I've left mask registers to a future patch as we'll need
to convert them to full vectors, shuffle, and then truncate.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D97609
I've included tests that require type legalization to split the
vector. The i64 version of these scalarizes on RV32 due to type
legalization visiting the result before the vector type. So we
have to abort our custom expansion to avoid creating target
specific nodes with an illegal type. Then type legalization ends
up scalarizing. We might be able to fix this by doing custom
splitting for large vectors in our handler to get down to a legal
type.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D98102
Previously we set the value to -1, but the SEW information could
be useful for scheduling.
Reviewed By: frasercrmck, rogfer01
Differential Revision: https://reviews.llvm.org/D98062
The default fixed vector expansion uses sra+xor+add since it can't
see that smax is legal due to our custom handling. So we select
smax(X, sub(0, X)) manually.
Scalable vectors are able to use the smax expansion automatically
for most cases. It crashes in one case because getConstant can't build a
SPLAT_VECTOR for nxvXi64 when i64 scalars aren't legal. So
we manually emit a SPLAT_VECTOR_I64 for that case.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D97991
The result of ISD::USUBSAT will never be larger than the LHS. We
can use this to put a bound on the number of leading zeros.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D98133
A setcc can be created during LegalizeDAG after select_cc has been
created. This combine will enable us to fold these late setccs.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D98132
This pattern occurs when lowering for overflow operations
introduce an xor after select_cc has already been formed.
I had to rework another combine that looked for select_cc of an xor
with 1. That xor will now get combined away so we just need to
look for the RHS of the select_cc being 1.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D98130
This patch addresses a compiler crash resulting from passing a
fixed-length type to one that expects scalable vector types. An
assertion was added to prevent this regressing in the future.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97868
This patch fixes up one case where the fixed-length-vector VL was
dropped (falling back to VLMAX) when inserting vector elements, as the
code would lower via ISD::INSERT_VECTOR_ELT (at index 0) which loses the
fixed-length vector information.
To this end, a custom node, VMV_S_XF_VL, was introduced to carry the VL
operand through to the final instruction. This node wraps the RVV
vmv.s.x and vmv.s.f instructions, which were being selected by
insert_vector_elt anyway.
There should be no observable difference in scalable-vector codegen.
There is still one outstanding drop from fixed-length VL to VLMAX, when
an i64 element is inserted into a vector on RV32; the splat (which is
custom legalized) has no notion of the original fixed-length vector
type.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97842
This function isn't exercised in lit tests today today according to
the code coverage report. But will be after the tests in D97543 and
D97559.
Posting this patch to help a crash that Fraser hit.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D97582
This patch enables support for lowering INSERT_VECTOR_ELT on
fixed-length vector types. The strategy follows that for scalable vector
types.
This patch also includes a quick fix to prevent the compiler infinitely
looping between lowering BUILD_VECTOR as VECTOR_SHUFFLE and back again.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97698
The default expansion of CONCAT_VECTORS goes through the stack. This
patch avoids that penalty by custom-lowering CONCAT_VECTORS to a series
of INSERT_SUBVECTOR nodes. Futher optimizations are possible, but this
is a good start.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97692
Like with EXTRACT_SUBVECTOR, INSERT_SUBVECTOR poses a problem
for vector masks as RVV isn't able to slide mask types around. We choose
instead to bitcast to equivalently-sized i8 types where we can, else we
zero-extend, perform the operation, and truncate back down.
One test was left disabled due to a crash in the legalizer.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97559
This patch fixes a bug where the lowering for INSERT_SUBVECTOR and
EXTRACT_SUBVECTOR would insist on first extracting a register-aligned
LMUL1 vector type before perfoming the slide up/down. This was even if
the vector was a fractional LMUL type, in which case the aligned
EXTRACT_SUBVECTOR was invalid.
This issue only occurred for scalable vector types, but a variety of
tests for both scalable and fixed-length vectors have been added to
ensure this does not regress in the future.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97556
This patch unifies the two disparate paths for lowering INSERT_SUBVECTOR
operations under one roof. Consequently, with this patch it is possible to
support any fixed-length subvector insertion, not just "cast-like" ones.
As before, support for the insertion of mask vectors will come in a
separate patch.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97543
This patch adds support for extracting subvectors from vector masks.
This can be either extracting a scalable vector from another, or a fixed-length
vector from a fixed-length or scalable vector.
Since RVV lacks a way to slide vector masks down on an element-wise
basis and we don't know the true length of the vector registers, in many
cases we must resort to using equivalently-sized i8 vectors to perform
the operation. When this is not possible we fall back and extend to a
suitable i8 vector.
Support was also added for fixed-length truncation to mask types.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97475
This patch addresses issues arising from the fact that the index type
used for subvector insertion/extraction is inconsistent between the
intrinsics and SDNodes. The intrinsic forms require i64 whereas the
SDNodes use the type returned by SelectionDAG::getVectorIdxTy.
Rather than update the intrinsic definitions to use an overloaded index
type, this patch fixes the issue by transforming the index to the
correct type as required. Any loss of index bits going from i64 to a
smaller type is unexpected, and will be caught by an assertion in
SelectionDAG::getVectorIdxConstant.
The patch also updates the documentation for INSERT_SUBVECTOR and adds
an assertion to its creation to bring it in line with EXTRACT_SUBVECTOR.
This necessitated changes to AArch64 which was using i64 for
EXTRACT_SUBVECTOR but i32 for INSERT_SUBVECTOR. Only one test changed
its codegen after updating the backend accordingly.
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D97459
Using ComputeNumSignBits or computeKnownBits we might be able
to determine that overflow is impossible.
This especially helps after type legalization if the type was
promoted from a type with half the bits or more. Type legalization
conservatively creates a promoted smulo/umulo and an overflow
check for the promoted bits. The overflow from the promoted
smulo/umulo is ORed with the result of the promoted bits
overflow check. Proving that the promoted smulo/umulo can never
overflow will leave us with just the promoted bits overflow check.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D97160
This will allow FrameIndex as the base address instead of
emitting a separate ADDI from isel. eliminateFrameIndex will likely turn
it back into an ADDI, but this makes things consistent with the
SDPatterns and VLPatterns.
I only tested one case for simplicity. I can test more if reviewers
want.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D97221
This patch extends the support for scalable-vector int->fp and fp->int
conversions by additionally handling fixed-length vectors.
The existing scalable-vector lowering re-expresses widening/narrowing by
x4+ conversions as standard nodes. The fixed-length vector support slots
in at "the end" of this process by lowering the now equally-sized and
widening/narrowing by x2 nodes to our custom VL versions.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97374
This patch extends the support for vector FP_ROUND and FP_EXTEND by
including support for fixed-length vector types. Since fixed-length
vectors use "VL" nodes and scalable vectors can use the standard nodes,
there is slightly more to do in the fixed-length case. A helper function
was introduced to try and reduce the divergent paths. It is expected
that this function will similarly come in useful for lowering the
int-to-fp and fp-to-int operations for fixed-length vectors.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97301
This patch extends support for our custom-lowering of scalable-vector
truncates to include those of fixed-length vectors. It does this by
co-opting the custom RISCVISD::TRUNCATE_VECTOR node and adding mask and
VL operands. This avoids unnecessary duplication of patterns and
inflation of the ISel table.
Some truncates go through CONCAT_VECTORS which currently isn't
efficiently handled, as it goes through the stack. This can be improved
upon in the future.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97202
This patch adds support for the custom lowering sign- and zero-extension
of fixed-length vector types. It does so through custom nodes. Since the
source and destination types are (necessarily) of different sizes, it is
possible that the source type is legal whilst the larger destination
type isn't. In this case the legalization makes heavy use of
EXTRACT_SUBVECTOR.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97194
This patch unifies the two disparate paths for lowering
EXTRACT_SUBVECTOR operations under one roof. Consequently, with this
patch it is possible to support any fixed-length subvector extraction,
not just "cast-like" ones.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97192
We always create the VL operand using a register, but if we can
determine that it came from an ADDI X0, imm with a sufficiently
small immediate, we can use VSETIVLI.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D97332
I've changed to use VL=1 for slidedown and shifts to avoid extra
element processing that we don't need.
The i64 fixed vector handling on i32 isn't great if the vector type
isn't legal due to an ordering issue in type legalization. If the
vector type isn't legal, we fall back to default legalization
which will bitcast the vector to vXi32 and use two independent extracts.
Doing better will require handling several different cases by
manually inserting insert_subvector/extract_subvector to adjust the type
to a legal vector before emitting custom nodes.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D97319
Rather than converting 3 signbits to bools and comparing them,
we can do bitwise logic on the whole vector and convert the
resulting sign bit to a bool at the end.
