Function MipsAsmParser::expandMemInst() did not properly handle
instruction `sc` with a symbol as an argument because first argument
would be counted twice. We add additional checks and handle this case
separately.
Patch by Mirko Brkusanin.
Differential Revision: https://reviews.llvm.org/D64252
llvm-svn: 368160
Currently we check whether LR is stored/loaded to/from inbetween the
loop decrement and loop end pseudo instructions. There's two problems
here:
- It relies on all load/store instructions being labelled as such in
tablegen.
- Actually any use of loop decrement is troublesome because the value
doesn't exist!
So we need to check for any read/write of LR that occurs between the
two instructions and revert if we find anything.
Differential Revision: https://reviews.llvm.org/D65792
llvm-svn: 368130
We have aliases that disambiguate memory forms of bt/btc/btr/bts
without suffixes to the 32-bit form. These aliases should have
been updated when the instructions were updated in r356413.
llvm-svn: 368127
The upper 4 bits of the immediate byte are used to encode a
register. We need to limit the explicit immediate to fit in the
remaining 4 bits.
Fixes PR42899.
llvm-svn: 368123
If we're after type legalization we should only be trying to turn
v2i64 into v2i32. So bitcast to v4i32, shuffle the even elements
together. Then use X86ISD::CVTSI2P. The alternative is to leave
the v2i64 type alone and let it scalarized. Hopefully keeping
it packed is better.
Fixes PR42905.
llvm-svn: 368091
https://reviews.llvm.org/D65698
This adds a KnownBits analysis pass for GISel. This was done as a
pass (compared to static functions) so that we can add other features
such as caching queries(within a pass and across passes) in the future.
This patch only adds the basic pass boiler plate, and implements a lazy
non caching knownbits implementation (ported from SelectionDAG). I've
also hooked up the AArch64PreLegalizerCombiner pass to use this - there
should be no compile time regression as the analysis is lazy.
llvm-svn: 368065
Summary:
This is tested by D61289 but has been pulled into a separate patch at
a reviewers request.
Reviewers: bogner, aditya_nandakumar, volkan, aemerson, paquette, arsenm, rovka
Reviewed By: arsenm
Subscribers: javed.absar, hiraditya, wdng, kristof.beyls, Petar.Avramovic, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D61321
llvm-svn: 368063
Summary:
Cleans X86.td's Barcelona entry to be more like the others,
by moving the features out of the `Proc<>`, thus potentially
making it possible to inherit from them.
Split off from D63628
Reviewers: craig.topper, RKSimon
Reviewed By: craig.topper
Subscribers: hiraditya, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65791
llvm-svn: 368061
Refactor emitFrameOffset to accept a StackOffset struct as its offset argument.
This method currently only supports byte offsets (MVT::i8) but will be extended
in a later patch to support scalable offsets (MVT::nxv1i8) as well.
Reviewers: thegameg, rovka, t.p.northover, efriedma, greened
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D61436
llvm-svn: 368049
To support spilling/filling of scalable vectors we need a more generic
representation of a stack offset than simply 'int'.
For this we introduce the StackOffset struct, which comprises multiple
offsets sized by their respective MVTs. Byte-offsets will thus be a simple
tuple such as { offset, MVT::i8 }. Adding two byte-offsets will result in a
byte offset { offsetA + offsetB, MVT::i8 }. When two offsets have different
types, we can canonicalise them to use the same MVT, as long as their
runtime sizes are guaranteed to have the same size-ratio as they would have
at compile-time.
When we have both scalable- and fixed-size objects on the stack, we can
create an offset that is:
({ offset_fixed, MVT::i8 } + { offset_scalable, MVT::nxv1i8 })
The struct also contains a getForFrameOffset() method that is specific to
AArch64 and decomposes the frame-offset to be used directly in instructions
that operate on the stack or index into the stack.
Note: This patch adds StackOffset as an AArch64-only concept, but we would
like to make this a generic concept/struct that is supported by all
interfaces that take or return stack offsets (currently as 'int'). Since
that would be a bigger change that is currently pending on D32530 landing,
we thought it makes sense to first show/prove the concept in the AArch64
target before proposing to roll this out further.
Reviewers: thegameg, rovka, t.p.northover, efriedma, greened
Reviewed By: rovka, greened
Differential Revision: https://reviews.llvm.org/D61435
llvm-svn: 368024
If we don't demand any non-undef shuffle elements then the assert will fail as all shuffle inputs would still be flagged as 'identity' safe.
Exposed by an incoming patch.
llvm-svn: 368022
Summary:
Before this patch MGATHER/MSCATTER is capable of representing all
common addressing modes, but only when illegal types are used.
This patch adds an IndexType property so more representations
are available when using legal types only.
Original modes:
vector of bases
base + vector of signed scaled offsets
New modes:
base + vector of signed unscaled offsets
base + vector of unsigned scaled offsets
base + vector of unsigned unscaled offsets
The current behaviour of addressing modes for gather/scatter remains
unchanged.
Patch by Paul Walker.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D65636
llvm-svn: 368008
Summary:
When the WebAssembly backend encounters a return type that doesn't
fit within i32, SelectionDAG performs sret demotion, adding an
additional argument to the start of the function that contains
a pointer to an sret buffer to use instead. However, this conflicts
with the emscripten sjlj lowering pass. There we translate calls like:
```
call {i32, i32} @foo()
```
into (in pseudo-llvm)
```
%addr = @foo
call {i32, i32} @__invoke_{i32,i32}(%addr)
```
i.e. we perform an indirect call through an extra function.
However, the sret transform now transforms this into
the equivalent of
```
%addr = @foo
%sret = alloca {i32, i32}
call {i32, i32} @__invoke_{i32,i32}(%sret, %addr)
```
(while simultaneously translation the implementation of @foo as well).
Unfortunately, this doesn't work out. The __invoke_ ABI expected
the function address to be the first argument, causing crashes.
There is several possible ways to fix this:
1. Implementing the sret rewrite at the IR level as well and performing
it as part of lowering to __invoke
2. Fixing the wasm backend to recognize that __invoke has a special ABI
3. A change to the binaryen/emscripten ABI to recognize this situation
This revision implements the middle option, teaching the backend to
treat __invoke_ functions specially in sret lowering. This is achieved
by
1) Introducing a new CallingConv ID for invoke functions
2) When this CallingConv ID is seen in the backend and the first argument
is marked as sret (a function pointer would never be marked as sret),
swapping the first two arguments.
Reviewed By: tlively, aheejin
Differential Revision: https://reviews.llvm.org/D65463
llvm-svn: 367935
FastISel already does this since the initial arm64 port was upstreamed, so
it seems there are no issues with doing this at -O0 for very small memcpys.
Gives a 0.2% geomean code size improvement on CTMark.
Differential Revision: https://reviews.llvm.org/D65758
llvm-svn: 367919
This patch changes our defualt legalization behavior for 16, 32, and
64 bit vectors with i8/i16/i32/i64 scalar types from promotion to
widening. For example, v8i8 will now be widened to v16i8 instead of
promoted to v8i16. This keeps the elements widths the same and pads
with undef elements. We believe this is a better legalization strategy.
But it carries some issues due to the fragmented vector ISA. For
example, i8 shifts and multiplies get widened and then later have
to be promoted/split into vXi16 vectors.
This has the potential to cause regressions so we wanted to get
it in early in the 10.0 cycle so we have plenty of time to
address them.
Next steps will be to merge tests that explicitly test the command
line option. And then we can remove the option and its associated
code.
llvm-svn: 367901
Patch D56593 by @courbet results in calls to `bcmp()` in some cases, should
the target support the it. Unless `TTI::MemCmpExpansionOptions()`
is overridden by the target.
In a proprietary benchmark we see a performance drop of about 12% on PNG
compression before this patch, though it passes all tests.
This patch mirrors X86 for AArch64 and initializes
`TTI::MemCmpExpansionOptions()` to then expand calls to `bcmp()` when
appropriate. No tuning of the parameters was performed, but, at this point,
it's enough to recover the performance drop above.
This problem also exists on ARM. Once a consensus is reached for AArch64, we
can work to fix ARM as well.
Authors:
- Evandro Menezes (@evandro) <e.menezes@samsung.com>
- Brian Rzycki (@brzycki) <b.rzycki@samsung.com>
Differential revision: https://reviews.llvm.org/D64805
llvm-svn: 367898
Summary:
The Arm Neoverse N1 Software Optimization Guide [1], Section "4.8 Branch
instruction alignment" states:
"Consider aligning subroutine entry points and branch targets to 32B
boundaries, within the bounds of the code-density requirements of the
program."
This patch sets the preferred function alignment on Neoverse N1 to 2^4=16B.
This was already the case in some of the latest Cortex-A CPUs. Benchmarking
in previous Cortex-A CPUs suggested that 16B alignment is already better
than the default. See commit d04ee305.
The reason we don't set it to 32B right now (as the optimisation guide
suggests) is that this will impact code size and perhaps the instruction
cache performance. Therefore we need benchmark numbers first.
I have also added testing for A75 and A76 that we were missing.
[1] https://developer.arm.com/docs/swog309707/latest
Reviewers: fhahn, greened, samparker, dmgreen
Reviewed By: dmgreen
Subscribers: dmgreen, javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65654
llvm-svn: 367894
Summary:
This is a follow up to r367237. MachineFunction::getMachineMemOperand()
adds the offset parameter to the existing offset instead of resetting it.
So we need to reset the offset to the correct value after calling this
function.
Reviewers: arsenm
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65557
llvm-svn: 367881
This was switching to use a format store for a non-format store for
f16 types. Also fixes i16/f16 stores on targets without legal f16.
The corresponding loads also need to be fixed.
llvm-svn: 367872
Without context we assume SGPR. Allowing VGPR constants theoretically
helps avoid a copy. This seems to not actually work now, and the
choice isn't based on the use bank.
llvm-svn: 367871
I'm not sure what complications these present, but the current
argument lowering is pretty much directly copied from the DAG
lowering, so I assume these work as they should.
No tests because I'm lazy and things are getting pretty close to the
point where the existing calling-conventions.ll can be shared with
SelectionDAG.
llvm-svn: 367870
Summary:
This patch adds initial support for the SVE calling convention such that
SVE types can be passed as arguments and return values to/from a
subroutine.
The SVE AAPCS states [1]:
z0-z7 are used to pass scalable vector arguments to a subroutine,
and to return scalable vector results from a function. If a
subroutine takes arguments in scalable vector or predicate
registers, or if it is a function that returns results in such
registers, it must ensure that the entire contents of z8-z23 are
preserved across the call. In other cases it need only preserve the
low 64 bits of z8-z15, as described in §5.1.2.
p0-p3 are used to pass scalable predicate arguments to a subroutine
and to return scalable predicate results from a function. If a
subroutine takes arguments in scalable vector or predicate
registers, or if it is a function that returns results in these
registers, it must ensure that p4-p15 are preserved across the call.
In other cases it need not preserve any scalable predicate register
contents.
SVE predicate and data registers are passed indirectly (i.e. spilled to the
stack and pass the address) if they exceed the registers used for argument
passing defined by the PCS referenced above. Until SVE stack support is merged
we can't spill SVE registers to the stack, so currently an llvm_unreachable is
used where we will eventually handle this.
[1] https://static.docs.arm.com/100986/0000/100986_0000.pdf
Reviewed By: ostannard
Differential Revision: https://reviews.llvm.org/D65448
llvm-svn: 367859
The test case is based on the example from the post-commit thread for:
https://reviews.llvm.org/rGc9171bd0a955
This replaces the x86-specific simple-type check from:
rL367766
with a check in the DAGCombiner. Adding the check isn't
strictly necessary after the fix from:
rL367768
...but it seems likely that we're heading for trouble if
we are creating weird types in this transform.
I combined the earlier legality check into the initial
clause to simplify the code.
So we should only try the trunc/sext transform at the
earliest combine stage, but we limit the transform to
simple types anyway because the TLI hook is probably
too lax about what it considers a free truncate.
llvm-svn: 367834
We process 2 elements at a time and expect the number of elements to be
even. Similar to D60690.
Reviewers: dmgreen, samparker, t.p.northover
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D65400
llvm-svn: 367831
Summary:
This is patch is part of a serie to introduce an Alignment type.
See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html
See this patch for the introduction of the type: https://reviews.llvm.org/D64790
Reviewers: courbet, jfb, jakehehrlich
Reviewed By: jfb
Subscribers: wuzish, jholewinski, arsenm, dschuff, nemanjai, jvesely, nhaehnle, javed.absar, sbc100, jgravelle-google, hiraditya, aheejin, kbarton, asb, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, dexonsmith, PkmX, jocewei, jsji, s.egerton, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65514
llvm-svn: 367828
Add an explicit construction of the ArrayRef, gcc 5 and earlier don't
seem to select the ArrayRef constructor which takes a C array when the
construction is implicit.
Original commit message:
- Avoid a crash when IPRA calls ARMFrameLowering::determineCalleeSaves
with a null RegScavenger. Simply not updating the register scavenger
is fine because IPRA only cares about the SavedRegs vector, the acutal
code of the function has already been generated at this point.
- Add a new hook to TargetRegisterInfo to get the set of registers which
can be clobbered inside a call, even if the compiler can see both
sides, by linker-generated code.
Differential revision: https://reviews.llvm.org/D64908
llvm-svn: 367819
Summary:
The SimplifyDemandedVectorElts function can replace with undef
when no elements are demanded, but due to how it interacts with
TargetLoweringOpts, it can only do this when the node has
no other users.
Remove a now unneeded DAG combine from the X86 backend.
Reviewers: RKSimon, spatel
Reviewed By: RKSimon
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65713
llvm-svn: 367788
This adds big endian MVE patterns for bitcasts. They are defined in llvm as
being the same as a store of the existing type and the load into the new. This
means that they have to become a VREV between the two types, working in the
same way that NEON works in big-endian. This also adds some example tests for
bigendian, showing where code is and isn't different.
The main difference, especially from a testing perspective is that vectors are
passed as v2f64, and so are VREV into and out of call arguments, and the
parameters are passed in a v2f64 format. Same happens for inline assembly where
the register class is used, so it is VREV to a v16i8.
So some of this is probably not correct yet, but it is (mostly) self-consistent
and seems to be consistent with how llvm treats vectors. The rest we can
hopefully fix later. More details about big endian neon can be found in
https://llvm.org/docs/BigEndianNEON.html.
Differential Revision: https://reviews.llvm.org/D65581
llvm-svn: 367780
This avoids the crash from:
https://bugs.llvm.org/show_bug.cgi?id=42880
...and I think it's a proper constraint for the TLI hook.
But that example raises questions about what happens to get us
into this situation (created i29 types) and what happens later
(why does legalization die on those types), so I'm not sure if
we will resolve the bug based on this change.
llvm-svn: 367766
Summary:
The allocsize attribute refers to call parameters by index.
Thus, when we add the extra parameter in sjlj lowering, we
need to increment the referenced paramater in the allocsize
attribute to avoid angering the Verifier.
Reviewed By: aheejin
Differential Revision: https://reviews.llvm.org/D65470
llvm-svn: 367765
Fix for https://bugs.llvm.org/show_bug.cgi?id=42760. A tBR_JTr
instruction is duplicated by tail duplication, which results in
the same jumptable with the same label being emitted twice.
Fix this by marking tBR_JTr as not duplicable. The corresponding
ARM/Thumb instructions are already marked as not duplicable.
Additionally also mark tTBB_JT and tTBH_JT to be consistent with
Thumb2, even though this shouldn't be strictly necessary.
Differential Revision: https://reviews.llvm.org/D65606
llvm-svn: 367753
This is an old commit that exposed a bug in the GISel importer, which caused
non-truncating stores to be selected for truncating store patterns. Now that's
been fixed in r367737 this can go back in.
llvm-svn: 367739
This is consistent with the target independent intrinsic handling.
Not sure this really matters since we just pull the constant out
using getZExtValue later.
llvm-svn: 367736
With newly added debuginfo type
metadata for preserve_array_access_index() intrinsic,
this patch did the following two things:
(1). checking validity before adding a new access index
to the access chain.
(2). calculating access byte offset in IR phase
BPFAbstractMemberAccess instead of when BTF is emitted.
