The only caller of this function is in the LocalStackSlotAllocation
and it creates base register of class returned by the target's
getPointerRegClass(). AMDGPU wants to use a different reg class
here so let materializeFrameBaseRegister to just create and return
whatever it wants.
Differential Revision: https://reviews.llvm.org/D95268
Similar to our free standing setcc patterns, we can use ADDI to
subtract the immediate from the other operand. Then the cmov
can check if the result is zero or non-zero.
Reviewed By: mundaym
Differential Revision: https://reviews.llvm.org/D95169
This adds an initial set of patterns for these instructions. Its
more complicated that I would like for the sh*add.uw instructions
because there is no guaranteed canonicalization for shl/and with
constants.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D95106
These instructions use a portion of the encodings for grevi and
gorci. The full encodings are only supported with Zbp. Note,
rev8 has a different encoding between rv32 and rv64.
Zbb is closer to being finalized that Zbp which has motivated
some decisions in this patch.
I'm treating rev8 and orc.b as separate instructions when
either Zbb or Zbp is enabled. This allows us to print to suggest
that either feature needs to be enabled to support these mnemonics.
I had tried to put HasStdExtZbbAndNotZbp on the Zbb instructions,
but that caused a diagnostic that said Zbp is required if neither
feature is enabled. We should really mention Zbb since its closer
to final.
This does require extra isel patterns for the different cases so
that bswap will always print as rev8 in assembly listing since
we can't use an InstAlias.
llvm-objdump disassembling should always pick the rev8 or orc.b
instructions. llvm-mc parsing and printing text will not convert
the grevi/gorci spellings to rev8/gorc.b. We could probably fix
this with a special case in processInstruction in the assembly
parser if it its important.
Reviewed By: asb, frasercrmck
Differential Revision: https://reviews.llvm.org/D94944
zext.h uses the same encoding as pack rd, rs, x0 in rv32 and
packw rd, rs, x0 in rv64. Encodings without x0 as the second source
are not valid in Zbb.
I've added two new instructions with these specific encodings with
predicates that enable them when either Zbb or Zbp is enabled.
The pack spelling will only be accepted with Zbp. The disassembler
will use the zext.h instruction when either feature is enabled.
Using the pack spelling will print as pack when llvm-mc is
emitting text. We could fix this with some custom code in
processInstruction if this is important, but I'm not sure it is.
Reviewed By: asb, frasercrmck
Differential Revision: https://reviews.llvm.org/D94818
Zext.h will need to come back to Zbb, but that only uses specific
encodings of pack.
Reviewed By: asb, frasercrmck
Differential Revision: https://reviews.llvm.org/D94742
This didn't make it into the published 0.93 spec, but it was the
intention.
But it is in the tex source as of this commit
d172f029c0
This means zext.w now requires Zba. Not sure if we should still use
pack if Zbp is enabled and Zba isn't. I'll leave that for the future
when pack is closer to being final.
Reviewed By: asb, frasercrmck
Differential Revision: https://reviews.llvm.org/D94736
The 0.93 spec has this implementation for add.uw
uint_xlen_t adduw(uint_xlen_t rs1, uint_xlen_t rs2) {
uint_xlen_t rs1u = (uint32_t)rs1;
return rs1u + rs2;
}
The 0.92 spec had the usages of rs1 and rs2 swapped.
Reviewed By: frasercrmck, asb
Differential Revision: https://reviews.llvm.org/D95090
Also renamed Zbe instructions to resolve name conflict even though
that change is in the 0.94 draft.
Reviewed By: asb, frasercrmck
Differential Revision: https://reviews.llvm.org/D94653
It's not really clear in the spec that these are in Zbp now, but
that's what I've gather from previous commits to the spec. I've
file an issue to get it documented properly.
Reviewed By: asb, frasercrmck
Differential Revision: https://reviews.llvm.org/D94652
This is the first of multiple patches to bring our 0.92
implementation up to 0.93.
Reviewed By: asb, frasercrmck
Differential Revision: https://reviews.llvm.org/D94568
The legacy PM's EP_CGSCCOptimizerLate was only used under not-O0.
Fixes clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp under the new PM.
Reviewed By: arsenm
Differential Revision: https://reviews.llvm.org/D95250
This patch implements codegen for __managed__ variable attribute for HIP.
Diagnostics will be added later.
Differential Revision: https://reviews.llvm.org/D94814
Simplify vperm2x128(concat(X,Y),concat(Z,W)) folding.
Use collectConcatOps / ISD::INSERT_SUBVECTOR to find the source subvectors instead of hardcoded immediate matching.