This is still a different algorithm than what we do in LegalizeDAG
through expandSADDOSSUBO. That algorithm needs to know that the
RHS of SSUBO is > 0, but that's costly when the type is split.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D97325
This code creates 3 setccs that need to be expanded. It was
creating a sign bit test as setge X, 0 which is non-canonical.
Canonical would be setgt X, -1. This misses the special case in
IntegerExpandSetCCOperands for sign bit tests that assumes
canonical form. If we don't hit this special case we end up
with a multipart setcc instead of just checking the sign of
the high part.
To fix this I've reversed the polarity of all of the setccs to
setlt X, 0 which is canonical. The rest of the logic should
still work. This seems to produce better code on RISCV which
lacks a setgt instruction.
This probably still isn't the best code sequence we could use here.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D97181
This patch extends the support for RVV INSERT_SUBVECTOR to cover those
which don't align to a vector register boundary. Like the support for
EXTRACT_SUBVECTOR in D96959, it accomplishes this by extracting the
nearest register-sized subvector (a subregister operation), then sliding
the vector down with VSLIDEDOWN, inserting the subvector to the first
position, and sliding the vector back up again afterwards.
Unlike subvector extraction, for vectors that occupy less than a full
vector register we must preserve the untouched elements. We do this by
lowering to an LMUL=1 INSERT_SUBVECTOR using the above method and
lowering that to a VSLIDEUP with a zero offset. This uses a
tail-undisturbed policy and so has the effect of "sliding in" the
subvector elements while preserving the surrounding ones.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D96972
An i64 AssertZExt from a type smaller than i32 has at least 33
leading zeros which mean it has at least 33 sign bits.
Since we have a couple patterns that use two sexti32, I've
switched to a ComplexPattern so tablegen didn't have to generate
9 different permutations.
As noted in the FIXME, maybe we should just call computeNumSignBits,
but we don't have tests that benefit from that yet.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D97130
The result must be less than or equal to the LHS side, so any
leading zeros in the left hand side must also exist in the result.
This is stronger than the previous behavior where we only considered
the sign bit being 0.
The affected test case used the sign bit being known 0 to change
a sign extend to a zero extend pre type legalization. After type
legalization the types were promoted to i64, but we no longer
knew bit 31 was zero. This shifts are are the equivalent of an
AND with 0xffffffff or zext_inreg X, i32. This patch allows us to
see that bit 31 is zero and remove the shifts.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D97124
This also removes a pattern from RISCV that is no longer needed
since the sexti32 on the LHS of the srem in the pattern implies
the result is sign extended so the sign_extend_inreg should be
removed in DAG combine now.
Reviewed By: luismarques, RKSimon
Differential Revision: https://reviews.llvm.org/D97133
This adds the IR for this C code
int32_t foo(uint16_t x, int16_t y) {
x %= y;
return x;
}
Note the dividend is unsigned and the divisor is signed. C type
promotion rules will extend them and use a 32-bit srem and the
function returns a 32-bit result.
We fail to use remw for this case. The zero extended input has
enough sign bits, but we won't consider (i64 AssertZext X, i16) in
the sexti32 isel pattern.
We also end up with a extra shifts to zero upper bits on the result.
computeKnownBits knew the result was positive before type legalization
and allowed the SIGN_EXTEND to become ZERO_EXTEND. But after promoting
to i64 we no longer know that bit 31 (and all bits above it) should
be 0.
This patch extends the support for RVV EXTRACT_SUBVECTOR to cover those
which don't align to a vector register boundary. It accomplishes this by
extracting the nearest register-sized subvector (a subregister
operation), then sliding the vector down with VSLIDEDOWN and extracting
the subvector from the first position (a COPY operation).
Since this procedure involves the use of VSCALE and multiplication, the
handling of such operations is done during lowering to simplify the
implementation and make use of DAG combining. This necessitated moving
some helper functions from RISCVISelDAGToDAG to RISCVTargetLowering.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D96959
With vector mask registers only allocatable to V0 (VMV0Regs) it is
relatively simple to generate code which uses multiple masks and naively
requires spilling.
This patch aims to improve codegen in such cases by telling LLVM it can
use VRRegs to hold masks. This will prevent spilling in many cases by
having LLVM copy to an available VR register.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D97055
Just like we do for isel patterns, we need to call selectVLOp
to prevent 0 from being selected to X0 by the default isel.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D97021
We previously used isel patterns for this, but that used quite
a bit of space in the isel table due to OR being associative
and commutative. It also wouldn't handle shifts/ands being in
reversed order.
This generalizes the shift/and matching from GREVI to
take the expected mask table as input so we can reuse it for
SHFLI.
There is no SHFLIW instruction, but we can promote a 32-bit
SHFLI to i64 on RV64. As long as bit 4 of the control bit isn't
set, a 64-bit SHFLI will preserve 33 sign bits if the input had
at least 33 sign bits. ComputeNumSignBits has been updated to
account for that to avoid sext.w in the tests.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D96661
This uses to division by constant optimization to use MULHU/MULHS.
Reviewed By: frasercrmck, arcbbb
Differential Revision: https://reviews.llvm.org/D96934
Due to vXi64 on RV32, I've directly emitted this using _VL ISD
opcodes. If it wasn't for that we could just use fixed vector
BUILD_VECTOR and VSELECT and let those each be legalized.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D96910
These should be NOPs so we can just replace with the input. This
matches what SVE does with isel patterns for all permutations.
Custom isel saves us from having to list all permurations for
all LMULs.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D96921
This patch adds support for INSERT_SUBVECTOR and EXTRACT_SUBVECTOR
(nominally where both operands are scalable vector types) where the
vector, subvector, and index align sufficiently to allow decomposition
to subregister manipulation:
* For extracts, the extracted subvector must correctly align with the
lower elements of a vector register.
* For inserts, the inserted subvector must be at least one full vector
register, and correctly align as above.
This approach should work for fixed-length vector insertion/extraction
too, but that will come later.
Reviewed By: craig.topper, khchen, arcbbb
Differential Revision: https://reviews.llvm.org/D96873
The type legalizer can call this code based on the scalar type so
we need to verify the vector type is a scalable vector.
I think due to how type legalization visits nodes, the vector type
will have already been legalized so we don't have an issue with
using MVT here like we did for EXTRACT_VECTOR_ELT.
I've added a test just in case.
The type legalizer is calling this code based on the scalar type so
we need to verify the input type is a scalable vector.
The vector type has also not been legalized yet when this is called
so we need to use EVT for it.
This patch adds support for fixed-length vector vselect. It does so by
lowering them to a custom unmasked VSELECT_VL node with a vector length
operand.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D96768
This patch proposes how to deal with RISC-V vector frame objects. The
layout of RISC-V vector frame will look like
|---------------------------------|
| scalar callee-saved registers |
|---------------------------------|
| scalar local variables |
|---------------------------------|
| scalar outgoing arguments |
|---------------------------------|
| RVV local variables && |
| RVV outgoing arguments |
|---------------------------------| <- end of frame (sp)
If there is realignment or variable length array in the stack, we will use
frame pointer to access fixed objects and stack pointer to access
non-fixed objects.
|---------------------------------| <- frame pointer (fp)
| scalar callee-saved registers |
|---------------------------------|
| scalar local variables |
|---------------------------------|
| ///// realignment ///// |
|---------------------------------|
| scalar outgoing arguments |
|---------------------------------|
| RVV local variables && |
| RVV outgoing arguments |
|---------------------------------| <- end of frame (sp)
If there are both realignment and variable length array in the stack, we
will use frame pointer to access fixed objects and base pointer to access
non-fixed objects.
|---------------------------------| <- frame pointer (fp)
| scalar callee-saved registers |
|---------------------------------|
| scalar local variables |
|---------------------------------|
| ///// realignment ///// |
|---------------------------------| <- base pointer (bp)
| RVV local variables && |
| RVV outgoing arguments |
|---------------------------------|
| /////////////////////////////// |
| variable length array |
| /////////////////////////////// |
|---------------------------------| <- end of frame (sp)
| scalar outgoing arguments |
|---------------------------------|
In this version, we do not save the addresses of RVV objects in the
stack. We access them directly through the polynomial expression
(a x VLENB + b). We do not reserve frame pointer when there is any RVV
object in the stack. So, we also access the scalar frame objects through the
polynomial expression (a x VLENB + b) if the access across RVV stack
area.
