Remove FeatureSlowMisaligned128Store from cyclone flags.
This flag causes splitting of 16 byte wide stores into 2 stored of 8
bytes. This was useful on older apple CPUs which were slow for 16byte
stores that were not aligned on 16byte. As the compiler often cannot
predict the actual alignment, the splitting was choosen.
This has been a topic for a lot of debate as the splitting also
decreases performance for some benchmarks. Measuring the effects on
newer apple chips (rdar://35525421) shows that it harms more cases than
it helps. So it is time to retire this workaround.
llvm-svn: 323289
Summary:
Fix an issue that's similar to what D41411 fixed:
float(__int128(float_var)) shouldn't be optimized to xscvdpsxds +
xscvsxdsp, as they mean (float)(int64_t)float_var.
Reviewers: jtony, hfinkel, echristo
Subscribers: sanjoy, nemanjai, hiraditya, llvm-commits, kbarton
Differential Revision: https://reviews.llvm.org/D42400
llvm-svn: 323270
I don't know if the unused classes were intended to be used and that the VEX version is really different than the legacy SSE version. Agner's tables don't show any differences. I'm just cleaning up assuming the current behavior is correct.
llvm-svn: 323263
All other intrinsic instructions put the _Int on the end. This make these instructions consistent and gets the prefix instregexs in the scheduler models to pick them up.
llvm-svn: 323261
Minor refactor to make it possible for LowerBUILD_VECTORAsVariablePermute to be used with a wider variety of shuffles op and types.
I'd have liked to add v4i32/v4f32 support as well but we don't see v4i32 index extractions at the moment (which is why I created D42308)
After this I intend to begin adding scaling support for PSHUFB (v8i16, v4i32, v2i64)) and VPERMPS (v4f64, v4i64).
Differential Revision: https://reviews.llvm.org/D42431
llvm-svn: 323260
In addition to that, make sure that there are no boolean vector types that
are associated with multiple register classes. Specifically, remove v32i1
and v64i1 from integer register classes. These types will correspond to
results of vector comparisons, and as such should belong to the vector
predicate class. Having them in scalar registers as well makes legalization
ambiguous.
llvm-svn: 323229
The grow_memory and current_memory instructions are expected to be
officially renamed to mem.grow and mem.size. Introduce new intrinsics
with the new names. These new names aren't yet official, so for now,
use them at your own risk.
Also, take this opportunity to add arguments for the currently unused
immediate field in those instructions.
llvm-svn: 323222
The existing code was already doing something very similar to subvector insertion so this allows us to remove the nearly duplicate code.
This patch is a little larger than it should be due to differences between the DQI handling between the two today.
llvm-svn: 323212
Some nodes produce multiple values so when obtaining the type of an ISD::OR we
need to make sure we ask for the correct one. Hopefully that's all of them.
llvm-svn: 323205
Summary:
For the most part its better to keep v32i1 as a mask type of a narrower width than trying to promote it to a ymm register.
I had to add some overrides to the methods that get the types for the calling convention so that we still use v32i8 for argument/return purposes.
There are still some regressions in here. I definitely saw some around shuffles. I think we probably should move vXi1 shuffle from lowering to a DAG combine where I think the extend and truncate we have to emit would be better combined.
I think we also need a DAG combine to remove trunc from (extract_vector_elt (trunc))
Overall this removes something like 13000 CHECK lines from lit tests.
Reviewers: zvi, RKSimon, delena, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D42031
llvm-svn: 323201
I'm not sure there's any way to generate these folding cases especially the movzx ones since even the register form is never emitted by codegen.
I'm just adding them to remove the difference with the autogenerated version of the folding table.
llvm-svn: 323200
As detailed in rL317463, PSHUFB (like most variable shuffle instructions) uses Op[0] for the source vector and Op[1] for the shuffle index vector, VPERMV works in reverse which is probably where the confusion comes from.
Differential Revision: https://reviews.llvm.org/D42380
llvm-svn: 323190
- Alter abs for micromips to have both AFGR64 and FGR64
variants, same as sqrt
- Remove sqrt and abs from MicroMips32r6InstrInfo.td,
use micromips FGR64 variants
- Restrict non-micromips abs/sqrt with NotInMicroMips
predicate
Differential revision: https://reviews.llvm.org/D41439
llvm-svn: 323184
Summary:
If we can match as a zero extend there's no need to flip the order to get an encoding benefit. As movzx is 3 bytes with independent source/dest registers. The shortest 'and' we could make is also 3 bytes unless we get lucky in the register allocator and its on AL/AX/EAX which have a 2 byte encoding.
This patch was more impressive before r322957 went in. It removed some of the same Ands that got deleted by that patch.
Reviewers: spatel, RKSimon
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D42313
llvm-svn: 323175
Some of the NOREX instructions are used in 32-bit mode making this printing confusing. It also doesn't provide a lot of value since you can see the h-register being used by the instruction.
llvm-svn: 323174
Add missing patterns for inserting v1i1 into a zero vector. Use insert_subvector to zero upper bits before inserting an element into a vXi1 vector. Replace kshift based isel pattern with insert_subvector based pattern now that code that caused the pattern has been fixed to emit insert_subvector.
llvm-svn: 323173
Summary:
First, we need to explain the core of the vulnerability. Note that this
is a very incomplete description, please see the Project Zero blog post
for details:
https://googleprojectzero.blogspot.com/2018/01/reading-privileged-memory-with-side.html
The basis for branch target injection is to direct speculative execution
of the processor to some "gadget" of executable code by poisoning the
prediction of indirect branches with the address of that gadget. The
gadget in turn contains an operation that provides a side channel for
reading data. Most commonly, this will look like a load of secret data
followed by a branch on the loaded value and then a load of some
predictable cache line. The attacker then uses timing of the processors
cache to determine which direction the branch took *in the speculative
execution*, and in turn what one bit of the loaded value was. Due to the
nature of these timing side channels and the branch predictor on Intel
processors, this allows an attacker to leak data only accessible to
a privileged domain (like the kernel) back into an unprivileged domain.
The goal is simple: avoid generating code which contains an indirect
branch that could have its prediction poisoned by an attacker. In many
cases, the compiler can simply use directed conditional branches and
a small search tree. LLVM already has support for lowering switches in
this way and the first step of this patch is to disable jump-table
lowering of switches and introduce a pass to rewrite explicit indirectbr
sequences into a switch over integers.
However, there is no fully general alternative to indirect calls. We
introduce a new construct we call a "retpoline" to implement indirect
calls in a non-speculatable way. It can be thought of loosely as
a trampoline for indirect calls which uses the RET instruction on x86.
