The commit D120104 enabled FeatureFuseAdrpAdd for -mcpu=generic,
allowing the linker to relax adrp;add pairs where possible. D132075
extended that to neoverse-n1, this patch extends it to all other cortex
and neoverse cpus for the same reasons.
Differential Revision: https://reviews.llvm.org/D134521
They're roughly ARMv8.6. This works in the .td file, but in
AArch64TargetParser.def, marking them v8.6 brings in support for the SM4
cryptographic hash and we don't actually have that. So TargetParser side
they're marked as v8.5, with the extra features (BF16 and I8MM added manually).
Finally, A16 supports the HCX extension in addition to v8.6. This has no
TargetParser implications.
This patch enables the LSLFast feature for Cortex-A76, Cortex-A77,
Cortex-A78, Cortex-A78C, Cortex-A710, Cortex-X1, Cortex-X2, Neoverse N1,
Neoverse N2, Neoverse V1 and the Neoverse 512TB pseudo-cpu, in-line with
the software optimization guides for those CPUs.
Differntial revision: https://reviews.llvm.org/D134273
This patch fixes the list of subtarget features enabled for the
Cortex-X1C processor, including the following:
* Fix incorrect version used for FeatureRCPC:
* Use FEAT_LRCPC2 instead of FEAT_LRCPC.
* Add missing v8.4-A features included in the TRM:
* Flag Manipulation Instructions - FeatureFlagM (FEAT_FlagM)
* Large System Extension 2 - FeatureLSE2 (FEAT_LSE2)
Reviewed By: vhscampos
Differential Revision: https://reviews.llvm.org/D132120
AdrpAdd fusion is already enabled for "generic" and it helps
the linker apply relocation relaxations for more adrp+add pairs.
This patch enables it for -mtune=neoverse-n1.
Differential revision: https://reviews.llvm.org/D132075
This patch adds the names of the Arm Architecture Reference Manual (ARM)
features to the corresponding Subtarget Features in the AArch64 backend
and target parser.
The aim of this is to make it clearer what architectural features a
subtarget feature might enable (so, which features a CPU must provide to
support that subtarget feature), and so make it easier to add new CPUs
in the future.
Differential Revision: https://reviews.llvm.org/D131257
This is used by disassemblers: `llvm-mc -disassemble -mattr=` and `llvm-objdump --mattr=`.
The main use case is for llvm-objdump to disassemble all known instructions
(D128030).
In user-facing tools, "all" is intentionally not supported in producers:
integrated assembler (`.arch_extension all`), clang -march (`-march=armv9.3a+all`).
Due to the code structure, `llvm-mc -mattr=+all` `llc -mattr=+all` are not
rejected (they are internal tool). Add `llvm/test/CodeGen/AArch64/mattr-all.ll`
to catch behavior changes.
AArch64SysReg::SysReg::haveFeatures: check `FeatureAll` to print
`AArch64SysReg::SysReg::AltName` for some system registers (e.g. `ERRIDR_EL1, RNDR`).
AArch64.td: add `AssemblerPredicateWithAll` to additionally test `FeatureAll`.
Change all `AssemblerPredicate` (except `UseNegativeImmediates`) to `AssemblerPredicateWithAll`.
utils/TableGen/{DecoderEmitter,SubtargetFeatureInfo}.cpp: support arbitrarily
nested all_of, any_of, and not.
Note: A predicate supports all_of, any_of, and not. For a target (though
currently not for AArch64) an encoding may be disassembled differently with
different target features.
Note: AArch64MCCodeEmitter::computeAvailableFeatures is not available to
the disassembler.
Reviewed By: peter.smith, lenary
Differential Revision: https://reviews.llvm.org/D128029
Update D120104 to add FeatureFuseAdrpAdd to Processor#TuneFeatures
instead of Processor#Features, similar to FeatureFuseAES, and matching
Tune*.
This enables FeatureFuseAdrpAdd for `clang -mcpu=xxx -mtune=generic` even
if xxx does not set FeatureFuseAdrpAdd.