Differential Revision: https://reviews.llvm.org/D94465
Non-splatted non-integer build_vector nodes were mistakenly being
lowered as VID expressions, which should not happen. VID can only be
used to select integer build_vector nodes.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D96718
The patterns mostly follow the scalar counterparts, save for some extra
optimizations to match the vector/scalar forms.
The patch adds a DAGCombine for ISD::FCOPYSIGN to try and reorder
ISD::FNEG around any ISD::FP_EXTEND or ISD::FP_TRUNC of the second
operand. This helps us achieve better codegen to match vfsgnjn.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D96028
This is annoying because the condition code legalization belongs
to LegalizeDAG, but our custom handler runs in Legalize vector ops
which occurs earlier.
This adds some of the mask binary operations so that we can combine
multiple compares that we need for expansion.
I've also fixed up RISCVISelDAGToDAG.cpp to handle copies of masks.
This patch contains a subset of the integer setcc patch as well.
That patch is dependent on the integer binary ops patch. I'll rebase
based on what order the patches go in.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D96567
If we're going to end up expanding anyway, we should do it early
so we don't create extra operations to handle the bytes added by
promotion.
Simlilar was done for BSWAP previously.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D96681
I believe I've covered all orderings of splat operands here. Better
canonicalization in lowering might help reduce this. I did not handle
the immediate adjustments needed for set(u)gt/set(u)lt.
Testing here is limited to byte types because the scalable vector
type used for masks for the store is calculated assuming 8 byte
elements. But for the setcc its based on the element count of the
container type for the setcc input. So they don't agree. We'll need
to enhanced D96352 to handle this I think.
Differential Revision: https://reviews.llvm.org/D96443
Unlike scalable vectors, I'm only using a ComplexPattern for
the immediate itself. The vmv_v_x is matched explicitly. We igore
the VL argument when matching a binary operator, but we do check
it when matching splat directly.
I left out tests for vXi64 as they fail on rv32 right now.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D96365
This patch extends the initial fixed-length vector support to include
smin, smax, umin, and umax.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D96491
This patch handles cast-like insert_subvector & extract_subvector
in which case:
1. index starts from 0.
2. inserting a fixed-width vector into a scalable vector,
or extracting a fixed-width vector from a scalable vector.
Reviewed By: craig.topper, frasercrmck
Differential Revision: https://reviews.llvm.org/D96352
If we wait until the type is legalized, we'll lose information
about the orginal type and need to use larger magic constants.
This gets especially bad on RISCV64 where i64 is the only legal
type.
I've limited this to simple scalar types so it only works for
i8/i16/i32 which are most likely to occur. For more odd types
we might want to do a small promotion to a type where MULH is legal
instead.
Unfortunately, this does prevent some urem/srem+seteq matching since
that still require legal types.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D96210
This refines how we determine which masks types are legal and adds
support for loads, stores, and all ones/zeros splats.
I left a fixme in store handling where I think we need to zero
extra bits if the type isn't a multiple of a byte. If I remember
right from X86 there was some case we could have a store of a
1, 2, or 4 bit mask and have a scalar zextload that then expected the
bits to be 0. Its tricky to zero the bits with RVV. We need to do
something like round VL up, zero a register, lower the VL back down,
then do a tail undisturbed move into the zero register. Another
option might be to generate a mask of 1/2/4 bits set with a VL of 8
and use that to mask off the bits.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D96468
The test cases extract a fixed element from a vector and splat it
into a vector. This gets DAG combined into a splat shuffle.
I've used some very wide vectors in the test to make sure we have
at least a couple tests where the element doesn't fit into the
uimm5 immediate of vrgather.vi so we fall back to vrgather.vx.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D96186
This patch optimizes a build_vector "index sequence" and lowers it to
the existing custom RISCVISD::VID node. This pattern is common in
autovectorized code.
The custom node was updated to allow it to be used by both scalable and
fixed-length vectors, thus avoiding pattern duplication.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D96332
As of the current draft these are no longer being considered
for the bitmanip spec. It wasn't clear what sub extension they
belonged in in the 0.93 spec.
So remove them. They can always be added back if something changes.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D96157
In vector v0.10, there are whole vector register load/store
instructions. I suggest to use the whole register load/store
instructions for generic load/store for scalable vector types. It could
save up vset{i}vl{i} for these load/store.
For fractional LMUL, I keep to use vle{eew}.v/vse{eew}.v instructions to
load/store partial vector registers.
Differential Revision: https://reviews.llvm.org/D95853
Building on the fixed vector support from D95705
I've added ISD nodes for vmv.v.x and vfmv.v.f and switched to
lowering the intrinsics to it. This allows us to share the same
isel patterns for both.
This doesn't handle splats of i64 on RV32 yet. The build_vector
gets converted to a vXi32 build_vector+bitcast during type
legalization. Not sure the best way to handle this at the moment.
Differential Revision: https://reviews.llvm.org/D96108
This is an alternative to D95563.
This is modeled after a similar feature for AArch64's SVE that uses
predicated scalable vector instructions.a
Rather than use predication, this patch uses an explicit VL operand.
I've limited it to always use LMUL=1 for now, but we can improve this
in the future.
This requires a bunch of new ISD opcodes to carry the VL operand.
I think we can probably lower intrinsics to these ISD opcodes to
cut down on the size of the isel table. Which is why I've added
patterns for all integer/float types and not just LMUL=1.
I'm only testing one vector width right now, but the width is
programmable via the command line.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D95705
This adds support for commuting operands and converting between
vfmadd and vfmacc to avoid register copies.
To avoid messing up intrinsic behavior, I've added new pseudo
instructions that have the isCommutable flag set. These pseudos also
force a tail agnostic policy. The intrinsic version still use
the tail undisturbed policy.
For best results it looks like we need to start with fmadd and only
pick fmacc if its beneficial. MachineCSE commutes without contraining
the operands and then commutes back if it didn't help with CSE. So
I've made sure that when the operand choice isn't constrained, we
will keep fmadd for MachineCSE and when it does the second commute,
we get back the original instruction.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D95800
This patch adds support for both the fadd reduction intrinsic, in both
the ordered and unordered modes.
The fmin and fmax intrinsics are not currently supported due to a
discrepancy between the LLVM semantics and the RVV ISA behaviour with
regards to signaling NaNs. This behaviour is likely fixed in version 2.3
of the RISC-V F/D/Q extension, but until then the intrinsics can be left
unsupported.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D95870
This patch adds support for the integer reduction intrinsics supported
by RVV. This excludes "mul" which has no corresponding instruction.
The reduction instructions in RVV have slightly complicated type
constraints given they always produce a single "M1" vector register.
They are lowered to custom nodes including the second "scalar" reduction
operand to simplify the patterns and in the hope that they can be useful
for future DAG combines.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D95620
This patch custom-legalizes all integer EXTRACT_VECTOR_ELT nodes where
SEW < XLEN to VMV_S_X nodes to help the compiler infer sign bits from
the result. This allows us to eliminate redundant sign extensions.
For parity, all integer EXTRACT_VECTOR_ELT nodes are legalized this way
so that we don't need TableGen patterns for some and not others.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D95741
This patch adds support for lowering the sqrt intrinsic to the RVV
vfsqrt instruction.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D96012
The vrgather.vv instruction uses a vector of indices with the same
SEW as operand 0. The vrgather.vx instructions use a scalar index
operand of XLen bits.
By splitting this into 2 intrinsics we are able to use LLVMatchType
in the definition to avoid specifying the type for the index operand
when creating the IR for the intrinsic. For .vv it will match the
operand 0 type. And for .vx it will match the type of the vl operand
we already needed to specify a type for.
I'm considering splitting more intrinsics. This was a somewhat
odd one because the .vx doesn't use the element type, it always
use XLen.
Reviewed By: HsiangKai
Differential Revision: https://reviews.llvm.org/D95979
This improves our coverage of these operations and shows that we
use really large constants for division by constant on i8/i16
especially on RV64. The issue is that BuildSDIV/BuildUDIV are
limited to legal types so we have to promote to i64 before it
kicks in. At that point we've lost the range information for the
original type.
Due to a clerical error, the sdiv operation was mapping to vdivu and
udiv to vdiv, when the opposite mapping is the correct one.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D95869
A follow up patch will add support for commuting operands or
changing opcode to vfmacc and friends.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D95662
Rather than materializing the 0xffff immediate for the AND, use
a shift left to remove the upper bits and then shift in zeros
from the right.
This pattern occurs when type legalizing an i16 right shift.
I've implemented this with custom selection code for a number of
reasons. I've limited this to the AND having a single use. We need
to compensate for SimplifyDemandedBits altering the AND mask. I'm
using *W opcodes on RV64. We may want to generlize this in the
future. For all these reason it seemed easiest to do it this way.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D95774
If we're going to end up expanding anyway, we should do it early
so we don't create extra operations to handle the bytes added by
promotion.