Further, we arrange for a specific call->ret sequence which ensures the
processor predicts the return to go to a controlled, known location. The
retpoline then "smashes" the return address pushed onto the stack by the
call with the desired target of the original indirect call. The result
is a predicted return to the next instruction after a call (which can be
used to trap speculative execution within an infinite loop) and an
actual indirect branch to an arbitrary address.
On 64-bit x86 ABIs, this is especially easily done in the compiler by
using a guaranteed scratch register to pass the target into this device.
For 32-bit ABIs there isn't a guaranteed scratch register and so several
different retpoline variants are introduced to use a scratch register if
one is available in the calling convention and to otherwise use direct
stack push/pop sequences to pass the target address.
This "retpoline" mitigation is fully described in the following blog
post: https://support.google.com/faqs/answer/7625886
We also support a target feature that disables emission of the retpoline
thunk by the compiler to allow for custom thunks if users want them.
These are particularly useful in environments like kernels that
routinely do hot-patching on boot and want to hot-patch their thunk to
different code sequences. They can write this custom thunk and use
`-mretpoline-external-thunk` *in addition* to `-mretpoline`. In this
case, on x86-64 thu thunk names must be:
```
__llvm_external_retpoline_r11
```
or on 32-bit:
```
__llvm_external_retpoline_eax
__llvm_external_retpoline_ecx
__llvm_external_retpoline_edx
__llvm_external_retpoline_push
```
And the target of the retpoline is passed in the named register, or in
the case of the `push` suffix on the top of the stack via a `pushl`
instruction.
There is one other important source of indirect branches in x86 ELF
binaries: the PLT. These patches also include support for LLD to
generate PLT entries that perform a retpoline-style indirection.
The only other indirect branches remaining that we are aware of are from
precompiled runtimes (such as crt0.o and similar). The ones we have
found are not really attackable, and so we have not focused on them
here, but eventually these runtimes should also be replicated for
retpoline-ed configurations for completeness.
For kernels or other freestanding or fully static executables, the
compiler switch `-mretpoline` is sufficient to fully mitigate this
particular attack. For dynamic executables, you must compile *all*
libraries with `-mretpoline` and additionally link the dynamic
executable and all shared libraries with LLD and pass `-z retpolineplt`
(or use similar functionality from some other linker). We strongly
recommend also using `-z now` as non-lazy binding allows the
retpoline-mitigated PLT to be substantially smaller.
When manually apply similar transformations to `-mretpoline` to the
Linux kernel we observed very small performance hits to applications
running typical workloads, and relatively minor hits (approximately 2%)
even for extremely syscall-heavy applications. This is largely due to
the small number of indirect branches that occur in performance
sensitive paths of the kernel.
When using these patches on statically linked applications, especially
C++ applications, you should expect to see a much more dramatic
performance hit. For microbenchmarks that are switch, indirect-, or
virtual-call heavy we have seen overheads ranging from 10% to 50%.
However, real-world workloads exhibit substantially lower performance
impact. Notably, techniques such as PGO and ThinLTO dramatically reduce
the impact of hot indirect calls (by speculatively promoting them to
direct calls) and allow optimized search trees to be used to lower
switches. If you need to deploy these techniques in C++ applications, we
*strongly* recommend that you ensure all hot call targets are statically
linked (avoiding PLT indirection) and use both PGO and ThinLTO. Well
tuned servers using all of these techniques saw 5% - 10% overhead from
the use of retpoline.
We will add detailed documentation covering these components in
subsequent patches, but wanted to make the core functionality available
as soon as possible. Happy for more code review, but we'd really like to
get these patches landed and backported ASAP for obvious reasons. We're
planning to backport this to both 6.0 and 5.0 release streams and get
a 5.0 release with just this cherry picked ASAP for distros and vendors.
This patch is the work of a number of people over the past month: Eric, Reid,
Rui, and myself. I'm mailing it out as a single commit due to the time
sensitive nature of landing this and the need to backport it. Huge thanks to
everyone who helped out here, and everyone at Intel who helped out in
discussions about how to craft this. Also, credit goes to Paul Turner (at
Google, but not an LLVM contributor) for much of the underlying retpoline
design.
Reviewers: echristo, rnk, ruiu, craig.topper, DavidKreitzer
Subscribers: sanjoy, emaste, mcrosier, mgorny, mehdi_amini, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D41723
llvm-svn: 323155
- Change inserted add ( V_ADD_{I|U}32_e32 ) to _e64 version ( V_ADD_{I|U}32_e64 ) so that the add uses a vreg for the carry; this prevents inserted v_add from killing VCC; the _e64 version doesn't accept a literal in its encoding, so we need to introduce a mov instr as well to get the imm into a register.
- Change pass name to "SI Load Store Optimizer"; this removes the '/', which complicates scripts.
Differential Revision: https://reviews.llvm.org/D42124
llvm-svn: 323153
As noted in another review, this loop is confusing. This commit cleans it up
somewhat.
Differential Revision: https://reviews.llvm.org/D42312
llvm-svn: 323136
Dsp and dspr2 require MIPS revision 2, while msa requires revision 5. Adding
warnings for cases when these flags are used with earlier revision.
Patch by Milos Stojanovic.
Differential Revision: https://reviews.llvm.org/D40490
llvm-svn: 323131
The change in r322988 caused a failure in the bootstrap build bot.
The problem was that directly gluing a BR_CCMASK node to a
compare-and-swap could lead to issues if other nodes were
chained in between. There is then no way to create a topological
sort that respects both the chain sequence and the glue property.
Fixed for now by rejecting the optimization in this case. As a
future enhancement, we may be able to handle additional cases
by swapping chain links around.
llvm-svn: 323129
Improves the code generation for v4f16 FCMP instructions when FullFP16 is not supported.
Generating FCTVL(s) rather than a longer series of FCVTs.
Differential Revision: https://reviews.llvm.org/D41772
llvm-svn: 323118
Primarily, this allows us to use the aggressive extraction mechanisms in combineExtractWithShuffle earlier and make use of UNDEF elements that may be lost during lowering.
Reapplied after rL322279 was reverted at rL322335 due to PR35918, underlying issue was fixed at rL322644.
llvm-svn: 323104
Summary:
This patch adds support for parsing/printing of named or unnamed
patterns that are used in SVE's PTRUE instruction, amongst others.
The pattern can be specified as a named pattern to initialize the predicate
vector or it can be specified as an immediate in the range 0-31.
Reviewers: fhahn, rengolin, evandro, mcrosier, t.p.northover
Reviewed By: fhahn
Subscribers: aemerson, javed.absar, tschuett, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D41818
llvm-svn: 323098
1. ReachingDefsAnalysis - Allows to identify for each instruction what is the “closest” reaching def of a certain register. Used by BreakFalseDeps (for clearance calculation) and ExecutionDomainFix (for arbitrating conflicting domains).