For (1), the metadata provided by all preserve_*_access_index()
intrinsics are used to check whether the to-be-added type
is a proper struct/union member or array element.
For (2), with all available metadata, calculating access byte
offset becomes easier in BPFAbstractMemberAccess IR phase.
This enables us to remove the unnecessary complexity in
BTFDebug.cpp.
New tests are added for
. user explicit casting to array/structure/union
. global variable (or its dereference) as the source of base
. multi demensional arrays
. array access given a base pointer
. cases where we won't generate relocation if we cannot find
type name.
Differential Revision: https://reviews.llvm.org/D65618
llvm-svn: 367735
These cases can come up when the extending loads combiner doesn't combine a
zext(load) to a zextload op, due to some other operation being in between, which
then gets simplified at a later stage.
Differential Revision: https://reviews.llvm.org/D65360
llvm-svn: 367723
Summary:
As part of this, define DenseMapInfo for MCRegister (and Register while I'm at it)
Depends on D65599
Reviewers: arsenm
Subscribers: MatzeB, qcolombet, jvesely, wdng, nhaehnle, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65605
llvm-svn: 367719
Add an equivalent ComplexRendererFns function for SelectNegArithImmed. This
allows us to select immediate adds of -1 by turning them into subtracts.
Update select-binop.mir to show that the pattern works.
Differential Revision: https://reviews.llvm.org/D65460
llvm-svn: 367700
This optimisation isn't generally profitable for ARM, because we can
save/restore many registers in the prologue and epilogue using the PUSH
and POP instructions, but mostly use individual LDR/STR instructions for
other spills.
Differential revision: https://reviews.llvm.org/D64910
llvm-svn: 367670
- Avoid a crash when IPRA calls ARMFrameLowering::determineCalleeSaves
with a null RegScavenger. Simply not updating the register scavenger
is fine because IPRA only cares about the SavedRegs vector, the acutal
code of the function has already been generated at this point.
- Add a new hook to TargetRegisterInfo to get the set of registers which
can be clobbered inside a call, even if the compiler can see both
sides, by linker-generated code.
Differential revision: https://reviews.llvm.org/D64908
llvm-svn: 367669
Summary:
When combining `extsw` and `sldi` in `PPCMIPeephole`, we have to check
if `extsw`'s second operand is a virtual register, otherwise we might
get miscompile.
Differential Revision: https://reviews.llvm.org/D65315
llvm-svn: 367645
Summary:
Fixes: https://bugs.llvm.org/show_bug.cgi?id=42441
Used to print:
<unknown>:0: error: Cannot represent a difference across sections
(the location was null).
Now prints:
err.s:20:3: error: Cannot represent a difference across sections
i32.const foo-bar
^
Note: I looked at adding a test for this, but I don't think it is
worth it. We're not testing error formatting in the Wasm backend :)
Reviewers: sbc100, jgravelle-google
Subscribers: dschuff, aheejin, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65602
llvm-svn: 367619
AMDGPU sometimes has legal s16 and <2 x s16> operations, but all
registers are really 32-bit. An unmerge destination really should ben
widened to a 32-bit register. If widening a scalarizing vector with a
target size that matches the vector size, bitcast to integer and
extract the relevant bits with shifts.
I'm not sure if this is the right place for this. This could arguably
be part of widenScalar for the result. I also have a growing feeling
that we're missing a bitcast legalize action.
llvm-svn: 367604
If a type is larger than a legal type and needs to be split, we would previously allow the multiply to be decomposed even if the split multiply is legal. Since the shift + add/sub code would also need to be split, its not any better to decompose it.
This patch figures out what type the mul will eventually be legalized to and then uses that type for the query. I tried just returning false illegal types and letting them get handled after type legalization, but then we can't recognize and i64 constant splat on 32-bit targets since will be destroyed by type legalization. We could special case vectors of i64 to avoid that...
Differential Revision: https://reviews.llvm.org/D65533
llvm-svn: 367601
A TYPE_INDEX operand (as used by call_indirect) used to be represented
by the InstPrinter as a symbol (e.g. .Ltype_index0@TYPE_INDEX) which
was a bit of a mismatch with the WasmObjectWriter which expects an
unnamed symbol, to receive the signature from and then turn into a
reloc.
There was really no good way to round-trip this information. An earlier
version of this patch tried to attach the signature information using
a .functype, but that ran into trouble when the symbol was re-emitted
without a name. Removing the name was a giant hack also.
The current version changes the assembly syntax to have an inline
signature spec for TYPEINDEX operands that is always unnamed, which
is much more elegant both in syntax and in implementation (as now the
assembler is able to follow the same path as the regular backend)
Reviewers: sbc100, dschuff, aheejin, jgravelle-google, sunfish, tlively
Subscribers: arphaman, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64758
llvm-svn: 367590
If an operand of the `lw/sw` instructions is a symbol, these instructions
incorrectly lowered using not-position-independent chain of commands.
For PIC code we should use `lw/addiu` instructions with the `R_MIPS_GOT16`
and `R_MIPS_LO16` relocations respectively. Instead of that LLVM generates
position dependent code with the `R_MIPS_HI16` and `R_MIPS_LO16`
relocations.
This patch provides a fix for the bug by handling PIC case separately in
the `MipsAsmParser::expandMemInst`. The main idea is to generate a chain
of PIC instructions to load a symbol address into a register and then
load the address content.
The fix is not optimal and does not fix all PIC-related problems. This
is a task for subsequent patches.
Differential Revision: https://reviews.llvm.org/D65524
llvm-svn: 367580
This adds SimplifyMultipleUseDemandedBitsForTargetNode X86 support and uses it to allow us to peek through vector insertions to avoid dependencies on entire insertion chains.
llvm-svn: 367570
Summary:
GCC Accepts both (reg) and 0(reg) for atomic instruction memory
operands. These instructions do not allow for an offset in their
encoding, so in the latter case, the 0 is silently dropped.
Due to how we have structured the RISCVAsmParser, the easiest way to add
support for parsing this offset is to add a custom AsmOperand and
parser. This parser drops all the parens, and just keeps the register.
This commit also adds a custom printer for these operands, which matches
the GCC canonical printer, printing both `(a0)` and `0(a0)` as `(a0)`.
Reviewers: asb, lewis-revill
Reviewed By: asb
Subscribers: s.egerton, hiraditya, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, kito-cheng, shiva0217, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, jfb, PkmX, jocewei, psnobl, benna, Jim, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65205
llvm-svn: 367553
Summary:
While there is always a `Value::replaceAllUsesWith()`,
sometimes the replacement needs to be conditional.
I have only cleaned a few cases where `replaceUsesWithIf()`
could be used, to both add test coverage,
and show that it is actually useful.
Reviewers: jdoerfert, spatel, RKSimon, craig.topper
Reviewed By: jdoerfert
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya, aheejin, george.burgess.iv, asbirlea, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65528
llvm-svn: 367548
The VREV64 instruction is apparently unpredictable if Qd == Qm, due to the
cross-beat nature of the instruction. This adds an earlyclobber to Qd, which
seems to be the same way we deal with this on other instructions like the
write-back on loads and stores.
Differential Revision: https://reviews.llvm.org/D65502
llvm-svn: 367544
Fix an issue where the compiler still allocates an emergency spill slot even
though it already decided to spill an extra callee-save register to use
as a scratch register.
Reviewers: gberry, thegameg, mstorsjo, t.p.northover
Reviewed By: thegameg
Differential Revision: https://reviews.llvm.org/D65504
llvm-svn: 367540
Fold load/store + G_GEP + G_CONSTANT when
immediate in G_CONSTANT fits into 16 bit signed integer.
Differential Revision: https://reviews.llvm.org/D65507
llvm-svn: 367535
In PowerPC, there is instruction to load vector in big endian element order when it's in little endian target.
So we can combine vector load + reverse into big endian load to eliminate the swap instruction.
Also combine vector reverse + store into big endian store.
Differential Revision: https://reviews.llvm.org/D65063
llvm-svn: 367516
Start migrating to a form that will be compatible with the global isel
emitter. Also should fix some overly lax checks on the memory type,
which allowed mis-selecting some illegal atomics.
llvm-svn: 367506
This is extremely specific, but saves three instructions when it's
legal. I don't think the code can be usefully generalized.
Differential Revision: https://reviews.llvm.org/D65351
llvm-svn: 367492
Thumb1 has very limited immediate modes, so turning an "and" into a
shift can save multiple instructions.
It's possible to simplify the generated code for test2 and test3 in
cmp-and-fold.ll a little more, but I'll implement that as a followup.
Differential Revision: https://reviews.llvm.org/D65175
llvm-svn: 367491
We have custom code that ignores the normal promoting type legalization on less than 128-bit vector types like v4i8 to emit pavgb, paddusb, psubusb since we don't have the equivalent instruction on a larger element type like v4i32. If this operation appears before a store, we can be left with an any_extend_vector_inreg followed by a truncstore after type legalization. When truncstore isn't legal, this will normally be decomposed into shuffles and a non-truncating store. This will then combine away the any_extend_vector_inreg and shuffle leaving just the store. On avx512, truncstore is legal so we don't decompose it and we had no combines to fix it.
This patch adds a new DAG combine to detect this case and emit either an extract_store for 64-bit stoers or a extractelement+store for 32 and 16 bit stores. This makes the avx512 codegen match the avx2 codegen for these situations. I'm restricting to only when -x86-experimental-vector-widening-legalization is false. When we're widening we're not likely to create this any_extend_inreg+truncstore combination. This means we should be able to remove this code when we flip the default. I would like to flip the default soon, but I need to investigate some performance regressions its causing in our branch that I wasn't seeing on trunk.
Differential Revision: https://reviews.llvm.org/D65538
llvm-svn: 367488
Summary:
This will make it possible to improve IPRA by taking into account
register usage in indirect calls.
NFC yet; this is just laying the groundwork to start building
up patches to take advantage of the information for improved register
allocation.
Reviewers: aditya_nandakumar, volkan, qcolombet, arsenm, rovka, aemerson, paquette
Subscribers: sdardis, wdng, javed.absar, hiraditya, jrtc27, atanasyan, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65488
llvm-svn: 367476
This feature instructs the backend to allow locally defined global variable
addresses to contain a pointer tag in bits 56-63 that will be ignored by
the hardware (i.e. TBI), but may be used by an instrumentation pass such
as HWASAN. It works by adding a MOVK instruction to the regular ADRP/ADD
sequence that sets bits 48-63 to the corresponding bits of the global, with
the linker bounds check disabled on the ADRP instruction to prevent the tag
from causing a link failure.
This implementation of the feature omits the MOVK when loading from or storing
to a global, which is sufficient for TBI. If the same approach is extended
to MTE, assuming that 0 is not configured as a catch-all tag, we will most
likely also need the MOVK in this case in order to avoid a tag mismatch.
Differential Revision: https://reviews.llvm.org/D65364
llvm-svn: 367475
This makes the field wider than MachineOperand::SubReg_TargetFlags so that
we don't end up silently truncating any higher bits. We should still catch
any bits truncated from the MachineOperand field as a consequence of the
assertion in MachineOperand::setTargetFlags().
Differential Revision: https://reviews.llvm.org/D65465
llvm-svn: 367474
Summary:
According to the Armv8.1-M manual CSEL, CSINC, CSINV and CSNEG are
"constrained unpredictable" when SP is used as the source register Rn.
The assembler should diagnose this case.
Reviewers: momchil.velikov, dmgreen, ostannard, simon_tatham, t.p.northover
Reviewed By: ostannard
Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65505
llvm-svn: 367433
Before combining insert_subvector(insert_subvector(vec, sub0, c0), sub1, c1) patterns, ensure that the subvectors are all the same type. On AVX512 targets especially we might have a mixture of 128/256 subvector insertions.
llvm-svn: 367429
Summary:
This adds the 'f' inline assembly constraint, as supported by GCC. An
'f'-constrained operand is passed in a floating point register. Exactly
which kind of floating-point register (32-bit or 64-bit) is decided
based on the operand type and the available standard extensions (-f and
-d, respectively).
This patch adds support in both the clang frontend, and LLVM itself.
Reviewers: asb, lewis-revill
Reviewed By: asb
Subscribers: hiraditya, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, kito-cheng, shiva0217, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, Jim, s.egerton, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D65500
llvm-svn: 367403
Use a switch instead of many isa<> while checking for supported
values. Also be explicit about which cast instructions are supported;
This allows the removal of SIToFP from GenerateSignBits.
llvm-svn: 367402
Summary:
* Loads and stores in SVE2 are gather/scatter not contiguous, fixed by
renaming multiclasses to reflect this and also updated comments.
* Remove aliases from load/store multiclasses that reflect the behaviour
of the original form.
* Fix bug in scatter store implementation, vector list should be used as
input, not output.
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D65392
llvm-svn: 367398
This adds the required extension to RISC-V's getRegForInlineAsmConstraint
in order to be able to correctly distringuish between the 32 and 64-bit
floating point registers when the generic fX name appears in inlineasm
clobber contraints. It also adds a check to validate that callee saved
floating point registers are only saved in this case when a hard-float
ABI is selected.
Differential Revision: https://reviews.llvm.org/D64751
llvm-svn: 367397
Summary:
* Clarify comment with SVE2 for predicated shifts and move next to other
shift instructions.
* Clarify comments for various instructions.
* Move FCVTX instruction next to other fp conversions.
* Move FLOGB to next to other fp instructions and fix description.
* Remove "cons" from non-constructive multiclass for bitwise shift-right
and accumulate instructions.
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D65390
llvm-svn: 367396
Summary:
This patch fixes a bug in the following instructions that should have been
implemented as destructive. A destructive instruction is an instruction where
one of the source registers also acts as the destination register. Therefore,
the contents of the source register, when the instruction begins execution, are
replaced by the result of the instruction when the instruction completes
execution [1]:
* SRI/SLI
* EORBT/EORTB
* TBX
* Narrowing top instructions
* FP convert precision instructions
These changes are non-functional from the assembler/diassembler point-of-view
but are necessary for correct codegen.
[1] https://static.docs.arm.com/ddi0584/ae/DDI0584A_e_SVE_supp_armv8A.pdf
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D65389
llvm-svn: 367394
In PowerPC, there is instruction to load vector in big endian element order when it's in little endian target.
So we can combine vector load + reverse into big endian load to eliminate the swap instruction.
Also combine vector reverse + store into big endian store.
llvm-svn: 367382
We had couple places which still return 10 as a maximum
occupancy. Fixed.
Also print comment about occupancy as compiler see it.
Differential Revision: https://reviews.llvm.org/D65423
llvm-svn: 367381
AMDGPU uses some custom code predicates for testing alignments.
I'm still having trouble comprehending the behavior of predicate bits
in the PatFrag hierarchy. Any attempt to abstract these properties
unexpectdly fails to apply them.
llvm-svn: 367373
Summary:
- Use the passed `DL` directly as retrieving data layout from CS by
checking the called function is not reliable. Under indirect function
call, there is no called function.
Subscribers: jholewinski, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65468
llvm-svn: 367349
Summary:
return_call and return_call_indirect are only valid if the return
types of the callee and caller match. We were previously not enforcing
that, which was producing invalid modules.
Reviewers: aheejin
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65246
llvm-svn: 367339
Empty condition strings are considerde always true. This removes a lot
of clutter from the generated matcher tables.
This shrinks the source size of AMDGPUGenDAGISel.inc from 7.3M to
6.1M.
llvm-svn: 367326
Addresses number of comment made on D64652 after commiting:
- Reorders function decls in the TargetLoweringObjectFileXCOFF class.
- Fix comment in MCSectionXCOFF to include description of external reference
csects.
- Convert several llvm_unreachables to report_fatal_error
- Convert several dyn_casts to casts as they are expected not to fail.
- Avoid copying DataLayout object.
llvm-svn: 367324
PR42819 showed an issue that we couldn't handle the case where we demanded a 'sub-sub-vector' of the SUBV_BROADCAST 'sub-vector' source.
This patch recognizes these cases and extracts the sub-sub-vector instead of trying to broadcast to a type smaller than the 'sub-vector' source.
llvm-svn: 367306
The code is now in a good enough state to pass the bunch of tests that
I have run (after fixing the bugs), so let's enable it by default.