This is helfpul on RISCV where we might have to promote i16 all
the way to i64.
Differential Revision: https://reviews.llvm.org/D95756
This demonstrates a missed optimization: the `vmv.x.s` instruction is
used to extract the element from the vector, and this instruction
already sign-extends the value to XLEN.
These instructions have been removed from the 0.94 bitmanip spec.
We should focus on optimizing the codegen without using them.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D95302
This patch adds support for the full range of vector int-to-float,
float-to-int, and float-to-float conversions on legal types.
Many conversions are supported natively in RVV so are lowered with
patterns. These include conversions between (element) types of the same
size, and those that are half/double the size of the input. When
conversions take place between types that are less than half or more
than double the size we must lower them using sequences of instructions
which go via intermediate types.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D95447
In d2927f786e, I added patterns
to remove (and X, 31) from sllw/srlw/sraw shift amounts.
There is code in SelectionDAGISel.cpp that knows to use
computeKnownBits to fill in bits of the mask that were removed
by SimplifyDemandedBits based on bits being known zero.
The non-W shift patterns use immbottomxlenset which allows the
mask to have more than log2(xlen) trailing ones, but doesn't
have a call to computeKnownBits to fill in bits of the mask that may
have been cleared by SimplifyDemandedBits.
This patch copies code from X86 to handle more than log2(xlen)
bottom bits set and uses computeKnownBits to fill in missing bits
before counting.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D95422
This patch fixes some crashes coming from
`RISCVISelLowering::getSetCCResultType`, which would occasionally return
an EVT constructed from an invalid MVT, which has a null Type pointer.
The attached test shows this happening currently for some fixed-length
vectors, which hit this issue when the V extension was enabled, even
though they're not legal types under the V extension. The fix was also
pre-emptively extended to scalable vectors which can't be represented as
an MVT, even though a test case couldn't be found for them.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D95434
Move the Suffix string into the VTypeInfo class so we don't need a helper class to get to it.
Adjust pseudo naming scheme for FPRs to put F16/F32/F64 in
place of F in the pseudo instruction name rather than as a suffix.
This avoids special cases like VFMERGE from the original patch.
Differential Revision: https://reviews.llvm.org/D95404
When spilling, the spill size will depend on the size of register class.
For .vf vector instructions, it may spill the floating point scalar
argument. In order to use the correct load/store instructions for
spilling, we need to provide the correct floating point register class
for the .vf vector pseudo instructions.
In this commit, we define the .vf pseudo instructions as three
different kinds of pseudo instructions for half/float/double. For
example, PseudoVFADD_M1 will become as PseudoVFADD_F16_M1,
PseudoVFADD_F32_M1, and PseudoVFADD_F64_M1.
Differential Revision: https://reviews.llvm.org/D95234
RISCV has to use 2 shifts for (i64 (zext_inreg X, i32)), but we
can use addiw rd, rs1, x0 for sext_inreg. We already understood this
when type legalizing i32 seteq/ne on rv64. But this transform in
SimplifySetCC would sometimes undo it.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D95289
This pattern can occur when an unsigned is used to index an array
on RV64.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D95290
Original patch by @rogfer01.
This patch adds support for insertelt and extractelt operations on
scalable vectors.
Special care must be taken on RV32 when dealing with i64 vectors as
there are no straightforward ways to insert a 64-bit element without a
register of that size. To that end, both are custom-lowered to different
sequences.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Fraser Cormack <fraser@codeplay.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94615
This makes our i8/i16 codegen more similar to the i32 codegen.
I've also added computeKnownBits support for DIVUW/REMUW so
that we can remove zero extending ANDs from the output. Without
this we end up turning DIVUW/REMUW back into DIVU/REMU via some
isel patterns.
Reviewed By: frasercrmck, luismarques
Differential Revision: https://reviews.llvm.org/D95322
As far as I know 32 bits arguments and returns on RV64 are always
sign extended to i64. So I think we should be taking this into
account around libcalls.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D95285
This patch adds support for scalable-vector splats in DAGCombiner's
`isConstantOrConstantVector` and `ISD::matchUnaryPredicate` functions,
which enable the SelectionDAG div/rem-by-constant optimizations for
scalable vector types.
It also fixes up one case where the UDIV optimization was generating a
SETCC without first consulting the target for its preferred SETCC result
type.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94501
This adds support for ".attribute arch" for all extensions that are
currently supported by the compiler.
Differential Revision: https://reviews.llvm.org/D94931
The patterns that use this really want to know if the operand has at
least 32 sign/zero bits.
This increases opportunities to use W instructions when the original
source used i8/i16. Not sure how much this matters for performance,
but it makes i8/i16 code more consistent with i32.
We try to do this during DAG combine with SimplifyDemandedBits,
but it fails if there are multiple nodes using the AND. For
example, multiple shifts using the same shift amount.
In RISC-V there is a single addressing mode of the form imm(reg) where
imm is a signed integer of 12-bit with a range of [-2048..2047] bytes
from reg.
The test MultiSource/UnitTests/C++11/frame_layout of the LLVM test-suite
exercises several scenarios with the stack, including function calls
where the stack will need to be realigned to to a local variable having
a large alignment of 4096 bytes.
In situations of large stacks, the RISC-V backend (in
RISCVFrameLowering) reserves an extra emergency spill slot which can be
used (if no free register is found) by the register scavenger after the
frame indexes have been eliminated. PrologEpilogInserter already takes
care of keeping the emergency spill slots as close as possible to the
stack pointer or frame pointer (depending on what the function will
use). However there is a final alignment step to honour the maximum
alignment of the stack that, when using the stack pointer to access the
emergency spill slots, has the side effect of setting them farther from
the stack pointer.
In the case of the frame_layout testcase, the net result is that we do
have an emergency spill slot but it is so far from the stack pointer
(more than 2048 bytes due to the extra alignment of a variable to 4096
bytes) that it becomes unreachable via any immediate offset.
During elimination of the frame index, many (regular) offsets of the
stack may be immediately unreachable already. Their address needs to be
computed using a register. A virtual register is created and later
RegisterScavenger should be able to find an unused (physical) register.
However if no register is available, RegisterScavenger will pick a
physical register and spill it onto an emergency stack slot, while we
compute the offset (restoring the chosen register after all this). This
assumes that the emergency stack slot is easily reachable (this is,
without requiring another register!).
This is the assumption we seem to break when we perform the extra
alignment in PrologEpilogInserter.
We can "float" the emergency spill slots by increasing (in absolute
value) their offsets from the incoming stack pointer. This way the
emergency spill slots will remain close to the stack pointer (once the
function has allocated storage for the stack, including the needed
realignment). The new size computed in PrologEpilogInserter is padding
so it should be OK to move the emergency spill slots there. Also because
we're increasing the alignment, the new location should stay aligned for
the purpose of the emergency spill slots.
Note that this change also impacts other backends as shown by the tests.
Changes are minor adjustments to the emergency stack slot offset.
Differential Revision: https://reviews.llvm.org/D89239
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
1. Op2 type in vrgather.vx should be XLEN instead of SEW
2. Add double type in vrgather-rv32 cases.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D95207
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 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
Previously we only matched (and (shl X, C1), 0xffffffff << C1)
which matches the InstCombine canonicalization order. But its
possible to see (shl (and X, 0xffffffff), C1) if the pattern
is introduced in SelectionDAG. For example, through expansion of
a GEP.
This is closer to the kind of code that these intrinsics are
targeted at. Note we fail to match slliu.w here because our pattern
looks for (and (shl X, C1), 0xffffffff << C1) rather than
(shl (and X, 0xffffffff), C1). I'll fix this in a follow up
commit.
For Zvlsseg, we need continuous vector registers for the values. We need
to define new register classes for the different combinations of (number
of fields and LMUL). For example,
when the number of fields(NF) = 3, LMUL = 2, the values will be assigned
to (V0M2, V2M2, V4M2), (V2M2, V4M2, V6M2), (V4M2, V6M2, V8M2), ...
We define the vlseg intrinsics with multiple outputs. There is no way to
describe the codegen patterns with multiple outputs in the tablegen
files. We do the codegen in RISCVISelDAGToDAG and use EXTRACT_SUBREG to
extract the values of output.
The multiple scalable vector values will be put into a struct. This
patch is depended on the support for scalable vector struct.
Differential Revision: https://reviews.llvm.org/D94229
If we are able to compare with 0 instead of 1, we might be able
to fold the setcc into a beqz/bnez.
