Summary:
When we restore an SGPR value from scratch, we first load it into a
temporary VGPR and then use v_readlane_b32 to copy the value from the
VGPR back into an SGPR.
We weren't setting the kill flag on the VGPR in the v_readlane_b32
instruction, so the register scavenger wasn't able to re-use this
temp value later.
I wasn't able to create a lit test for this.
Reviewers: arsenm
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D19744
llvm-svn: 268287
Summary:
Hello,
Building a recent gcc on a powerpc-linux system advertsing:
Red Hat Enterprise Linux Server release 5.10 (Tikanga)
we stumbled on a compilation error on a file originating
from compiler-rt/lib/sanitizer-common.
sanitizer_platform_limits_linux.cc #includes asm/posix_types.h,
which, on our system, uses __kernel_fd_set and associated macros.
These aren't defined at the point of their use, and the compilation
fails with symptoms like:
In file included from ../../../../src/libsanitizer/sanitizer_common/sanitizer_platform_limits_linux.cc:29:0:
/usr/include/asm/posix_types.h:72:51: error: '__kernel_fd_set' has not been declared
static __inline__ void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
...
The attached patch is a suggestion to fix this, by including linux/posix_types.h
instead of asm/posix_types.h. linux/posix_types defines the necessary types and
macros, then #includes asm/posix_types.h.
We have been using it locally for gcc without problems for a couple of years
on powerpc, x86 and x86_64-linux platforms. It is still needed for gcc-6 on
our powerpc host and applies cleanly on the compiler-rt trunk.
Comments ?
Thanks much in advance for your feedback,
With Kind Regards,
Olivier
Reviewers: llvm-commits, kcc
Subscribers: kcc, kubabrecka
Differential Revision: http://reviews.llvm.org/D19799
llvm-svn: 268283
We were negating an immediate that was going to be used in a SUBri form
unnecessarily. Since ADD/SUB are very similar we *can* do that, but we have to
change the SUB to an ADD at the same time. This also applies to ADD, and allows
us to handle a slightly larger range of immediates for those two operations.
rdar://25992245
llvm-svn: 268276
Summary:
We don't have sign-/zero-extending ldg/ldu instructions defined,
so we need to emulate them with explicit CVTs. We were originally
handling the i8 case, but not any other cases.
Fixes PR26185
Reviewers: jingyue, jlebar
Subscribers: jholewinski
Differential Revision: http://reviews.llvm.org/D19615
llvm-svn: 268272
As shown in the diff, we used to add to CFLAA's cache by doing
`Cache[Fn] = buildSetsFrom(Fn)`. `buildSetsFrom(Fn)` may cause `Cache`
to reallocate its underlying storage, if this happens and `Cache[Fn]`
was evaluated prior to `buildSetsFrom(Fn)`, then we'll store the result
to a bad address.
Patch by Jia Chen.
llvm-svn: 268269
PDB has a lot of similar data structures. We already have code
for parsing a Name Map, but PDB seems to have a different but
very similar structure that is a hash table. This is the
beginning of code needed in order to parse the name hash table,
but it is not yet complete. It parses the basic metadata of
the hash table, the bucket array, and the names buffer, but
doesn't use any of these fields yet as the data structure
requires a non-trivial amount of work to understand.
llvm-svn: 268268
When running cc1 with -flto=thin, it is followed by GlobalOpt, which
requires the callgraph. This saves rebuilding one.
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 268266
Summary:
The goal of the patch is to bring checkers in their appropriate namespace.
This path doesn't change any behavior.
Reviewers: alexfh
Subscribers: cfe-commits
Differential Revision: http://reviews.llvm.org/D19811
llvm-svn: 268264
Before this change, we would pass all non-HFA record arguments on
Windows with byval. Byval often blocks optimizations and results in bad
code generation. Windows now uses the existing workaround that other
x86_32 platforms use.
I also expanded the workaround to handle C++ records with constructors
on Windows. On non-Windows platforms, we have to keep generating the
same LLVM IR prototypes if we want our bitcode to be ABI compatible.
Otherwise we will encounter mismatch issues like PR21573.
Essentially fixes PR27522 in Clang instead of LLVM.
Reviewers: hans
Differential Revision: http://reviews.llvm.org/D19756
llvm-svn: 268261
Summary:
Add support for detecting hazards in SMEM soft clauses, so that we only
break the clauses when necessary, either by adding s_nop or re-ordering
other alu instructions.
Reviewers: arsenm
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D18870
llvm-svn: 268260
Summary:
This intrinsic is used to get flat-shaded fragment shader inputs. Those are
uniform across a primitive, but a fragment shader wave may process pixels from
multiple primitives (as indicated by the prim_mask), and so that's where
divergence can arise.
Reviewers: arsenm, tstellarAMD
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D19747
llvm-svn: 268259
Make it possible that TryToSimplifyUncondBranchFromEmptyBlock merges empty
basic block including lifetime intrinsics as well as phi nodes and
unconditional branch into its successor or predecessor(s).
If successor of empty block has single predecessor, all contents including
lifetime intrinsics are sinked into the successor. Otherwise, they are
hoisted into its predecessor(s) and then merged into the predecessor(s).
Patch by Josh Yoon <josh.yoon@samsung.com>!
Differential Revision: http://reviews.llvm.org/D19257
llvm-svn: 268254
Because modernize-make-shared do almost the same job as
modernize-make-unique, I refactored common code to MakeSmartPtrCheck.
http://reviews.llvm.org/D19183
llvm-svn: 268253
This is where it was originally, until LoopVersioningLICM was
inserted before in r259986, I don't believe it was on purpose.
Differential Revision: http://reviews.llvm.org/D19809
From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 268252
This adds llvm-pdbdump to the list of tools which get printed with
the full path in verbose mode. This makes it easier to take the
whole run line from verbose output and run it again without prepending
with the builds bin directory.
llvm-svn: 268250
This happens on a 64-bit platform that uses SizeClassAllocator32 (e.g. ASan on AArch64). When querying a large invalid pointer, `__sanitizer_get_allocated_size(0xdeadbeefdeadbeef)`, an assertion will fail. This patch changes PointerIsMine to return false if the pointer is outside of [kSpaceBeg, kSpaceBeg + kSpaceSize).
Differential Revision: http://reviews.llvm.org/D15008
llvm-svn: 268243
Simon Pilgrim