2. ExecutionDomainFix - Changes the variant of the instructions in order to minimize domain crossings.
3. BreakFalseDeps - Breaks false dependencies.
4. LoopTraversal - Creatws a traversal order of the basic blocks that is optimal for loops (introduced in revision L293571). Both ExecutionDomainFix and ReachingDefsAnalysis use this to determine the order they will traverse the basic blocks.
This also included the following changes to ExcecutionDepsFix original logic:
1. BreakFalseDeps and ReachingDefsAnalysis logic no longer restricted by a register class.
2. ReachingDefsAnalysis tracks liveness of reg units instead of reg indices into a given reg class.
Additional changes in affected files:
1. X86 and ARM targets now inherit from ExecutionDomainFix instead of ExecutionDepsFix. BreakFalseDeps also was added to the passes they activate.
2. Comments and references to ExecutionDepsFix replaced with ExecutionDomainFix and BreakFalseDeps, as appropriate.
Additional refactoring changes will follow.
This commit is (almost) NFC.
The only functional change is that now BreakFalseDeps will break dependency for all register classes.
Since no additional instructions were added to the list of instructions that have false dependencies, there is no actual change yet.
In a future commit several instructions (and tests) will be added.
This is the first of multiple patches that fix bugzilla https://bugs.llvm.org/show_bug.cgi?id=33869
Most of the patches are intended at refactoring the existent code.
Additional relevant reviews:
https://reviews.llvm.org/D40331https://reviews.llvm.org/D40332https://reviews.llvm.org/D40333https://reviews.llvm.org/D40334
Differential Revision: https://reviews.llvm.org/D40330
Change-Id: Icaeb75e014eff96a8f721377783f9a3e6c679275
llvm-svn: 323087
Summary:
This patch adds an implementation of targetShrinkDemandedConstant that tries to keep shrinkdemandedbits from removing bits that would otherwise have been recognized as a movzx.
We still need a follow patch to stop moving ands across srl if the and could be represented as a movzx before the shift but not after. I think this should help with some of the cases that D42088 ended up removing during isel.
Reviewers: spatel, RKSimon
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D42265
llvm-svn: 323048
This change applies to places where we would turn 128/256-bit code into 512-bit in order to get a wider element type through sext/zext. Any 512-bit types that already existed in the IR/DAG will be left that way.
The width preference has no effect on codegen behavior when the target does not have AVX512 enabled. So AVX/AVX2 codegen cannot be limited via this mechanism yet.
If the preference is lower than 256 we may still use a 256 bit type to do the operation. Constraining to 128 bits makes it much more difficult to support some operations. For many of these cases we need to change element width while keeping element count constant which is easiest done by switching between 256 and 128 bit.
The preference is only obeyed when AVX512 and VLX are available. This means the preference is not obeyed for KNL, but is obeyed for SKX, Cannonlake, and Icelake. For KNL, the only way to do masked operation is on 512-bit registers so we would have to completely disable masking to obey the preference. We would also lose support for gather, scatter, ctlz, vXi64 multiplies, etc. This may change in the future, but this simplifies the initial implementation.
Differential Revision: https://reviews.llvm.org/D41895
llvm-svn: 323016
This will cause the vectorizers to do some limiting of the vector widths they create. This is not a strict limit. There are reasons I know of that the loop vectorizer will generate larger vectors for.
I've written this in such a way that the interface will only return a properly supported width(0/128/256/512) even if the attribute says something funny like 384 or 10.
This has been split from D41895 with the remainder in a follow up commit.
llvm-svn: 323015
On current machines we have load-on-condition instructions that can be
used to directly implement the SETCC semantics. If we have those, it is
always preferable to use them instead of generating the IPM sequence.
llvm-svn: 322989
In order to implement a test whether a compare-and-swap succeeded, the
SystemZ back-end currently emits a rather inefficient sequence of first
converting the CC result into an integer, and then testing that integer
against zero. This commit changes the back-end to simply directly test
the CC value set by the compare-and-swap instruction.
llvm-svn: 322988
The SystemZ back-end uses a sequence of IPM followed by arithmetic
operations to implement the SETCC primitive. This is currently done
early during SelectionDAG. This patch moves generating those sequences
to much later in SelectionDAG (during PreprocessISelDAG).
This doesn't change much in generated code by itself, but it allows
further enhancements that will be checked-in as follow-on commits.
llvm-svn: 322987
Fix a performance regression caused by r322737.
While trying to make it easier to replace compares with existing adds and
subtracts, I accidentally stopped it from doing so in some cases. This should
fix that. I'm also fixing another potential bug in that commit.
Differential Revision: https://reviews.llvm.org/D42263
llvm-svn: 322972
RuntimeLibcallSignatures previously manually initialized all the libcall
names into an array and searched it linearly for the first match to lookup
the corresponding index.
r322802 switched that to initializing a map keyed by the libcall name.
Neither of these approaches works correctly because some libcall numbers use
the same name on different platforms (e.g. the "l" suffixed functions
use f80 or f128 or ppcf128).
This change fixes that by ensuring that each name only goes into the map
once. It also adds tests.
Differential Revision: https://reviews.llvm.org/D42271
llvm-svn: 322971
Sign-extension opcodes have been split into a separate proposal from
the main threads proposal, so switch them to their own target
feature. See:
https://github.com/WebAssembly/sign-extension-ops
llvm-svn: 322966
Try to reverse the constant-shrinking that happens in SimplifyDemandedBits()
for 'and' masks when it results in a smaller sign-extended immediate.
We are also able to detect dead 'and' ops here (the mask is all ones). In
that case, we replace and return without selecting the 'and'.
Other targets might want to share some of this logic by enabling this under a
target hook, but I didn't see diffs for simple cases with PowerPC or AArch64,
so they may already have some specialized logic for this kind of thing or have
different needs.
This should solve PR35907:
https://bugs.llvm.org/show_bug.cgi?id=35907
Differential Revision: https://reviews.llvm.org/D42088
llvm-svn: 322957
This avoids playing games with pseudo pass IDs and avoids using an
unreliable MRI::isSSA() check to determine whether register allocation
has happened.
Note that this renames:
- MachineLICMID -> EarlyMachineLICM
- PostRAMachineLICMID -> MachineLICMID
to be consistent with the EarlyTailDuplicate/TailDuplicate naming.
llvm-svn: 322927
Re-commit of r322200: The testcase shouldn't hit machineverifiers
anymore with r322917 in place.
Large callframes (calls with several hundreds or thousands or
parameters) could lead to situations in which the emergency spillslot is
out of range to be addressed relative to the stack pointer.
This commit forces the use of a frame pointer in the presence of large
callframes.
This commit does several things:
- Compute max callframe size at the end of instruction selection.
- Add mirFileLoaded target callback. Use it to compute the max callframe size
after loading a .mir file when the size wasn't specified in the file.