Often these setccs start life as an xor that gets converted to
a setcc by DAG combiner's rebuildSetcc. I looked into a detecting
(xor X, 1) and converting to (seteq X, 0) based on boolean contents
being 0/1 in rebuildSetcc instead of using computeKnownBits. It was
very perturbing to AMDGPU tests which I didn't look closely at.
It had a few changes on a couple other targets, but didn't seem
to be much if any improvement.
Reviewed By: lenary
Differential Revision: https://reviews.llvm.org/D94730
Original patch by @rogfer01.
This patch adds support for sign-, zero-, and any-extension from
scalable mask vector types to integer vector types, as well as
truncation in the opposite direction.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Fraser Cormack <fraser@codeplay.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94590
This recommits 2c51bef76c.
I've fixed the broken check line from when I renamed the test function.
Original commit message:
This builds on D94142 where scalable vectors are allowed in structs.
I did have to fix one scalable vector issue in the vector type
creation for these intrinsics where we used getVectorNumElements
instead of ElementCount.
This builds on D94142 where scalable vectors are allowed in structs.
I did have to fix one scalable vector issue in the vector type
creation for these intrinsics where we used getVectorNumElements
instead of ElementCount.
Differential Revision: https://reviews.llvm.org/D94149
Add Zbt (ternary) extension code generation to the select lowering
tests since it can have a significant impact on how select is
lowered.
While we are here make the neg-abs commands more consistent with
the other tests.
Reviewed By: lenary
Differential Revision: https://reviews.llvm.org/D94798
Original patch by @rogfer01.
This patch supports vector truncates, which on RVV must be done in a
series of instructions truncating by one power-of-two at a time. This is
done through custom-lowering and a custom node to avoid LLVM
re-combining the split TRUNCATE nodes.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Fraser Cormack <fraser@codeplay.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94796
The vcompress intrinsic is defined such that it requires a tail
undisturbed policy. This patch makes it so we can use the tail
agnostic policy if the user has passed vundefined to the dest
operand.
We need to do something similar for masked policy, but we need
annotation of which instructions use the mask policy first.
Not sure if this is sufficient for scheduling or if we'll need to
select different pseudos that don't have a tied def.
Reviewed By: evandro
Differential Revision: https://reviews.llvm.org/D94566
RISC-V would like to use a struct of scalable vectors to return multiple
values from intrinsics. This woud also be needed for target independent
intrinsics like llvm.sadd.overflow.
This patch removes the existing restriction for this. I've modified
StructType::isSized to consider a struct containing scalable vectors
as unsized so the verifier won't allow loads/stores/allocas of these
structs.
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D94142
SimplifyDemandedBits can remove set bits from immediates from instructions
like AND/OR/XOR. This can prevent them from being efficiently
codegened on RISCV.
This adds an initial version that tries to keep or form 12 bit
sign extended immediates for AND operations to enable use of ANDI.
If that doesn't work we'll try to create a 32 bit sign extended immediate
to use LUI+ADDIW.
More optimizations are possible for different size immediates or
different operations. But this is a good starting point that already
has test coverage.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D94628
The first parameter should be selected if the condition is true and
the last parameter if the condition is false. Prior to this change
it was the other way round which was confusing.
Differential Revision: https://reviews.llvm.org/D94729
I noticed in D94450 that there were quite a few places where we generate
the sequence:
```
xN <- comparison ...
xN <- xor xN, 1
bnez xN, symbol
```
Given we know the XOR will be used by BRCOND, which only looks at the lowest
bit, I think we can remove the XOR and just invert the branch condition in
these cases?
The case mostly seems to come up in floating point tests, where there is often
more logic to combine the results of multiple SETCCs, rather than a single
(BRCOND (SETCC ...) ...).
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94535
This regenerates these tests using utils/update_llc_test_checks.py so
that future changes in this area don't have the noise of lots of `@plt`
lines being added.
I also removed the `nounwind`s from the stack-realignment.ll test to
increase coverage on the generated call frame information.
Some FP compares expand to a sequence ending with (xor X, 1) to invert the result. If
the consumer is a select_cc we can likely get rid of this xor by fixing
up the select_cc condition.
This patch combines (select_cc (xor X, 1), 0, setne, trueV, falseV) -
(select_cc X, 0, seteq, trueV, falseV) if we can prove X is 0/1.
Reviewed By: lenary
Differential Revision: https://reviews.llvm.org/D94546
This patch custom lowers ISD::VSCALE into a csrr vlenb followed
by a shift right by 3 followed by a multiply by the scale amount.
I've added computeKnownBits support to indicate that the csrr vlenb
always produces 3 trailng bits of 0s so the shift right is "exact".
This allows the shift and multiply sequence to be nicely optimized
into a single shift or removed completely when the scale amount is
a power of 2.
The non power of 2 case multiplying by 24 is still producing
suboptimal code. We could remove the right shift and use a
multiply by 3. Hopefully we can improve DAG combine to fix that
since it's not unique to this sequence.
This replaces D94144.
Reviewed By: HsiangKai
Differential Revision: https://reviews.llvm.org/D94249
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: lenary, craig.topper
Differential Revision: https://reviews.llvm.org/D93767
We can use a 0 immediate to avoid needing to materialize 0 into
an FPR first.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D94459
If SETO/SETUO aren't legal, they'll be expanded and we'll end up
with 3 comparisons.
SETONE is equivalent to (SETOGT || SETOLT)
so if one of those operations is supported use that expansion. We
don't need both since we can commute the operands to make the other.
SETUEQ can be implemented with !(SETOGT || SETOLT) or (SETULE && SETUGE).
I've only implemented the first because it didn't look like most of the
affected targets had legal SETULE/SETUGE.
Reviewed By: frasercrmck, tlively, nemanjai
Differential Revision: https://reviews.llvm.org/D94450
All i8/i16 and several i32 tests were testing immediate shift amounts
which exceeded the bits in the vector elements, creating poison values.
Amend the tests to test well-behaved shift amounts.
Define the `vfclass` IR intrinsics for the respective V instructions.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Evandro Menezes <evandro.menezes@sifive.com>
Differential Revision: https://reviews.llvm.org/D94356
Original patch by @rogfer01.
This patch adds ISel patterns for the above operations to the
corresponding vector/vector and vector/scalar RVV instructions, as well
as extra patterns to match operand-swapped scalar/vector vfrsub and
vfrdiv.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Fraser Cormack <fraser@codeplay.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94408
Original patch by @rogfer01.
All ordered comparisons except ONE are supported natively, and all
unordered comparisons except UNE are expanded into sequences involving
explicit NaN checks and mask arithmetic.
Additionally, we expand GT,OGT,GE,OGE to their swapped-operand versions, and
pattern-match those back to the "original", swapping operands once more. This
way we catch both operations and both "vf" and "fv" forms with fewer patterns.
Also add support for floating-point splat_vector, with an optimization for
splatting fpimm0.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Fraser Cormack <fraser@codeplay.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94242
Original patch by @rogfer01.
The RVV integer comparison instructions are defined in such a way that
many LLVM operations are defined by using the "opposite" comparison
instruction and swapping the operands. This is done in this patch in
most cases, except for the mappings where the immediate range must be
adjusted to accomodate:
va < i --> vmsle{u}.vi vd, va, i-1, vm
va >= i --> vmsgt{u}.vi vd, va, i-1, vm
That is left for future optimization; this patch supports all operations
but in the case of the missing mappings the immediate will be moved to
a scalar register first.
Since there are so many condition codes and operand cases to check, it
was decided to reduce the test burden by only testing the "vscale x 8"
vector types.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Fraser Cormack <fraser@codeplay.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94168
This improves llvm::isConstOrConstSplat by allowing it to analyze
ISD::SPLAT_VECTOR nodes, in order to allow more constant-folding of
operations using scalable vector types.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94168
This is a first change needed to fix a crash in which the emergency
spill splot ends being out of reach. This happens when we run the
register scavenger after we have eliminated the frame indexes. The fix
for the actual crash will come in a later change.
This change removes an extra stack size increase we do in
RISCVFrameLowering::determineFrameLayout.
We don't have to change the size of the stack here as
PEI::calculateFrameObjectOffsets is already doing this with the right
size accounting the extra alignment.
Differential Revision: https://reviews.llvm.org/D89237
1. Break MUL with specific constant to a SLLI and an ADD/SUB on riscv32
with the M extension.
2. Break MUL with specific constant to two SLLI and an ADD/SUB, if the
constant needs a pair of LUI/ADDI to construct.