I may have given bad advice, and skipping sext_inreg when matching SSAT
patterns is not valid on it's own. It at least needs to sext_inreg the
input again, but as far as I can tell is still only valid based on
demanded bits. For the moment disable that part of the combine,
hopefully reimplementing it in the future more correctly.
combineX86ShufflesConstants/canonicalizeShuffleMaskWithHorizOp can both handle/earlyout shuffles with inputs of different widths, so delay widening as late as possible to make it easier to match constant folds etc.
The plan is to eventually move the widening inside combineX86ShuffleChain so that we don't create any new nodes unless we successfully combine the shuffles.
rGbe69e66b1cd8 added the fold, but DAGCombiner.visitVECTOR_SHUFFLE doesn't merge shuffles if the inner shuffle is a splat, so we need to bail.
The non-fast-horiz-ops paths see some minor regressions, we might be able to improve on this after lowering to target shuffles.
Fix PR48823
This replaces the isSaturatingConditional function with
LowerSaturatingConditional that directly returns a new SSAT or
USAT SDValue, instead of returning true and the components of it.
Allow parsing generated mir with custom pseudo source value tokens.
Also rename pseudo source values to have more meaningful names.
Relands ba7dcd8542, which had memory leaks.
Differential Revision: https://reviews.llvm.org/D95215
I have removed an unnecessary assert in LoopVectorizationCostModel::getInstructionCost
that prevented a cost being calculated for select instructions when using
scalable vectors. In addition, I have changed AArch64TTIImpl::getCmpSelInstrCost
to only do special cost calculations for fixed width vectors and fall
back to the base version for scalable vectors.
I have added a simple cost model test for cmps and selects:
test/Analysis/CostModel/sve-cmpsel.ll
and some simple tests that show we vectorize loops with cmp and select:
test/Transforms/LoopVectorize/AArch64/sve-basic-vec.ll
Differential Revision: https://reviews.llvm.org/D95039
During instruction selection, there is an inconsistency in choosing
the initial soffset value. With certain early passes, this value is
getting modified and that brought additional fixup during
eliminateFrameIndex to work for all cases. This whole transformation
looks trivial and can be handled better.
This patch clearly defines the initial value for soffset and keeps it
unchanged before eliminateFrameIndex. The initial value must be zero
for MUBUF with a frame index. The non-frame index MUBUF forms that
use a raw offset from SP will have the stack register for soffset.
During frame elimination, the soffset remains zero for entry functions
with zero dynamic allocas and no callsites, or else is updated to the
appropriate frame/stack register.
Also, did some code clean up and made all asserts around soffset
stricter to match.
Reviewed By: scott.linder
Differential Revision: https://reviews.llvm.org/D95071
Having a custom inliner doesn't really fit in with the new PM's
pipeline. It's also extra technical debt.
amdgpu-inline only does a couple of custom things compared to the normal
inliner:
1) It disables inlining if the number of BBs in a function would exceed
some limit
2) It increases the threshold if there are pointers to private arrays(?)
These can all be handled as TTI inliner hooks.
There already exists a hook for backends to multiply the inlining
threshold.
This way we can remove the custom amdgpu-inline pass.
This caused inline-hint.ll to fail, and after some investigation, it
looks like getInliningThresholdMultiplier() was previously getting
applied twice in amdgpu-inline (https://reviews.llvm.org/D62707 fixed it
not applying at all, so some later inliner change must have fixed
something), so I had to change the threshold in the test.
Reviewed By: rampitec
Differential Revision: https://reviews.llvm.org/D94153
The DWARF numbers of vector registers are already defined in
riscv-elf-psabi. The DWARF number for vector is start from 96.
Correct the DWARF numbers of vector registers.
Differential Revision: https://reviews.llvm.org/D94749
These instructions produce 2*SEW result so the input can't have
an LMUL=8 or the result would need a non-existant LMUL=16. So
only create pseudos for LMUL up to 4.
Differential Revision: https://reviews.llvm.org/D95189
PowerPC has its custom scheduler heuristic. It calls parent classes'
tryCandidate in override version, but the function returns void, so this
way doesn't actually help. This patch duplicates code from base scheduler
into PPC machine scheduler class, which does what we wanted.
Reviewed By: steven.zhang
Differential Revision: https://reviews.llvm.org/D94464
The fault-only-first-load instructions can reduce VL if an element
other than element 0 triggers a memory fault. This can be used to
vectorize loops with data dependent exit conditions like strcmp or
strlen.
This patch adds a VL output to these intrinsics so that the new
VL value can be captured by software. This will be expanded to
'csrr gpr, vl' after the vleff instruction during SelectionDAG.
By doing this with one intrinsic we are able to guarantee that the
csrr reads the VL value produced by the vleff instruction. Having
it as a separate intrinsic would make it impossible to guarantee
ordering without making every other vector intrinsic have side
effects.