- Let TargetFrameLowering::hasFP() return true if there exists a
callframe > 255 bytes.
- Always place the emergency spillslot close to FP if we have a frame
pointer.
- Note that `useFPForScavengingIndex()` would previously return false
when a base pointer was available leading to the emergency spillslot
getting allocated late (that's the whole effect of this callback).
Which made no sense to me so I took this case out: Even though the
emergency spillslot is technically not referenced by FP in this case
we still want it allocated early.
Differential Revision: https://reviews.llvm.org/D40876
llvm-svn: 322919
Do not create CALLSEQ_START/CALLSEQ_END when there is no callframe to
setup and the callframe size is 0.
- Fixes an invalid callframe nesting for byval arguments, which would
look like this before this patch (as in `big-byval.ll`):
...
ADJCALLSTACKDOWN 32768, 0, ... # Setup for extfunc
...
ADJCALLSTACKDOWN 0, 0, ... # setup for memcpy
...
BL &memcpy ...
ADJCALLSTACKUP 0, 0, ... # destroy for memcpy
...
BL &extfunc
ADJCALLSTACKUP 32768, 0, ... # destroy for extfunc
- Saves us two instructions in the common case of zero-sized stackframes.
- Remove an unnecessary scheduling barrier (hence the small unittest
changes).
Differential Revision: https://reviews.llvm.org/D42006
llvm-svn: 322917
This adds a new instrinsic to support the rdpid instruction. The implementation is a bit weird because the intrinsic is defined as always returning 32-bits, but the assembler support thinks the instruction produces a 64-bit register in 64-bit mode. But really it zeros the upper 32 bits. So I had to add separate patterns where 64-bit mode uses an extract_subreg.
Differential Revision: https://reviews.llvm.org/D42205
llvm-svn: 322910
Summary:
This patch implements d16 support for image load, image store and image sample intrinsics.
Reviewers:
Matt, Brian.
Differential Revision:
https://reviews.llvm.org/D3991
llvm-svn: 322903
Remove the tight coupling between llvm/CodeGenRuntimeLibcalls.def and
the table of supported singatures for wasm. This will allow adding new libcalls
without changing wasm's signature table.
Also, some cleanup:
Use ManagedStatics instead of const tables to avoid memory/binary bloat.
Use a StringMap instead of a linear search for name lookup.
Differential Revision: https://reviews.llvm.org/D35592
llvm-svn: 322802
Every known PE COFF target emits /EXPORT: linker flags into a .drective
section. The AsmPrinter should handle this.
While we're at it, use global_values() and emit each export flag with
its own .ascii directive. This should make the .s file output more
readable.
llvm-svn: 322788
Summary:
This patch adds a new target option in order to control GlobalISel.
This will allow the users to enable/disable GlobalISel prior to the
backend by calling `TargetMachine::setGlobalISel(bool Enable)`.
No test case as there is already a test to check GlobalISel
command line options.
See: CodeGen/AArch64/GlobalISel/gisel-commandline-option.ll.
Reviewers: qcolombet, aemerson, ab, dsanders
Reviewed By: qcolombet
Subscribers: rovka, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D42137
llvm-svn: 322773
Trying to link
__attribute__((weak, visibility("hidden"))) extern int foo;
int *main(void) {
return &foo;
}
on OS X fails with
ld: 32-bit RIP relative reference out of range (-4294971318 max is +/-2GB): from _main (0x100000FAB) to _foo@0x00001000 (0x00000000) in '_main' from test.o for architecture x86_64
The problem being that 0 cannot be computed as a fixed difference from
%rip. Exactly the same issue exists on ELF and we can use the same
solution.
llvm-svn: 322739
This extends my previous patches to also optimize overflow-checked multiplies during SelectionDAG.
Differential revision: https://reviews.llvm.org/D40922
llvm-svn: 322738
The ARM backend contains code that tries to optimize compares by replacing them with an existing instruction that sets the flags the same way. This allows it to replace a "cmp" with a "adds", generalizing the code that replaces "cmp" with "sub". It also heuristically disables sinking of instructions that could potentially be used to replace compares (currently only if they're next to each other).
Differential revision: https://reviews.llvm.org/D38378
llvm-svn: 322737
Most are just replaced with instrs lists, but a few regexps have been further generalized to match more instructions with a single pattern.
llvm-svn: 322734
If we are splatting pairs of 32-bit elements, we can use a 64-bit broadcast to get the job done.
We could probably could probably do this with other sizes too, for example four 16-bit elements. Or we could broadcast pairs of 16-bit elements using a 32-bit element broadcast. But I've left that as a future improvement.
I've also restricted this to AVX2 only because we can only broadcast loads under AVX.
Differential Revision: https://reviews.llvm.org/D42086
llvm-svn: 322730
We legalize selects of masks with scalar conditions using a bitcast to an integer type. But if we are in 32-bit mode we can't convert v64i1 to i64. So instead split the v64i1 to v32i1 and concat it back together. Each half will then be legalized by bitcasting to i32 which is fine.
The test case is a little indirect. If we have the v64i1 select in IR it will get legalized by legalize vector ops which has a run of type legalization after it. That type legalization run is able to fix this i64 bitcast. So in order to avoid that we need a build_vector of a splat which legalize vector ops will ignore. Legalize DAG will then turn that into a select via LowerBUILD_VECTORvXi1. And the select will get legalized. In this case there is no type legalizer run to cleanup the bitcast.
This fixes pr35972.
llvm-svn: 322724
candidates with coldcc attribute.
This patch adds support for the coldcc calling convention for Power.
This changes the set of non-volatile registers. It includes a pass to stress
test the implementation by marking all static directly called functions with
the coldcc attribute through the option -enable-coldcc-stress-test. It also
includes an option, -ppc-enable-coldcc, to add the coldcc attribute to
functions which are cold at all call sites based on BlockFrequencyInfo when
the containing function does not call any non cold functions.
Differential Revision: https://reviews.llvm.org/D38413
llvm-svn: 322721
BRCTH is capable of a long branch which needs to be recognized during branch
relaxation. This is done by checking for ExtraRelaxSize == 0.
Review: Ulrich Weigand
llvm-svn: 322688
This assert typically happens if an unstructured CFG is passed
to the pass. This can happen if the pass is run independently
without the structurizer.
llvm-svn: 322685
Summary:
Loading a vector of 4 half-precision FP sometimes results in an LD1
of 2 single-precision FP + a reversal. This results in an incorrect
byte swap due to the conversion from little endian to big endian.
In order to generate the correct byte swap, it is easier to
generate the correct LD1 of 4 half-precision FP, thus avoiding the
subsequent reversal.
Reviewers: craig.topper, jmolloy, olista01
Reviewed By: olista01
Subscribers: efriedma, samparker, SjoerdMeijer, rogfer01, aemerson, rengolin, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D41863
llvm-svn: 322663
When the compressed instruction set is enabled, the 16-bit c.nop can be
generated if necessary.