Differential Revision: https://reviews.llvm.org/D65277
llvm-svn: 367297
Revert the hardware loop upon finding a LoopEnd that doesn't target
the loop header, instead of asserting a failure.
Differential Revision: https://reviews.llvm.org/D65268
llvm-svn: 367296
Summary:
The LoadStoreOptimizer was creating instructions with 2
MachineMemOperands, which meant they were assumed to alias with all other instructions,
because MachineInstr:mayAlias() returns true when an instruction has multiple
MachineMemOperands.
This was preventing these instructions from being merged again, and was
giving the scheduler less freedom to reorder them.
Reviewers: arsenm, nhaehnle
Reviewed By: arsenm
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65036
llvm-svn: 367237
As discussed on rL367171, we have a problem where the depth recursion used in combineX86ShufflesRecursively was subtly different to computeKnownBits etc. - it starts at Depth=1 instead of Depth=0 like the others and has a different maximum recursion depth.
This NFC patch fixes the recursion depth to start at 0, so we can more easily reuse depth values in calls from combineX86ShufflesRecursively and its helper functions in computeKnownBits etc.
llvm-svn: 367232
For llvm/test/MC/RISCV/rv64i-aliases-invalid.s, UBSan reports:
lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp:371:9: runtime error:
load of value 3879186881, which is not a valid value for type
'RISCVMCExpr::VariantKind'
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior
lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp:371:9 in
It turns out that evaluateConstantImm does not set `VK` and it remains
unitialized when doing comparisons in `isImmXLenLI()`.
Differential Revision: https://reviews.llvm.org/D65347
llvm-svn: 367230
Summary:
The existing isDivergent(Value) methods query whether a value is
divergent at its definition. However even if a value is uniform at its
definition, a use of it in another basic block can be divergent because
of divergent control flow between the def and the use.
This patch adds new isDivergent(Use) methods to DivergenceAnalysis,
LegacyDivergenceAnalysis and GPUDivergenceAnalysis.
This might allow D63953 or other similar workarounds to be removed.
Reviewers: alex-t, nhaehnle, arsenm, rtaylor, rampitec, simoll, jingyue
Reviewed By: nhaehnle
Subscribers: jfb, jvesely, wdng, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65141
llvm-svn: 367218
- Remove some unused typedefs.
- Rename BinOpChain struct to MulCandidate.
- Remove the size method of MulCandidate.
- Store only the first input of the ValueList provided to
MulCandidate, as it's the only value we care about. This means we
don't have to perform any ugly (and unnecessary) iterations of the
list later on.
llvm-svn: 367208
Summary:
If isel is presented with <2 x half> vectors then it will correctly select
v_pk_fma style instructions.
If isel is presented with e.g. <4 x half> vectors it will scalarize, unlike for
other instruction types (such as fadd, fmul etc.)
Added extra support to enable this. Updated one of the tests to include a test
for this (as well as extending the test to GFX9)
Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, tpr, t-tye, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65325
Change-Id: I50a4577a3f8223fb53992af3b7d26121f65b71ee
llvm-svn: 367206
The pmaddwd inserts a truncate, if that truncate would end up
creating additional instructions instead of making a zext
narrower, then we shouldn't do it.
I've restricted this to only sse4.1 targets since on prior
targets the zext will be done in stages. So the truncate will
probably not create additional instructions. Might need some
more investigation of mul shrinking and the other pmaddwd
transform to be sure this is the right decision.
There might be a slight regression on AVX1 targets due to add
splitting. Hard to say for sure. Maybe we need to look into
using the vector reduction flag to use 2 narrow loads and a
blend instead of extracting and inserting.
llvm-svn: 367198
This reverts r340478 and r340631 and replaces them with a simpler
method of just letting DAG combine revisit the nodes to handle
the other operand.
llvm-svn: 367195
This adds the patterns required to transform xor P0, -1 to a VPNOT. The
instruction operands have to change a little for this, adding an in and an out
VCCR reg and using a custom DecodeMVEVPNOT for the decode.
Differential Revision: https://reviews.llvm.org/D65133
llvm-svn: 367192
These are some better patterns for converting between predicates and floating
points. Much like the extends, we select "1"/"-1" or "0" depending on the
predicate value. Or we perform a compare against 0 to convert to a predicate.
Differential Revision: https://reviews.llvm.org/D65103
llvm-svn: 367191
Recommit rL367100 which was reverted at rL367141. Until PR42777 is fixed, we no longer get the benefits of peeking through bitcasts but it does still remove a GetDemandedBits user and gives us the equivalent combines.
llvm-svn: 367172
Add partial instruction selection for intrinsics like this:
```
declare i32 @llvm.aarch64.stlxr(i64, i32*)
```
(This only handles the case where a G_ZEXT is feeding the intrinsic.)
Also make sure that the added store instruction actually has the memory op from
the original G_STORE.
Update select-stlxr-intrin.mir and arm64-ldxr-stxr.ll.
Differential Revision: https://reviews.llvm.org/D65355
llvm-svn: 367163
Adds machine operand lowering for MCSymbolSDNodes to the PowerPC
backend. This is needed to produce call instructions in assembly for AIX
because the callee operand is a MCSymbolSDNode. The test is XFAIL'ed for
asserts due to a (valid) assertion in PEI that the AIX ABI isn't supported yet.
Differential Revision: https://reviews.llvm.org/D63738
llvm-svn: 367133
Summary:
The bitperm feature flag is now prefixed with SVE2, as it is for all other SVE2
extensions
Patch by Maciej Gabka.
Reviewers: sdesmalen, rovka, chill, SjoerdMeijer, rengolin
Reviewed By: SjoerdMeijer, rengolin
Differential Revision: https://reviews.llvm.org/D65327
llvm-svn: 367124
In preperation for AIX support in FrameLowering: replace a number of literal
'8' that represent the stack offset of the condition register save area with
a member in PPCFrameLowering.
Patch by Chris Bowler.
llvm-svn: 367111
Void return used to have unsigned with value 0 for virtual register
but with addition of Register class and changes to arguments to lowerCall
this is no longer valid.
Check for void return by inspecting the Ty field in OrigRet.
Differential Revision: https://reviews.llvm.org/D65321
llvm-svn: 367107
Add llvm.amdgcn.softwqm intrinsic which behaves like llvm.amdgcn.wqm
only if there is other WQM computation in the shader.
Reviewers: nhaehnle, tpr
Reviewed By: nhaehnle
Subscribers: arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64935
llvm-svn: 367097
Embedded Trace Extension and Trace Buffer Extension are optional
future architecture extensions.
(cf. https://developer.arm.com/architectures/cpu-architecture/a-profile/exploration-tools)
Their system registers are documented here:
https://developer.arm.com/docs/ddi0601/a
ETE shares register names with ETM. One exception is the ETE
TRCEXTINSELR0 register, which has the same encoding as the ETM
TRCEXTINSELR register (but different semantics). This patch treats
them as aliases: the assembler will accept both names, emitting
identical encoding, and the disassembler will keep disassembling
to TRCEXRINSELR.
Differential Revision: https://reviews.llvm.org/D63707
llvm-svn: 367093
Both WhileLoopStart and LoopEnd may get turned into a cmp and br pair,
so add an implicit def to these pseudo instructions in case that WLS
and LE aren't generated.
Differential Revision: https://reviews.llvm.org/D65275
llvm-svn: 367089
Summary:
This is an alternate approach to D57970.
Currently funclets reuse the same stack slots that are used in the
parent function for saving callee-saved xmm registers. If the parent
function modifies a callee-saved xmm register before an excpetion is
thrown, the catch handler will overwrite the original saved value.
This patch allocates space in funclets stack for saving callee-saved xmm
registers and uses RSP instead RBP to access memory.
Reviewers: andrew.w.kaylor, LuoYuanke, annita.zhang, craig.topper,
RKSimon
Subscribers: rnk, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63396
Signed-off-by: pengfei <pengfei.wang@intel.com>
llvm-svn: 367088
handleAssignments gives up pretty easily on structs, and i8 values for
some reason. The other case that doesn't work is when an implicit sret
needs to be inserted if the return size exceeds the number of return
registers.
llvm-svn: 367082
Currently, the CO-RE offset relocation does not work
if any struct/union member or array element is a typedef.
For example,
typedef const int arr_t[7];
struct input {
arr_t a;
};
func(...) {
struct input *in = ...;
... __builtin_preserve_access_index(&in->a[1]) ...
}
The BPF backend calculated default offset is 0 while
4 is the correct answer. Similar issues exist for struct/union
typedef's.
When getting struct/union member or array element type,
we should trace down to the type by skipping typedef
and qualifiers const/volatile as this is what clang did
to generate getelementptr instructions.
(const/volatile member type qualifiers are already
ignored by clang.)
This patch fixed this issue, for each access index,
skipping typedef and const/volatile/restrict BTF types.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D65259
llvm-svn: 367062
Currently, we expect the CO-RE offset relocation records
a string encoding the original getelementptr access index,
so kernel bpf loader can decode it correctly.
For example,
struct s { int a; int b; };
struct t { int c; int d; };
#define _(x) (__builtin_preserve_access_index(x))
int get_value(const void *addr1, const void *addr2);
int test(struct s *arg1, struct t *arg2) {
return get_value(_(&arg1->b), _(&arg2->d));
}
We expect two offset relocations:
reloc 1: type s, access index 0, 1
reloc 2: type t, access index 0, 1
Two globals are created to retain access indexes for the
above two relocations with global variable names.
The first global has a name "0:1:". Unfortunately,
the second global has the name "0:1:.1" as the llvm
internals automatically add suffix ".1" to a global
with the same name. Later on, the BPF peels the last
character and record "0:1" and "0:1:." in the
relocation table.
This is not desirable. BPF backend could use the global
variable suffix knowledge to generate correct access str.
This patch rather took an approach not relying on
that knowledge. It generates "s:0:1:" and "t:0:1:" to
avoid global variable suffixes and later on generate
correct index access string "0:1" for both records.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D65258
llvm-svn: 367030
Summary:
- As LCSSA is turned on just before isel, it may create PHI of the flow,
which is consumed by pseudo structurized CFG instructions. When that
PHIs are eliminated in O0, COPY may be placed wrongly as the these
pseudo structurized CFG instructions are considering prologue of MBB.
- Run extra `unreachable-mbb-elimination` at the end of isel to clean up
PHIs.
Reviewers: arsenm, rampitec
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64353
llvm-svn: 367023
... for the vector forms of `{SQ,UQ,}{INC,DEC}P` instructions. Also continue
supporting the exsting behaviour of not requiring an explicit size
specifier. The preferred disasembly is *with* the specifier.
This is implemented by redefining intruction forms to require vector predicates
with explicit size and adding aliases, which allow a predicate with no size.
Differential Revision: https://reviews.llvm.org/D65145
llvm-svn: 367019
Summary:
In PostRA phase, we often have to find out the most recent definition
of a register. This patch adds getDefMIPostRA so that other methods
can use it rather than implementing it repeatedly.
Differential Revision: https://reviews.llvm.org/D65131
llvm-svn: 366990
Summary:
Add a new method which tries to compute the target address referenced by an operand.
This patch supports x86_64 RIP-relative addressing for now.
It is necessary to print referenced symbol names in llvm-objdump.
Reviewers: andreadb, MaskRay, grosbach, jgalenson, craig.topper
Reviewed By: MaskRay, craig.topper
Subscribers: bcain, rupprecht, jhenderson, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63847
llvm-svn: 366987
Before, we weren't able to select things like this for G_GEP:
add x0, x8, #8
And instead we'd materialize the 8.
This teaches GISel to do that. It gives some considerable code size savings
on 252.eon-- about 4%!
Differential Revision: https://reviews.llvm.org/D65248
llvm-svn: 366959
Throughout the legalizerinfo we currently make the assumption that the target
has neon and FP target features available. Fixing it will require a refactor of
the whole thing, so until then make sure we fall back.
Works around PR42734
Differential Revision: https://reviews.llvm.org/D65244
llvm-svn: 366957
Summary:
This was originally reported in D62818.
https://rise4fun.com/Alive/oPH
InstCombine does the opposite fold, in hope that `C l>>/<< Y` expression
will be hoisted out of a loop if `Y` is invariant and `X` is not.
But as it is seen from the diffs here, if it didn't get hoisted,
the produced assembly is almost universally worse.
Much like with my recent "hoist add/sub by/from const" patches,
we should get almost universal win if we hoist constant,
there is almost always an "and/test by imm" instruction,
but "shift of imm" not so much, so we may avoid having to
materialize the immediate, and thus need one less register.
And since we now shift not by constant, but by something else,
the live-range of that something else may reduce.
Special care needs to be applied not to disturb x86 `BT` / hexagon `tstbit`
instruction pattern. And to not get into endless combine loop.
Reviewers: RKSimon, efriedma, t.p.northover, craig.topper, spatel, arsenm
Reviewed By: spatel
Subscribers: hiraditya, MaskRay, wuzish, xbolva00, nikic, nemanjai, jvesely, wdng, nhaehnle, javed.absar, tpr, kristof.beyls, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62871
llvm-svn: 366955
If we have a G_MUL, and either the LHS or the RHS of that mul is the legal
shift value for a load addressing mode, we can fold it into the load.
This gives some code size savings on some SPEC tests. The best are around 2%
on 300.twolf and 3% on 254.gap.
Differential Revision: https://reviews.llvm.org/D65173
llvm-svn: 366954
This introduces a new family of combiner helper routines that re-use the
target specific cost model from SelectionDAG, and generate inline implementations
of the memcpy family of intrinsics.
The combines are only enabled at optimization levels higher than -O0, and give
very substantial performance improvements.
Differential Revision: https://reviews.llvm.org/D65167
llvm-svn: 366951
To support prefetch mode 3 we need to pad current
cacheline and fill 3 cachelines after. Current padding
is only sufficient for mode 2.
Differential Revision: https://reviews.llvm.org/D65236
llvm-svn: 366938
This removes the VCEQ/VCNE/VCGE/VCEQZ/etc nodes, just using two called VCMP and
VCMPZ with an extra operand as the condition code. I believe this will make
some combines simpler, allowing us to just look at these codes and not the
operands. It also helps fill in a missing VCGTUZ MVE selection without adding
extra nodes for it.
Differential Revision: https://reviews.llvm.org/D65072
llvm-svn: 366934
This patch adds support for recognizing cases where a larger vector type is being used to reduce just the elements in the lower subvector:
e.g. <8 x i32> reduction pattern in a <16 x i32> vector:
<4,5,6,7,u,u,u,u,u,u,u,u,u,u,u,u>
<2,3,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
<1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
matchBinOpReduction returns the lower extracted subvector in such cases, assuming isExtractSubvectorCheap accepts the extraction.
I've only enabled it for X86 reduction sums so far. I intend to enable it for the bitop/minmax cases in future patches, and eventually I think its worth turning it on all the time. This is mainly just a case of ensuring calls to matchBinOpReduction don't make assumptions on the vector width based on the original vector extraction.
Fixes the x86 partial reduction sum cases in PR33758 and PR42023.
Differential Revision: https://reviews.llvm.org/D65047
llvm-svn: 366933
The prevents us from trying to convert an i1 predicate vector to a float, or
vice-versa. Better patterns are possible, which will follow in a subsequent
commit. For now we just expand them.
Differential Revision: https://reviews.llvm.org/D65066
llvm-svn: 366931
Fix an off-by-one error which made us not look at the last element of the
zero vector. This caused a miscompile in 188.ammp.
Differential Revision: https://reviews.llvm.org/D65168
llvm-svn: 366930
MVE VCMP instructions can use a general purpose register as the second operand.
This adds the combines for it, selecting from a compare of a vdup.
Differential Revision: https://reviews.llvm.org/D65061
llvm-svn: 366924
This adds a DeMorgan combine for OR's of compares to turn them into AND's,
helping prevent them from going into and out of gpr registers. It also fills in
the VCLE and VCLT nodes that MVE can select, allowing it to invert more
compares.
Differential Revision: https://reviews.llvm.org/D65059
llvm-svn: 366920
Add a number of folds to convert and(vcmp, vcmp) into a single VPT block, where
the second vcmp becomes predicated on the first.
The VCMP; VPST; VCMP will eventually be converted to VPT; VCMP in the
VPTBlockPass.
