It's more aggressive than we need to be, and leads to strange
workarounds in other places like call return value inference. Instead,
just directly mark an edge viable.
Tests by Florian Hahn.
Differential Revision: https://reviews.llvm.org/D49408
llvm-svn: 337507
Representing size and capacity directly as unsigned and calculate
`end()` using `begin() + size()`.
This limits the maximum size/capacity of a vector to UINT32_MAX.
https://reviews.llvm.org/D48518
llvm-svn: 337504
Summary:
Currently all type ids are emitted into the index file when it is
written. For distributed ThinLTO, that meant that all type ids were
being duplicated into every single distributed index file, regardless of
whether they were referenced, leading to huge amounts of unnecessary
duplication and size bloat.
Keep track of the type id GUIDs actually referenced by the GV summary
records being emitted, and only emit those type IDs.
Add a new test, and fix test/Assembler/thinlto-summary.ll so that all
type ids are referenced to prevent deletion in that test.
Reviewers: pcc
Subscribers: mehdi_amini, inglorion, eraman, steven_wu, dexonsmith, vitalybuka, llvm-commits
Differential Revision: https://reviews.llvm.org/D49565
llvm-svn: 337503
We have a number of cases where we fail to reduce vector op widths, performing the op in a larger vector and then extracting a subvector. This is often because by default it would create illegal types.
This peephole patch attempts to handle a few common cases detailed in PR36761, which typically involved extension+conversion to vX2f64 types.
Differential Revision: https://reviews.llvm.org/D49556
llvm-svn: 337500
The last argument is expected to be the destination buffer size (or less).
Detects if it points to destination buffer size directly or via a variable.
Detects if it is an integral, try to detect if the destination buffer can receive the source length.
Updating bsd-string.c unit tests as it make it fails now.
Reviewers: george.karpenpov, NoQ
Reviewed By: george.karpenkov
Differential Revision: https://reviews.llvm.org/D48884
llvm-svn: 337499
constant, don't convert the rest into a packed struct.
If an array constant has a large non-zero portion and a large zero
portion, we want to emit the first part as an array and the rest as a
zeroinitializer if possible. This fixes a memory usage regression from
r333141 when compiling PHP.
llvm-svn: 337498
Previously, clang marked the specialization as invalid without emitting a
diagnostic. This lead to an assert in CodeGen.
rdar://41806724
Differential revision: https://reviews.llvm.org/D49085
llvm-svn: 337497
For the most part, these changes were from the RFC. I made a few minor
word/structure changes, but nothing significant. I also regenerated the
example output, and adjusted the text accordingly.
Differential Revision: https://reviews.llvm.org/D49527
llvm-svn: 337496
This particular version of GCC seems to break bitfields when a method
appears between two bitfield members.
Personally, I think it's nice to keep bitfields close together so that
it's easy to check how things are packed, so I moved the method after
SubClassData.
Fixes PR38168.
llvm-svn: 337495
It fires on things like SmallVector<std::pair<int, int>>, where we
intentionally use memcpy instead of calling the assignment operator.
This warning fires in practically every LLVM TU, so we have to do
something about it, even if we aren't interested in being 100% warning
clean with GCC.
Reported as PR37337
llvm-svn: 337492
Returning SDValue() means nothing was changed. Returning the result of CombineTo returns the first argument of CombineTo. This is specially detected by DAGCombiner as meaning that something changed, but worklist management was already taken care of.
I think the only real effect of this change is that we now properly update the Statistic the counts the number of combines performed. That's the only thing between the check for null and the check for N in the DAGCombiner.
llvm-svn: 337491
This is mostly a preparation work for adding a limited support for
select instructions. It proved to be difficult to do due to size and
irregularity of Vectorizer::isConsecutiveAccess, this is fixed here I
believe.
It also turned out that these changes make it simpler to finish one of
the TODOs and fix a number of other small issues, namely:
1. Looking through bitcasts to a type of a different size (requires
careful tracking of the original load/store size and some math
converting sizes in bytes to expected differences in indices of GEPs).
