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
Same fix as rL334110: I noticed while working on zero-idiom + dependency-breaking support (PR36671) that most of our binary instruction schedule tests were reusing the same src registers, which would cause the tests to fail once we enable scalar zero-idiom support on btver2.
llvm-svn: 334302
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
Summary: Macros are terribly spammy at the moment and this offers some relief.
Reviewers: ioeric
Subscribers: ilya-biryukov, MaskRay, jkorous, cfe-commits
Differential Revision: https://reviews.llvm.org/D47936
llvm-svn: 334287
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
Summary: Add `StringRef::rsplit(StringRef Separator)` to achieve the function of getting the tail substring according to the separator. A typical usage is to get `data` in `std::basic_string::data`.
Reviewers: mehdi_amini, zturner, beanz, xbolva00, vsk
Reviewed By: zturner, xbolva00, vsk
Subscribers: vsk, xbolva00, llvm-commits, MTC
Differential Revision: https://reviews.llvm.org/D47406
llvm-svn: 334283
Summary:
Default copy/move constructors and assignment operators leave wrong m_sets[i].registers pointers.
Made the class movable and non-copyable (it's difficult to imagine when it needs to be copied).
Reviewers: clayborg
Reviewed By: clayborg
Differential Revision: https://reviews.llvm.org/D47728
llvm-svn: 334282
CGM.GetAddrOfConstantCString() sets the adress of the created GlobalValue
to unnamed. When emitting the object file LLVM will mark the surrounding
section as SHF_MERGE iff the string is nul-terminated and contains no
other nuls (see IsNullTerminatedString). This results in problems when
saving temporaries because LLVM doesn't set an EntrySize, so reading in
the serialized assembly file fails.
This never happened for the GPU binaries because they usually contain
a nul-character somewhere. Instead this only affected the module ID
when compiling relocatable device code.
However, this points to a potentially larger problem: If we put a
constant string into a named section, we really want the data to end
up in that section in the object file. To avoid LLVM merging sections
this patch unmarks the GlobalVariable's address as unnamed which also
fixes the problem of invalid serialized assembly files when saving
temporaries.
Differential Revision: https://reviews.llvm.org/D47902
llvm-svn: 334281
r334215 changed the error message the tool prints for invalid thread
arguments to -exec-next command. This adjust the test to match that.
llvm-svn: 334279
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
This also fixes a bug where SymbolFileDWARF was returning the same
function multiple times - this can happen if both mangled and demangled
names match the regex. Other lookup lookup functions had code to handle
this case, but it was forgotten here.
llvm-svn: 334277
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
Summary:
This patch implements the non-regex variant of GetFunctions. To share
more code with the Apple implementation, I've extracted the common
filtering code from that class into a utility function on the DWARFIndex
base class.
The new implementation also searching the accelerator table multiple
times -- previously it could happen that the apple table would return
the same die more than once if one specified multiple search flags in
name_type_mask. This way, I separate table iteration from filtering, and
so we can be sure each die is inserted at most once.
Reviewers: clayborg, JDevlieghere
Subscribers: aprantl, lldb-commits
Differential Revision: https://reviews.llvm.org/D47881
llvm-svn: 334273
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
Summary:
This patch improves the check to match the desugared "string" type (so that it
can handle custom-implemented string classes), see the newly-added test.
Reviewers: alexfh
Subscribers: klimek, xazax.hun, cfe-commits
Differential Revision: https://reviews.llvm.org/D47704
llvm-svn: 334270
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
This change uses 'const' for the retryingWriteAll(...) API and removes
unnecessary 'static' local variables in getting the temporary filename.
llvm-svn: 334267
Summary:
This fixes http://llvm.org/PR32274.
This change adds a test to ensure that we're able to link XRay modes and
the runtime to binaries that don't need to depend on the C++ standard
library or a C++ ABI library. In particular, we ensure that this will work
with C programs compiled+linked with XRay.
To make the test pass, we need to change a few things in the XRay
runtime implementations to remove the reliance on C++ ABI features. In
particular, we change the thread-safe function-local-static
initialisation to use pthread_* instead of the C++ features that ensure
non-trivial thread-local/function-local-static initialisation.
Depends on D47696.
Reviewers: dblaikie, jfb, kpw, eizan
Reviewed By: kpw
Subscribers: echristo, eizan, kpw, mgorny, llvm-commits
Differential Revision: https://reviews.llvm.org/D46998
llvm-svn: 334262
Test changes are due to differences in how we generate undef elements now. We also changed the types used for extractf128_si256/insertf128_si256 to match the signature of the builtin that previously existed which this patch resurrects. This also matches gcc.
llvm-svn: 334261
Summary:
The patch adds support of splitted functions (when MSVC is used with PGO) and function-level linking feature.
SymbolFilePDB::ParseCompileUnitLineTable function relies on fact that ranges of compiled source files in the binary are continuous and don't intersect each other. The function creates LineSequence for each file and inserts it into LineTable, and implementation of last one relies on continuity of the sequence. But it's not always true when function-level linking enabled, e.g. in added input test file test-pdb-function-level-linking.exe there is xstring's std__basic_string_char_std__char_traits_char__std__allocator_char_____max_size (.00454820) between test-pdb-function-level-linking.cpp's foo (.00454770) and main (.004548F0).
To fix the problem this patch renews the sequence on each address gap.
Reviewers: asmith, zturner
Reviewed By: asmith
Subscribers: aleksandr.urakov, labath, mgorny, lldb-commits
Differential Revision: https://reviews.llvm.org/D47708
llvm-svn: 334260
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
Michael Berg