Differential Revision: https://reviews.llvm.org/D65058
llvm-svn: 366910
Much like integers, this adds MVE floating point compares and select. It
requires a lot more buildvector/shuffle code because we may need to expand the
compares without mve.fp, and requires support for and/or because of the way we
lower llvm condition codes.
Some original code by David Sherwood
Differential Revision: https://reviews.llvm.org/D65054
llvm-svn: 366909
This adds some basic, "worst case" handling for MVE predicate Or/And/Xor. It
does this by going into and out of GPRs, doing the operation on scalars.
Code by David Sherwood.
Differential Revision: https://reviews.llvm.org/D65053
llvm-svn: 366907
This change make sure that llvm does not emit an invalid IT block
by putting the constant pool in the middle of an IT block.
We have code to try to avoid putting a constant island in the middle of an
IT block, but it only works if we see an IT between the one currently
referencing CPE and possible insertion point. If the first instruction
we look at is the VLDRD after the IT , we never see the IT and does not
realize that the instruction doing the load could be in an IT block itself.
Differential Revision: https://reviews.llvm.org/D64621
Change-Id: I24cecb37cded75e8992870bd997f6226853bd920
llvm-svn: 366905
This adds support code for building and shuffling i1 predicate registers. It
generally uses two basic principles, either converting the predicate into an
scalar (through a PREDICATE_CAST) and doing scalar operations on it there, or
by converting the register to an full vector register and back.
Some of the code here is a not super efficient but will hopefully cover most
cases of moving i1 vectors around and can be improved in subsequent patches.
Some code by David Sherwood.
Differential Revision: https://reviews.llvm.org/D65052
llvm-svn: 366890
This adds the very basics for MVE vector predication, adding integer VCMP and
VSEL instruction support. This is done through predicate registers (MVT::v16i1,
MVT::v8i1, MVT::v4i1), but otherwise using same mechanics as NEON to custom
lower setcc's through ARMISD::VCXX nodes (VCEQ, VCGT, VCEQZ, etc).
An extra VCNE was added, as this can be handled sensibly by MVE's expanded
number of VCMP condition codes. (There are also VCLE and VCLT which are added
later).
VPSEL is also added here, simply selecting on the vselect.
Original code by David Sherwood.
Differential Revision: https://reviews.llvm.org/D65051
llvm-svn: 366885
While combining two loads into a single load, we often need to
reorder the pointer operands for the new load. This reordering was
broken in the cases where there was a chain of values that built up
the pointer.
Differential Revision: https://reviews.llvm.org/D65193
llvm-svn: 366881
We need to be able to load and store s128 for memcpy inlining, where we want to
generate Q register mem ops. Making these legal also requires that we add some
support in other instructions. Regbankselect should also know about these since
they have no GPR register class that can hold them, so need special handling to
live on the FPR bank.
Differential Revision: https://reviews.llvm.org/D65166
llvm-svn: 366857
Currently PowerPC backend emits code like this:
r3 = li 0
std r3, 264(r1)
r3 = li 0
std r3, 272(r1)
This patch fixes that and other cases where a register already contains a value that is loaded so we will get:
r3 = li 0
std r3, 264(r1)
std r3, 272(r1)
Differential Revision: https://reviews.llvm.org/D64220
llvm-svn: 366840
LegalizeDAG tries to legal the DAG by legalizing nodes before
their operands.
If we create a new node, we end up legalizing it after its operands.
This prevents some of the optimizations that can be done when the
operand is a build_vector since the build_vector will have been
legalized to something else.
Differential Revision: https://reviews.llvm.org/D65132
llvm-svn: 366835
When we select the XRO variants of loads, we can pull in very specific shifts
(of the size of an element). E.g.
```
ldr x1, [x2, x3, lsl #3]
```
This teaches GISel to handle these when they're coming from shifts
specifically.
This adds a new addressing mode function, `selectAddrModeShiftedExtendXReg`
which recognizes this pattern.
This also packs this up with `selectAddrModeRegisterOffset` into
`selectAddrModeXRO`. This is intended to be equivalent to `selectAddrModeXRO`
in AArch64ISelDAGtoDAG.
Also update load-addressing-modes to show that all of the cases here work.
Differential Revision: https://reviews.llvm.org/D65119
llvm-svn: 366819
While lowering test.set.loop.iterations, it wasn't checked how the
brcond was using the result and so the wls could branch to the loop
preheader instead of not entering it. The same was true for
loop.decrement.reg.
So brcond and br_cc and now lowered manually when using the hwloop
intrinsics. During this we now check whether the result has been
negated and whether we're using SETEQ or SETNE and 0 or 1. We can
then figure out which basic block the WLS and LE should be targeting.
Differential Revision: https://reviews.llvm.org/D64616
llvm-svn: 366809
Replace float load/store pair with integer load/store pair when it's only used in load/store,
because float load/store instructions cost more cycles then integer load/store.
A typical scenario is when there is a call with more than 13 float arguments passing, we need pass them by stack.
So we need a load/store pair to do such memory operation if the variable is global variable.
Differential Revision: https://reviews.llvm.org/D64195
llvm-svn: 366775
The xform has no real valuewhen it's using out of a complex pattern
output. The complex pattern was already creating TargetConstants with
i16, so this was just unnecessary machinery.
This allows global isel to import the simple cases once the complex
pattern is implemented.
llvm-svn: 366743
The build_vector will become a constant pool load. By using the
desired type initially, it ensures we don't generate a bitcast
of the constant pool load which will need to be folded with
the load.
While experimenting with another patch, I noticed that when the
load type and the constant pool type don't match, then
SimplifyDemandedBits can't handle it. While we should probably
fix that, this was a simple way to fix the issue I saw.
llvm-svn: 366732
Summary:
Since we are planning to add ADDIStocHA for 32bit in later patch, we decided
to change 64bit one first to follow naming convention with 8 behind opcode.
Patch by: Xiangling_L
Differential Revision: https://reviews.llvm.org/D64814
llvm-svn: 366731
Stubs out a TargetLoweringObjectFileXCOFF class, implementing only
SelectSectionForGlobal for common symbols. Also adds an override of
EmitGlobalVariable in PPCAIXAsmPrinter which adds a number of defensive errors
and adds support for emitting common globals.
llvm-svn: 366727
ARMLowOverheadLoops would assert a failure if it did not find all the
pseudo instructions that comprise the hardware loop. Instead of doing
this, iterate through all the instructions of the function and revert
any remaining pseudo instructions that haven't been converted.
Differential Revision: https://reviews.llvm.org/D65080
llvm-svn: 366691
We need to ensure that the number of T's is correct when adding multiple
instructions into the same VPT block.
Differential revision: https://reviews.llvm.org/D65049
llvm-svn: 366684
This patch enables us to find the source loads for each element, splitting them into a Load and ByteOffset, and attempts to recognise consecutive loads that are in fact from the same source load.
A helper function, findEltLoadSrc, recurses to find a LoadSDNode and determines the element's byte offset within it. When attempting to match consecutive loads, byte offsetted loads then attempt to matched against a previous load that has already been confirmed to be a consecutive match.
Next step towards PR16739 - after this we just need to account for shuffling/repeated elements to create a vector load + shuffle.
Fixed out of bounds load assert identified in rL366501
Differential Revision: https://reviews.llvm.org/D64551
llvm-svn: 366681
ARM has code to recognise uses of the "returned" function parameter
attribute which guarantee that the value passed to the function in r0
will be returned in r0 unmodified. IPRA replaces the regmask on call
instructions, so needs to be told about this to avoid reverting the
optimisation.
Differential revision: https://reviews.llvm.org/D64986
llvm-svn: 366669
Summary:
In the atomic optimizer, save doing a bunch of work and generating a
bunch of dead IR in the fairly common case where the result of an
atomic op (i.e. the value that was in memory before the atomic op was
performed) is not used. NFC.
Reviewers: arsenm, dstuttard, tpr
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, t-tye, hiraditya, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64981
llvm-svn: 366667
As detailed on PR42674, we can reduce a vXi8 down until we have the final <8 x i8>, and then use PSADBW with zero, to sum those values. We then extract the bottom i8, discarding any overflow from the upper bits of the i16 result.
llvm-svn: 366636
Sometimes, you can end up with cross-bank copies between same-sized GPRs and
FPRs, which feed into G_STOREs. When these copies feed only into stores, they
aren't necessary; we can just store using the original register bank.
This provides some minor code size savings for some floating point SPEC
benchmarks. (Around 0.2% for 453.povray and 450.soplex)
This issue doesn't seem to show up due to regbankselect or anything similar. So,
this patch introduces an early select function, `contractCrossBankCopyIntoStore`
which performs the contraction when possible. The selector then continues
normally and selects the correct store opcode, eliminating needless copies
along the way.
Differential Revision: https://reviews.llvm.org/D65024
llvm-svn: 366625
Summary:
Add immutable WASM global `__tls_align` which stores the alignment
requirements of the TLS segment.
Add `__builtin_wasm_tls_align()` intrinsic to get this alignment in Clang.
The expected usage has now changed to:
__wasm_init_tls(memalign(__builtin_wasm_tls_align(),
__builtin_wasm_tls_size()));
Reviewers: tlively, aheejin, sbc100, sunfish, alexcrichton
Reviewed By: tlively
Subscribers: dschuff, jgravelle-google, hiraditya, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D65028
llvm-svn: 366624
This change reverts most of the previous register name generation.
The real problem is that RegisterTuple does not generate asm names.
Added optional operand to RegisterTuple. This way we can simplify
register name access and dramatically reduce the size of static
tables for the backend.
Differential Revision: https://reviews.llvm.org/D64967
llvm-svn: 366598
This should now handle everything except structs passed as multiple
registers.
I think most of the packing logic should be handled by
handleAssignments, but I'm unclear on what the contract is for
multiple registers. This is copying how x86 handles this.
This does change the behavior of the test_sgpr_alignment0 amdgpu_vs
test. I don't think shader arguments should try to follow the
alignment, and registers need to be repacked. I also don't think it
matters, since I think the pointers are packed to the beginning of the
argument list anyway.
llvm-svn: 366582
This is the more natural lowering, and presents more opportunities to
reduce 64-bit ops to 32-bit.
This should also help avoid issues graphics shaders have had with
64-bit values, and simplify argument lowering in globalisel.
llvm-svn: 366578
Summary:
For split-stack, if the nested argument (i.e. R10) is not used, no need to save/restore it in the prologue.
Reviewers: thanm
Reviewed By: thanm
Subscribers: mstorsjo, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64673
llvm-svn: 366569
We'd like to remove this whole function, because these are properties of
functions, not the target as a whole. These two are easy to remove
because they are only used for emitting ARM build attributes, which
expects them to represent the defaults for the whole module, not just
the last function generated.
This is needed to get correct build attributes when using IPRA on ARM,
because IPRA causes resetTargetOptions to get called before
ARMAsmPrinter::emitAttributes.
Differential revision: https://reviews.llvm.org/D64929
llvm-svn: 366562
Summary:
According to the new Armv8-M specification
https://static.docs.arm.com/ddi0553/bh/DDI0553B_h_armv8m_arm.pdf the
instructions SQRSHRL and UQRSHLL now have an additional immediate
operand <saturate>. The new assembly syntax is:
SQRSHRL<c> RdaLo, RdaHi, #<saturate>, Rm
UQRSHLL<c> RdaLo, RdaHi, #<saturate>, Rm
where <saturate> can be either 64 (the existing behavior) or 48, in
that case the result is saturated to 48 bits.
The new operand is encoded as follows:
#64 Encoded as sat = 0
#48 Encoded as sat = 1
sat is bit 7 of the instruction bit pattern.
This patch adds a new assembler operand class MveSaturateOperand which
implements parsing and encoding. Decoding is implemented in
DecodeMVEOverlappingLongShift.
Reviewers: ostannard, simon_tatham, t.p.northover, samparker, dmgreen, SjoerdMeijer
Reviewed By: simon_tatham
Subscribers: javed.absar, kristof.beyls, hiraditya, pbarrio, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64810
llvm-svn: 366555
It is necessary to generate fixups in .debug_frame or .eh_frame as
relaxation is enabled due to the address delta may be changed after
relaxation.
There is an opcode with 6-bits data in debug frame encoding. So, we
also need 6-bits fixup types.
Differential Revision: https://reviews.llvm.org/D58335
llvm-svn: 366524
I plan on adding memcpy optimizations in the GlobalISel pipeline, but we can't
do that unless we delay lowering to actual function calls. This patch changes
the translator to generate G_INTRINSIC_W_SIDE_EFFECTS for these functions, and
then have each target specify that using the new custom legalizer for intrinsics
hook that they want it expanded it a libcall.
Differential Revision: https://reviews.llvm.org/D64895
llvm-svn: 366516
Add support for folding G_GEPs into loads of the form
```
ldr reg, [base, off]
```
when possible. This can save an add before the load. Currently, this is only
supported for loads of 64 bits into 64 bit registers.
Add a new addressing mode function, `selectAddrModeRegisterOffset` which
performs this folding when it is profitable.
Also add a test for addressing modes for G_LOAD.
Differential Revision: https://reviews.llvm.org/D64944
llvm-svn: 366503
Summary:
Add `__builtin_wasm_tls_base` so that LeakSanitizer can find the thread-local
block and scan through it for memory leaks.
Reviewers: tlively, aheejin, sbc100
Subscribers: dschuff, jgravelle-google, hiraditya, sunfish, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D64900
llvm-svn: 366475
There doesn't seem to be a practical reason for these instructions to have
different restrictions on the types of relocations that they may be used
with, notwithstanding the language in the ELF AArch64 spec that implies that
specific relocations are meant to be used with specific instructions.
For example, we currently forbid the first instruction in the following
sequence, despite it currently being used by clang to generate a global
reference under -mcmodel=large:
movz x0, #:abs_g0_nc:foo
movk x0, #:abs_g1_nc:foo
movk x0, #:abs_g2_nc:foo
movk x0, #:abs_g3:foo
Therefore, allow MOVK/MOVN/MOVZ to accept the union of the set of relocations
that they currently accept individually.
Differential Revision: https://reviews.llvm.org/D64466
llvm-svn: 366461
It is necessary to generate fixups in .debug_frame or .eh_frame as
relaxation is enabled due to the address delta may be changed after
relaxation.
There is an opcode with 6-bits data in debug frame encoding. So, we
also need 6-bits fixup types.
Differential Revision: https://reviews.llvm.org/D58335
llvm-svn: 366442
This patch enables us to find the source loads for each element, splitting them into a Load and ByteOffset, and attempts to recognise consecutive loads that are in fact from the same source load.
A helper function, findEltLoadSrc, recurses to find a LoadSDNode and determines the element's byte offset within it. When attempting to match consecutive loads, byte offsetted loads then attempt to matched against a previous load that has already been confirmed to be a consecutive match.
Next step towards PR16739 - after this we just need to account for shuffling/repeated elements to create a vector load + shuffle.
Differential Revision: https://reviews.llvm.org/D64551
llvm-svn: 366441
LEA doesn't affect flags, so use it more liberally to replace an ADD when
we know that the ADD operands affect flags.
In the motivating example from PR40483:
https://bugs.llvm.org/show_bug.cgi?id=40483
...this lets us avoid duplicating a math op just to avoid flag conflict.
As mentioned in the TODO comments, this heuristic can be extended to
fire more often if that leads to more improvements.
Differential Revision: https://reviews.llvm.org/D64707
llvm-svn: 366431
Summary:
PerformVMOVRRDCombine ommits adding a offset
of 4 to the PointerInfo, when converting a
f64 = load[M]
to
{i32, i32} = {load[M], load[M + 4]}
Which would allow the machine scheduller
to break dependencies with the second load.
- pr42638
Reviewers: eli.friedman, dmgreen, ostannard
Reviewed By: ostannard
Subscribers: ostannard, javed.absar, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64870
llvm-svn: 366423
I'm not convinced the code this calls is properly vetted for
vXi1 vectors. Experimental vector widening legalization testing
for D55251 is now hitting an assertion failure inside
EltsFromConsecutiveLoads. This is occurring from a v2i1 load
having a store size different than its VT size. Hopefully
this commit will keep such issues from happening.
llvm-svn: 366405
Implement IR intrinsics for stack tagging. Generated code is very
unoptimized for now.
