Without this, the combination of `-ast-dump=json` and `-ast-dump-filter FILTER` produces invalid JSON: the first line is a string that says `Dumping $SOME_DECL_NAME: `.
Reviewed By: aaron.ballman
Differential Revision: https://reviews.llvm.org/D108441
1. Add support to vectorize induction variables of loops that are
not mapped to any vector dimension in SuperVectorize pass.
2. Fix a bug in getForInductionVarOwner.
Reviewed By: dcaballe
Differential Revision: https://reviews.llvm.org/D111370
NOTE: some files are being removed from those files that are clang-formatted
which means some lack of formatting is slipping through the net on reviews
There were 2 related but over-specified folds for:
C1 - X == C
One allowed multi-use but was limited to equal constants.
The other allowed different constants but disallowed multi-use.
This combines the 2 folds into a more general match.
The test diffs show the multi-use cases that were falling
through the cracks.
https://alive2.llvm.org/ce/z/4_hEt2
define i1 @src(i8 %x, i8 %subC, i8 %C) {
%s = sub i8 %subC, %x
%r = icmp eq i8 %s, %C
ret i1 %r
}
define i1 @tgt(i8 %x, i8 %subC, i8 %C) {
%newC = sub i8 %subC, %C
%isneg = icmp eq i8 %x, %newC
ret i1 %isneg
}
We would like to start pushing -mcpu=generic towards enabling the set of
features that improves performance for some CPUs, without hurting any
others. A blend of the performance options hopefully beneficial to all
CPUs. The largest part of that is enabling in-order scheduling using the
Cortex-A55 schedule model. This is similar to the Arm backend change
from eecb353d0e which made -mcpu=generic perform in-order scheduling
using the cortex-a8 schedule model.
The idea is that in-order cpu's require the most help in instruction
scheduling, whereas out-of-order cpus can for the most part out-of-order
schedule around different codegen. Our benchmarking suggests that
hypothesis holds. When running on an in-order core this improved
performance by 3.8% geomean on a set of DSP workloads, 2% geomean on
some other embedded benchmark and between 1% and 1.8% on a set of
singlecore and multicore workloads, all running on a Cortex-A55 cluster.
On an out-of-order cpu the results are a lot more noisy but show flat
performance or an improvement. On the set of DSP and embedded
benchmarks, run on a Cortex-A78 there was a very noisy 1% speed
improvement. Using the most detailed results I could find, SPEC2006 runs
on a Neoverse N1 show a small increase in instruction count (+0.127%),
but a decrease in cycle counts (-0.155%, on average). The instruction
count is very low noise, the cycle count is more noisy with a 0.15%
decrease not being significant. SPEC2k17 shows a small decrease (-0.2%)
in instruction count leading to a -0.296% decrease in cycle count. These
results are within noise margins but tend to show a small improvement in
general.
When specifying an Apple target, clang will set "-target-cpu apple-a7"
on the command line, so should not be affected by this change when
running from clang. This also doesn't enable more runtime unrolling like
-mcpu=cortex-a55 does, only changing the schedule used.
A lot of existing tests have updated. This is a summary of the important
differences:
- Most changes are the same instructions in a different order.
- Sometimes this leads to very minor inefficiencies, such as requiring
an extra mov to move variables into r0/v0 for the return value of a test
function.
- misched-fusion.ll was no longer fusing the pairs of instructions it
should, as per D110561. I've changed the schedule used in the test
for now.
- neon-mla-mls.ll now uses "mul; sub" as opposed to "neg; mla" due to
the different latencies. This seems fine to me.
- Some SVE tests do not always remove movprfx where they did before due
to different register allocation giving different destructive forms.
- The tests argument-blocks-array-of-struct.ll and arm64-windows-calls.ll
produce two LDR where they previously produced an LDP due to
store-pair-suppress kicking in.
- arm64-ldp.ll and arm64-neon-copy.ll are missing pre/postinc on LPD.
- Some tests such as arm64-neon-mul-div.ll and
ragreedy-local-interval-cost.ll have more, less or just different
spilling.
- In aarch64_generated_funcs.ll.generated.expected one part of the
function is no longer outlined. Interestingly if I switch this to use
any other scheduled even less is outlined.
Some of these are expected to happen, such as differences in outlining
or register spilling. There will be places where these result in worse
codegen, places where they are better, with the SPEC instruction counts
suggesting it is not a decrease overall, on average.
Differential Revision: https://reviews.llvm.org/D110830
ParseSingleMember has two large ifs around the back of it's body:
`if (!is_artificial)` and `if (member_type)`. This patch just converts those
to early-exits. The patch is NFC. It even retains the curious fact that
Objective-C properties that fail to parse are silently ignored, but now there
is at least a FIXME that points this out.
C++20 and later allow you to pass no argument for the ... parameter in
a variadic macro, whereas earlier language modes and C disallow it.