Reviewed By: alexander-shaposhnikov, peter.smith
Differential Revision: https://reviews.llvm.org/D128787
According D125377, we order STP Q's by ascending address. While on some
targets, paired 128 bit loads and stores are slow, so the STP will split
into STRQ and STUR, so I hope these stores will also be ordered.
Also add subtarget feature ascend-store-address to control the aggressive order.
Reviewed By: dmgreen, fhahn
Differential Revision: https://reviews.llvm.org/D126700
Following discussion on D120261 and D121208 it seems better to remove the
concept of Streaming SVE from the subtarget/assembler predicates and
instead reason about 'SVE' and 'SME' as its higher level features, rather
than trying to model this runtime mode through explicit feature flags.
This patch is largely NFC.
Reviewed By: paulwalker-arm, david-arm
Differential Revision: https://reviews.llvm.org/D125977
Add support for the Ampere Computing Ampere1 core.
Ampere1 implements the AArch64 state and is compatible with ARMv8.6-A.
Differential Revision: https://reviews.llvm.org/D117112
This diff splits fuse-literals feature and enables fuse-adrp-add by default,
in particular, it adjusts instruction scheduling to place ADRP+ADD pairs together.
This also enables the linker to apply the relaxations described in
d2ca58c54b.
Differential revision: https://reviews.llvm.org/D120104
Test plan: make check-all
This reverts commit edb7ba714a.
This changes BLR_BTI to take variable_ops meaning that we can accept
a register or a label. The pattern still expects one argument so we'll
never get more than one. Then later we can check the type of the operand
to choose BL or BLR to emit.
(this is what BLR_RVMARKER does but I missed this detail of it first time around)
Also require NoSLSBLRMitigation which I missed in the first version.
Some implementations of setjmp will end with a br instead of a ret.
This means that the next instruction after a call to setjmp must be
a "bti j" (j for jump) to make this work when branch target identification
is enabled.
The BTI extension was added in armv8.5-a but the bti instruction is in the
hint space. This means we can emit it for any architecture version as long
as branch target enforcement flags are passed.
The starting point for the hint number is 32 then call adds 2, jump adds 4.
Hence "hint #36" for a "bti j" (and "hint #34" for the "bti c" you see
at the start of functions).
The existing Arm command line option -mno-bti-at-return-twice has been
applied to AArch64 as well.
Support is added to SelectionDAG Isel and GlobalIsel. FastIsel will
defer to SelectionDAG.
Based on the change done for M profile Arm in https://reviews.llvm.org/D112427Fixes#48888
Reviewed By: danielkiss
Differential Revision: https://reviews.llvm.org/D121707
Reland of D120906 after sanitizer failures.
This patch aims to reduce a lot of the boilerplate around adding new subtarget
features. From the SubtargetFeatures tablegen definitions, a series of calls to
the macro GET_SUBTARGETINFO_MACRO are generated in
ARM/AArch64GenSubtargetInfo.inc. ARMSubtarget/AArch64Subtarget can then use
this macro to define bool members and the corresponding getter methods.
Some naming inconsistencies have been fixed to allow this, and one unused
member removed.
This implementation only applies to boolean members; in future both BitVector
and enum members could also be generated.
Differential Revision: https://reviews.llvm.org/D120906
This patch aims to reduce a lot of the boilerplate around adding new subtarget
features. From the SubtargetFeatures tablegen definitions, a series of calls to
the macro GET_SUBTARGETINFO_MACRO are generated in
ARM/AArch64GenSubtargetInfo.inc. ARMSubtarget/AArch64Subtarget can then use
this macro to define bool members and the corresponding getter methods.
Some naming inconsistencies have been fixed to allow this, and one unused
member removed.
This implementation only applies to boolean members; in future both BitVector
and enum members could also be generated.
Differential Revision: https://reviews.llvm.org/D120906
It was included in HasV8_0rOps when D88660 first introduced that
architecture definition. In D118045 I moved it out of there and into
ProcessorFeatures.R82, so that -mcpu=cortex-r82 would continue to
behave the same as before but -march=armv8-r would include only the
mandatory parts of the architecture.