Two special intrinsics, llvm.aarch64.irg.sp and llvm.aarch64.tagp are
used to implement a tagged stack frame pointer in a virtual register.
Differential Revision: https://reviews.llvm.org/D64172
llvm-svn: 366360
Summary:
Since the target has no significant advantage of vectorization,
vector instructions bous threshold bonus should be optional.
amdgpu-inline-arg-alloca-cost parameter default value and the target
InliningThresholdMultiplier value tuned then respectively.
Reviewers: arsenm, rampitec
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, eraman, hiraditya, haicheng, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64642
llvm-svn: 366348
The original behavior was to always emit the offsets to each call site in the
call site table as uleb128 values, however on some architectures (eg RISCV)
these uleb128 offsets into the code cannot always be resolved until link time
(because relaxation will invalidate any calculated offsets), and there are no
appropriate relocations for uleb128 values. As a consequence it needs to be
possible to specify an alternative.
This also switches RISCV to use DW_EH_PE_udata4 for call side encodings in
.gcc_except_table
Differential Revision: https://reviews.llvm.org/D63415
Patch by Edward Jones.
llvm-svn: 366329
Summary:
Missed in the original commit, use the correct callee-saved register
list for spilling, instead of the standard SVR432 list. This avoids
needlessly spilling the SPE non-volatile registers when they're not used.
As part of this, also add where missing, and sort, the spill opcode
checks for SPE and SPE4 register classes.
Reviewers: nemanjai, hfinkel, joerg
Subscribers: kbarton, jsji, llvm-commits
Differential Revision: https://reviews.llvm.org/D56703
llvm-svn: 366319
Summary:
Pointed out in a comment for D49754, register spilling will currently
spill SPE registers at almost any offset. However, the instructions
`evstdd` and `evldd` require a) 8-byte alignment, and b) a limit of 256
(unsigned) bytes from the base register, as the offset must fix into a
5-bit offset, which ranges from 0-31 (indexed in double-words).
The update to the register spill test is taken partially from the test
case shown in D49754.
Additionally, pointed out by Kei Thomsen, globals will currently use
evldd/evstdd, though the offset isn't known at compile time, so may
exceed the 8-bit (unsigned) offset permitted. This fixes that as well,
by forcing it to always use evlddx/evstddx when accessing globals.
Part of the patch contributed by Kei Thomsen.
Reviewers: nemanjai, hfinkel, joerg
Subscribers: kbarton, jsji, llvm-commits
Differential Revision: https://reviews.llvm.org/D54409
llvm-svn: 366318
Add narrowScalar to half of original size for G_ICMP.
ClampScalar G_ICMP's operands 2 and 3 to to s32.
Select G_ICMP for pointers for MIPS32. Pointer compare is same
as for integers, it is enough to declare them as legal type.
Differential Revision: https://reviews.llvm.org/D64856
llvm-svn: 366317
Migrate CallLowering::lowerReturnVal to use the same infrastructure as
lowerCall/FormalArguments and remove the now obsolete code path from
splitToValueTypes.
Forgot to push this earlier.
llvm-svn: 366308
This directive forces to use the alternate register for context pointer.
For example, this code:
.cplocal $4
jal foo
expands to:
ld $25, %call16(foo)($4)
jalr $25
Differential Revision: https://reviews.llvm.org/D64743
llvm-svn: 366300
As well as other LLVM targets we do not handle "offsettable"
memory addresses in any special way. In other words, the "o" constraint
is an exact equivalent of the "m" one. But some existing code require
the "o" constraint support.
This fixes PR42589.
Differential Revision: https://reviews.llvm.org/D64792
llvm-svn: 366299
Summary:
Currently, on Emscripten, dynamic linking is not supported with threads.
This means that if thread-local storage is used, it must be used in a
statically-linked executable. Hence, local-exec is the only possible model.
This diff compiles all TLS variables to use local-exec on Emscripten as a
temporary measure until dynamic linking is supported with threads.
The goal for this is to allow C++ types with constructors to be thread-local.
Currently, when `clang` compiles a `thread_local` variable with a constructor,
it generates `__tls_guard` variable:
@__tls_guard = internal thread_local global i8 0, align 1
As no TLS model is specified, this is treated as general-dynamic, which we do
not support (and cannot support without implementing dynamic linking support
with threads in Emscripten). As a result, any C++ constructor in `thread_local`
variables would not compile.
By compiling all `thread_local` as local-exec, `__tls_guard` will compile and
we can support C++ constructors with TLS without implementing dynamic linking
with threads.
Depends on D64537
Reviewers: tlively, aheejin, sbc100
Reviewed By: aheejin
Subscribers: dschuff, jgravelle-google, hiraditya, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64776
llvm-svn: 366275
Summary:
Thread local variables are placed inside a `.tdata` segment. Their symbols are
offsets from the start of the segment. The address of a thread local variable
is computed as `__tls_base` + the offset from the start of the segment.
`.tdata` segment is a passive segment and `memory.init` is used once per thread
to initialize the thread local storage.
`__tls_base` is a wasm global. Since each thread has its own wasm instance,
it is effectively thread local. Currently, `__tls_base` must be initialized
at thread startup, and so cannot be used with dynamic libraries.
`__tls_base` is to be initialized with a new linker-synthesized function,
`__wasm_init_tls`, which takes as an argument a block of memory to use as the
storage for thread locals. It then initializes the block of memory and sets
`__tls_base`. As `__wasm_init_tls` will handle the memory initialization,
the memory does not have to be zeroed.
To help allocating memory for thread-local storage, a new compiler intrinsic
is introduced: `__builtin_wasm_tls_size()`. This instrinsic function returns
the size of the thread-local storage for the current function.
The expected usage is to run something like the following upon thread startup:
__wasm_init_tls(malloc(__builtin_wasm_tls_size()));
Reviewers: tlively, aheejin, kripken, sbc100
Subscribers: dschuff, jgravelle-google, hiraditya, sunfish, jfb, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D64537
llvm-svn: 366272
This is part of what is requested by PR42023:
https://bugs.llvm.org/show_bug.cgi?id=42023
There's an extension needed for FP add, but exactly how we would specify
that using flags is not clear to me, so I left that as a TODO.
We're still missing patterns for partial reductions when the input vector
is 256-bit or 512-bit, but I think that's a failure of vector narrowing.
If we can reduce the widths, then this matching should work on those tests.
Differential Revision: https://reviews.llvm.org/D64760
llvm-svn: 366268
Summary:
This is exposed by our internal testing.
The reduced testcase will assert with "Impossible reg-to-reg copy"
We can't use COPY to do 32-bit to 64-bit conversion.
Reviewers: kbarton, hfinkel, nemanjai
Reviewed By: hfinkel
Subscribers: hiraditya, MaskRay, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64499
llvm-svn: 366255
I think this manages to not break the DAG handling with the divergent
predicates because the stadalone divergent patterns end up with a
higher priority than the pattern on the instruction definition.
The 16-bit versions don't work yet.
llvm-svn: 366254
When it is AReg_1024 this results in unnecessary copying into
AGPRs of a 32 element vectors even though they are not intended
for an mfma instruction.
Differential Revision: https://reviews.llvm.org/D64815
llvm-svn: 366252
Now that the patterns use the new PatFrag address space support, the
only blocker to importing most load patterns is the addressing mode
complex patterns.
llvm-svn: 366237
Summary:
Extend the atomic optimizer to handle signed and unsigned max and min
operations, as well as add and subtract.
Reviewers: arsenm, sheredom, critson, rampitec
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64328
llvm-svn: 366235
Apparently the check for legal instructions during instruction
select does not happen without an asserts build, so these would
successfully select in release, and fail in debug.
Make s16 and/or/xor legal. These can just be selected directly
to the 32-bit operation, as is already done in SelectionDAG, so just
make them legal.
llvm-svn: 366210
The jcvt intrinsic defined in ACLE [1] is available when ARM_FEATURE_JCVT is defined.
This change introduces the AArch64 intrinsic, wires it up to the instruction and a new clang builtin function.
The __ARM_FEATURE_JCVT macro is now defined when an Armv8.3-A or higher target is used.
I've implemented the target detection logic in Clang so that this feature is enabled for architectures from armv8.3-a onwards (so -march=armv8.4-a also enables this, for example).
make check-all didn't show any new failures.
[1] https://developer.arm.com/docs/101028/latest/data-processing-intrinsics
Differential Revision: https://reviews.llvm.org/D64495
llvm-svn: 366197
The canonical GNU form of JALR resembles a load/store instruction rather
than placing the immediate offset as a separate argument, so match this
behaviour. Also add parser-only aliases for the three-operand form, and
add other shorter aliases also emitted by GNU tools.
Differential Revision: https://reviews.llvm.org/D55277
Patch by James Clarke.
llvm-svn: 366179
RISCVAsmBackend::shouldInsertExtraNopBytesForCodeAlign() assumed that the
align specified would be greater than or equal to the minimum nop length, but
that is not always the case - for example if a user specifies ".align 0" in
assembly.
Differential Revision: https://reviews.llvm.org/D63274
Patch by Edward Jones.
llvm-svn: 366176
The bool result of shouldInsertExtraNopBytesForCodeAlign() is not checked but
the returned nop count is unconditionally read even though it could be
uninitialized.
Differential Revision: https://reviews.llvm.org/D63285
Patch by Edward Jones.
llvm-svn: 366175
Since PseudoCALL defines AsmString, it can be generated from assembly,
and so code-gen patterns should be defined separately to be consistent
with the style of the RISCV backend. Other pseudo-instructions exist
that have code-gen patterns defined directly, but these instructions are
purely for code-gen and cannot be written in assembly.
Differential Revision: https://reviews.llvm.org/D64012
Patch by James Clarke.
llvm-svn: 366174
Previously, this function didn't check the IsPCRel argument. But doing so is a
useful check for errors, and also seemingly necessary for FK_Data_4 (which we
produce a R_RISCV_32_PCREL relocation for if IsPCRel).
Other than R_RISCV_32_PCREL, this should be NFC. Future exception handling
related patches will include tests that capture this behaviour.
llvm-svn: 366172
Use the MemoryVT field. This will be necessary for tablegen to
automatically handle patterns for GlobalISel.
Doesn't handle the d16 lo/hi patterns. Those are a special case since
it involvess the custom node type.
llvm-svn: 366168
We mostly avoid sub with immediate but there are a couple cases that can create them. One is the add 128, %rax -> sub -128, %rax trick in isel. The other is when a SUB immediate gets created for a compare where both the flags and the subtract value is used. If we are unable to linearize the SelectionDAG to satisfy the flag user and the sub result user from the same instruction, we will clone the sub immediate for the two uses. The one that produces flags will eventually become a compare. The other will have its flag output dead, and could then be considered for LEA creation.
I added additional test cases to add.ll to show the the sub -128 trick gets converted to LEA and a case where we don't need to convert it.
This showed up in the current codegen for PR42571.
Differential Revision: https://reviews.llvm.org/D64574
llvm-svn: 366151
Summary:
This adds missing utility methods and copy instruction handling for
`exnref` type and also adds tests.
`tee` instruction tests are missing because `isTee` is currently only
used in ExplicitLocals pass and testing that pass in mir requires
serialization of stackified registers in mir files, which is a bit
nontrivial because `MachineFunctionInfo` only has info of vreg numbers
(which are large integers) but not the mir's register numbers. But this
change is quite trivial anyway.
Reviewers: tlively
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64705
llvm-svn: 366149
Summary:
We agreed to rename `except_ref` to `exnref` for consistency with other
reference types in
https://github.com/WebAssembly/exception-handling/issues/79. This also
renames WebAssemblyInstrExceptRef.td to WebAssemblyInstrRef.td in order
to use the file for other reference types in future.
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, hiraditya, sunfish, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64703
llvm-svn: 366145
Summary:
These are emitted as identifiers by the InstPrinter, so we should
parse them as such. These could potentially clash with symbols of
the same name, but that is out of our (the WebAssembly backend) control.
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, aheejin, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64770
llvm-svn: 366139
Summary:
Enable hoisting and merging m0 defs that are initialized with the same
immediate value. Fixes bug where removed instructions are not considered
to interfere with other inits, and make sure to not hoist inits before block
prologues.
Reviewers: rampitec, arsenm
Reviewed By: rampitec
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64766
llvm-svn: 366135
We already do this for the flat and DS instructions, although it is
certainly uglier and more verbose.
This will allow using separate pattern definitions for extload and
zextload. Currently we get away with using a single PatFrag with
custom predicate code to check if the extension type is a zextload or
anyextload. The generic mechanism the global isel emitter understands
treats these as mutually exclusive. I was considering making the
pattern emitter accept zextload or sextload extensions for anyextload
patterns, but in global isel, the different extending loads have
distinct opcodes, and there is currently no mechanism for an opcode
matcher to try multiple (and there probably is very little need for
one beyond this case).
llvm-svn: 366132
If a 1-bit value is in a 32-bit VGPR, the scalar opcodes set SCC to
whether the result is 0. If the inputs are SCC, these can be copied to
a 32-bit SGPR to produce an SCC result.
llvm-svn: 366125
This is a hack until I come up with a better way of dealing with the
pseudo-register banks used for boolean values. If the use instruction
constrains the register, the selector for the def instruction won't
see that the bank was VCC. A 1-bit SReg_32 is could ambiguously have
been SCCRegBank or VCCRegBank in wave32.
This is necessary to successfully select branches with and and/or/xor
condition.
llvm-svn: 366120
The extra test change is correct, although how it arrives there is a
bug that needs work. With wave32, the test for isVCC ambiguously
reports true for an SCC or VCC source. A new allocatable pseudo
register class for SCC may be necesssary.
llvm-svn: 366119
We need to make sure that we are sensibly dealing with vectors of types v2i64
and v2f64, even if most of the time we cannot generate native operations for
them. This mostly adds a lot of testing, plus fixes up a couple of the issues
found. And, or and xor can be legal for v2i64, and shifts combining needs a
slight fixup.
Differential Revision: https://reviews.llvm.org/D64316
llvm-svn: 366106
inttofp (trunc (extelt X, 0)) --> inttofp (extelt (bitcast X), 0)
We have pseudo-vectorization of scalar int to FP casts, so this tries to
make that more likely by replacing a truncate with a bitcast. I didn't see
any test diffs starting from 'uitofp', so I left that as a TODO. We can't
only match the shorter trunc+extract pattern because there's an opposing
transform somewhere, so we infinite loop. Waiting to try this during
lowering is another possibility.
A motivating case is shown in PR39975 and included in the test diffs here:
https://bugs.llvm.org/show_bug.cgi?id=39975
Differential Revision: https://reviews.llvm.org/D64710
llvm-svn: 366098
I think we only turn out of range shiftss to undef when
all elements are out of range or the shift amount is a splat out
of range. I'm not sure which, I didn't check.
During lowering we can split a shift where some elements
are out of range into multiple shifts. This can create a
new shift with a splat shift amount that is out of range.
This patch returns undef for this case.
Fixes PR42615.
Differential Revision: https://reviews.llvm.org/D64699
llvm-svn: 366096
Insert these during codegenprepare.
This works around a DAG issue where generic combines eliminate the and
asserting the high bits are zero, which then exposes an unknown read
source to the mul combine. It doesn't worth the hassle of trying to
insert an AssertZext or something to try to deal with it.
llvm-svn: 366094
This adds basic lowering for MVE shifts. There are many shifts in MVE, but the
instructions handled here are:
VSHL (imm)
VSHRu (imm)
VSHRs (imm)
VSHL (vector)
VSHL (register)
MVE, like NEON before it, doesn't have shift right by a vector (or register).
We instead have to negate the amount and shift in the opposite direction. This
means we have to convert any SHR's into a form of SHL (that is still signed or
unsigned) with a negated condition and selecting from there. MVE still does
have shifting by an immediate for SHL, ASR and LSR.
This adds lowering for these and for register forms, which work well for shift
lefts but may require an extra fold of neg(vdup(x)) -> vdup(neg(x)) to potentially
work optimally for right shifts.
