loop vectorizer to not do so when runtime pointer checks are needed and
share code with the new (not yet enabled) load/store saturation runtime
unrolling. Also ensure that we only consider the runtime checks when the
loop hasn't already been vectorized. If it has, the runtime check cost
has already been paid.
I've fleshed out a test case to cover the scalar unrolling as well as
the vector unrolling and comment clearly why we are or aren't following
the pattern.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200530 91177308-0d34-0410-b5e6-96231b3b80d8
The entry block of a function starts with all the static allocas. The change
in r195513 splits the block before those allocas, which has the effect of
turning them into dynamic allocas. That breaks all sorts of things. Change to
split after the initial allocas, and also add a comment explaining why the
block is split.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200515 91177308-0d34-0410-b5e6-96231b3b80d8
when the input is a concat_vectors and the insert replaces one of the
concat halves:
Lower half: fold (insert_subvector (concat_vectors X, Y), Z) ->
(concat_vectors Z, Y)
Upper half: fold (insert_subvector (concat_vectors X, Y), Z) ->
(concat_vectors X, Z)
This can be seen with the following IR:
define <8 x float> @lower_half(<4 x float> %v1, <4 x float> %v2, <4 x
float> %v3) {
%1 = shufflevector <4 x float> %v1, <4 x float> %v2, <8 x i32> <i32
0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%2 = tail call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x
float> %1, <4 x float> %v3, i8 0)
The vinsertf128 intrinsic is converted into an insert_subvector node
in SelectionDAGBuilder.cpp.
Using AVX, without the patch this generates two vinsertf128 instructions:
vinsertf128 $1, %xmm1, %ymm0, %ymm0
vinsertf128 $0, %xmm2, %ymm0, %ymm0
With the patch this is optimized into:
vinsertf128 $1, %xmm1, %ymm2, %ymm0
Patch by Robert Lougher.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200506 91177308-0d34-0410-b5e6-96231b3b80d8
When converting from "or + br" to two branches, or converting from
"and + br" to two branches, we correctly update the edge weights of
the two branches.
The previous attempt at r200431 was reverted at r200434 because of
two testing case failures. I modified my patch a little, but forgot
to re-run "make check-all".
Testing case CodeGen/ARM/lsr-unfolded-offset.ll is updated because of
the patch's impact on branch probability which causes changes in
spill placement.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200502 91177308-0d34-0410-b5e6-96231b3b80d8
This doesn't set errno, so this should be OK.
Also update the documentation to explicitly state
that errno are not set.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200501 91177308-0d34-0410-b5e6-96231b3b80d8
These should end up (in ELF) as R_X86_64_32S relocs, not R_X86_64_32.
Kill the horrid and incomplete special case and FIXME in
EncodeInstruction() and set things up so it can infer the signedness
from the ImmType just like it can the size and whether it's PC-relative.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200495 91177308-0d34-0410-b5e6-96231b3b80d8
COFF has only one symbol table.
MachO has a LC_DYSYMTAB, but that is not a symbol table, just extra info about
the one symbol table (LC_SYMTAB).
IR (coming soon) also has only one table.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200488 91177308-0d34-0410-b5e6-96231b3b80d8
Modern compilers (Clang 3.4, GCC 4.8) warn on variadic macros being
introduced in C99, which produces a huge number of useless diagnostics
since this macro is unused in the whole project.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200479 91177308-0d34-0410-b5e6-96231b3b80d8
utohexstr provides a temporary string, making it unsafe to use with the Twine
interface which will not copy the string. Switch to using std::string.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200457 91177308-0d34-0410-b5e6-96231b3b80d8
This is acceptted by clang and gcc, but MSVC seems to balk at it. As it is
unneeded, simply drop it. Fixes MSVC buildbots.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200456 91177308-0d34-0410-b5e6-96231b3b80d8
exp2 is not available on Windows. Fortunately, we are calculating powers of 2
with expontents within the range of [4,12]. Simply use an equivalent bitshift
operation to repair compilation with MSVC which does not provide this standard
function.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200454 91177308-0d34-0410-b5e6-96231b3b80d8
The SWAP instruction only exists in a 32-bit variant, but the 64-bit
atomic swap can be implemented in terms of CASX, like the other atomic
rmw primitives.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200453 91177308-0d34-0410-b5e6-96231b3b80d8
The .object_arch directive indicates an alternative architecture to be specified
in the object file. The directive does *not* effect the enabled feature bits
for the object file generation. This is particularly useful when the code
performs runtime detection and would like to indicate a lower architecture as
the requirements than the actual instructions used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200451 91177308-0d34-0410-b5e6-96231b3b80d8
Enhance the ARM specific parsing support in llvm-readobj to support attributes.
This allows for simpler tests to validate encoding of the build attributes as
specified in the ARM ELF specification.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200450 91177308-0d34-0410-b5e6-96231b3b80d8
.movsp is an ARM unwinding directive that indicates to the unwinder that a
register contains an offset from the current stack pointer. If the offset is
unspecified, it defaults to zero.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200449 91177308-0d34-0410-b5e6-96231b3b80d8
This enhances the ARMAsmParser to handle .tlsdescseq directives. This is a
slightly special relocation. We must be able to generate them, but not consume
them in assembly. The relocation is meant to assist the linker in generating a
TLS descriptor sequence. The ELF target streamer is enhanced to append
additional fixups into the current segment and that is used to emit the new
R_ARM_TLS_DESCSEQ relocations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200448 91177308-0d34-0410-b5e6-96231b3b80d8
Add support for tlsdesc relocations which are part of the ABI, marked as
experimental. These relocations permit the linker to perform TLS reference
optimizations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200447 91177308-0d34-0410-b5e6-96231b3b80d8
This adds support for TLS CALL relocations. TLS CALL relocations are used to
indicate to the linker to generate appropriate entries to resolve TLS references
via an appropriate function invocation (e.g. __tls_get_addr(PLT)).
In order to accomodate the linker relaxation of the TLS access model for the
references (GD/LD -> IE, IE -> LE), the relocation addend must be incomplete.
This requires that the partial inplace value is also incomplete (i.e. 0). We
simply avoid the offset value calculation at the time of the fixup adjustment in
the ARM assembler backend.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200446 91177308-0d34-0410-b5e6-96231b3b80d8
None of the object file formats reported error on iterator increment. In
retrospect, that is not too surprising: no object format stores symbols or
sections in a linked list or other structure that requires chasing pointers.
As a consequence, all error checking can be done on begin() and end().
This reduces the text segment of bin/llvm-readobj in my machine from 521233 to
518526 bytes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200442 91177308-0d34-0410-b5e6-96231b3b80d8