In fact, that was a mistake. Firstly, Cortex-R82 _doesn't_ implement
that feature, so it makes no sense to deliberately enable it for that
CPU in particular. But also, it's an extension that only adds system
registers, and we're generally more relaxed about where we enable
those (because kernel developers find it useful to write sysreg-access
instructions after runtime checking, and because sysreg accesses
aren't manufactured during code generation so the risk is small).
So, in line with that usual AArch64 policy, FeatureSpecRestrict ought
to be considered part of 8.0-R for LLVM purposes. So I'm moving it
back into HasV8_0rOps, where it started out.
Reviewed By: lenary
Differential Revision: https://reviews.llvm.org/D120830
A bug was introduced in 5ea35791e6 that
gave the wrong name and description for TuneExynosM4. This patch fixes
that and changes it back to m3.
Differential Revision: https://reviews.llvm.org/D120665
The following SubtargetFeatures are removed from the definition of
HasV8_0rOps, on the grounds that they are optional in Armv8.4-A, and
therefore (by the definition of Armv8.0-R) also optional in v8.0-R:
* performance monitoring: FeaturePerfMon
* cryptography: FeatureSM4 and FeatureSHA3
* half-precision FP: FeatureFullFP16, FeatureFP16FML
* speculation control: FeatureSSBS, FeaturePredRes, FeatureSB,
FeatureSpecRestrict
This isn't the full set of features that are listed as optional in the
spec. FeatureCCIDX and FeatureTRACEV8_4 are also optional. But LLVM
includes those in HasV8_3aOps and HasV8_4aOps respectively (I think on
the grounds that the system registers they enable are useful to be
able to access after a runtime check), and so for consistency, I've
left those in HasV8_0rOps too.
After this commit, HasV8_0rOps is a strict subset of HasV8_4aOps (but
missing features that are not in Armv8.0-R at all).
The definition of Cortex-R82 is correspondingly updated to add most of
the features that I've removed from base Armv8.0-R (with the exception
of the cryptography ones), since that particular implementation of
v8.0-R does have them.
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D118045
This family of instructions includes CPYF (copy forward), CPYB (copy
backward), SET (memset) and SETG (memset + initialise MTE tags), with
some sub-variants to indicate whether address translation is done in a
privileged or unprivileged way. For the copy instructions, you can
separately specify the read and write translations (so that kernels
can safely use these instructions in syscall handlers, to memcpy
between the calling process's user-space memory map and the kernel's
own privileged one).
The unusual thing about these instructions is that they write back to
multiple registers, because they perform an implementation-defined
amount of copying each time they run, and write back to _all_ the
address and size registers to indicate how much remains to be done
(and the code is expected to loop on them until the size register
becomes zero). But this is no problem in LLVM - you just define each
instruction to have multiple outputs, multiple inputs, and a set of
constraints tying their register numbers together appropriately.
This commit introduces a special subtarget feature called MOPS (after
the name the spec gives to the CPU id field), which is a dependency of
the top-level 8.8-A feature, and uses that to enable most of the new
instructions. The SETMG instructions also depend on MTE (and the test
checks that).
Differential Revision: https://reviews.llvm.org/D116157
This patch introduces support for targetting the Armv9.3-A architecture,
which should map to the existing Armv8.8-A extensions.
Differential Revision: https://reviews.llvm.org/D116158
This is the first commit in a series that implements support for
"armv8.8-a" architecture. This should contain all the necessary
boilerplate to make the 8.8-A architecture exist from LLVM and Clang's
point of view: it adds the new arch as a subtarget feature, a definition
in TargetParser, a name on the command line, an appropriate set of
predefined macros, and adds appropriate tests. The new architecture name
is supported in both AArch32 and AArch64.
However, in this commit, no actual _functionality_ is added as part of
the new architecture. If you specify -march=armv8.8a, the compiler
will accept it and set the right predefines, but generate no code any
differently.
Differential Revision: https://reviews.llvm.org/D115694
When this pass was originally implemented, the fix pass was enabled
using a llvm command-line flag. This works fine, except in the case of
LTO, where the flag is not passed into the linker plugin in order to
enable the function pass in the LTO backend.
