)
suggests it isn't worth it.
Reviewers: spatel, craig.topper
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D47883
llvm-svn: 334222
This breaks the OpenFlags enumeration into two separate
enumerations: OpenFlags and CreationDisposition. The first
controls the behavior of the API depending on whether or not
the target file already exists, and is not a flags-based
enum. The second controls more flags-like values.
This yields a more easy to understand API, while also allowing
flags to be passed to the openForRead api, where most of the
values didn't make sense before. This also makes the apis more
testable as it becomes easy to enumerate all the configurations
which make sense, so I've added many new tests to exercise all
the different values.
llvm-svn: 334221
This avoids regressions in a future AMDGPU change
to make v4i16/v4f16 legal. For these types, build_vector
is implemented as bitcasted operations on v2i32. This
combine was creating v4i16s out of what would have been
already been a v2i32 build_vector, creating a mess
of nodes that never get cleaned up.
I'm not sure this is the right condition to check.
I initially tried just checking for the legality of the
new build_vector. This works for my case, but breaks dozens
of x86 tests. A Mips test seems to show some improvement
or at least a neutral change. I don't want to think
about how long it would take to analyze the set of
different x86 vector operations impacted.
Test included in future commit.
llvm-svn: 334218
These weren't included in D19544 - probably just an oversight.
D40044 made it more likely that we'll have LLVM math intrinsics rather
than libcalls, so this bug was more easily exposed.
As the tests/code show, we already have the complete mappings for pow/exp/log.
I don't have any experience with SVML, so I don't know if anything else is
missing. It's also not clear to me that we should be doing this transform in
IR rather than DAG/isel, but that's a separate issue.
Differential Revision: https://reviews.llvm.org/D47610
llvm-svn: 334211
The implementation follows the MIPS backend and expands the pseudo instruction
directly during asm parsing. As the result, only real MC instructions are
emitted to the MCStreamer. The actual expansion to real instructions is
similar to the expansion performed by the GNU Assembler.
This patch supersedes D41949.
Differential Revision: https://reviews.llvm.org/D46118
Patch by Mario Werner.
llvm-svn: 334203
BitPermutationSelector sets Repl32 flag for bit groups which can be (potentially) benefit from 32-bit rotate-and-mask instructions with bit replication, i.e. rlwinm/rlwimi copies lower 32 bits into upper 32 bits on 64-bit PowerPC before rotation.
However, enforcing 32-bit instruction sometimes results in redundant generated code.
For example, the following simple code is compiled into rotldi + rlwimi while it can be compiled into only rldimi instruction if Repl32 flag is not set on the bit group for (a & 0xFFFFFFFF).
uint64_t func(uint64_t a, uint64_t b) {
return (a & 0xFFFFFFFF) | (b << 32) ;
}
To avoid such problem, this patch checks the potential benefit of Repl32 flag before setting it. If a bit group does not require rotation (i.e. RLAmt == 0) and won't be merged into another group, we do not benefit from Repl32 flag on this group.
Differential Revision: https://reviews.llvm.org/D47867
llvm-svn: 334195
isORCopyInst and isReadOrWriteToDSPReg functions were producing warning
that some statements my fall through.
Patch by Nikola Prica.
Differential Revision: https://reviews.llvm.org/D47876
llvm-svn: 334194
Simplify combineVectorTruncationWithPACKSS to just a SIGN_EXTEND_INREG followed by using the existing truncateVectorWithPACK instead of duplicating code.
llvm-svn: 334193
We do the same thing in rewriteSingleStoreAlloca.
Fixes PR37632.
Reviewers: chandlerc, davide, efriedma
Reviewed By: davide
Differential Revision: https://reviews.llvm.org/D47825
llvm-svn: 334187
This has two main components. First, widen
widen short constant loads in DAG when they have
the correct alignment. This is already done a bit in
AMDGPUCodeGenPrepare, since that has access to
DivergenceAnalysis. This can't help kernarg loads
created in the DAG. Start to use DAG divergence analysis
to help this case.
The second part is to avoid kernel argument lowering
breaking the alignment of short vector elements because
calling convention lowering wants to split everything
into legal register types.
