There were cases where the backend computed a wrong permute mask for a VPERM2X128 node.
Example:
\code
define <8 x float> @foo(<8 x float> %a, <8 x float> %b) {
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 6, i32 7, i32 undef, i32 undef, i32 6, i32 7>
ret <8 x float> %shuffle
}
\code end
Before this patch, llc (with -mattr=+avx) emitted the following vperm2f128:
vperm2f128 $0, %ymm0, %ymm0, %ymm0 # ymm0 = ymm0[0,1,0,1]
With this patch, llc emits a vperm2f128 with a correct permute mask:
vperm2f128 $17, %ymm0, %ymm0, %ymm0 # ymm0 = ymm0[2,3,2,3]
Differential Revision: http://reviews.llvm.org/D8119
llvm-svn: 231601
This test case was supposed to test the range analysis but it became just
another delinearization test case after enabling delinearization.
Suggested-by: Johannes Doerfert
llvm-svn: 231599
When code generating array index expressions the types of the different
components of the index expressions may not always match. We extend the type of
the index expression (if possible) and assert otherwise.
llvm-svn: 231592
The performance test case just committed was the last open issue I was aware of.
We enable this by default to increase test coverage and to possibly trigger
reports of issues yet unknown.
llvm-svn: 231590
If an output is large, its base relocation section can be also large.
For example, chrome.dll is almost 300 MB, and it has about 9 million
base relocations. Creating the section took 1.5 seconds on my machine.
This patch changes the way to create the section so that we can use
parallel_sort to group base relocations by high bits. This change
makes the linker almost 4% faster for the above test case on my machine.
If I replace parallel_sort with std::sort, performance remains the same,
so single thread performance should remain the same.
This has no functionality change. The output should be identical as
before.
llvm-svn: 231585
All defined symbols from all archive files are inserted to _archiveMap,
so performance of hash table matters here (I'm not trying to convert
all std::maps with DenseMaps). This change seems to make the linker
0.5% - 1% faster for my test case.
llvm-svn: 231584
This patch reverts r231545 "PECOFF: Do not add extraneous symbols
to the dead strip root." CrWinClangLLD buildbot is currently broken.
Since I can't reproduce the issue locally, I'm reverting the most
relevant change.
llvm-svn: 231582
We have an increasing number of cases where we are creating commuted shuffle masks - all implementing nearly the same code.
This patch adds a static helper function - ShuffleVectorSDNode::commuteMask() and replaces a number of cases to use it.
Differential Revision: http://reviews.llvm.org/D8139
llvm-svn: 231581
Linux/GNU on AArch64 EH ABI Level III is implemented using exception frame
tables as defined in LSB II.11.6. The exception frame tables use the DWARF
Exception Header Encoding as described in LSB II.11.5.1. We already defined the
appropriate definition _LIBUNWIND_SUPPORT_DWARF_UNWIND to enable this.
llvm-svn: 231580
lib/ExecutionEngine/Targets has no Makefile, causing the autoconf build
to fail. Solve this by bringing the COFF implementation of RuntimeDyld
in line like the Mach-O and ELF implementations.
llvm-svn: 231579
AArch64 uses // as the comment character (although, Darwin uses ;). However,
since we are using the C preprocessor on these files, // can be used as the
comment character across the board.
Tweak the platform guard to recognise __aarch64__ as well as __arm64__ for the
platform identifier.
llvm-svn: 231578
Provide basic support for dynamically loadable coff objects. Only handles a subset of x64 currently.
Patch by Andy Ayers!
Differential Revision: http://reviews.llvm.org/D7793
llvm-svn: 231574
In theory this allows the compiler to skip materializing the array on
the stack. In practice clang often fails to do that, but that's a
different story. NFC.
llvm-svn: 231571
I disabled putting the new global into the same COMDAT as the function for now.
There's a fundamental problem when we inline references to the global but still
have the global in a COMDAT linked to the inlined function. Since this is only
an optimization there may be other versions of the COMDAT around that are
missing the new global and hell breaks loose at link time.
I hope the chromium build doesn't break this time :)
llvm-svn: 231564
This patch fixes the logic in the DAGCombiner that folds an AND node according
to rule: (and (X (load V)), C) -> (X (load V))
An AND between a vector load 'X' and a constant build_vector 'C' can be folded
into the load itself only if we can prove that the AND operation is redundant.
The algorithm implemented by 'visitAND' firstly computes the splat value 'S'
from C, and then checks if S has the lower 'B' bits set (where B is the size in
bits of the vector element type). The algorithm takes into account also the
'undef' bits in the splat mask.
Unfortunately, the algorithm only worked under the assumption that the size of S
is a multiple of the vector element type. With this patch, we conservatively
avoid folding the AND if the splat bits are not compatible with the vector
element type.
Added X86 test and-load-fold.ll
Differential Revision: http://reviews.llvm.org/D8085
llvm-svn: 231563
libc++. This lets me almost self-host on Linux with libc++ and libc++abi
very simply.
Currently, MCJIT and OrcJIT are failing due to uncaught exceptions, and
the Go binding tests are failing to build due to not linking in the
correct C++ standard library.
llvm-svn: 231560
simplicity in build systems, silence '-stdlib=libc++' when linking. Even
if we're not linking C++ code per-se, we may be passing this flag so
that when we are linking C++ code we pick up the desired standard
library. While most build systems already provide separate C and C++
compile flags, many conflate link flags. Sadly, CMake is among them
causing this warning in a libc++ selfhost.
llvm-svn: 231559
Johannes Doerfert