Differential Revision: https://reviews.llvm.org/D41221
Patch by Shiva Chen.
llvm-svn: 322658
Mark G_FPEXT and G_FPTRUNC as legal or libcall, depending on hardware
support, but only for conversions between float and double.
Also add the necessary boilerplate so that the LegalizerHelper can
introduce the required libcalls. This also works only for float and
double, but isn't too difficult to extend when the need arises.
llvm-svn: 322651
The match* functions have the annoying behavior of modifying its inputs.
Save and restore the inputs, just in case the early out for AVX512 is
hit. This is still not great and its only a matter of time this kind of
bug happens again, but I couldn't come up with a better pattern without
rewriting significant chunks of this code. Fixes PR35977.
llvm-svn: 322644
When "xer" is specified as clobbered register in inline assembler, clang can accept it, but llvm simply ignore it when lowered to machine instructions. It may cause problems later in scheduler.
This patch adds a new register XER aliased to CARRY, and adds it to register class CARRYRC. Now PPCTargetLowering::getRegForInlineAsmConstraint can return correct register number for inline asm constraint "{xer}", and scheduler behave correctly.
Differential Revision: https://reviews.llvm.org/D41967
llvm-svn: 322591
Summary:
This patch adds CustomRenderer which renders the matched
operands to the specified instruction.
Targets can enable the matching of SDNodeXForm by adding
a definition that inherits from GICustomOperandRenderer and
GISDNodeXFormEquiv as follows.
def gi_imm8 : GICustomOperandRenderer<"renderImm8”>,
GISDNodeXFormEquiv<imm8_xform>;
Custom renderer functions should be of the form:
void render(MachineInstrBuilder &MIB, const MachineInstr &I);
Reviewers: dsanders, ab, rovka
Reviewed By: dsanders
Subscribers: kristof.beyls, javed.absar, llvm-commits, mgrang, qcolombet
Differential Revision: https://reviews.llvm.org/D42012
llvm-svn: 322582
These pseudos are not supposed to be visible to user.
This patch reduced the auto-generated instruction matcher. For example,
the following words are removed from keyword list of LLVM BPF assembler.
- MCK__35_, // '#'
- MCK__COLON_, // ':'
- MCK__63_, // '?'
- MCK_ADJCALLSTACKDOWN, // 'ADJCALLSTACKDOWN'
- MCK_ADJCALLSTACKUP, // 'ADJCALLSTACKUP'
- MCK_PSEUDO, // 'PSEUDO'
- MCK_Select, // 'Select'
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
llvm-svn: 322535
As commented on the existing code:
// The Reg operand should be a virtual register, which is defined
// outside the current basic block. DAG combiner has done a pretty
// good job in removing truncating inside a single basic block.
However, when the Reg operand comes from bpf_load_[byte | half | word]
intrinsics, the generic optimizer doesn't understand their results are
zero extended, so these single basic block elimination opportunities were
missed.
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
llvm-svn: 322534
Prior to this we had a separate instruction and register class that excluded eax to prevent matching the instruction that would encode with 0x90.
This patch changes this to just use an InstAlias to force xchgl %eax, %eax to use XCHG32rr instruction in 64-bit mode. This gets rid of the separate instruction and register class.
llvm-svn: 322532
As mentioned on PR35869, (and came up recently on D41517) we don't create a MMX zero register via the PXOR but instead perform a spill to stack from a XMM zero register.
This patch adds support for direct MMX zero vector creation and should make it easier to add better constant vector creation in the future as well.
Differential Revision: https://reviews.llvm.org/D41908
llvm-svn: 322525
Add support for custom execution domain fixing and implement support for BLENDPD/BLENDPS/PBLENDD/PBLENDW.
Differential Revision: https://reviews.llvm.org/D42042
llvm-svn: 322524
In some cases we do not copy implicit defs from pseudo to real
VOP instructions. It has no visible impact at the moment thus no
tests are affected or added.
Differential Revision: https://reviews.llvm.org/D41783
llvm-svn: 322496
Since a load and test instruction treat its operands as signed, it can only
replace a logical compare for EQ/NE uses.
Review: Ulrich Weigand
https://bugs.llvm.org/show_bug.cgi?id=35662
llvm-svn: 322488
Summary:
For example, VSQRTSDZr and VSQRTSSZr were missing the predicate.
Also fix braces indentation and braces for consistency.
Reviewers: craig.topper, RKSimon
Suscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41983
llvm-svn: 322478
We have to take special care to avoid the cases where the result of the truncate would be padded with zero elements.
Ideally we'd just use ISD::TRUNCATE for these cases instead.
llvm-svn: 322454
Extend vXi1 conditions of vXi8/vXi16 selects even before type legalization gets a chance to split wide vectors. Previously we would only extend 128 and 256 bit vectors. But if we start with a 512 bit vector or wider that needs to be split we wouldn't extend until after the split had taken place. By extending early we improve the results of type legalization.
Don't widen condition of 128/256 bit vXi16/vXi8 selects when we have BWI but not VLX. We can still use a mask register by widening the select to 512-bits instead. This is similar to what we do for compares already.
llvm-svn: 322450
In addition to the existing match as part of a loop-reduction, add a
straightforward pattern match for DAG-contained patterns.
Reviewers: RKSimon, craig.topper
Subscribers: llvm-commits
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D41811
llvm-svn: 322446
This avoids having the result type stick around until lowering where we have to extend the setcc and insert a truncate. If we get the types converted early we can do more to optimize it.
llvm-svn: 322432
*Mostly* NFC. Still updating the test though just for completeness.
This moves the hasAddressTaken check to MachineOutliner.cpp and replaces it
with a per-basic block test rather than a per-function test. The old test was
too conservative and was preventing functions in C programs from being
outlined even though they were safe to outline.
This was mostly a problem in C sources.
llvm-svn: 322425
Summary:
A recent change
321556: AMDGPU: Remove mayLoad/hasSideEffects from MIMG stores
can allow the machine instruction scheduler to move an image store past
an image load using the same descriptor.
V2: Fixed by marking image ops as mayAlias and isAliased. This may be
overly conservative, and we may need to revisit.
V3: Reverted test change done on 321556.
Reviewers: arsenm, nhaehnle, dstuttard
Subscribers: llvm-commits, t-tye, yaxunl, wdng, kzhuravl
Differential Revision: https://reviews.llvm.org/D41969
llvm-svn: 322419
Fix typos in the default scheduling resources when using the post indexed
addressing modes.
Differential revision: https://reviews.llvm.org/D40511
llvm-svn: 322392
We can probably take this a step further since the only
user of the isUsed flag is AsmParser it should probably
be doing this explicitly. For now this is a step in the
right direction though.
