Summary: On Linux, /usr/include/bits/byteswap-16.h defines __byteswap_16(x) as an inlined LRVH (Load Reversed Half-word) instruction. The SystemZ back-end did not support this opcode and the inlined assembly would cause a fatal error.
Reviewers: bryanpkc, uweigand
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D18732
llvm-svn: 269688
getModuleContainingLocation ends up on the hot-path for typical C code
which can lead to calls to getFileIDSlow.
To speed this up, short circuit inferModuleFromLocation when there
aren't any modules, implicit or otherwise.
This shaves 4-5% build time when building the linux kernel.
llvm-svn: 269687
This is a compile time optimization: keeping a large file to process
at the end hurts parallelism.
The heurisitic used right now is the input buffer size, however we
may want to consider the number of functions to import or the
different number of files to load for importing as well.
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 269684
This is reducing pressure on the OS memory system, and is NFC
when not using a cache.
I measure a 10x memory consumption reduction when linking opt
with full debug info.
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 269682
Embedded bitcode should have private linkage instead of appending or external.
Otherwise, it will cause link failure due to duplicated symbols.
Also add llvm.embedded.module and llvm.cmdline to llvm.compiler.used so they
don't get optimized out.
rdar://problem/21555860
llvm-svn: 269679
The new X86 shuffle lowering can do just fine without transforming vselects
into vector_shuffles. It looks like the only thing this code does right now
is cause trouble - in particular, it can lead to combine/legalization infinite
loops.
Note that it's not completely NFC, since some of the shuffle masks get inverted,
which may cause slight differences further down the line. We may want to find
a way to invert those masks, but that's orthogonal to this commit.
This fixes the hang in PR27689.
llvm-svn: 269676
Visual Studio's C++ standard library headers include intrin.h, so the intrinsic
headers get included a lot more often in Microsoft mode than elsewhere. The
AVX512 intrinsics are a lot of code (0.7 MB, causing 30% compile time overhead
for small programs including e.g. <string> and 6% compile time overhead for
larger projects like e.g. v8). Since multiversioning can't be relied on in
Microsoft mode (cl.exe doesn't support it), having faster compiles seems like
the much better tradeoff until we have a better intrinsic story going forward
(which we'll need for e.g. PR19898).
Actually using intrinsics on Windows already requires the right /arch:
settings, so this patch should have no big behavior change.
See also thread "The intrinsics headers (especially avx512) are too big. What
to do about it?" on cfe-dev.
http://reviews.llvm.org/D20291
llvm-svn: 269675
licensees actually see in the toolchain we deliver to them. This will
reduce the set of local patches we have to maintain. The triple is
not changing. (The term ORBIS is an internal code name for PS4.)
llvm-svn: 269672
licensees actually see in the toolchain we deliver to them. This will
reduce the set of local patches we have to maintain. The triple is
not changing. (The term ORBIS is an internal code name for PS4.)
llvm-svn: 269671
Add supported OpenCL extensions to target info. It serves as default values to save the users of the burden setting each supported extensions and optional core features in command line.
Re-commit after fixing build error due to missing override attribute.
Differential Revision: http://reviews.llvm.org/D19484
llvm-svn: 269670
This patch renames the option enabling the store-to-load forwarding conflict
detection optimization. This change was requested in the review of D20241.
llvm-svn: 269668
Also s/Cycles/Iters/ in NumCyclesForStoreLoadThroughMemory to make it
clear that this is not about clock cycles but loop cycles/iterations.
llvm-svn: 269667
Clang performs directory walk while searching headers inside modules by
using the ::sys::fs instead of ::vfs. This prevents any code that uses
the VFS (e.g, reproducer scripts) to actually find such headers, since
the VFS will never be searched for those.
Change these places to use vfs::recursive_directory_iterator and
vfs::directory_iterator instead.
Differential Revision: http://reviews.llvm.org/D20266
rdar://problem/25880368
llvm-svn: 269661
The selection of the vectorization factor currently doesn't consider
interleaved accesses. The vectorization factor is based on the maximum safe
dependence distance computed by LAA. However, for loops with interleaved
groups, we should instead base the vectorization factor on the maximum safe
dependence distance divided by the maximum interleave factor of all the
interleaved groups. Interleaved accesses not in a group will be scalarized.
Differential Revision: http://reviews.llvm.org/D20241
llvm-svn: 269659
Summary:
When using a multi-configuration build (i.e. MSVC) the output path where
libraries are dropped is incorrect.