2. Reusing partial analysis of pointers done by first attempt in proving
them consecutive instead of starting from scratch. This added limited
support for nested GEPs co-existing with difficult sext/zext
instructions. This also required a careful handling of negative
differences between constant parts of offsets.
3. Handing a case where the first pointer index is not an add, but
something else (a function parameter for instance).
I observe an increased number of successful vectorizations on a large
set of shader programs. Only few shaders are affected, but those that
are affected sport >5% less loads and stores than before the patch.
Reviewed By: rampitec
Differential-Revision: https://reviews.llvm.org/D49342
llvm-svn: 337489
As we already return true from needsAggressiveScheduling() for the most recent
hardware it would be cleaner to just return true for all PowerPC hardware.
Differential Revision: https://reviews.llvm.org/D48663
llvm-svn: 337488
This change fixes possibly invalid access to the internal data structure during
library shutdown. In a heavily oversubscribed situation, the library shutdown
sequence can reach the point where resources are deallocated while there still
exist threads in their final spinning loop. The added loop in
__kmp_internal_end() checks if there are such busy-waiting threads and blocks
the shutdown sequence if that is the case. Two versions of kmp_wait_template()
are now used to minimize performance impact.
Patch by Hansang Bae
Differential Revision: https://reviews.llvm.org/D49452
llvm-svn: 337486
Summary:
Add __llvm_profile_get_filename interface to get the profile filename,
which can be used for identifying which profile file belongs to an app
when multiple binaries are instrumented and dumping profiles into the
same directory. The filename includes the path.
Reviewers: davidxl
Subscribers: delcypher, #sanitizers, llvm-commits
Differential Revision: https://reviews.llvm.org/D49529
llvm-svn: 337482
provided by an outer template.
We made the incorrect assumption in various places that the only way we
can have any arguments already provided for a pack during template
argument deduction was from a partially-specified pack. That's not true;
we can also have arguments from an enclosing already-instantiated
template, and that can even result in the function template's own pack
parameters having a fixed length and not being packs for the purposes of
template argument deduction.
llvm-svn: 337481
Some trivial cases in udivrem were handled by directly assigning 0 or 1
to APInt objects. This would set the bit width to 1, instead of the bit
width of the inputs. A potentially undesirable side effect of that is
that with the bit width of 1, 1 equals -1.
Differential Revision: https://reviews.llvm.org/D49554
llvm-svn: 337478
Summary:
Currently, the ABI list test only works for ABI version 1. This commit
allows running the ABI list test with ABI version 2. It also adds an
ABI list file for ABI v2 on Mac OS X.
Reviewers: EricWF
Subscribers: mgorny, christof, dexonsmith, llvm-commits, mclow.lists
Differential Revision: https://reviews.llvm.org/D49509
llvm-svn: 337477
StringRef's data() returns a string that may be non-null-terminated.
Switch to using StringRefs from const char pointers in visitor notes
to avoid problems.
llvm-svn: 337474
Summary:
This patch introduces a new member to SymExpr, which stores the symbol complexity, avoiding recalculating it every time computeComplexity() is called.
Also, increase the complexity of conjured Symbols by one, so it's clear that it has a greater complexity than its underlying symbols.
Reviewers: NoQ, george.karpenkov
Reviewed By: NoQ, george.karpenkov
Subscribers: xazax.hun, szepet, a.sidorin
Differential Revision: https://reviews.llvm.org/D49232
llvm-svn: 337472
Summary: Currently, isConsecutiveAccess() detects two pointers(PtrA and PtrB) as consecutive by
comparing PtrB with BaseDelta+PtrA. This works when both pointers are factorized or
both of them are not factorized. But isConsecutiveAccess() fails if one of the
pointers is factorized but the other one is not.
Here is an example:
PtrA = 4 * (A + B)
PtrB = 4 + 4A + 4B
This patch uses getMinusSCEV() to compute the distance between two pointers.
getMinusSCEV() allows combining the expressions and computing the simplified distance.
Author: FarhanaAleen
Reviewed By: rampitec
Differential Revision: https://reviews.llvm.org/D49516
llvm-svn: 337471
This diagnoses calls to memset that have the second and third arguments
transposed, for example:
memset(buf, sizeof(buf), 0);
This is done by checking if the third argument is a literal 0, or if the second
is a sizeof expression (and the third isn't). The first check is also done for
calls to bzero.