The intrinsics are expanded during lowering into two ISD nodes
that are glued together. These ISD nodes will go
through isel separately, but should maintain the glue so that they
get emitted adjacently by InstrEmitter.
I've only ran the chain through the vleff instruction, allowing
the READ_VL to be deleted if it is unused.
Reviewed By: HsiangKai
Differential Revision: https://reviews.llvm.org/D94286
Upgrade RISC-V V extension to v1.0-08a0b46.
Indexed load/store have ordered and unordered form.
New whole vector load/store.
Differential Revision: https://reviews.llvm.org/D93614
This adds cost modelling for the inloop vectorization added in
745bf6cf44. Up until now they have been modelled as the original
underlying instruction, usually an add. This happens to works OK for MVE
with instructions that are reducing into the same type as they are
working on. But MVE's instructions can perform the equivalent of an
extended MLA as a single instruction:
%sa = sext <16 x i8> A to <16 x i32>
%sb = sext <16 x i8> B to <16 x i32>
%m = mul <16 x i32> %sa, %sb
%r = vecreduce.add(%m)
->
R = VMLADAV A, B
There are other instructions for performing add reductions of
v4i32/v8i16/v16i8 into i32 (VADDV), for doing the same with v4i32->i64
(VADDLV) and for performing a v4i32/v8i16 MLA into an i64 (VMLALDAV).
The i64 are particularly interesting as there are no native i64 add/mul
instructions, leading to the i64 add and mul naturally getting very
high costs.
Also worth mentioning, under NEON there is the concept of a sdot/udot
instruction which performs a partial reduction from a v16i8 to a v4i32.
They extend and mul/sum the first four elements from the inputs into the
first element of the output, repeating for each of the four output
lanes. They could possibly be represented in the same way as above in
llvm, so long as a vecreduce.add could perform a partial reduction. The
vectorizer would then produce a combination of in and outer loop
reductions to efficiently use the sdot and udot instructions. Although
this patch does not do that yet, it does suggest that separating the
input reduction type from the produced result type is a useful concept
to model. It also shows that a MLA reduction as a single instruction is
fairly common.
This patch attempt to improve the costmodelling of in-loop reductions
by:
- Adding some pattern matching in the loop vectorizer cost model to
match extended reduction patterns that are optionally extended and/or
MLA patterns. This marks the cost of the reduction instruction correctly
and the sext/zext/mul leading up to it as free, which is otherwise
difficult to tell and may get a very high cost. (In the long run this
can hopefully be replaced by vplan producing a single node and costing
it correctly, but that is not yet something that vplan can do).
- getExtendedAddReductionCost is added to query the cost of these
extended reduction patterns.
- Expanded the ARM costs to account for these expanded sizes, which is a
fairly simple change in itself.
- Some minor alterations to allow inloop reduction larger than the highest
vector width and i64 MVE reductions.
- An extra InLoopReductionImmediateChains map was added to the vectorizer
for it to efficiently detect which instructions are reductions in the
cost model.
- The tests have some updates to show what I believe is optimal
vectorization and where we are now.
Put together this can greatly improve performance for reduction loop
under MVE.
Differential Revision: https://reviews.llvm.org/D93476
This recommits 71ed4b6ce5 with
the polarity of some of the pattern corrected.
Original commit message:
The custom expansion of select operations in the RISC-V backend
interferes with the matching of cmov instructions. Legalizing
select when the Zbt extension is available solves that problem.
Reviewed By: luismarques, craig.topper
Differential Revision: https://reviews.llvm.org/D93767
`X86AsmParser::ParseIntelExpression` has a while loop. In the body,
calls to MCAsmLexer::UnLex can force a reallocation in the MCAsmLexer's
`CurToken` SmallVector, invalidating saved references to
`MCAsmLexer::getTok()`.
`const MCAsmToken &Tok` is such a saved reference, and this moves it
from outside the while loop to inside the body, fixing a
use-after-realloc.
`Tok` will still be reused across calls to `Lex()`, each of which
effectively destroys and constructs the pointed-to token. I'm a bit
skeptical of this usage pattern, but it seems broadly used in the
X86AsmParser (and others) so I'm leaving it alone (for now).
Somehow this bug was exposed by https://reviews.llvm.org/D94739,
resulting in test failures in dot-operator related tests in
llvm/test/tools/llvm-ml. I suspect the exposure path is related to
optimizer changes from splitting up the grow operation, but I haven't
dug all the way in. Regardless, there are already tests in tree that
cover this; they might fail consistently if we added ASan
instrumentation to SmallVector.
Differential Revision: https://reviews.llvm.org/D95112
Hsiangkai Wang