We no longer diagnose in C++20 and later modes. This fixes PR51609.
Some of the first supported version field were incorrectly attributed to a later branch.
It wasn't possible to correctly determine the "introduced version" with my naive implementation
using git blame alone, (especially if the type had been changed from a bool -> enum)
I saw more things attributed to clang-format 13 than I remembered and reviewed
those options to determine their introduced version.
Reviewed By: HazardyKnusperkeks
Differential Revision: https://reviews.llvm.org/D110803
There is a bug reported at https://bugs.llvm.org/show_bug.cgi?id=48938
After looking through the glibc, I found the `atexit(f)` is the same as `__cxa_atexit(f, NULL, NULL)`. In orc runtime, we identify different JITDylib by their dso_handle value, so that a NULL dso_handle is invalid. So in this patch, I added a `PlatformJDDSOHandle` to ELFNixRuntimeState, and functions which are registered by atexit will be registered at PlatformJD.
Reviewed By: lhames
Differential Revision: https://reviews.llvm.org/D111413
The current code checks whether the vector's element type is a valid structure element type, rather than a valid vector element type. The two have separate implementations and but only accept very slightly different sets of types, which is probably why this wasn't caught before.
Differential Revision: https://reviews.llvm.org/D109655
CodeGenFunction::InitTempAlloca() inits the static alloca within the
entry block which may *not* necessarily be correct always.
For example, the current instruction insertion point (pointed by the
instruction builder) could be a program point which is hit multiple
times during the program execution, and it is expected that the static
alloca is initialized every time the program point is hit.
Hence remove CodeGenFunction::InitTempAlloca(), and initialize the
static alloca where the instruction insertion point is at the moment.
This patch, as a starting attempt, removes the calls to
CodeGenFunction::InitTempAlloca() which do not have any side effect on
the lit tests.
Reviewed By: rjmccall
Differential Revision: https://reviews.llvm.org/D111293
Commit 573531fb1f fixed the colon at the
end of a CHECK line (was a semicolon by mistake). With the check
enabled, it turned out that it was failing. Check for the correct
content.
Also add the missing colon to the next CHECK line.
This test is crashing 9 out of 10 runs in CI, but I can't reproduce
locally right now. Disabling to get the CI back to green and avoid
backsliding with more ASAN issues that would go unnoticed.
In this case, we know statically that we're destroying the most-derived
class, so the vptr must already point to the current class and never
needs to be updated.
fae0dfa implemented the new __ibm128 type, this patch enables its
complex form.
Reviewed By: rjmccall
Differential Revision: https://reviews.llvm.org/D109948
Currently, there're multiple float types that can be represented by
__attribute__((mode(xx))). It's parsed, and then a corresponding type is
created if available.
This refactor moves the enum for mode into a global enum class visible
to ASTContext.
Reviewed By: aaron.ballman, erichkeane
Differential Revision: https://reviews.llvm.org/D111391
This patch adds support for the
`__kmpc_get_hardware_num_threads_in_block` function that returns the
number of threads. This was missing in the new runtime and was used by
the AMDGPU plugin which prevented it from using the new runtime. This
patchs also unified the interface for getting the thread numbers in the
frontend.
Originally authored by jdoerfert.
Reviewed By: JonChesterfield
Differential Revision: https://reviews.llvm.org/D111475
566690b0 uses size information in float semantics, but PPCDoubleDouble
left them empty.
As follow-up, we can consider remove PPCDoubleDoubleLegacy and fill
other fields in the future.
Reviewed By: foad
Differential Revision: https://reviews.llvm.org/D111398
Until we hit the first barrier we should not call `mapping::isSPMDMode`
with all threads. Instead, we now have (and use during initialization) a
`mapping::isMainThreadInGenericMode` overload that takes the known
SPMD-mode state and one that queries it.
Reviewed By: tianshilei1992
Differential Revision: https://reviews.llvm.org/D111381
When the option -polly-loopfusion-greedy is set, the ScheduleOptimizer
tries to aggressively fuse any band it can and does not violate any
dependences.
As part if the implementation, the functionalty for copying a band
into an new schedule was extracted out of the ScheduleTreeRewriter.
We have a string litteral (via CPP) used to construct `StringRef`, which
is used to construct a `SmallString`. Just construct the latter
directly.
Differential Revision: https://reviews.llvm.org/D111322
There are functions where we do not want function instrumentation which is why we have `__attribute__((no_instrument_function))`. Extending this functionality to disable instrumentation for Objective-C methods as well. Objective C methods like `+load` run premain and having instrumentation on them causes runtime errors depending on the implementation of `__cyg_profile_func_enter` etc. functions
Reviewed By: rjmccall, aaron.ballman
Differential Revision: https://reviews.llvm.org/D111286
william woodruff