This avoids the non-trivial overhead of creating a TaskGroup in these degenerate
cases, but also exposes parallelism. It turns out that the default executor
underlying TaskGroup prevents recursive parallelism - so an instance of a task
group being alive will make nested ones become serial.
This is a big issue in MLIR in some dialects, if they have a single instance of
an outer op (e.g. a firrtl.circuit) that has many parallel ops within it (e.g.
a firrtl.module). This patch side-steps the problem by avoiding creating the
TaskGroup in the unneeded case. See this issue for more details:
https://github.com/llvm/circt/issues/993
Note that this isn't a really great solution for the general case of nested
parallelism. A redesign of the TaskGroup stuff would be better, but would be
a much more invasive change.
Differential Revision: https://reviews.llvm.org/D101699
This can come up in rare situations, where a csel is created with
identical operands. These can be folded simply to the original value,
allowing the csel to be removed and further simplification to happen.
This patch also removes FCSEL as it is unused, not being produced
anywhere or lowered to anything.
Differential Revision: https://reviews.llvm.org/D101687
- Previously, https://reviews.llvm.org/D101308 removed prefixes from register while printing them out. This was especially needed for inline asm statements which used input/output operands.
- However, the backend SystemZAsmParser, accepts both prefixed registers and prefix-less registers as part of its implementation
- This patch aims to change that by ensuring that prefixed registers are only allowed for the ATT dialect.
Reviewed By: uweigand
Differential Revision: https://reviews.llvm.org/D101665
Need to check if target allows/supports masked gathers before trying to
estimate its cost, otherwise we may fail to vectorize some of the
patterns because of too pessimistic cost model.
Part of D57059.
Differential Revision: https://reviews.llvm.org/D101297
Since googlebench builds as c++11, the change there is incorrect and breaks the
googlebench build when the STL implementation is strict about std::enable_if_t
not being available in lesser c++ versions.
partial revert of: 1bd6123b781120c9190b9ba58b900cdcb718cdd1 (https://reviews.llvm.org/D74384)
Differential Revision: https://reviews.llvm.org/D101583
Need to check if target allows/supports masked gathers before trying to
estimate its cost, otherwise we may fail to vectorize some of the
patterns because of too pessimistic cost model.
Part of D57059.
Differential Revision: https://reviews.llvm.org/D101297
As we gradually move more elements of LV to VPlan, we are trying to
reduce the number of places that still has to check IR of the original
loop.
This patch adjusts the code to fix cross iteration phis to get the PHIs
to fix directly from the VPlan that is executed. We still need the
original PHI to check for first-order recurrences, but we can get rid of
that once we model that explicitly in VPlan as well.
Reviewed By: Ayal
Differential Revision: https://reviews.llvm.org/D99293
This patch adds the basic functions needed for controlling auto conversion on z/OS.
Auto conversion is enabled on untagged input file to ASCII by making the assumption that all untagged files are EBCDIC encoded. Output files are auto converted to EBCDIC IBM-1047.
This change also enables conversion for stdin/stdout/stderr.
For more information on how fcntl controls codepage https://www.ibm.com/docs/en/zos/2.4.0?topic=descriptions-fcntl-bpx1fct-bpx4fct-control-open-file-descriptors
Reviewed By: anirudhp
Differential Revision: https://reviews.llvm.org/D100483
Similarly to D101096, this makes sure that MMO operands get propagated
through from MVE gathers/scatters to the Machine Instructions. This
allows extra scheduling freedom, not forcing the instructions to act as
scheduling barriers. We create MMO's with an unknown size, specifying
that they can load from anywhere in memory, similar to the masked_gather
or X86 intrinsics.
Differential Revision: https://reviews.llvm.org/D101219
SITargetLowering::LowerFormalArguments asserts that none of these
features are used for graphics calling conventions, so
AnnotateKernelFeatures should not add them.
Differential Revision: https://reviews.llvm.org/D101534
Add address sanitizer instrumentation support for accesses to global
and constant address spaces in AMDGPU. It strictly avoids instrumenting
the stack and assumes x86 as the host.
Reviewed by: vitalybuka
Differential Revision: https://reviews.llvm.org/D99071
We create MMO's for the VLDn/VSTn intrinsics in ARMTargetLowering::
getTgtMemIntrinsic, but they do not currently make it ll the way through
ISel. This changes that in the various places it needs changing, making
sure that the MMO is propagate through to the final instruction. This
can help in scheduling, not treating the VLD2/VST2 as a scheduling
barrier.