Differential Revision: https://reviews.llvm.org/D64212
llvm-svn: 366056
This just moves the shift instruction definitions further down the
ARMInstrMVE.td file, to make positioning patterns slightly more natural.
llvm-svn: 366054
This adjusts the way that we lower NEON shifts to use a DAG target node, not
via a neon intrinsic. This is useful for handling MVE shifts operations in the
same the way. It also renames some of the immediate shift nodes for
consistency, and moves some of the processing of immediate shifts into
LowerShift allowing it to capture more cases.
Differential Revision: https://reviews.llvm.org/D64426
llvm-svn: 366051
Summary:
SSE1 only supports v4f32. But does have instructions like movlps/movhps that load/store 64-bits of memory.
This patch breaks the connection between the node VT of the vzext_load/vextract_store patterns and the memory VT. Enabling a v4f32 node with a 64-bit memory VT. I've used i64 as the memory VT here. I've written the PatFrag predicate to just check the store size not the specific VT. I think the VT will only matter for CSE purposes. We could use v2f32, but if we want to start using these operations in more places a simple integer type might make the most sense.
I'd like to maybe use this same thing for SSE2 and later as well, but that will need more work to be supported by EltsFromConsecutiveLoads to avoid regressing lit tests. I'd maybe also like to combine bitcasts with these load/stores nodes now that the types are disconnected. And I'd also like to consider canonicalizing (scalar_to_vector + load) to vzext_load.
If you want I can split the mechanical tablegen stuff where I added the 32/64 off from the sse1 change.
Reviewers: spatel, RKSimon
Reviewed By: RKSimon
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64528
llvm-svn: 366034
The vmovlb instructions can be uses to sign or zero extend vector registers
between types. This adds some patterns for them and relevant testing. The
VBICIMM generation is also put behind a hasNEON check (as is already done for
VORRIMM).
Code originally by David Sherwood.
Differential Revision: https://reviews.llvm.org/D64069
llvm-svn: 366008
This selects integer VNEG instructions, which can be especially useful with shifts.
Differential Revision: https://reviews.llvm.org/D64204
llvm-svn: 366006
This simply makes the MVE integer min and max instructions legal and adds the
relevant patterns for them.
Differential Revision: https://reviews.llvm.org/D64026
llvm-svn: 366004
This adds support for the floor/ceil/trunc/... series of instructions,
converting to various forms of VRINT. They use the same suffixes as their
floating point counterparts. There is not VTINTR, so nearbyint is expanded.
Also added a copysign test, to show it is expanded.
Differential Revision: https://reviews.llvm.org/D63985
llvm-svn: 366003
This adds the patterns for minnm and maxnm from the fminnum and fmaxnum nodes,
similar to scalar types.
Original patch by Simon Tatham
Differential Revision: https://reviews.llvm.org/D63870
llvm-svn: 366002
These should really use v32f32, but were defined as v32i32
due to the lack of the v32f32 type.
Differential Revision: https://reviews.llvm.org/D64667
llvm-svn: 365972
Summary:
Most of these functions can work for MachineInstr and MCInst
equally now.
Reviewers: dschuff
Subscribers: MatzeB, sbc100, jgravelle-google, aheejin, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64643
llvm-svn: 365965
Split AArch64FrameLowering::resolveFrameIndexReference in two parts
* Finding frame offset for the index.
* Finding base register and offset to that register.
The second part will be used to implement a virtual frame pointer in
armv8.5 MTE stack instrumentation lowering.
Reviewers: pcc, vitalybuka, hctim, ostannard
Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64171
llvm-svn: 365958
Before 2018, mesa used to use byval interchangably with inreg, which
didn't really make sense. Fix tests still using it to avoid breaking
in a future commit.
llvm-svn: 365953
This fixes https://bugs.llvm.org/show_bug.cgi?id=42606 by extending
D64213. Instead of only checking if the carry comes from a matching
operation, we now check the full chain of carries. Otherwise we might
custom lower the outermost addcarry, but then generically legalize
an inner addcarry.
Differential Revision: https://reviews.llvm.org/D64658
llvm-svn: 365949
This patch series adds support for the next-generation arch13
CPU architecture to the SystemZ backend.
This includes:
- Basic support for the new processor and its features.
- Assembler/disassembler support for new instructions.
- CodeGen for new instructions, including new LLVM intrinsics.
- Scheduler description for the new processor.
- Detection of arch13 as host processor.
Note: No currently available Z system supports the arch13
architecture. Once new systems become available, the
official system name will be added as supported -march name.
llvm-svn: 365932
We can use the C flag from NEG to detect that the input was zero.
Really we could probably use the Z flag too. But C matches what
we'd do for usubo 0, X.
Haven't found a test case for this due to the usubo formation
in CGP. But I verified if I comment out the CGP code this
transformation catches some of the same cases.
llvm-svn: 365929
Summary:
r363675 changed the exec modification helper function, now called
execMayBeModifiedBeforeUse, so that if no UseMI is specified it checks
all instructions in the basic block, even beyond the last use. That
meant that the DPP combiner no longer worked in any basic block that
ended with a control flow instruction, and in particular it didn't work
on code sequences generated by the atomic optimizer.
Fix it by reinstating the old behaviour but in a new helper function
execMayBeModifiedBeforeAnyUse, and limiting the number of instructions
scanned.
Reviewers: arsenm, vpykhtin
Subscribers: kzhuravl, nemanjai, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kbarton, MaskRay, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64393
llvm-svn: 365910
Summary:
D64497 allowed abs/neg source modifiers on v_cndmask_b32 but it doesn't
make any sense to apply them to f16 operands; they would interpret the
bits of the value as an f32, giving nonsensical results. This patch
restricts them to f32 operands.
Reviewers: arsenm, hakzsam
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64636
llvm-svn: 365904
Summary:
Useful for jumps, such as `j .`.
I am not sure who should review this. Do not hesitate to change the reviewers if needed.
Reviewers: asb, jrtc27, lenary
Reviewed By: lenary
Subscribers: MaskRay, lenary, hiraditya, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, Jim, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63669
Patch by John LLVM (JohnLLVM)
llvm-svn: 365881
There is not match for the `MipsJmpLink texternalsym` and `MipsJmpLink
tglobaladdr` patterns for microMIPS R6. As a result LLVM incorrectly
selects the `JALRC16` compact 2-byte instruction which takes a target
instruction address from a register only and assign `R_MIPS_32` relocation
for this instruction. This relocation completely overwrites `JALRC16`
and nearby instructions.
This patch adds missed matching patterns, selects `BALC` instruction and
assign a correct `R_MICROMIPS_PC26_S1` relocation.
Differential Revision: https://reviews.llvm.org/D64552
llvm-svn: 365870
Follow up to D58597, where it was noted that the commuted ISD::SUB variant
was having problems with lack of combines.
See also D63958 where we untangled setcc/sub pairs.
Differential Revision: https://reviews.llvm.org/D58875
llvm-svn: 365791
Summary:
As of binutils 2.32, ld has a bogus TLS relaxation error when the GD/LD
code sequence using R_X86_64_GOTPCREL (instead of R_X86_64_GOTPCRELX) is
attempted to be relaxed to IE/LE (binutils PR24784). gold and lld are good.
In gcc/config/i386/i386.md, there is a configure-time check of as/ld
support and the GOT relaxation will not be used if as/ld doesn't support
it:
if (flag_plt || !HAVE_AS_IX86_TLS_GET_ADDR_GOT)
return "call\t%P2";
return "call\t{*%p2@GOT(%1)|[DWORD PTR %p2@GOT[%1]]}";
In clang, -DENABLE_X86_RELAX_RELOCATIONS=OFF is the default. The ld.bfd
bogus error can be reproduced with:
thread_local int a;
int main() { return a; }
clang -fno-plt -fpic a.cc -fuse-ld=bfd
GOTPCRELX gained relative good support in 2016, which is considered
relatively new. It is even difficult to conditionally default to
-DENABLE_X86_RELAX_RELOCATIONS=ON due to cross compilation reasons. So
work around the ld.bfd bug by only using GOT when GOTPCRELX is enabled.
Reviewers: dalias, hjl.tools, nikic, rnk
Reviewed By: nikic
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64304
llvm-svn: 365752
This patch addresses a couple of problems:
1) The maximum supported offset of LE is -4094.
2) The offset of WLS also needs to be checked, this uses a
maximum positive offset of 4094.
The use of BasicBlockUtils has been changed because the block offsets
weren't being initialised, but the isBBInRange checks both positive
and negative offsets.
ARMISelLowering has been tweaked because the test case presented
another pattern that we weren't supporting.
llvm-svn: 365749
The VQDMLAH.U8, VQDMLAH.U16 and VQDMLAH.U32 instructions don't
actually exist: the Armv8.1-M architecture spec only lists signed
forms of that instruction. The unsigned ones were added in error: they
existed in an early draft of the spec, but they were removed before
the public version, and we missed that particular spec change.
Also affects the variant forms VQDMLASH, VQRDMLAH and VQRDMLASH.
Reviewers: miyuki
Subscribers: javed.absar, kristof.beyls, hiraditya, dmgreen, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64502
llvm-svn: 365747
Skip copies between virtual registers during search for UseDefs
and DefUses.
Since each operand has one def search for UseDefs is straightforward.
But since operand can have many uses, we have to check all uses of
each copy we traverse during search for DefUses.
Differential Revision: https://reviews.llvm.org/D64486
llvm-svn: 365744
When one of the uses/defs of ambiguous instruction is also ambiguous
visit it recursively and search its uses/defs for instruction with
only one mapping available.
When all instruction in a chain are ambiguous arbitrary mapping can
be selected. For s64 operands in ambiguous chain fprb is selected since
it results in less instructions then having to narrow scalar s64 to s32.
For s32 both gprb and fprb result in same number of instructions and
gprb is selected like a general purpose option.
At the moment we always avoid cross register bank copies.
TODO: Implement a model for costs calculations of different mappings
on same instruction and cross bank copies. Allow cross bank copies
when appropriate according to cost model.
Differential Revision: https://reviews.llvm.org/D64485
llvm-svn: 365743
Two functional changes have been made here:
- Now search up from any add instruction to find the chains of
operations that we may turn into a smlad. This allows the
generation of a smlad which doesn't accumulate into a phi.
- The search function has been corrected to stop it falsely searching
up through an invalid path.
The bulk of the changes have been making the Reduction struct a class
and making it more C++y with getters and setters.
Differential Revision: https://reviews.llvm.org/D61780
llvm-svn: 365740
Summary:
Wasm does not currently support `llvm.clear_cache` intrinsic, and this
prints a proper error message instead of segfault.
Reviewers: dschuff, sbc100, sunfish
Subscribers: jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64322
llvm-svn: 365731
We use the functions that convert to three address to do the
conversion, but changing an 8 or 16 bit will cause it to create
a virtual register. This can't be done after register allocation
where this pass runs.
I've switched the pass completely to a white list of instructions
that can be converted to LEA instead of a blacklist that was
incorrect. This will avoid surprises if we enhance the three
address conversion function to include additional instructions
in the future.
Fixes PR42565.
llvm-svn: 365720
Unfortunately subo formation in CGP prevents obvious ways of
testing this.
But we already have BLSI in here and the flag behavior is
well understood.
Might become more useful if we improve PR42571.
llvm-svn: 365702
Summary: llvm/IR/GlobalValue.h can't be included in MC, that creates a circular dependency between MC and IR libraries. This circular dependency is causing an issue for build system that enforce layering.
Author: Xiangling_L
Reviewers: sfertile, jasonliu, hubert.reinterpretcast, gribozavr
Reviewed By: gribozavr
Subscribers: wuzish, nemanjai, hiraditya, kbarton, MaskRay, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64445
llvm-svn: 365701
Since we have distinct types for pointers and scalars, G_INTTOPTRs can sometimes
obstruct attempts to find constant source values. These usually come about when
try to do some kind of null pointer check. Teaching getConstantVRegValWithLookThrough
about this operation allows the CBZ/CBNZ optimization to catch more cases.
This change also improves the case where we can't find a constant source at all.
Previously we would emit a cmp, cset and tbnz for that. Now we try to just emit
a cmp and conditional branch, saving an instruction.
The cumulative code size improvement of this change plus D64354 is 5.5% geomean
on arm64 CTMark -O0.
Differential Revision: https://reviews.llvm.org/D64377
llvm-svn: 365690
Some minor cleanup.
This function in Utils does the same thing as `findMIFromReg`. It also looks
through copies, which `findMIFromReg` didn't.
Delete `findMIFromReg` and use `getOpcodeDef` instead. This only happens in
`tryOptVectorDup` right now.
Update opt-shuffle-splat to show that we can look through the copies now, too.
Differential Revision: https://reviews.llvm.org/D64520
llvm-svn: 365684
There are a few places where we walk over copies throughout
AArch64InstructionSelector.cpp. In Utils, there's a function that does exactly
this which we can use instead.
Note that the utility function works with the case where we run into a COPY
from a physical register. We've run into bugs with this a couple times, so using
it should defend us from similar future bugs.
Also update opt-fold-compare.mir to show that we still handle physical registers
properly.
Differential Revision: https://reviews.llvm.org/D64513
llvm-svn: 365683
Rework the TTI cache and software prefetching APIs to prepare for the
introduction of a general system model. Changes include:
- Marking existing interfaces const and/or override as appropriate
- Adding comments
- Adding BasicTTIImpl interfaces that delegate to a subtarget
implementation
- Adding a default "no information" subtarget implementation
Only a handful of targets use these interfaces currently: AArch64,
Hexagon, PPC and SystemZ. AArch64 already has a custom subtarget
implementation, so its custom TTI implementation is migrated to use
the new facilities in BasicTTIImpl to invoke its custom subtarget
implementation. The custom TTI implementations continue to exist for
the other targets with this change. They are not moved over to
subtarget-based implementations.
The end goal is to have the default subtarget implementation defer to
the system model defined by the target. With this change, the default
subtarget implementation essentially returns "no information" for
these interfaces. None of the existing users of TTI will hit that
implementation because they define their own custom TTI
implementations and won't use the BasicTTIImpl implementations.
Once system models are in place for the targets that use these
interfaces, their custom TTI implementations can be removed.
Differential Revision: https://reviews.llvm.org/D63614
llvm-svn: 365676
This renames the type so it doesn't sound like its based off the load size - as we're moving towards supporting combining loads of different sizes.
llvm-svn: 365655
Summary:
D59191 added support for these modifiers in the assembler and
disassembler. This patch just teaches instruction selection that it can
use them.
Reviewers: arsenm, tstellar
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64497
llvm-svn: 365640
Cache the LoadSDNode nodes so we can easily map to/from the element index instead of packing them together - this will be useful for future patches for PR16739 etc.
llvm-svn: 365620
This patch checks to see if the vector element loads are based off a dereferenceable pointer that covers the entire vector width, in which case we don't need to have element loads at both extremes of the vector width - just the start (base pointer) of it.
Another step towards partial vector loads......
Differential Revision: https://reviews.llvm.org/D64205
llvm-svn: 365614
Summary:
Use the same predicates as VSTMDB/VLDMIA since VPUSH/VPOP alias to
these.
Patch by Momchil Velikov.
Reviewers: ostannard, simon_tatham, SjoerdMeijer, samparker, t.p.northover, dmgreen
Reviewed By: dmgreen
Subscribers: javed.absar, kristof.beyls, hiraditya, dmgreen, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64413
llvm-svn: 365604
In SelectionDAG AMDGPU treated these as legal, but this was mostly
because the bitcasts required for FP types were painful. Theoretically
the bitpattern should eventually match to bfi, so don't bother trying
to get the patterns to import.
llvm-svn: 365583
This should prevent doing this on pre-sse4.1 targets or for 256
bit vectors without avx2.
I don't know of a failure from this. Op legalization will probably
take care of, but seemed better to be safe.
llvm-svn: 365577
A short granule is a granule of size between 1 and `TG-1` bytes. The size
of a short granule is stored at the location in shadow memory where the
granule's tag is normally stored, while the granule's actual tag is stored
in the last byte of the granule. This means that in order to verify that a
pointer tag matches a memory tag, HWASAN must check for two possibilities:
* the pointer tag is equal to the memory tag in shadow memory, or
* the shadow memory tag is actually a short granule size, the value being loaded
is in bounds of the granule and the pointer tag is equal to the last byte of
the granule.