Differential Revision: https://reviews.llvm.org/D41971
llvm-svn: 322386
Part of the fix for https://bugs.llvm.org/show_bug.cgi?id=35812.
This patch ensures that the compare operand for the atomic compare and swap
is properly zero-extended to 32 bits if applicable.
A follow-up commit will fix the extension for the SETCC node generated when
expanding an ATOMIC_CMP_SWAP_WITH_SUCCESS. That will complete the bug fix.
Differential Revision: https://reviews.llvm.org/D41856
llvm-svn: 322372
For hard float with VFP4, it is legal. Otherwise, we use libcalls.
This needs a bit of support in the LegalizerHelper for soft float
because we didn't handle G_FMA libcalls yet. The support is trivial, as
the only difference between G_FMA and other libcalls that we already
handle is that it has 3 input operands rather than just 2.
llvm-svn: 322366
This patch teaches the Arm back-end to generate the SMMULR, SMMLAR and SMMLSR
instructions from equivalent IR patterns.
Differential Revision: https://reviews.llvm.org/D41775
llvm-svn: 322361
Without a register with a size being mentioned the instruction is ambiguous in at&t syntax. With Intel syntax the memory operation caries a size that can be used to disambiguate.
llvm-svn: 322356
While the suffix isn't required to disambiguate the instructions, it is required in order to parse the instructions when the suffix is specified in order to match the GNU assembler.
llvm-svn: 322354
Summary:
Very basic stack instrumentation using tagged pointers.
Tag for N'th alloca in a function is built as XOR of:
* base tag for the function, which is just some bits of SP (poor
man's random)
* small constant which is a function of N.
Allocas are aligned to 16 bytes. On every ReturnInst allocas are
re-tagged to catch use-after-return.
This implementation has a bunch of issues that will be taken care of
later:
1. lifetime intrinsics referring to tagged pointers are not
recognized in SDAG. This effectively disables stack coloring.
2. Generated code is quite inefficient. There is one extra
instruction at each memory access that adds the base tag to the
untagged alloca address. It would be better to keep tagged SP in a
callee-saved register and address allocas as an offset of that XOR
retag, but that needs better coordination between hwasan
instrumentation pass and prologue/epilogue insertion.
3. Lifetime instrinsics are ignored and use-after-scope is not
implemented. This would be harder to do than in ASan, because we
need to use a differently tagged pointer depending on which
lifetime.start / lifetime.end the current instruction is dominated
/ post-dominated.
Reviewers: kcc, alekseyshl
Subscribers: srhines, kubamracek, javed.absar, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D41602
llvm-svn: 322324
The PeepholeOptimizer would fail for vregs without a definition. If this
was caused by an undef operand abort to keep the code simple (so we
don't need to add logic everywhere to replicate the undef flag).
Differential Revision: https://reviews.llvm.org/D40763
llvm-svn: 322319
While updating clang tests for having clang set dso_local I noticed
that:
- There are *a lot* of tests to update.
- Many of the updates are redundant.
They are redundant because a GV is "obviously dso_local". This patch
starts formalizing that a bit by requiring that internal and private
GVs be dso_local too. Since they all are, we don't have to print
dso_local to the textual representation, making it a bit more compact
and easier to read.
llvm-svn: 322317
Summary: This is a preparatory step for D41811: refactoring code for breaking vector operands of binary operation to legal-types.
Reviewers: RKSimon, craig.topper, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41925
llvm-svn: 322296
In practice, this patch has no effect on scheduling.
There is no test case as there already exists a comprehensive test case for
LSE Atomics.
Patch by Stefan Teleman
Differential Revision: https://reviews.llvm.org/D40694
llvm-svn: 322291
Primarily, this allows us to use the aggressive extraction mechanisms in combineExtractWithShuffle earlier and make use of UNDEF elements that may be lost during lowering.
llvm-svn: 322279
Summary:
As RKSimon suggested in pr35820, in the case that Src is smaller in
bit-size than Indices, need to widen Src to avoid type mismatch.
Fixes pr35820
Reviewers: RKSimon, craig.topper
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41865
llvm-svn: 322272
Although the register scavenger can often find a spare register, an emergency
spill slot is needed to guarantee success. Reserve this slot in cases where
the function is known to have a large stack (meaning the scavenger may be
needed when forming stack addresses).
llvm-svn: 322269
If the index is v2i64 we can use the scatter instruction that has v4i32/v4f32 data register, v2i64 index, and v2i1 mask. Similar was already done for gather.
Implement custom widening for v2i32 data to remove the code that reverses type legalization during lowering.
llvm-svn: 322254
Revert for now as the testcase is hitting a pre-existing verifier error
that manifest as a failure when expensive checks are enabled (or
-verify-machineinstrs) is used.
This reverts commit r322200.
llvm-svn: 322231
After D41349, we can no get a MCSubtargetInfo into the MCAsmBackend constructor. This allows us to get NOPL from a subtarget feature rather than a CPU name blacklist.
Differential Revision: https://reviews.llvm.org/D41721
llvm-svn: 322227
Branch relaxation is needed to support branch displacements that overflow the
instruction's immediate field.
Differential Revision: https://reviews.llvm.org/D40830
llvm-svn: 322224
This is a prerequisite for the branch relaxation pass, and allows a number of
optimisation passes (e.g. BranchFolding and MachineBlockPlacement) to work.
Differential Revision: https://reviews.llvm.org/D40808
llvm-svn: 322222
Includes support for expanding va_copy. Also adds support for using 'aligned'
registers when necessary for vararg calls, and ensure the frame pointer always
points to the bottom of the vararg spill region. This is necessary to ensure
that the saved return address and stack pointer are always available at fixed
known offsets of the frame pointer.
Differential Revision: https://reviews.llvm.org/D40805
llvm-svn: 322215
Currently we infer the scale at isel time by analyzing whether the base is a constant 0 or not. If it is we assume scale is 1, else we take it from the element size of the pass thru or stored value. This seems a little weird and I think it makes more sense to make it explicit in the DAG rather than doing tricky things in the backend.
Most of this patch is just making sure we copy the scale around everywhere.
Differential Revision: https://reviews.llvm.org/D40055
llvm-svn: 322210
ADRP instructions weren't being outlined because they're PC-relative and thus
fail the LR checks. This patch adds a special case for ADRPs to
getOutliningType to make sure that ADRPs can be outlined and updates the MIR
test.
llvm-svn: 322207
Large callframes (calls with several hundreds or thousands or
parameters) could lead to situations in which the emergency spillslot is
out of range to be addressed relative to the stack pointer.
This commit forces the use of a frame pointer in the presence of large
callframes.
This commit does several things:
- Compute max callframe size at the end of instruction selection.