Differential Revision: https://reviews.llvm.org/D101096
Setting the preffered function alignment to 16 for Cortex A53/A55
improves performance in a wide range of benchmarks. This brings it
in line with the Cortex-A53/A55 tuning that is used in GCC
(gcc/config/aarch64/aarch64.c).
Differential Revision: https://reviews.llvm.org/D101636
Change-Id: I2ce47fe7ab5e3b54f49c89038d8da4e404742de2
This allows for a much more efficient encoding for small negative
numbers by storing the sign bit first and negating the rest of
the bits. This was already being used for OPC_CheckInteger.
For every in tree target this affects, the table got smaller.
R600GenDAGISel.inc saw the largest reduction of 7K.
I did have to add a new opcode for StringIntegers used for
register class ids and subregister indices since we don't have the
integer value to encode. The enum name is emitted directly into
the table. Previously assumed the enum would expand to a positive
7-bit number. We might be able to just shift that right by 1 and
assume it is a positive 6 bit number, but that will need more
investigation.
This shrinks the immediate that isel table needs to emit for these
instructions. Hoping this allows me to change OPC_EmitInteger to
use a better variable length encoding for representing negative
numbers. Similar to what was done a few months ago for OPC_CheckInteger.
The alternative encoding uses less bytes for negative numbers, but
increases the number of bytes need to encode 64 which was a very
common number in the RISCV table due to SEW=64. By using Log2 this
becomes 6 and is no longer a problem.
As opposed to going through the Aliasee type.
For opaque pointers, we're trying to remove uses of PointerType::getElementType().
Reviewed By: dblaikie
Differential Revision: https://reviews.llvm.org/D101715
This patch introduces a helper to obtain an iterator range for the
PHI-like recipes in a block.
Reviewed By: Ayal
Differential Revision: https://reviews.llvm.org/D100101
This update supports the following transformation:
```
select(extract(mul_with_overflow(a, _), _), (a == 0), false)
=>
and(extract(mul_with_overflow(a, _), _), (a == 0))
```
which is correct because if `a` was poison the select's condition was
also poison.
This update is splitted from D101423.
X32 uses 32-bit ELF object files with 32-bit alignment, so the
.note.gnu.property section needs to be emitted as it is for X86.
Reviewed By: MaskRay
Differential Revision: https://reviews.llvm.org/D101689
Introduce basic schedule model for AMD Zen 3 CPU's, a.k.a `znver3`.
This is fully built from scratch, from llvm-mca measurements
and documented reference materials.
Nothing was copied from `znver2`/`znver1`.
I believe this is in a reasonable state of completion for inclusion,
probably better than D52779 `bdver2` was :)
Namely:
* uops are pretty spot-on (at least what llvm-mca can measure)
{F16422596}
* latency is also pretty spot-on (at least what llvm-mca can measure)
{F16422601}
* throughput is within reason
{F16422607}
I haven't run much benchmarks with this,
however RawSpeed benchmarks says this is beneficial:
{F16603978}
{F16604029}
I'll call out the obvious problems there:
* i didn't really bother with X87 instructions
* i didn't really bother with obviously-microcoded/system instructions
* There are large discrepancy in throughput for `mr` and `rm` instructions.
I'm not really sure if it's a modelling defect that needs to be fixed,
or it's a defect of measurments.
* Pipe distributions are probably bad :)
I can't do much here until AMD allows that to be fixed
by documenting the appropriate counters and updating libpfm
That being said, as @RKSimon notes:
>>! In D94395#2647381, @RKSimon wrote:
> I'll mention again that all the znver* models appear to be very inaccurate wrt SIMD/FPU instructions <...>
so how much worse this could possibly be?!
Things that aren't there:
* Various tunings: zero idioms, etc. That is follow-ups.
Differential Revision: https://reviews.llvm.org/D94395
This seems to be a leftover from when the BackedgeTakenInfo
stored multiple exit counts with manual memory management. At
some point this was switchted to a simple vector, and there should
be no need to micro-manage the clearing anymore. We can simply
drop the loop from the map and the the destructor do its job.
Apply the same logic used to check if CMPXCHG nodes should be expanded
at -O0: the register allocator may end up spilling some register in
between the atomic load/store pairs, breaking the atomicity and possibly
stalling the execution.
Fixes PR48017
Reviewed By: efriedman
Differential Revision: https://reviews.llvm.org/D101163
Pre-requisite for D101163, the `NOLSE-0O` case shows registers being
spilled inside the rmw loop.
Use two separate prefixes for the `LSE-O0` case as some outputs differ
only by a comment that update_llc_test_checks.py ignores but lit does
not, causing the test to fail unexpectedly when run.