Pointer tags between 1 to `TG-1` are possible and are as likely as any other
tag. This means that these tags in memory have two interpretations: the full
tag interpretation (where the pointer tag is between 1 and `TG-1` and the
last byte of the granule is ordinary data) and the short tag interpretation
(where the pointer tag is stored in the granule).
When HWASAN detects an error near a memory tag between 1 and `TG-1`, it
will show both the memory tag and the last byte of the granule. Currently,
it is up to the user to disambiguate the two possibilities.
Because this functionality obsoletes the right aligned heap feature of
the HWASAN memory allocator (and because we can no longer easily test
it), the feature is removed.
Also update the documentation to cover both short granule tags and
outlined checks.
Differential Revision: https://reviews.llvm.org/D63908
llvm-svn: 365551
Basically the problem is that X86 doesn't set the Fast flag from
allowsMemoryAccess on certain CPUs due to slow unaligned memory
subtarget features. This prevents bitcasts from being folded into
loads and stores. But all vector loads and stores of the same width
are the same cost on X86.
This patch merges the allowsMemoryAccess call into isLoadBitCastBeneficial to allow X86 to skip it.
Differential Revision: https://reviews.llvm.org/D64295
llvm-svn: 365549
Stubs out a number of the classes needed to produce a new object file format
(XCOFF) for the powerpc-aix target. For testing input is an empty module which
produces an object file with just a file header.
Differential Revision: https://reviews.llvm.org/D61694
llvm-svn: 365541
Function return instruction lowering, currently uses the fixed register pair s[30:31] for holding
the return address. It can be any SGPR pair other than the CSRs. Created an SGPR pair sub-register class
exclusive of the CSRs, and used this regclass while lowering the return instruction.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D63924
llvm-svn: 365512
Summary:
There was an error being thrown from isDesirableToCommuteWithShift in
some tests. This was tracked down to the method being called before
legalisation, with an extended value type, not a machine value type.
In the case I diagnosed, the error was only hit with an instruction sequence
involving `i24`s in the add and shift. `i24` is not a Machine ValueType, it is
instead an Extended ValueType which was causing the issue.
I have added a test to cover this case, and fixed the error in the callback.
Reviewers: asb, luismarques
Reviewed By: asb
Subscribers: hiraditya, rbar, johnrusso, simoncook, apazos, sabuasal, niosHD, kito-cheng, shiva0217, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, rkruppe, PkmX, jocewei, psnobl, benna, Jim, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64425
llvm-svn: 365511
If we have an icmp->brcond->br sequence where the brcond just branches to the
next block jumping over the br, while the br takes the false edge, then we can
modify the conditional branch to jump to the br's target while inverting the
condition of the incoming icmp. This means we can eliminate the br as an
unconditional branch to the fallthrough block.
Differential Revision: https://reviews.llvm.org/D64354
llvm-svn: 365510
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
Select gprb or fprb when def/use register operand of G_PHI is
used/defined by either:
copy to/from physical register or
instruction with only one mapping available for that use/def operand.
Integer s64 phi is handled with narrowScalar when mapping is applied,
produced artifacts are combined away. Manually set gprb to all register
operands of instructions created during narrowScalar.
Differential Revision: https://reviews.llvm.org/D64351
llvm-svn: 365494
Select gprb or fprb when def/use register operand of G_SELECT is
used/defined by either:
copy to/from physical register or
instruction with only one mapping available for that use/def operand.
Integer s64 select is handled with narrowScalar when mapping is applied,
produced artifacts are combined away. Manually set gprb to all register
operands of instructions created during narrowScalar.
For selection of floating point s32 or s64 select it is enough to set
fprb of appropriate size and selectImpl will do the rest.
Differential Revision: https://reviews.llvm.org/D64350
llvm-svn: 365492
The `sge/sgeu Dst, Src1, Src2/Imm` pseudo instructions set register
`Dst` to 1 if register `Src1` is greater than or equal `Src2/Imm` and
to 0 otherwise.
Differential Revision: https://reviews.llvm.org/D64314
llvm-svn: 365476
The `sgt/sgtu Dst, Src1, Src2/Imm` pseudo instructions set register
`Dst` to 1 if register `Src1` is greater than `Src2/Imm` and to 0 otherwise.
Differential Revision: https://reviews.llvm.org/D64313
llvm-svn: 365475
Dump the DWARF information about call sites and call site parameters into
debug info sections.
The patch also provides an interface for the interpretation of instructions
that could load values of a call site parameters in order to generate DWARF
about the call site parameters.
([13/13] Introduce the debug entry values.)
Co-authored-by: Ananth Sowda <asowda@cisco.com>
Co-authored-by: Nikola Prica <nikola.prica@rt-rk.com>
Co-authored-by: Ivan Baev <ibaev@cisco.com>
Differential Revision: https://reviews.llvm.org/D60716
llvm-svn: 365467
APInt::getSExtValue will assert if getMinSignedBits() > 64. This can happen,
for instance, if examining an i128. Avoid this assertion by checking
Imm.getMinSignedBits() <= 64 before doing
getTLI()->isLegalAddImmediate(Imm.getSExtValue()). We could directly check
getMinSignedBits() <= 12 but it seems better to reuse the isLegalAddImmediate
helper for this.
Differential Revision: https://reviews.llvm.org/D64390
llvm-svn: 365462
Summary:
`extsw` and `sldi` are supposed to be combined if they are in the same
BB in instruction selection phase. This patch handles the case where
extsw and sldi are not in the same BB.
Differential Revision: https://reviews.llvm.org/D63806
llvm-svn: 365430
Summary:
Even with functions with `no-prototype` attribute, there can be an
argument `sret` (structure return) attribute, which is an optimization
when a function return type is a struct. Fixes PR42420.
Reviewers: sbc100
Subscribers: dschuff, jgravelle-google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64318
llvm-svn: 365426
Porting over the part of `emitComparison` in AArch64ISelLowering where we use
TST to represent a compare.
- Rename `tryOptCMN` to `tryFoldIntegerCompare`, since it now also emits TSTs
when possible.
- Add a utility function for emitting a TST with register operands.
- Rename opt-fold-cmn.mir to opt-fold-compare.mir, since it now also tests the
TST fold as well.
Differential Revision: https://reviews.llvm.org/D64371
llvm-svn: 365404
Summary:
This makes it so that IR files using triples without an environment work
out of the box, without normalizing them.
Typically, the MSVC behavior is more desirable. For example, it tends to
enable things like constant merging, use of associative comdats, etc.
Addresses PR42491
Reviewers: compnerd
Subscribers: hiraditya, dexonsmith, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64109
llvm-svn: 365387
Make the FP register callee saved.
This is tricky because now the FP needs to be spilled in the prolog
relative to the incoming SP register, rather than the frame register
used throughout the rest of the function. I don't like how this
bypassess the standard mechanism for CSR spills just to get the
correct insert point. I may look for a better solution, since all CSR
VGPRs may also need to have all lanes activated. Another option might
be to make getFrameIndexReference change the base register if the
frame index is a CSR, and then try to figure out the right insertion
point in emitProlog.
If there is a free VGPR lane available for SGPR spilling, try to use
it for the FP. If that would require intrtoducing a new VGPR spill,
try to use a free call clobbered SGPR. Only fallback to introducing a
new VGPR spill as a last resort.
This also doesn't attempt to handle SGPR spilling with scalar stores.
llvm-svn: 365372
Summary:
Before, they were one category of operands which could cause
crashes in non-sensical combinations, e.g. "f32.const symbol".
Now these are forced to be an error.
Reviewers: dschuff
Subscribers: sbc100, jgravelle-google, aheejin, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64039
llvm-svn: 365351
Select gprb or fprb when loaded value is used by either:
copy to physical register or
instruction with only one mapping available for that use operand.
Load of integer s64 is handled with narrowScalar when mapping is applied,
produced artifacts are combined away. Manually set gprb to all register
operands of instructions created during narrowScalar.
Differential Revision: https://reviews.llvm.org/D64269
llvm-svn: 365323
Select gprb or fprb when stored value is defined by either:
copy from physical register or
instruction with only one mapping available for that def operand.
Store of integer s64 is handled with narrowScalar when mapping is applied,
produced artifacts are combined away. Manually set gprb to all register
operands of instructions created during narrowScalar.
Differential Revision: https://reviews.llvm.org/D64268
llvm-svn: 365322
Summary of changes:
- simplified handling of FLAT offset: offset_s13 and offset_u12 have been replaced with flat_offset;
- provided information about error position for pre-gfx9 targets;
- improved errors handling.
Reviewers: artem.tamazov, arsenm, rampitec
Differential Revision: https://reviews.llvm.org/D64244
llvm-svn: 365321
Summary:
According to a recently updated Armv8-M spec
(https://static.docs.arm.com/ddi0553/bh/DDI0553B_h_armv8m_arm.pdf) the
32-bit width versions of the following instructions:
* VQDMLADH
* VQDMLADHX
* VQRDMLADH
* VQRDMLADHX
* VQDMLSDH
* VQDMLSDHX
* VQRDMLSDH
* VQRDMLSDHX
are no longer unpredictable when their output register is the same as
one of the input registers.
This patch updates the assembler parser and the corresponding tests
and also removes @earlyclobber from the instruction constraints.
Reviewers: simon_tatham, ostannard, dmgreen, SjoerdMeijer, samparker
Reviewed By: simon_tatham
Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64250
llvm-svn: 365306
Defines RISCV registers for getExceptionPointerRegister() and
getExceptionSelectorRegister().
Differential Revision: https://reviews.llvm.org/D63411
Patch by Edward Jones.
Modified by Alex Bradbury to add CHECK lines to exception-pointer-register.ll.
llvm-svn: 365301
This can help avoid a copy or enable load folding.
On SSE4.1 targets we can commute it to blendi instead.
I had to make shufpd with a 0x02 immediate commutable as well
since we expect commuting to be reversible.
llvm-svn: 365292
These patterns are the same as the MOVLPDmr and MOVHPDmr patterns,
but with a bitcast at the end. We can just select the PD instruction
and let execution domain fixing switch to PS.
llvm-svn: 365267
These narrow the load so we can only do it if the load isn't
volatile.
There also tests in vector-shuffle-128-v4.ll that this should
support, but we don't seem to fold bitcast+load on pre-sse4.2
targets due to the slow unaligned mem 16 flag.
llvm-svn: 365266
Only custom lower uaddo+addcarry or usubo+subcarry chains and leave
mixtures like usubo+addcarry or uaddo+subcarry to the generic
legalizer. Otherwise we run into issues because SystemZ uses
different CC values for carries and borrows.
Fixes https://bugs.llvm.org/show_bug.cgi?id=42512.
Differential Revision: https://reviews.llvm.org/D64213
llvm-svn: 365242
Add a string attribute instead of directly setting
MachineFunctionInfo. This avoids trying to get the analysis in the
MachineFunctionInfo in a way that doesn't work with the new pass
manager.
This will also avoid re-visiting the call graph for every single
function.
llvm-svn: 365241
The Size either needs to be 0 meaning we aren't folding
a stack reload. Or the stack slot needs to be at least
16 bytes. I've also added a paranoia check ensure the
RCSize is at leat 16 bytes as well. This avoids any
FR32/FR64 surprises, but I think we already filtered
those earlier.
All of our test case have Size as either 0 or 16 and
RCSize == 16. So the Size <= 16 check worked for those
cases.
llvm-svn: 365234
The indirect call sequence on PPC requires that the TOC base register be saved
prior to the indirect call and restored after the call since the indirect call
may branch to a global entry point in another DSO which will update the TOC
base. Over the last couple of years, we have improved this to:
- be able to hoist TOC saves from loops (with changes to MachineLICM)
- avoid multiple saves when one dominates the other[s]
However, it is still possible to have multiple TOC saves dynamically in the
execution path if there is no dominance relationship between them.
This patch moves the TOC save to the prologue when one of the TOC saves is in a
block that post-dominates entry (i.e. it cannot be avoided) or if it is in a
block that is hotter than entry.
Differential revision: https://reviews.llvm.org/D63803
llvm-svn: 365232
These patterns use 128-bit loads, but the instructions only load
64-bits. We shouldn't narrow the load if its volatile.
Fixes another variant of PR42079
llvm-svn: 365225
This was identical to a pattern for MOVPQI2QImr with a bitcast
as an input. But we should be able to turn MOVPQI2QImr into
MOVLPSmr in the execution domain fixup pass so we shouldn't
need this.
llvm-svn: 365224
Revision r365061 changed a skip of debug instructions for a skip
of meta instructions. This is not safe, as IMPLICIT_DEF is classed
as a meta instruction.
llvm-svn: 365202
On RISC-V, the `cycle` CSR holds a 64-bit count of the number of clock
cycles executed by the core, from an arbitrary point in the past. This
matches the intended semantics of `@llvm.readcyclecounter()`, which we
currently leave to the default lowering (to the constant 0).
With this patch, we will now correctly lower this intrinsic to the
intended semantics, using the user-space instruction `rdcycle`. On
64-bit targets, we can directly lower to this instruction.
On 32-bit targets, we need to do more, as `rdcycle` only returns the low
32-bits of the `cycle` CSR. In this case, we perform a custom lowering,
based on the PowerPC lowering, using `rdcycleh` to obtain the high
32-bits of the `cycle` CSR. This custom lowering inserts a new basic
block which detects overflow in the high 32-bits of the `cycle` CSR
during reading (because multiple instructions are required to read). The
emitted assembly matches the suggested assembly in the RISC-V
specification.
Differential Revision: https://reviews.llvm.org/D64125
llvm-svn: 365201
Revision r365061 changed a skip of debug instructions for a skip
of meta instructions. This is not safe, as IMPLICIT_DEF is classed
as a meta instruction.
llvm-svn: 365198
This adds some handling for VMOVimm, using the same method that NEON uses. We
create VMOVIMM/VMVNIMM/VMOVFPIMM nodes based on the immediate, and select them
using the now renamed ARMvmovImm/etc. There is also an extra 64bit immediate
mode that I have not yet added here.
Code by David Sherwood
Differential Revision: https://reviews.llvm.org/D63884
llvm-svn: 365178
Summary:
We attempt to prevent folding immediates with multiple users under optsize. But we only do this from store nodes and X86ISD::ADD/SUB/XOR/OR/AND patterns. We don't do it for ISD::ADD/SUB/XOR/OR/AND even though we count them as users when deciding whether to fold into other nodes. This leads to situations where we block folding to a compare for example, but still fold into an AND or OR as seen in PR27202.
Unfortunately touching the isel patterns in tablegen for the ISD::ADD/SUB/XOR/OR/AND opcodes will cause the patterns to be unusable for fast isel. And we don't have a way to make a fast isel only pattern.
To workaround this, this patch adds custom isel in front of the isel table that will select the non-immediate forms if the immediate has additional users. This may create some issues for ANDN and NOT matching. And there's room for improvement with unsigned 32 immediates on 64-bit AND.
This patch needs more thorough test cases, but I wanted to get feedback on the direction. Please send me any other test cases you've seen in the wild.
I think we probably have the same issue with the immediate matching when we fold RMW from X86ISD::ADD/SUB/XOR/OR/AND. And our TEST immedaite shrinking logic. Our cost modeling for immediates that can fit in a sign extended 8-bit immediate on a 16/32/64 bit operation is completely wrong.
I also wonder if we should update the ConstantHoisting cost model and block folding for "opaque" constants. But of course constants can still be created by DAG combine and lowering optimizations.
Fixes PR27202
Reviewers: spatel, RKSimon, andreadb
Reviewed By: RKSimon
Subscribers: jsji, hiraditya, jdoerfert, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D59909
llvm-svn: 365163
Summary:
Since the changes to introduce vec3 and vec5, INSERT_VECTOR for these
sizes has been marked "expand", which made LegalizeDAG lower it to loads
and stores via a stack slot. The code got optimized a bit later, but the
now-unused stack slot was never deleted.
This commit avoids that problem by custom lowering INSERT_SUBVECTOR into
an EXTRACT_VECTOR_ELT and INSERT_VECTOR_ELT for each element in the
subvector to insert.
V2: Addressed review comments re test.