When loading a split type, load the nearest 4-byte aligned
segment and shift to get the desired bits. This extra
load of the earlier argument piece ends up merging,
and the bit extract hopefully folds out.
There are a number of improvements and regressions with
this, but I think as-is this is a better compromise between
several of the worst parts of SelectionDAG.
Particularly when i16 is legal, this produces worse code
for i8 and i16 element vector kernel arguments. This is
partially due to the very weak load merging the DAG does.
It only looks for fairly specific combines between pairs
of loads which no longer appear. In particular this
causes v4i16 loads to be split into 2 components when
previously the two halves were merged.
Worse, because of the newly introduced shifts, there
is a lot more unnecessary vector packing and unpacking code
emitted. At least some of this is due to reporting
false for isTypeDesirableForOp for i16 as a workaround for
the lack of divergence information in the DAG. The cases
where this happens it doesn't actually matter, but the
relevant code in SimplifyDemandedBits doens't have the context
to know to ignore this.
The use of the scalar cache is probably more important
than the mess of mostly scalar instructions doing this packing
and unpacking. Future work can fix this, possibly by making better
use of the new DAG divergence information for controlling promotion
decisions, or adding another version of shift + trunc + shift
combines that doesn't only know about the used types.
llvm-svn: 334180
Summary: Prevent folding of operations with memory loads when one of the sources has undefined register update.
Reviewers: craig.topper
Subscribers: llvm-commits, mike.dvoretsky, ashlykov
Differential Revision: https://reviews.llvm.org/D47621
llvm-svn: 334175
Summary:
When the branch folder hoist code into a predecessor it adjust live-in's
in the blocks it hoist code from. However it fail to handle hoisted code
that contain a defed register that originally is live-in in the block
through a super register.
This is fixed by replacing the live-in handling code with calls to
utility functions in LivePhysRegs.
Reviewers: kparzysz, gberry, MatzeB, uweigand, aprantl
Reviewed By: kparzysz
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D47529
llvm-svn: 334163
This is needed to get CC operand in right place, as expected by the
SchedModel.
Review: Ulrich Weigand
https://reviews.llvm.org/D47820
llvm-svn: 334161
When denormals are supported we are producing a full division for
1.0f / x. That still can be replaced by the faster version:
bool c = fabs(x) > 0x1.0p+96f;
float s = c ? 0x1.0p-32f : 1.0f;
x *= s;
return s * v_rcp_f32(x)
in case if requested accuracy is 2.5ulp or less. The same version
is used if denormals are not supported for non 1.0 numerators, where
just v_rcp_f32 is then used for 1.0 numerator.
The optimization of 1/x is extended to the case -1/x, which is the
same except for the resulting sign bit.
OpenCL conformance passed with both enabled and disabled denorms.
Differential Revision: https://reviews.llvm.org/D47805
llvm-svn: 334142
With the upcoming patch to add summary parsing support, IsAnalysis would
be true in contexts where we are not performing module summary analysis.
Rename to the more specific and approprate HaveGVs, which is essentially
what this flag is indicating.
llvm-svn: 334140
The bug report:
https://bugs.llvm.org/show_bug.cgi?id=36036
...requests a DAG change for this, but an IR canonicalization
probably handles most cases. If we still want to match this
pattern in the backend, there's a proposal for that too:
D47831
Alive proofs including nsw/nuw cases that were first noted in:
D46988
https://rise4fun.com/Alive/Kmp
This patch is largely copied from the existing code that was
initially added with:
D40984
...but I didn't see much gain from trying to share code.
llvm-svn: 334137
Fixes terrible code on targets without f16 support. The
legalization creates a mess that is difficult to recover
from. Also should avoid randomly breaking these tests
multiple times in sequence in future commits.
Some regressions in cases where it happens to be better
to pull the source modifier after the conversion.
llvm-svn: 334132
Summary:
This is [[ https://bugs.llvm.org/show_bug.cgi?id=37603 | PR37603 ]].
https://godbolt.org/g/VCMNpShttps://rise4fun.com/Alive/idM
When doing bit manipulations, it is quite common to calculate some bit mask,
and apply it to some value via `and`.