Reviewed by: craig.topper
Differential Revision: https://reviews.llvm.org/D93619
Define the `vfsqrt` IR intrinsics for the respective V instructions.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Evandro Menezes <evandro.menezes@sifive.com>
Differential Revision: https://reviews.llvm.org/D93745
The patterns that want to use 'vnot' use a custom PatFrag. This is
because 'vnot' uses immAllOnesV which implicitly uses BUILD_VECTOR
rather than SPLAT_VECTOR.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94078
There is no test coverage for the mulhs or mulhu patterns as I can't get
the DAGCombiner to generate them for scalable vectors. There are a few
places in that still need updating for that to work. I left the patterns
in regardless as they are correct.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D94073
This alias for andi x, 255 was recently added to the spec. If we
print it, code we output can't be compiled with -fno-integrated-as
unless the GNU assembler is also a version that supports alias.
Reviewed By: lenary
Differential Revision: https://reviews.llvm.org/D93826
There are vmsle(u).vx and vmsle(u).vi instructions, but there is
only vmslt(u).vx and no vmslt(u).vi. vmslt(u).vi can be emulated
for some immediates by decrementing the immediate and using vmsle(u).vi.
To avoid the user needing to know about this, this patch does this
conversion.
The assembler does the same thing for vmslt(u).vi and vmsge(u).vi
pseudoinstructions. There is no vmsge(u).vx intrinsic or
instruction so this patch is limited to vmslt(u).
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D94070
With the i32 these patterns will only fire on RV32, but they
don't look RV32 specific.
Reviewed By: lenary
Differential Revision: https://reviews.llvm.org/D93843
One or more cmov instructions could be generated for these functions
when the Zbt extension is present.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93768
Define intrinsics:
1. vfcvt.xu.f.v/vfcvt.x.f.v
2. vfcvt.rtz.xu.f.v/vfcvt.rtz.x.f.v
3. vfcvt.f.xu.v/vfcvt.f.x.v
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Monk Chiang <monk.chiang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93933
Define intrinsics:
1. vfncvt.xu.f.w/vfncvt.x.f.w
2. vfncvt.rtz.xu.f.w/vfncvt.rtz.x.f.w
3. vfncvt.f.xu.w/vfncvt.f.x.w
4. vfncvt.f.f.w/vfncvt.rod.f.f.w
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Monk Chiang <monk.chiang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93932
Define intrinsics:
1. vfwcvt.xu.f.v/vfwcvt.x.f.v
2. vfwcvt.rtz.xu.f.v/vfwcvt.rtz.x.f.v
3. vfwcvt.f.xu.v/vfwcvt.f.x.v
4. vfwcvt.f.f.v
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Monk Chiang <monk.chiang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93855
The matching for intrinsic names is forgiving about types in the
name being absent or wrong. Once the intrinsic is parsed its
name will remangled to include the real types.
This commit fixes the names to have at least enough correct types
so that the name used in the test is a prefix of the canonical name.
The big missing part is the type for the VL parameter which changes
size between rv32 and rv64.
While I was in here I noticed that we were missing some tests for
double on rv32 so I fixed that by copying from rv64 and fixing up
the VL argument type.
This patch defines vcompress intrinsics and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Differential revision: https://reviews.llvm.org/D93809
Define vsext/vzext intrinsics.and lower to V instructions.
Define new fraction register class fields in LMULInfo and a
NoReg to present invalid LMUL register classes.
Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93893
This complements the existing RVV ISel patterns for arithmetic, bitwise
and shifts with the remaining operations in those categories: sub, and,
xor, sra.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93852
If the destination is tied, then user has some control of the
register used for input. They would have the ability to control
the value of any tail elements. By using tail agnostic we take
this option away from them.
Its not clear that the intrinsics are defined such that this isn't
supposed to work. And undisturbed is a valid implementation for agnostic
so code wouldn't even fail to work on all systems if we always used
agnostic.
The vcompress intrinsic is defined to require tail undisturbed so
at minimum we need this for that instruction or need to redefine
the intrinsic.
I've made an exception here for vmv.s.x/fmv.s.f and reduction
instructions which only write to element 0 regardless of the tail
policy. This allows us to keep the agnostic policy on those which
should allow better redundant vsetvli removal.
An enhancement would be to check for undef input and keep the
agnostic policy, but we don't have good test coverage for that yet.
Reviewed By: khchen
Differential Revision: https://reviews.llvm.org/D93878
The spec for these instructions include this note. "The destination register
cannot overlap either the source register or the mask register ('v0') if the
instruction is masked." So we need earlyclobber to enforce this constraint.
I've regenerated the tests with update_llc_test_checks.py to show the
effects of the earlyclobber.
Reviewed By: khchen, frasercrmck
Differential Revision: https://reviews.llvm.org/D93867
Define vmclr.m/vmset.m intrinsics and lower to vmxor.mm/vmxnor.mm.
Ideally all rvv pseudo instructions could be implemented in C header,
but those two instructions don't take an input, codegen can not guarantee
that the source register becomes the same as the destination.
We expand pseduo-v-inst into corresponding v-inst in
RISCVExpandPseudoInsts pass.
Reviewed By: craig.topper, frasercrmck
Differential Revision: https://reviews.llvm.org/D93849
Define those intrinsics and lower to V instructions.
Use update_llc_test_checks.py for viota.m tests to check
earlyclobber is applied correctly.
mask viota.m tests uses the same argument as input and mask for
avoid dependency of D93364.
We work with @rogfer01 from BSC to come out this patch.
Reviewed By: HsiangKai
Differential Revision: https://reviews.llvm.org/D93823
Define vwredsumu/vwredsum/vfwredosum/vfwredsum
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Differential Revision: https://reviews.llvm.org/D93807
Define vpopc/vfirst intrinsics and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93795
Define vector mask-register logical intrinsics and lower them
to V instructions. Also define pseudo instructions vmmv.m
and vmnot.m.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Differential Revision: https://reviews.llvm.org/D93705
This patch defines vrgather intrinsics and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Differential revision: https://reviews.llvm.org/D93797
integer group:
vredsum/vredmaxu/vredmax/vredminu/vredmin/vredand/vredor/vredxor
float group:
vfredosum/vfredsum/vfredmax/vfredmin
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Differential Revision: https://reviews.llvm.org/D93746
This patch extends the SDNode ISel support for RVV from only the
vector/vector instructions to include the vector/scalar and
vector/immediate forms.
It uses splat_vector to carry the scalar in each case, except when
XLEN<SEW (RV32 SEW=64) when a custom node `SPLAT_VECTOR_I64` is used for
type-legalization and to encode the fact that the value is sign-extended
to SEW. When the scalar is a full 64-bit value we use a sequence to
materialize the constant into the vector register.
The non-intrinsic ISel patterns have also been split into their own
file.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Fraser Cormack <fraser@codeplay.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93312
Also include a special case pattern to use vmv.v.x vd, zero when
the argument is 0.0.
Reviewed By: khchen
Differential Revision: https://reviews.llvm.org/D93672
This patch defines vfwmacc, vfwnmacc, vfwmsc, vfwnmsac intrinsics
and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Differential Revision: https://reviews.llvm.org/D93693
Define vmerge/vfmerge intrinsics and lower to V instructions.
Include support for vector-vector vfmerge by vmerge.vvm.
We work with @rogfer01 from BSC to come out this patch.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93674
Define the vfmin, vfmax IR intrinsics for the respective V instructions.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Evandro Menezes <evandro.menezes@sifive.com>
Differential Revision: https://reviews.llvm.org/D93673
This patch defines vfmadd/vfnmacc, vfmsac/vfnmsac, vfmadd/vfnmadd,
and vfmsub/vfnmsub lower to V instructions.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Differential Revision: https://reviews.llvm.org/D93691
This patch defines vwmacc[u|su|us] intrinsics and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Differential Revision: https://reviews.llvm.org/D93675
This patch enables jump table lowering in the RISC-V backend.
In addition to the test case included, the new lowering was
tested by compiling the OCaml runtime and running it under qemu.
Differential Revision: https://reviews.llvm.org/D92097
Define vector compare intrinsics and lower them to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93368
Define vleff intrinsics and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93516
This defines vmadd, vmacc, vnmsub, and vnmsac intrinsics and
lower to V instructions.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Differential Revision: https://reviews.llvm.org/D93632
Define the `vand`, `vor` and `vxor` IR intrinsics for the respective V instructions.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Evandro Menezes <evandro.menezes@sifive.com>
Differential Revision: https://reviews.llvm.org/D93574
This patch base on D93366, and define vector fixed-point intrinsics.