Differential Revision: https://reviews.llvm.org/D63160
Change-Id: I9e3c13e36f68cfa3431bb9814851cc1f673274e1
llvm-svn: 365148
Bitcast v4i32 to v8f32 and back again - it might be worth adding isel patterns for X86PShufd v8i32 on AVX1 targets like we did for X86Blendi to avoid the bitcasts?
llvm-svn: 365125
The arm condition codes for GE is N==V (and for LT is N!=V). If the source of
flags cannot set V (overflow), such as a cmp against #0, then we can use the
simpler PL and MI conditions that only check N. As these PL/MI conditions are
simpler than GE/LT, other passes like the peephole optimiser can have a better
time optimising away the redundant CMPs.
The exception is the VSEL instruction, which cannot take the PL code, so there
the transform favours GE.
Differential Revision: https://reviews.llvm.org/D64160
llvm-svn: 365117
This adds patterns for the simpler VAND, VORR and VEOR bitwise vector
instructions. It also adjusts the top16Zero PatLeaf to not match on vector
instructions, which can otherwise cause problems.
Code written by David Sherwood.
Differential Revision: https://reviews.llvm.org/D63867
llvm-svn: 365113
Summary:
"ww" and "ws" are both constraint codes for VSX vector registers that
hold scalar double data. "ww" is preferred for float while "ws" is
preferred for double.
Reviewed By: jsji
Differential Revision: https://reviews.llvm.org/D64119
llvm-svn: 365106
Wasm doesn't have a direct way to lower indirectbr, so hook up the
IndirectBrExpandPass to lower indirectbr into a switch.
Fixes PR42498
Reviewers: aheejin
Differential Revision: https://reviews.llvm.org/D64161
llvm-svn: 365096
This is split out from my patches to split register allocation into a
separate SGPR and VGPR phase, and has some parts that aren't yet used
(like maintaining LiveIntervals).
This simplifies making the frame pointer register callee saved. As it
is now, the code to determine callee saves needs to predict all the
possible SGPR spills and how many callee saved VGPRs are needed. By
handling this before PrologEpilogInserter, it's possible to just check
the spill objects that already exist.
Change-Id: I29e6df4034afcf949e06f8ef44206acb94696f04
llvm-svn: 365095
Summary:
Hip texture type is equivalent to OpenCL image. So, we need to set the Image type for kernel arguments with __hip_texture type.
Differential revision: https://reviews.llvm.org/D63850
llvm-svn: 365073
Precedence was wrong in an assert added in r364961. Add braces around the
assertion condition to make it right.
See: https://reviews.llvm.org/D64084
llvm-svn: 365069
Instead of just stopping to see if we have a G_CONSTANT, instead, look through
G_TRUNCs, G_SEXTs, and G_ZEXTs.
This gives an average ~1.3% code size improvement on CINT2000 at -O3.
Differential Revision: https://reviews.llvm.org/D64108
llvm-svn: 365063
This patch generalizes the fix in D61680 to ignore all meta instructions,
not just debug info.
Patch by Chris Dawson.
Differential Revision: https://reviews.llvm.org/D62605
llvm-svn: 365061
We previously marked all the tests with branch funnels as
`-verify-machineinstrs=0`.
This is an attempt to fix it.
1) `ICALL_BRANCH_FUNNEL` has no defs. Mark it as `let OutOperandList =
(outs)`
2) After that we hit an assert: ``` Assertion failed: (Op.getValueType()
!= MVT::Other && Op.getValueType() != MVT::Glue && "Chain and glue
operands should occur at end of operand list!"), function AddOperand,
file
/Users/francisvm/llvm/llvm/lib/CodeGen/SelectionDAG/InstrEmitter.cpp,
line 461. ```
The chain operand was added at the beginning of the operand list. Move
that to the end.
3) After that we hit another verifier issue in the pseudo expansion
where the registers used in the cmps and jmps are not added to the
livein lists. Add the `EFLAGS` to all the new MBBs that we create.
PR39436
Differential Review: https://reviews.llvm.org/D54155
llvm-svn: 365058
If we have more then 2 shuffle ops to combine, try to use combineX86ShuffleChainWithExtract to see if some are from the same super vector.
llvm-svn: 365050
iff the number of elements doesn't change.
This gets around an issue with combineX86ShuffleChain not being able to hint which domain is preferred for shuffles that can be done with either.
Fixes regression introduced in rL365041
llvm-svn: 365044
This better accounts for the cost/benefit of removing extract_subvectors from the shuffle and will be more useful in future patches.
The vpermq predicate regression will be fixed shortly.
llvm-svn: 365041
Assert that the shift amount is in range and create vXi8 shift masks in a way that doesn't cause MSVC/cppcheck shift result is truncated then extended warnings.
llvm-svn: 365024
For Thumb2, we prefer low regs (costPerUse = 0) to allow narrow
encoding. However, current allocation order is like:
R0-R3, R12, LR, R4-R11
As a result, a lot of instructs that use R12/LR will be wide instrs.
This patch changes the allocation order to:
R0-R7, R12, LR, R8-R11
for thumb2 and -Osize.
In most cases, there is no extra push/pop instrs as they will be folded
into existing ones. There might be slight performance impact due to more
stack usage, so we only enable it when opt for min size.
https://reviews.llvm.org/D30324
llvm-svn: 365014
Summary:
This is the backend part of [[ https://bugs.llvm.org/show_bug.cgi?id=42457 | PR42457 ]].
In middle-end, we'd want to prefer the form with two adds - D63992,
but as this diff shows, not every target will prefer that pattern.
Out of 4 targets for which i added tests all seem to be ok with inc-of-add for scalars,
but only X86 prefer that same pattern for vectors.
Here i'm adding a new TLI hook, always defaulting to the inc-of-add,
but adding AArch64,ARM,PowerPC overrides to prefer inc-of-add only for scalars.
Reviewers: spatel, RKSimon, efriedma, t.p.northover, hfinkel
Reviewed By: efriedma
Subscribers: nemanjai, javed.absar, kristof.beyls, kbarton, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64090
llvm-svn: 365010
There are two main issues preventing us from generating immediate form shifts:
1) We have partial SelectionDAG imported support for G_ASHR and G_LSHR shift
immediate forms, but they currently don't work because the amount type is
expected to be an s64 constant, but we only legalize them to have homogenous
types.
To deal with this, first we introduce a custom legalizer to *only* custom legalize
s32 shifts which have a constant operand into a s64.
There is also an additional artifact combiner to fold zexts(g_constant) to a
larger G_CONSTANT if it's legal, a counterpart to the anyext version committed
in an earlier patch.
2) For G_SHL the importer can't cope with the pattern. For this I introduced an
early selection phase in the arm64 selector to select these forms manually
before the tablegen selector pessimizes it to a register-register variant.
Differential Revision: https://reviews.llvm.org/D63910
llvm-svn: 364994
Summary:
Before, inline assembly gets mangled by the SjLj transformation.
For example, in a function with setjmp/longjmp, this LLVM IR code
call void asm sideeffect "", ""()
would be transformed into
call void @__invoke_void(void ()* asm sideeffect "", "")
This is invalid, and results in the error:
Cannot take the address of an inline asm!
In this diff, we skip the transformation for inline assembly.
Reviewers: aheejin, tlively
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya, sunfish, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64115
llvm-svn: 364985
There were two issues here: one, some of the relevant instructions were
missing the expected "FrameSetup" flag, and two,
ARMAsmPrinter::EmitUnwindingInstruction wasn't expecting "mov"
instructions in the prologue.
I'm sticking the additional state into ARMFunctionInfo so it's obvious
it only applies to the current function.
I considered a few alternative approaches where we would compute the
correct unwind information as part of the prologue/epilogue lowering,
but it seems like a lot of work to introduce pseudo-instructions, and
the current code seems to be reliable enough.
Fixes https://bugs.llvm.org/show_bug.cgi?id=42408.
Differential Revision: https://reviews.llvm.org/D63964
llvm-svn: 364970
This teaches `tryOptSelect` to handle folding G_ICMP, and removes the
requirement that the G_SELECT we're dealing with is floating point.
Some refactoring to make this work nicely as well:
- Factor out the scalar case from the selection code for G_ICMP into
`emitIntegerCompare`.
- Make `tryOptCMN` return a MachineInstr* instead of a bool.
- Make `tryOptCMN` not modify the instruction being selected.
- Factor out the CMN emission into `emitCMN` for readability.
By doing this this way, we can get all of the compare selection optimizations
in select emission.
Differential Revision: https://reviews.llvm.org/D64084
llvm-svn: 364961
Ordinarily it is lowered as a build_vector of each extract_vector_elt,
which in turn get lowered to bitcasts and bit shifts. Very little
understand the lowered extract pattern, resulting in much worse
code. We treat concat_vectors of v2i16 as legal, so prefer that.
llvm-svn: 364959
Don't use APInt::getZExtValue() if you can avoid it - eventually someone will call it with i128 or something that doesn't fit into 64-bits.
In this case it was completely superfluous as we'd moved the rest of the code to always use APInt.
Fixes the <1 x i128> addition bug in PR42486
llvm-svn: 364953
Similar for (V)MOVSD. Ultimately, I'd like to see about folding
scalar_to_vector+load to vzload. Which would select as (V)MOVSSrm
so this is closer to that.
llvm-svn: 364948
The register bank for the destination of the sample argument copy was
wrong. We shouldn't be constraining each source to the result register
bank. Allow constraining the original register to the right size.
llvm-svn: 364928
Pull out CombineShuffleWithExtract lambda to new combineX86ShuffleChainWithExtract wrapper and refactored it to handle more than 2 shuffle inputs - this will allow combineX86ShufflesRecursively to call this in a future patch.
llvm-svn: 364924
Passing a vector type over the soft-float ABI involves it being split
into four GPRs, so the first thing that has to happen at the start of
the function is to recombine those into a vector register. The ABI
types all vectors as v2f64, so we need to support BUILD_VECTOR for
that type, which I do in this patch by allowing it to be expanded in
terms of INSERT_VECTOR_ELT, and writing an ISel pattern for that in
turn. Similarly, I provide a rule for EXTRACT_VECTOR_ELT so that a
returned vector can be marshalled back into GPRs.
While I'm here, I've also added ISD::UNDEF to the list of operations
we turn back on in `setAllExpand`, because I noticed that otherwise it
gets expanded into a BUILD_VECTOR with explicit zero inputs, leading
to pointless machine instructions to zero out a vector register that's
about to have every lane overwritten of in any case.
Reviewers: dmgreen, ostannard
Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63937
llvm-svn: 364910
If you compile with `-mattr=+mve` (enabling integer MVE instructions
but not floating-point ones), then the scalar FP //registers// exist
and it's legal to move things in and out of them, load and store them,
but it's not legal to do arithmetic on them.
In D60708, the calls to `addRegisterClass` in ARMISelLowering that
enable use of the scalar FP registers became conditionalised on
`Subtarget->hasFPRegs()` instead of `Subtarget->hasVFP2Base()`, so
that loads, stores and moves of those registers would work. But I
didn't realise that that would also enable all the operations on those
types by default.
Now, if the target doesn't have basic VFP, we follow up those
`addRegisterClass` calls by turning back off all the nontrivial
operations you can perform on f32 and f64. That causes several
knock-on failures, which are fixed by allowing the `VMOVDcc` and
`VMOVScc` instructions to be selected even if all you have is
`HasFPRegs`, and adjusting several checks for 'is this a double in a
single-precision-only world?' to the more general 'is this any FP type
we can't do arithmetic on?'. Between those, the whole of the
`float-ops.ll` and `fp16-instructions.ll` tests can now run in
MVE-without-FP mode and generate correct-looking code.
One odd side effect is that I had to relax the check lines in that
test so that they permit test functions like `add_f` to be generated
as tailcalls to software FP library functions, instead of ordinary
calls. Doing that is entirely legal, but the mystery is why this is
the first RUN line that's needed the relaxation: on the usual kind of
non-FP target, no tailcalls ever seem to be generated. Going by the
llc messages, I think `SoftenFloatResult` must be perturbing the code
generation in some way, but that's as much as I can guess.
Reviewers: dmgreen, ostannard
Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63938
llvm-svn: 364909
We were relying on combineX86ShufflesRecursively to handle this - this patch gets it done earlier which should make it easier for other code to use resolveTargetShuffleInputsAndMask.
llvm-svn: 364906
After implemented this hook, we will model the memory dependency in the scheduling dependency graph more precise,
and will have more opportunity to reorder the load/stores, as they didn't have the dependency at some condition
Differential Revision: https://reviews.llvm.org/D63804
llvm-svn: 364886
v2i64 vzload defines a 64-bit memory access. It doesn't look like
we have any coverage for this either way.
Also remove some vzload usages where the instruction loads only
16-bits.
llvm-svn: 364851
These instructions only read 64-bits of memory so we shouldn't
allow a full vector width load to be pattern matched in case it
is marked volatile.
Instead allow vzload or scalar_to_vector+load.
Also add a DAG combine to turn full vector loads into vzload when
used by one of these instructions if the load isn't volatile.
This fixes another case for PR42079
llvm-svn: 364838
Tests don't cover the masked input path since non-kernel arguments
aren't lowered yet.
Test is copied directly from the existing test, with 2 additions.
llvm-svn: 364833
Replace the brcond for the 2 cases that act as branches. For now
follow how the current system works, although I think we can
eventually get rid of the pseudos.
llvm-svn: 364832
This needs to be extended to s32, and expanded into cmp+select. This
is relying on the fact that widenScalar happens to leave the
instruction in place, but this isn't a guaranteed property of
LegalizerHelper.
llvm-svn: 364831
The function findPotentialBlockers may consider debug info instructions as
potential blockers and may stop searching for a store-load pair prematurely.
This patch corrects this and tests the cases where the store is separated
from the load by more than InspectionLimit debug instructions.
Patch by Chris Dawson.
Differential Revision: https://reviews.llvm.org/D62408
llvm-svn: 364829
The condition register bank must be scc or vcc so that a copy will be
inserted, which will be lowered to a compare.
Currently greedy unnecessarily forces using a VCC select.
llvm-svn: 364825
Summary:
ds_ordered_count can now simultaneously operate on up to 4 dwords
in a single instruction, which are taken from (and returned to)
lanes 0..3 of a single VGPR.
Change-Id: I19b6e7b0732b617c10a779a7f9c0303eec7dd276
Reviewers: mareko, arsenm, rampitec
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63716
llvm-svn: 364815
Also works around tablegen defect in selecting add with unused carry,
but if we have to manually select GEP, might as well handle add
manually.
llvm-svn: 364806
There are several things broken, but at least emit the right thing for
gfx9.
The import of the pattern with the unused carry out seems to not
work. Needs a special class for clamp, because OperandWithDefaultOps
doesn't really work.
llvm-svn: 364804
We can already widenSubVector to a specific type (of the same scalar type) - this variant just specifies the target vector size.
This will be useful when CombineShuffleWithExtract relaxes the need to have the same scalar type for all shuffle operand subvector sources.
llvm-svn: 364803
Summary:
According to the ARMARM, the VQDMLADH, VQRDMLADH, VQDMLSDH and
VQRDMLSDH instructions handle their results as follows: "The base
variant writes the results into the lower element of each pair of
elements in the destination register, whereas the exchange variant
writes to the upper element in each pair". I.e., the initial content
of the output register affects the result, as usual, we model this
with an additional input.
Also, for 32-bit variants Qd is not allowed to be the same register as
Qm and Qn, we use @earlyclobber to indicate this.
This patch also changes vpred_r to vpred_n because the instructions
don't have an explicit 'inactive' operand.
Reviewers: dmgreen, ostannard, simon_tatham
Reviewed By: simon_tatham
Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D64007
llvm-svn: 364796
Summary:
The stride should depend on the wave size, not the hardware generation.
Also, the 32_FLOAT format is 0x16, not 16; though that shouldn't be
relevant.
Change-Id: I088f93bf6708974d085d1c50967f119061da6dc6
Reviewers: arsenm, rampitec, mareko
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63808
llvm-svn: 364788
This was checking the size of the register with the value of the size,
which happens to be exec. Also fix assuming VCC is 64-bit to fix
wave32.
Also remove some untested handling for physical registers which is
skipped. This doesn't insert the V_CNDMASK_B32 if SCC is the physical
copy source. I'm not sure if this should be trying to handle this
special case instead of dealing with this in copyPhysReg.
llvm-svn: 364761
Simon Atanasyan