The typical C code looks like:
```
int mask_signed_add(int nbits) {
return (1 << nbits) - 1;
}
```
which is translated into (with `-O3`)
```
define dso_local i32 @mask_signed_add(int)(i32) local_unnamed_addr #0 {
%2 = shl i32 1, %0
%3 = add nsw i32 %2, -1
ret i32 %3
}
```
But there is a second, less readable variant:
```
int mask_signed_xor(int nbits) {
return ~(-(1 << nbits));
}
```
which is translated into (with `-O3`)
```
define dso_local i32 @mask_signed_xor(int)(i32) local_unnamed_addr #0 {
%2 = shl i32 -1, %0
%3 = xor i32 %2, -1
ret i32 %3
}
```
Since we created such a mask, it is quite likely that we will use it in `and` next.
And then we may get rid of `not` op by folding into `andn`.
But now that i have actually looked:
https://godbolt.org/g/VTUDmU
_some_ backend changes will be needed too.
We clearly loose `bzhi` recognition.
Reviewers: spatel, craig.topper, RKSimon
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D47428
llvm-svn: 334127
Summary:
In D47428, i propose to choose the `~(-(1 << nbits))` as the canonical form of low-bit-mask formation.
As it is seen from these tests, there is a reason for that.
AArch64 currently better handles `~(-(1 << nbits))`, but not the more traditional `(1 << nbits) - 1` (sic!).
The other way around for X86.
It would be much better to canonicalize.
This patch is completely monkey-typing.
I don't really understand how this works :)
I have based it on `// x & (-1 >> (32 - y))` pattern.
Also, when we only have `BMI`, i wonder if we could use `BEXTR` with `start=0` ?
Related links:
https://bugs.llvm.org/show_bug.cgi?id=36419https://bugs.llvm.org/show_bug.cgi?id=37603https://bugs.llvm.org/show_bug.cgi?id=37610https://rise4fun.com/Alive/idM
Reviewers: craig.topper, spatel, RKSimon, javed.absar
Reviewed By: craig.topper
Subscribers: kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D47453
llvm-svn: 334125
These encodings correspond to the cases in the normal encoding scheme where there is no index and our modrm reading code initially decodes it as such. The VSIB handling code tried to compensate for this, but failed to add the base needed to make later code do the right thing.
Fixes PR37712.
llvm-svn: 334121
The index size is represented by the letter after the 'v'. The number represents the memory size. If an 'x' appears after the number its means the index register can be from VR128X/VR256X instead of VR128/VR256.
As vy512mem uses a VR256X index it should have an x.
And vz256mem uses a VR512 index so it shouldn't have an x.
I admit these names kind of suck and are confusing.
llvm-svn: 334120
As detailed on Agner's Microarchitecture doc (21.8 AMD Bobcat and Jaguar pipeline - Dependency-breaking instructions), all these instructions are dependency breaking and zero the destination register.
llvm-svn: 334119
Summary:
This change uses fmf subflags to guard optimizations as well as unsafe. These changes originated from D46483.
It contains only context for fsqrt.
Reviewers: spatel, hfinkel, arsenm
Reviewed By: spatel
Subscribers: hfinkel, wdng, andrew.w.kaylor, wristow, efriedma, nemanjai
Differential Revision: https://reviews.llvm.org/D47749
llvm-svn: 334113
Make TII isCopyInstr() return MachineOperands through pointer to pointer
instead via reference.
Patch by Nikola Prica.
Differential Revision: https://reviews.llvm.org/D47364
llvm-svn: 334105
If no alignment is set, the abi/preferred alignment of structs will be
used which may be higher than required. This can lead to extra padding
and in the end an increase in data size.
Differential Revision: https://reviews.llvm.org/D47633
llvm-svn: 334099
We should never get different CodeGen based on whether the code is being
compiled in debug mode so we must skip over @llvm.dbg.value (and similar)
calls.
Should fix at least the worst part of PR37690.
llvm-svn: 334090
Clement Courbet