Now LTO exists, the expectation now is to use target features rather
than command-line arguments to control code generation, as this ensures
that different command-line arguments in different files are correctly
represented, and target-features always get to the LTO plugin as they
are encoded into LLVM IR.
The fall-out of this change is that the fix pass has to always be added
to the backend pass pipeline, so now it makes no changes if the function
does not have the right target feature to enable it. This should make a
minimal difference to compile time.
One advantage is it's now much easier to enable when compiling for a
Cortex-A53, as CPUs imply their own individual sets of target-features,
in a more fine-grained way. I haven't done this yet, but it is an
option, if the fix should be enabled in more places.
Existing tests of the user interface are unaffected, the changes are to
reflect that the argument is now turned into a target feature.
Reviewed By: tmatheson
Differential Revision: https://reviews.llvm.org/D114703
The support for neoverse-512tvb mirrors the same option available in GCC[1].
There is no functional effect for this option yet.
This patch ensures the driver accepts "-mcpu=neoverse-512tvb", and enough
plumbing is in place to allow the new option to be used in the future.
[1]https://gcc.gnu.org/onlinedocs/gcc/AArch64-Options.html
Differential Revision: https://reviews.llvm.org/D112406
This change introduces subtarget features to predicate certain
instructions and system registers that are available only on
'A' profile targets. Those features are not present when
targeting a generic CPU, which is the default processor.
In other words the generic CPU now means the intersection of
'A' and 'R' profiles. To maintain backwards compatibility we
enable the features that correspond to -march=armv8-a when the
architecture is not explicitly specified on the command line.
References: https://developer.arm.com/documentation/ddi0600/latest
Differential Revision: https://reviews.llvm.org/D110065
Following on from an earlier patch that introduced support for -mtune
for AArch64 backends, this patch splits out the tuning features
from the processor features. This gives us the ability to enable
architectural feature set A for a given processor with "-mcpu=A"
and define the set of tuning features B with "-mtune=B".
It's quite difficult to write a test that proves we select the
right features according to the tuning attribute because most
of these relate to scheduling. I have created a test here:
CodeGen/AArch64/misched-fusion-addr-tune.ll
that demonstrates the different scheduling choices based upon
the tuning.
Differential Revision: https://reviews.llvm.org/D111551
This patch adds patterns to match the following with INC/DEC:
- @llvm.aarch64.sve.cnt[b|h|w|d] intrinsics + ADD/SUB
- vscale + ADD/SUB
For some implementations of SVE, INC/DEC VL is not as cheap as ADD/SUB and
so this behaviour is guarded by the "use-scalar-inc-vl" feature flag, which for SVE
is off by default. There are no known issues with SVE2, so this feature is
enabled by default when targeting SVE2.
Reviewed By: david-arm
Differential Revision: https://reviews.llvm.org/D111441
armv9-a, armv9.1-a and armv9.2-a can be targeted using the -march option
both in ARM and AArch64.
- Armv9-A maps to Armv8.5-A.
- Armv9.1-A maps to Armv8.6-A.
- Armv9.2-A maps to Armv8.7-A.
- The SVE2 extension is enabled by default on these architectures.
- The cryptographic extensions are disabled by default on these
architectures.
The Armv9-A architecture is described in the Arm® Architecture Reference
Manual Supplement Armv9, for Armv9-A architecture profile
(https://developer.arm.com/documentation/ddi0608/latest).
Reviewed By: SjoerdMeijer
Differential Revision: https://reviews.llvm.org/D109517
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
v8.4 says that normal loads/stores of 128-bytes are single-copy atomic if
they're properly aligned (which all LLVM atomics are) so we no longer need to
do a full RMW operation to guarantee we got a clean read.
FeaturePMU was created in AArch64 to accommodate one missing system
register, PMMIR_EL1, in commit ffcd7698ae.
However, the Performance Monitors extension already had a target
feature, which is called FeaturePerfMon. Therefore, FeaturePMU is
redundant.
This patch removes FeaturePMU and merges its contents into
FeaturePerfMon.
Reviewed By: dnsampaio
Differential Revision: https://reviews.llvm.org/D109246
David Sherwood