1. vaaddu/vaadd/vasubu/vasub
2. vsmul
3. vssrl/vssra
4. vnclipu/vnclip
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Differential Revision: https://reviews.llvm.org/D93508
Define vector vfwmul intrinsics and lower them to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93584
Define vector vfwadd/vfwsub intrinsics and lower them to V
instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93583
Define vector vfsgnj/vfsgnjn/vfsgnjx intrinsics and lower them to V
instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93581
Define vector vfmul/vfdiv/vfrdiv intrinsics and lower them to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93580
Define vlxe/vsxe intrinsics and lower to vlxei<EEW>/vsxei<EEW>
instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Differential Revision: https://reviews.llvm.org/D93471
To support OpenCL, which typically uses SPIR as an IR, non-zero address
spaces must be accounted for. This patch makes the RISC-V target assume
no-op address space casts across the board, which effectively removes
the need to support addrspacecast instructions in the backend.
For a RISC-V implementation with different configurations or specialized
address spaces where casts aren't no-ops, the function can be adjusted
as required.
Reviewed By: jrtc27
Differential Revision: https://reviews.llvm.org/D93536
This patch adds two IR intrinsics for vsetvli instruction. One to set the vector length to a user specified value and one to set it to vlmax. The vlmax uses the X0 source register encoding.
Clang builtins will follow in a separate patch
Differential Revision: https://reviews.llvm.org/D92973
The default behavior for any_extend of a constant is to zero extend.
This occurs inside of getNode rather than allowing type legalization
to promote the constant which would sign extend. By using sign extend
with getNode the constant will be sign extended. This gives a better
chance for isel to find a simm5 immediate since all xlen bits are
examined there.
For instructions that use a uimm5 immediate, this change only affects
constants >= 128 for i8 or >= 32768 for i16. Constants that large
already wouldn't have been eligible for uimm5 and would need to use a
scalar register.
If the instruction isn't able to use simm5 or the immediate is
too large, we'll need to materialize the immediate in a register.
As far as I know constants with all 1s in the upper bits should
materialize as well or better than all 0s.
Longer term we should probably have a SEW aware PatFrag to ignore
the bits above SEW before checking simm5.
I updated about half the test cases in some tests to use a negative
constant to get coverage for this.
Reviewed By: evandro
Differential Revision: https://reviews.llvm.org/D93487
This time with tests.
Original message:
Similar to D93365, but for floating point. No need for special ISD opcodes
though. We can directly isel these from intrinsics. I had to use anyfloat_ty
instead of anyvector_ty in the intrinsics to make LLVMVectorElementType not
crash when imported into the -gen-dag-isel tablegen backend.
Differential Revision: https://reviews.llvm.org/D93426
This adds intrinsics for vmv.x.s and vmv.s.x.
I've used stricter type constraints on these intrinsics than what we've been doing on the arithmetic intrinsics so far. This will allow us to not need to pass the scalar type to the Intrinsic::getDeclaration call when creating these intrinsics.
A custom ISD is used for vmv.x.s in order to implement the change in computeNumSignBitsForTargetNode which can remove sign extends on the result.
I also modified the MC layer description of these instructions to show the tied source/dest operand. This is different than what we do for masked instructions where we drop the tied source operand when converting to MC. But it is a more accurate description of the instruction. We can't do this for masked instructions since we use the same MC instruction for masked and unmasked. Tools like llvm-mca operate in the MC layer and rely on ins/outs and Uses/Defs for analysis so I don't know if we'll be able to maintain the current behavior for masked instructions. So I went with the accurate description here since it was easy.
Reviewed By: frasercrmck
Differential Revision: https://reviews.llvm.org/D93365
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Craig Topper <craig.topper@sifive.com>
Differential Revision: https://reviews.llvm.org/D93514
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: ShihPo Hung <shihpo.hung@sifive.com>
Co-Authored-by: Monk Chiang <monk.chiang@sifive.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93366
Define vlse/vsse intrinsics and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93445
Define vector widening mul intrinsics and lower them to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93381
Define vector mul/div/rem intrinsics and lower them to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93380
If users want to use vector floating point instructions, they need to
specify 'F' extension additionally.
Differential Revision: https://reviews.llvm.org/D93282
Define vle/vse intrinsics and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Zakk Chen <zakk.chen@sifive.com>
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93359
Refine tablegen pattern for vector load/store, and follow
D93012 to separate masked and unmasked definitions for
pseudo load/store instructions.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D93284
Define vfadd/vfsub/vfrsub intrinsics and lower to V instructions.
We work with @rogfer01 from BSC to come out this patch.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93291
Define vwadd/vwaddu/vwsub/vwsubu intrinsics and lower to V instructions.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Hsiangkai Wang <kai.wang@sifive.com>
Differential Revision: https://reviews.llvm.org/D93108
Add simple pass for removing redundant vsetvli instructions within a basic block. This handles the case where the AVL register and VTYPE immediate are the same and no other instructions that change VTYPE or VL are between them.
There are going to be more opportunities for improvement in this space as we development more complex tests.
Differential Revision: https://reviews.llvm.org/D92679
The compiler is making no effort to preserve upper elements. To do so would require another source operand tied with the destination and a different intrinsic interface to give control of this source to the programmer.
This patch changes the tail policy to agnostic so that the CPU doesn't need to make an effort to preserve them.
This is consistent with the RVV intrinsic spec here https://github.com/riscv/rvv-intrinsic-doc/blob/master/rvv-intrinsic-rfc.md#configuration-setting
Differential Revision: https://reviews.llvm.org/D93080
There is an in-progress proposal for the following pseudo-instructions
in the assembler, to complement the existing `sext.w` rv64i instruction:
- sext.b
- sext.h
- zext.b
- zext.h
- zext.w
The `.b` and `.h` variants are available with rv32i and rv64i, and `zext.w` is
only available with `rv64i`.
These are implemented primarily as pseudo-instructions, as these instructions
expand to multiple real instructions. In the case of `zext.b`, this expands to a
single rv32/64i instruction, so it is implemented with an InstAlias (like
`sext.w` is on rv64i).
The proposal is available here: https://github.com/riscv/riscv-asm-manual/pull/61
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D92793
If SETUNE isn't legal, UO can use the NOT of the SETO expansion.
Removes some complex isel patterns. Most of the test changes are
from using XORI instead of SEQZ.
Differential Revision: https://reviews.llvm.org/D92008
Regenerated using:
./llvm/utils/update_llc_test_checks.py -u llvm/test/CodeGen/RISCV/*.ll
This has added comments to spill-related instructions and added @plt to
some symbols.
Differential Revision: https://reviews.llvm.org/D92841
We can use these instructions for single bit immediates that are too large for ANDI/ORI/CLRI.
The _10 test cases are to make sure that we still use ANDI/ORI/CLRI for small immediates.
Differential Revision: https://reviews.llvm.org/D92262
A rotate by half the bitwidth swaps the bottom and top half which is the same as one of the MSB GREVI stage.
We have to do this as a special combine because we prefer to keep (rotl/rotr X, BitWidth/2) as a rotate rather than a single stage GREVI.
Differential Revision: https://reviews.llvm.org/D92286
Move fold of (sext (not i1 x)) -> (add (zext i1 x), -1) from X86 to DAGCombiner to improve codegen on other targets.
Differential Revision: https://reviews.llvm.org/D91589
clang/lib/CodeGen/CodeGenModule sets dso_local on applicable function declarations,
we don't need to duplicate the work in TargetMachine:shouldAssumeDSOLocal.
(Actually the long-term goal (started by r324535) is to drop TargetMachine::shouldAssumeDSOLocal.)
By not implying dso_local, we will respect dso_local/dso_preemptable specifiers
set by the frontend. This allows the proposed -fno-direct-access-external-data
option to work with -fno-pic and prevent a canonical PLT entry (SHN_UNDEF with non-zero st_value)
when taking the address of a function symbol.
This patch should be NFC in terms of the Clang emitted assembly because the case
we don't set dso_local is a case Clang sets dso_local. However, some tests don't
set dso_local on some function declarations and expose some differences. Most
tests have been fixed to be more robust in the previous commit.
The companion RFC (http://lists.llvm.org/pipermail/llvm-dev/2020-October/145850.html) gives lots of details on the overall strategy, but we summarize it here:
LLVM IR involving vector types is going to be selected using pseudo instructions (only MachineInstr). These pseudo instructions contain dummy operands to represent the vector type being operated and the vector length for the operation.
These two dummy operands, as set by instruction selection, will be used by the custom inserter to prepend every operation with an appropriate vsetvli instruction that ensures the vector architecture is properly configured for the operation. Not in this patch: later passes will remove the redundant vsetvli instructions.
Register classes of tuples of vector registers are used to represent vector register groups (LMUL > 1).