Differential revision: https://reviews.llvm.org/D49112
llvm-svn: 337470
This patch fixes the latency/throughput of LEA instructions in the BtVer2
scheduling model.
On Jaguar, A 3-operands LEA has a latency of 2cy, and a reciprocal throughput of
1. That is because it uses one cycle of SAGU followed by 1cy of ALU1. An LEA
with a "Scale" operand is also slow, and it has the same latency profile as the
3-operands LEA. An LEA16r has a latency of 3cy, and a throughput of 0.5 (i.e.
RThrouhgput of 2.0).
This patch adds a new TIIPredicate named IsThreeOperandsLEAFn to X86Schedule.td.
The tablegen backend (for instruction-info) expands that definition into this
(file X86GenInstrInfo.inc):
```
static bool isThreeOperandsLEA(const MachineInstr &MI) {
return (
(
MI.getOpcode() == X86::LEA32r
|| MI.getOpcode() == X86::LEA64r
|| MI.getOpcode() == X86::LEA64_32r
|| MI.getOpcode() == X86::LEA16r
)
&& MI.getOperand(1).isReg()
&& MI.getOperand(1).getReg() != 0
&& MI.getOperand(3).isReg()
&& MI.getOperand(3).getReg() != 0
&& (
(
MI.getOperand(4).isImm()
&& MI.getOperand(4).getImm() != 0
)
|| (MI.getOperand(4).isGlobal())
)
);
}
```
A similar method is generated in the X86_MC namespace, and included into
X86MCTargetDesc.cpp (the declaration lives in X86MCTargetDesc.h).
Back to the BtVer2 scheduling model:
A new scheduling predicate named JSlowLEAPredicate now checks if either the
instruction is a three-operands LEA, or it is an LEA with a Scale value
different than 1.
A variant scheduling class uses that new predicate to correctly select the
appropriate latency profile.
Differential Revision: https://reviews.llvm.org/D49436
llvm-svn: 337469
device IDs are now 64-bit integers (as opposed to 32-bit)
map flags are 64-bit long (used to be 32-bit)
mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field
Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler)
llvm-svn: 337468
Fix bot failure from r37465. Move the new lto_flags append under the
check for whether lto_supported. Otherwise TestingConfig may not have
that member.
llvm-svn: 337467
Summary:
Executes both LTO and ThinLTO CFI tests an additional time using the new
pass manager. I only bothered to add with gold and not lld as testing
with one linker should be sufficient. I didn't add for APPLE or WIN32
since I don't have a way to test those.
Depends on D49429.
Reviewers: pcc
Subscribers: dberris, mgorny, mehdi_amini, delcypher, dexonsmith, #sanitizers, llvm-commits
Differential Revision: https://reviews.llvm.org/D49432
llvm-svn: 337465
DanglingInternalBufferChecker.
A pointer referring to the elements of a basic_string may be invalidated
by calling a non-const member function, except operator[], at, front,
back, begin, rbegin, end, and rend. The checker now warns if the pointer
is used after such operations.
Differential Revision: https://reviews.llvm.org/D49360
llvm-svn: 337463
When output style is GNU and amount of sections is >= SHN_LORESERVE,
llvm-readobj reports zero number of sections instead of actual value.
The patch fixes that.
Differential revision: https://reviews.llvm.org/D49544
llvm-svn: 337462
Summary:
Enable these passes for CFI and WPD in ThinLTO and LTO with the new pass
manager. Add a couple of tests for both PMs based on the clang tests
tools/clang/test/CodeGen/thinlto-distributed-cfi*.ll, but just test
through llvm-lto2 and not with distributed ThinLTO.
Reviewers: pcc
Subscribers: mehdi_amini, inglorion, eraman, steven_wu, dexonsmith, llvm-commits
Differential Revision: https://reviews.llvm.org/D49429
llvm-svn: 337461
The new test checks that we are actually able to read data from these
kinds of elf headers correctly instead of just that we read the section
number correctly. It is also easier to figure out what's going on in the
test.
llvm-svn: 337459