- Add mirFileLoaded target callback. Use it to compute the max callframe size
after loading a .mir file when the size wasn't specified in the file.
- Let TargetFrameLowering::hasFP() return true if there exists a
callframe > 255 bytes.
- Always place the emergency spillslot close to FP if we have a frame
pointer.
- Note that `useFPForScavengingIndex()` would previously return false
when a base pointer was available leading to the emergency spillslot
getting allocated late (that's the whole effect of this callback).
Which made no sense to me so I took this case out: Even though the
emergency spillslot is technically not referenced by FP in this case
we still want it allocated early.
Differential Revision: https://reviews.llvm.org/D40876
llvm-svn: 322200
For hard float, it is legal.
For soft float, we need to lower to 0 - x first, and then we can use the
libcall for G_FSUB. This is undoing some of the canonicalization
performed by the IRTranslator (which introduces G_FNEG when it sees a
0 - x). Ideally, that canonicalization would be performed by a
pre-legalizer pass that would allow targets to opt out of this behaviour
rather than dance around it in the legalizer.
llvm-svn: 322168
Summary:
This extends TableGen's AsmMatcherEmitter with code that generates
a table with tied-operand constraints. The constraints are checked
when parsing the instruction. If an operand is not equal to its tied operand,
the assembler will give an error.
Patch [2/3] in a series to add operand constraint checks for SVE's predicated ADD/SUB.
Reviewers: olista01, rengolin, mcrosier, fhahn, craig.topper, evandro, echristo
Reviewed By: fhahn
Subscribers: javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D41446
llvm-svn: 322166
Since a load and test instruction treat its operands as signed, it can only
replace a logical compare for EQ/NE uses.
Review: Ulrich Weigand
https://bugs.llvm.org/show_bug.cgi?id=35662
llvm-svn: 322161
This patch makes the following changes to the schedule of instructions in the
prologue and epilogue.
The stack pointer update is moved down in the prologue so that the callee saves
do not have to wait for the update to happen.
Saving the lr is moved down in the prologue to hide the latency of the mflr.
The stack pointer is moved up in the epilogue so that restoring of the lr can
happen sooner.
The mtlr is moved up in the epilogue so that it is away form the blr at the end
of the epilogue. The latency of the mtlr can now be hidden by the loads of the
callee saved registers.
This commit is almost identical to this one: r322036 except that two warnings
that broke build bots have been fixed.
The revision number is D41737 as before.
llvm-svn: 322124
Summary:
I had a case where multiple nested uniform ifs resulted in code that did
v_cmp comparisons, combining the results with s_and_b64, s_or_b64 and
s_xor_b64 and using the resulting mask in s_cbranch_vccnz, without first
ensuring that bits for inactive lanes were clear.
There was already code for inserting an "s_and_b64 vcc, exec, vcc" to
clear bits for inactive lanes in the case that the branch is instruction
selected as s_cbranch_scc1 and is then changed to s_cbranch_vccnz in
SIFixSGPRCopies. I have added the same code into SILowerControlFlow for
the case that the branch is instruction selected as s_cbranch_vccnz.
This de-optimizes the code in some cases where the s_and is not needed,
because vcc is the result of a v_cmp, or multiple v_cmp instructions
combined by s_and/s_or. We should add a pass to re-optimize those cases.
Reviewers: arsenm, kzhuravl
Subscribers: wdng, yaxunl, t-tye, llvm-commits, dstuttard, timcorringham, nhaehnle
Differential Revision: https://reviews.llvm.org/D41292
llvm-svn: 322119
Summary:
If the vector type is transformed to non-vector single type, the compile
may crash trying to get vector information about non-vector type.
Reviewers: RKSimon, spatel, mkuper, hfinkel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41862
llvm-svn: 322106
Normally target independent DAG combine would do this combine based on getSetCCResultType, but with VLX getSetCCResultType returns a vXi1 type preventing the DAG combining from kicking in.
But doing this combine can allow us to remove the explicit sign extend that would otherwise be emitted.
This patch adds a target specific DAG combine to combine the sext+setcc when the result type is the same size as the input to the setcc. I've restricted this to FP compares and things that can be represented with PCMPEQ and PCMPGT since we don't have full integer compare support on the older ISAs.
Differential Revision: https://reviews.llvm.org/D41850
llvm-svn: 322101
In -debug output we print "pred:" whenever a MachineOperand is a
predicate operand in the instruction descriptor, and "opt:" whenever a
MachineOperand is an optional def in the instruction descriptor.
Differential Revision: https://reviews.llvm.org/D41870
llvm-svn: 322096
Fixed issue that was found on sanitizer-x86_64-linux-fast.
I changed the result type of 'Parser.getTok().getString().lower()'
in AArch64AsmParser::tryParseSVEPredicateVector() from 'StringRef' to
'auto', since StringRef::lower() returns a std::string.
llvm-svn: 322092
Summary:
Parsing of the '/m' (merging) or '/z' (zeroing) suffix of a predicate operand.
Patch [2/3] in a series to add predicated ADD/SUB instructions for SVE.
Reviewers: rengolin, mcrosier, evandro, fhahn, echristo, MatzeB, t.p.northover
Reviewed By: fhahn
Subscribers: t.p.northover, MatzeB, aemerson, javed.absar, tschuett, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D41442
llvm-svn: 322070
Summary:
This commit enables some of the arithmetic instructions for Nios2 ISA (for both
R1 and R2 revisions), implements facilities required to emit those instructions
and provides LIT tests for added instructions.
Reviewed By: hfinkel
Differential Revision: https://reviews.llvm.org/D41236
Author: belickim <mateusz.belicki@intel.com>
llvm-svn: 322069
CET (Control-Flow Enforcement Technology) introduces a new mechanism called IBT (Indirect Branch Tracking).
According to IBT, each Indirect branch should land on dedicated ENDBR instruction (End Branch).
The new pass adds ENDBR instructions for every indirect jmp/call (including jumps using jump tables / switches).
For more information, please see the following:
https://software.intel.com/sites/default/files/managed/4d/2a/control-flow-enforcement-technology-preview.pdf
Differential Revision: https://reviews.llvm.org/D40482
Change-Id: Icb754489faf483a95248f96982a4e8b1009eb709
llvm-svn: 322062
The code that checks the immediate wasn't masking to the lower 3-bits like the code in X86InstrInfo.cpp that's used by the peephole pass does.
llvm-svn: 322060
The CTRLoop pass performs checks on the argument of certain libcalls/intrinsics,
and assumes the arguments must be of a simple type. This isn't always the case
though. For example if we unroll and vectorize a loop we may end up with vectors
larger then the largest legal type, along with intrinsics that operate on those
wider types. This happened in the ffmpeg build, where we unrolled a loop and
ended up with a sqrt intrinsic that operated on V16f64, triggering an assertion.