Example:
```
C:\src\llvm\examples>d:\src\llvm\build\Release\bin\clang-cl.exe -fsanitize=address test.cc
LINK : fatal error LNK1181: cannot open input file 'd:\src\llvm\build\Release\bin\..\lib\clang\3.9.0\lib\windows\clang_rt.asan-i386.lib'
```
The dropped executable path contains the configuration 'Release':
```
'd:\src\llvm\build\Release\bin\..\lib\clang\3.9.0\lib\windows\Release\clang_rt.asan-i386.lib'
```
The variable 'RUNTIME_OUTPUT_DIRECTORY' is used to specify the output directory.
But CMAKE is appending the current configuration (i.e. Debug, Release).
see: https://cmake.org/cmake/help/v3.0/prop_tgt/RUNTIME_OUTPUT_DIRECTORY.html
```
"Multi-configuration generators (VS, Xcode) append a per-configuration subdirectory to the specified directory."
```
To avoid this problem, the configuration specific variable must be set:
'RUNTIME_OUTPUT_DIRECTORY_DEBUG', 'RUNTIME_OUTPUT_DIRECTORY_RELEASE', and so on.
Reviewers: ddunbar, chapuni, rnk
Subscribers: kubabrecka, llvm-commits
Differential Revision: http://reviews.llvm.org/D20261
llvm-svn: 269658
Summary:
Cleanup some code by using appropriate APIs.
Some coding style cleanups.
There is no behavior changes.
- Function `IncludeSorter::CreateFixIt` can be replaced by `FixItHint::CreateReplacement`.
- Function `cleanPath` is a wrapper for `llvm::sys::path::remove_dots`.
Reviewers: alexfh
Subscribers: cfe-commits
Differential Revision: http://reviews.llvm.org/D20279
llvm-svn: 269656
Without a diagnostic handler installed, llc's behaviour is to exit on the first
error that it encounters. This is very different from the behaviour of clang
and other front ends, which try to gather as many errors as possible before
exiting.
This commit adds a diagnostic handler to llc, allowing it to find and report
more than one error. The old behaviour is preserved under a flag (-exit-on-error).
Some of the tests fail with the new diagnostic handler, so they have to use the
new flag in order to run under the previous behaviour. Some of these are known
bugs, others need further investigation. Ideally, we should fix the tests and
remove the flag at some point in the future.
Reapplied after fixing the LLDB build that was broken due to the new
DiagnosticSeverity in LLVMContext.h, and fixed an UB in the new change.
Patch by Diana Picus.
llvm-svn: 269655
We should use the musl linker only when there's no environment specified and
the vendor is MTI. The new test verifies this behaviour and is a follow-up to
the r269411 commit that added the vendor field check.
llvm-svn: 269651
Both of above tests fail on arm and bugs have been reported on android already.
Adding arm-linux decorator because android decorator doesnt xfail these test when run on linux.
llvm-svn: 269647
This patch uses PSHUFB to lower vector CTLZ and avoid (slower) scalarizations.
The leading zero count of each 4-bit nibble of the vector is determined by using a PSHUFB lookup. Pairs of results are then repeatedly combined up to the original element width.
Differential Revision: http://reviews.llvm.org/D20016
llvm-svn: 269646
KMP_USE_FUTEX preprocessor definition defined in kmp_lock.h is used
inconsequently throughout LLVM libomp code.
* some .c files that use this define do not include kmp_lock.h file,
in effect guarded part of code are never compiled
* some places in code use architecture-depending preprocessor
logic expressions which effectively disable use of Futex for
AArch64 architecture, all these places should use
'#if KMP_USE_FUTEX' instead to avoid any further confusions
* some places use KMP_HAS_FUTEX which is nowhere defined,
KMP_USE_FUTEX should be used instead
Differential Revision: http://reviews.llvm.org/D19629
llvm-svn: 269642
Summary:
The failure r269410 worked around turned out to be caused by an incorrect
evaluation of R_MICROMIPS_GOT16 which then caused the GOT entries to be
incorrect.
This patch fixes the evaluation and reverts r269410.
Reviewers: sdardis, vkalintiris, rafael
Subscribers: rafael, dsanders, sdardis, llvm-commits
Differential Revision: http://reviews.llvm.org/D20242
llvm-svn: 269641
NPL now assumes it is running from a single thread now, so its thread-safety is untested
anyway (and if that assumption is broken, we'll have bigger problems (due to ptrace restrictions)
than a couple of missing mutexes).
llvm-svn: 269640
Summary:
This fixes PR27682. Additionally, '.set micromips' by itself is not sufficient
to raise the EF_MIPS_MICROMIPS flag. It is also necessary to emit a microMIPS
instruction. This has also been fixed.
Reviewers: sdardis, vkalintiris, rafael
Subscribers: rafael, dsanders, sdardis, llvm-commits
Differential Revision: http://reviews.llvm.org/D20214
llvm-svn: 269639
Xinliang David Li