- using qualified pointer addrspace in intrinsics class to avoid .f32 mangling
- changed too common atomic mangling to ds
- added missing intrinsics to AMDGPUTTIImpl::getTgtMemIntrinsic
Reviewed by: b-sumner
Differential Revision: https://reviews.llvm.org/D42383
llvm-svn: 323516
load instruction
The function `Thumb1InstrInfo::loadRegFromStackSlot` accepts only the `tGPR`
register class. The function serves to emit a `tLDRspi` instruction and
certainly any subset of the `tGPR` register class is a valid destination of the
load.
Differential revision: https://reviews.llvm.org/D42535
llvm-svn: 323514
This is the groundwork for Armv8.2-A FP16 code generation .
Clang passes and returns _Float16 values as floats, together with the required
bitconverts and truncs etc. to implement correct AAPCS behaviour, see D42318.
We will implement half-precision argument passing/returning lowering in the ARM
backend soon, but for now this means that this:
_Float16 sub(_Float16 a, _Float16 b) {
return a + b;
}
gets lowered to this:
define float @sub(float %a.coerce, float %b.coerce) {
entry:
%0 = bitcast float %a.coerce to i32
%tmp.0.extract.trunc = trunc i32 %0 to i16
%1 = bitcast i16 %tmp.0.extract.trunc to half
<SNIP>
%add = fadd half %1, %3
<SNIP>
}
When FullFP16 is *not* supported, we don't make f16 a legal type, and we get
legalization for "free", i.e. nothing changes and everything works as before.
And also f16 argument passing/returning is handled.
When FullFP16 is supported, we do make f16 a legal type, and have 2 places that
we need to patch up: f16 argument passing and returning, which involves minor
tweaks to avoid unnecessary code generation for some bitcasts.
As a "demonstrator" that this works for the different FP16, FullFP16, softfp
modes, etc., I've added match rules to the VSUB instruction description showing
that we can codegen this instruction from IR, but more importantly, also to
some conversion instructions. These conversions were causing issue before in
the FP16 and FullFP16 cases.
I've also added match rules to the VLDRH and VSTRH desriptions, so that we can
actually compile the entire half-precision sub code example above. This showed
that these loads and stores had the wrong addressing mode specified: AddrMode5
instead of AddrMode5FP16, which turned out not be implemented at all, so that
has also been added.
This is the minimal patch that shows all the different moving parts. In patch
2/3 I will add some efficient lowering of bitcasts, and in 2/3 I will add the
remaining Armv8.2-A FP16 instruction descriptions.
Thanks to Sam Parker and Oliver Stannard for their help and reviews!
Differential Revision: https://reviews.llvm.org/D38315
llvm-svn: 323512
Type legalization would prevent any i64 operands to the build_vector from existing before we get here. The coverage bots show this code as uncovered.
llvm-svn: 323506
The original autoupgrade for kunpck intrinsics used a bitcasted scalar shift, or, and. This combine would turn this into a concat_vectors. Now the kunpck intrinsics are autoupgraded to a vector shuffle that will become a concat_vectors.
llvm-svn: 323504
This listed all legal 128-bit integer types individually, but since we already know we have a legal type and its integer, we can just check is128BitVector.
llvm-svn: 323502
When pass creates a MOV instruction for
lea (%base,%index,1), %dst => mov %base,%dst; add %index,%dst
modification it should clean the killed flag for base
if base is equal to index.
Otherwise verifier complains about usage of killed register in add instruction.
Reviewers: lsaba, zvi, zansari, aaboud
Reviewed By: lsaba
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D42522
llvm-svn: 323497
This patch enables aggressive FMA by default on T99, and provides a -mllvm
option to enable the same on other AArch64 micro-arch's (-mllvm
-aarch64-enable-aggressive-fma).
Test case demonstrating the effects on T99 is included.
Patch by: steleman (Stefan Teleman)
Differential Revision: https://reviews.llvm.org/D40696
llvm-svn: 323474
The asm parser puts the lock prefix in the MCInst flags so we need to check that in addition to TSFlags. This matches what the ATT printer does.
llvm-svn: 323469
The regular expressions and the imul names caused some instructions to be matched by multiple regexs creating unpredictable results.
This changes them all to use explicit instrs instead.
While doing this I also found that some instructions in Skylake were missing load latency so I fixed that too.
llvm-svn: 323406
The IMUL instruction names mixed with the prefix matching of the instregex lead to some strange matches. The worst being that several memory instructions are using the register form latency.
I don't know what the right answer is, so I've left TODOs and will try to work with the AMD folks to get this cleaned up.
llvm-svn: 323405
MMX instrutions all start with MMX_ so the 64 isn't needed for disambigutation.
SSE/AVX1 instructions are assumed 128-bit so we don't need to say 128.