Differential Revision: https://reviews.llvm.org/D41758
llvm-svn: 322055
I had to drop fast-isel-abort from a test because we can't fast isel some of the mask stuff. When we used intrinsics we implicitly fell back to SelectionDAG for the intrinsic call without triggering the abort error. But with native IR that doesn't happen the same way.
llvm-svn: 322050
The pattern was this
def : Pat<(i32 (zext (i8 (bitconvert (v8i1 VK8:$src))))),
(MOVZX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS VK8:$src, GR32)), sub_8bit))>, Requires<[NoDQI]>;
but if you just let (i32 (zext X)) match byte itself you'll get MOVZX32rr8. And if you let (i8 (bitconvert (v8i1 VK8:$src))) match by itself you'll get (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS VK8:$src, GR32)), sub_8bit).
So we can just let isel do the two patterns naturally.
llvm-svn: 322049
This commit does two things. Firstly, it adds a collection of flags which can
be passed along to the target to encode information about the MBB that an
instruction lives in to the outliner.
Second, it adds some of those flags to the AArch64 outliner in order to add
more stack instructions to the list of legal instructions that are handled
by the outliner. The two flags added check if
- There are calls in the MachineBasicBlock containing the instruction
- The link register is available in the entire block
If the link register is available and there are no calls, then a stack
instruction can always be outlined without fixups, regardless of what it is,
since in this case, the outliner will never modify the stack to create a
call or outlined frame.
The motivation for doing this was checking which instructions are most often
missed by the outliner. Instructions like, say
%sp<def> = ADDXri %sp, 32, 0; flags: FrameDestroy
are very common, but cannot be outlined in the case that the outliner might
modify the stack. This commit allows us to outline instructions like this.
llvm-svn: 322048
This patch makes the following changes to the schedule of instructions in the
prologue and epilogue.
The stack pointer update is moved down in the prologue so that the callee saves
do not have to wait for the update to happen.
Saving the lr is moved down in the prologue to hide the latency of the mflr.
The stack pointer is moved up in the epilogue so that restoring of the lr can
happen sooner.
The mtlr is moved up in the epilogue so that it is away form the blr at the end
of the epilogue. The latency of the mtlr can now be hidden by the loads of the
callee saved registers.
Differential Revision: https://reviews.llvm.org/D41737
llvm-svn: 322036
This patch allows `r7` to be used, regardless of its use as a frame pointer, as
a temporary register when popping `lr`, and also falls back to using a high
temporary register if, for some reason, we weren't able to find a suitable low
one.
Differential revision: https://reviews.llvm.org/D40961
Fixes https://bugs.llvm.org/show_bug.cgi?id=35481
llvm-svn: 321989
(Target)FrameLowering::determineCalleeSaves can be called multiple
times. I don't think it should have side-effects as creating stack
objects and setting global MachineFunctionInfo state as it is doing
today (in other back-ends as well).
This moves the creation of stack objects from determineCalleeSaves to
assignCalleeSavedSpillSlots.
Differential Revision: https://reviews.llvm.org/D41703
llvm-svn: 321987
I had removed the qualifiers around the autogenerated folding table so I could compare with the manual table, but didn't intend to commit the change.
llvm-svn: 321971
Summary:
There are few oddities that occur due to v1i1, v8i1, v16i1 being legal without v2i1 and v4i1 being legal when we don't have VLX. Particularly during legalization of v2i32/v4i32/v2i64/v4i64 masked gather/scatter/load/store. We end up promoting the mask argument to these during type legalization and then have to widen the promoted type to v8iX/v16iX and truncate it to get the element size back down to v8i1/v16i1 to use a 512-bit operation. Since need to fill the upper bits of the mask we have to fill with 0s at the promoted type.
It would be better if we could just have the v2i1/v4i1 types as legal so they don't undergo any promotion. Then we can just widen with 0s directly in a k register. There are no real v4i1/v2i1 instructions anyway. Everything is done on a larger register anyway.
This also fixes an issue that we couldn't implement a masked vextractf32x4 from zmm to xmm properly.
We now have to support widening more compares to 512-bit to get a mask result out so new tablegen patterns got added.
I had to hack the legalizer for widening the operand of a setcc a bit so it didn't try create a setcc returning v4i32, extract from it, then try to promote it using a sign extend to v2i1. Now we create the setcc with v4i1 if the original setcc's result type is v2i1. Then extract that and don't sign extend it at all.
There's definitely room for improvement with some follow up patches.
Reviewers: RKSimon, zvi, guyblank
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D41560
llvm-svn: 321967
Summary:
I believe legalization is really expecting that ReplaceNodeResults will return something with the same type as the thing that's being legalized. Ultimately, it uses the output to replace the uses in the DAG so the type should match to make that work.
There are two relevant cases here. When crbits are enabled, then i1 is a legal type and getSetCCResultType should return i1. In this case, the truncate will be between i1 and i1 and should be removed (SelectionDAG::getNode does this). Otherwise, getSetCCResultType will be i32 and the legalizer will promote the truncate to be i32 -> i32 which will be similarly removed.
With this fixed we can remove some code from PromoteIntRes_SETCC that seemed to only exist to deal with the intrinsic being replaced with a larger type without changing the other operand. With the truncate being used for connectivity this doesn't happen anymore.
Reviewers: hfinkel
Reviewed By: hfinkel
Subscribers: nemanjai, llvm-commits, kbarton
Differential Revision: https://reviews.llvm.org/D41654
llvm-svn: 321959
The instructions that load 64-bits or an xmm register should be TB_NO_REVERSE to avoid the load being widened during unfold. The instructions that load 128-bits need to ensure 128-bit alignment.
llvm-svn: 321956
The memory form of the xmm->xmm version only writes 64-bits. If we use it in the folding tables and its get used for a stack spill, only half the slot will be written. Then a reload may read all 128-bits which will pull in garbage. But without the spill the upper bits of the register would have been zero. By not folding we would preserve the zeros.
llvm-svn: 321950
We don't do fine grained feature control like this on features prior to AVX512.
We do still have checks in place in the assembly parser itself that prevents %zmm references or %xmm16-31 from being parsed without at least -mattr=avx512f. Same for rounding control and mask operands. That will prevent the table matcher from matching for any instructions that need those features and that's probably good enough.
llvm-svn: 321947
This is the last step needed to fix PR33325:
https://bugs.llvm.org/show_bug.cgi?id=33325
We're trading branch and compares for loads and logic ops.
This makes the code smaller and hopefully faster in most cases.
The 24-byte test shows an interesting construct: we load the trailing scalar
elements into vector registers and generate the same pcmpeq+movmsk code that
we expected for a pair of full vector elements (see the 32- and 64-byte tests).
Differential Revision: https://reviews.llvm.org/D41714
llvm-svn: 321934
Matthias Braun