AVX2 instructions should use a Y to indicate 256-bits.
llvm-svn: 323402
These were treated as optional suffixes, but the regular expressions are already prefix matches so this is unnecessary. It breaks the binary search optimization in tablegen due to the top level question mark.
llvm-svn: 323401
The code in EmitFunctionEntryCode needs to know the maximum stack
alignment, but it runs very early in the selection process (before
lowering). The final stack alignment may change during lowering, so
the code needs to be moved to where the alignment is known.
llvm-svn: 323374
The tablegen imported patterns for sext(load(a)) don't check for single uses
of the load or delete the original after matching. As a result two loads are
left in the generated code. This particular issue will be fixed by adding
support for a G_SEXTLOAD opcode in future.
There are however other potential issues around this that wouldn't be fixed by
a G_SEXTLOAD, so until we have a proper solution we don't try to handle volatile
loads at all in the AArch64 selector.
Fixes/works around PR36018.
llvm-svn: 323371
As discussed in D41484, PMADDWD for 'zero extended' vXi32 is nearly always a better option than PMULLD:
On SNB it will result in code that isn't any faster, but not any slower so we may as well keep it.
On KNL it only has half the throughput, so I've disabled it on there - ideally there'd be a better way than this.
Differential Revision: https://reviews.llvm.org/D42258
llvm-svn: 323367
Summary:
Move reserveRegisterTuples into AMDGPURegisterInfo and use it in
R600RegisterInfo::getReservedRegs and
R600InstrInfo::reserveIndirectRegisters to ensure that all super
registers of reserved registers are also marked as reserved.
Before this change, under certain circumstances, the registers %t1_x and
%t1_xyzw would be marked as reserved, but %t1_xy and %t1_xyz would not
be, leading to the register allocator sometimes assigning a register to
%t1_xy, which is invalid since %t1_x is reserved.
Reviewers: arsenm, tstellar, MatzeB, qcolombet
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, mcrosier, llvm-commits
Differential Revision: https://reviews.llvm.org/D42448
llvm-svn: 323356
Summary: For long shifts, the inlined version takes about 20 instructions on Thumb1. To avoid the code bloat, expand to __aeabi_ calls if target is Thumb1.
Reviewers: samparker
Reviewed By: samparker
Subscribers: samparker, aemerson, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D42401
llvm-svn: 323354
The regexs are treated as a prefix match already so the checking for optional text at the end provides no value. Instead it prevents the binary search optimization in tablegen from kicking in due to the top level question mark.
llvm-svn: 323351
Summary:
Loads/stores of some NEON vector types are promoted to other vector
types with different lane sizes but same vector size. This is not a
problem in little-endian but, when in big-endian, it requires
additional byte reversals required to preserve the lane ordering
while keeping the right endianness of the data inside each lane.
For example:
%1 = load <4 x half>, <4 x half>* %p
results in the following assembly:
ld1 { v0.2s }, [x1]
rev32 v0.4h, v0.4h
This patch changes the promotion of these loads/stores so that the
actual vector load/store (LD1/ST1) takes care of the endianness
correctly and there is no need for further byte reversals. The
previous code now results in the following assembly:
ld1 { v0.4h }, [x1]
Reviewers: olista01, SjoerdMeijer, efriedma
Reviewed By: efriedma
Subscribers: aemerson, rengolin, javed.absar, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D42235
llvm-svn: 323325
This matches what MSVC does for alloca() function calls on ARM.
Even if MSVC doesn't support VLAs at the language level, it does
support the alloca function.
On the clang level, both the _alloca() (when emulating MSVC, which is
what the alloca() function expands to) and __builtin_alloca() builtin
functions, and VLAs, map to the same LLVM IR "alloca" function - so
within LLVM they're not distinguishable from each other.
Differential Revision: https://reviews.llvm.org/D42292
llvm-svn: 323308
I think these instructions used to be named differently and the regular expression reflected that. I guess we must have correct itinerary information that made this not matter for the scheduler test?
llvm-svn: 323305
There are a couple tricky things with this patch.
I had to add an override of isVectorLoadExtDesirable to stop DAG combine from combining sign_extend with loads after legalization since we legalize sextload using a load+sign_extend. Overriding this hook actually prevents a lot sextloads from being created in the first place.
I also had to add isel patterns because DAG combine blindly combines sign_extend+truncate to a smaller sign_extend which defeats what legalization was trying to do.
Differential Revision: https://reviews.llvm.org/D42407
llvm-svn: 323301
This is already a simplification, and should help with avoiding a plt
reference when calling an intrinsic with -fno-plt.
With this change we return false for null GVs, so the caller only
needs to check the new metadata to decide if it should use foo@plt or
*foo@got.
llvm-svn: 323297
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
Dmitry Preobrazhensky