Those pseudos are eventually lowered into the actual instructions when emitting the MCInsts.
About the patch:
Because there is a bit of initial infrastructure required, this is the minimal patch that allows us to select instructions for 3 LLVM IR instructions: load, add and store vectors of integers. LLVM IR operations have "whole-vector" semantics (as in they generate values for all the elements).
Later patches will extend the information represented in TableGen.
Authored-by: Roger Ferrer Ibanez <rofirrim@gmail.com>
Co-Authored-by: Evandro Menezes <evandro.menezes@sifive.com>
Co-Authored-by: Craig Topper <craig.topper@sifive.com>
Differential Revision: https://reviews.llvm.org/D89449
This makes the llvm-objdump output much more readable and closer to binutils objdump. This builds on D76591
It requires changing the OperandType for certain immediates to "OPERAND_PCREL" so tablegen will generate code to pass the instruction's address. This means we can't do the generic check on these instructions in verifyInstruction any more. Should I add it back with explicit opcode checks? Or should we add a new operand flag to control the passing of address instead of matching the name?
Differential Revision: https://reviews.llvm.org/D92147
This enables bswap/bitreverse to combine with other GREVI patterns or each other without needing to add more special cases to the DAG combine or new DAG combines.
I've also enabled the existing GREVI combine for GREVIW so that it can pick up the i32 bswap/bitreverse on RV64 after they've been type legalized to GREVIW.
Differential Revision: https://reviews.llvm.org/D92253
Not sure why bswap was treated specially. This also applies to bitreverse
or generic grevi. We can improve this in future patches.
For now I just wanted to get the consistency and the test coverage
as I plan to make some other changes around bswap.
If Sext is cheaper than Zext for a target, we can use that to promote the operands of UMIN/UMAX. Using sext just makes numbers with the sign bit set even larger when treated as an unsigned number and it has no effect on number without the sign bit set. So the relative order doesn't change. This is similar to what we already do for promoting SETCC.
This is helpful on RISCV where i32 arguments are sign extended on RV64 and many instructions are able to produce results with 33 sign bits.
Differential Revision: https://reviews.llvm.org/D92128
Start with an assumption that FMA is faster than Fmul+FAdd. If thats not true
on some particular implementation we can add a tuning parameter in the future.
I've update the fmuladd test cases and added new test cases for fast math flag
based contraction.
Differential Revision: https://reviews.llvm.org/D91987
We currently don't match this which limits the effectiveness of D91120 until
InstCombine starts canonicalizing to llvm.abs. This should be easy to remove
if/when we remove the SPF_ABS handling.
Differential Revision: https://reviews.llvm.org/D92118
This is the logically correct thing to do. But it generates worse
code for i32 umin/umax on the rv64 due to type legalize requesting
zext even though the arguments are sext. Maybe we can teach type
legalizer to use sext for umin/umax for RISCV.
It's also producing possibly worse code on i64 on RV32 since we
still end up with selects that become branches. But this seems
like something we could improve in type legalization or DAG combine.
Hopefully this makes D92095 work for RISCV with Zbb.
This adds custom opcodes for FSLW/FSRW so we can type legalize
fshl/fshr without needing to match a sign_extend_inreg.
I've used the operand order from fshl/fshr to make the isel
pattern similar to the non-W form. It was also hard to decide
another order since the register instruction has the shift amount
as the second operand, but the immediate instruction has it as
the third operand.
Differential Revision: https://reviews.llvm.org/D91479
This is a special calling convention to be used by the GHC compiler.
Patch by Andreas Schwab (schwab)
Differential Revision: https://reviews.llvm.org/D89788
X86 was already specially marking fma as commutable which allowed
tablegen to autogenerate commuted patterns. This moves it to the target
independent definition and fix up the targets to remove now
unneeded patterns.
Unfortunately, the tests change because the commuted version of
the patterns are generating operands in a different than the
explicit patterns.
Differential Revision: https://reviews.llvm.org/D91842
Previously we required a sra to pattern match these properly in isel. If the consumer didn't need the result sign extended we'll have an srl instead of sra and fail to match.
This patch switches to custom legalizing to GREVIW using portions of D91259.
Differential Revision: https://reviews.llvm.org/D91457
This should result in better utilization of RORIW since we
don't need to look for a SIGN_EXTEND_INREG that may not exist.
Also remove rotl/rotr isel matching to GREVI and just prefer RORI.
This is to keep consistency so we don't have to match ROLW/RORW
to GREVIW as well. I imagine RORI/RORIW performance will be the
same or better than GREVI.
Differential Revision: https://reviews.llvm.org/D91449
This moves the recognition of GREVI and GORCI from TableGen patterns
into a DAGCombine. This is done primarily to match "deeper" patterns in
the future, like (grevi (grevi x, 1) 2) -> (grevi x, 3).
TableGen is not best suited to matching patterns such as these as the compile
time of the DAG matchers quickly gets out of hand due to the expansion of
commutative permutations.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D91259
We need to make sure the upper 32 bits are all ones to ensure the result is properly sign extended. Previously we only checked the lower 32 bits of the mask. I've also added a check that the shift amount is less than 32. Without that the original code asserts inside maskLeadingOnes if the SROI check is removed or the SROIW pattern is checked first. I've refactored the code to use early outs to reduce nesting.
I've also updated SLOIW matching with the same changes, but I couldn't find a broken test case with the existing code.
Differential Revision: https://reviews.llvm.org/D90961
The fshl and fshr intrinsics are defined to modulo their shift amount by the bitwidth of one of their inputs. The FSR/FSL instructions read one extra bit from the shift amount. If that bit is set the inputs are swapped. In order to preserve the semantics of the llvm intrinsics we need to make sure that the extra bit isn't set. DAG combine or instcombine may have removed any mask that was originally present.
We could be smarter here and try to use computeKnownBits to check if the bit is known zero, but wanted to start with correctness.
Differential Revision: https://reviews.llvm.org/D90905
This uses the shiftop PatFrags to handle the masked shift amount
and unmasked shift amount cases. That also checks XLen as part
of the masked amount check so we don't need separate RV32 and RV64
patterns.
Differential Revision: https://reviews.llvm.org/D91016
Out of bounds shifts are undefined and these instructions mask
their shift amount before use. So we don't need to see a mask
in order to select the instructions.
The multiply part of FMA is commutable, but TargetSelectionDAG.td
doesn't have it marked as commutable so tablegen won't automatically
create the additional patterns.
So manually add commuted patterns.
D80526 added custom lowering to pick the si lib call on RV64, but this custom handling is only enabled when the F and D extension are both disabled. This prevents the si library call from being used for double when F is enabled but D is not.
This patch changes the behavior so we always enable the Custom hook on RV64 and decide in ReplaceNodeResults if we should emit a libcall based on whether the FP type should be softened or not.
Differential Revision: https://reviews.llvm.org/D90817
There is no FSLI instruction, but we can emulate it using FSRI by swapping operands and subtracting the immediate from the bitwidth.
Differential Revision: https://reviews.llvm.org/D90826
With new test file this time.
Original message
This new test covers both with and without the F extension enabled.
This shows that the fptosi/fptoui for double->i32 use a different
libcall depending on whether the F extension is enabled. If it's
not enabled we use the 'si' library call. If it is enabled we use 'di'.
This new test covers both with and without the F extension enabled.
This shows that the fptosi/fptoui for double->i32 use a different
libcall depending on whether the F extension is enabled. If it's
not enabled we use the 'si' library call. If it is enabled we use 'di'.
fsl/fsr take their shift amount in $rs2 or an immediate. The
sources are $rs1 and $rs3.
fshl/fshr ISD opcodes both concatenate operand 0 in the high bits and
operand 1 in the lower bits. fshl returns the high bits after
shifting and fshr returns the low bits. So a shift amount of 0
returns operand 0 for fshl and operand 1 for fshr.
fsl/fsr concatenate their operands in different orders such that
$rs1 will be returned for a shift amount of 0. So $rs1 needs to
come from operand 0 of fshl and operand 1 of fshr.
Differential Revision: https://reviews.llvm.org/D90735
We need to ensure the upper 32 bits of the mask are zero.
So that the srl shifts zeroes into the lower 32 bits.
Differential Revision: https://reviews.llvm.org/D90585
DAGCombine doesn't canonicalize rotl/rotr with immediate so we
need patterns for both.
Remove the custom matcher for rotl to RORI and just use a SDNodeXForm
to convert the immediate instead. Doing this gives priority to the
rev32/rev16 versions of grevi over rori since an explicit immediate
is more precise than any immediate. I also added rotr patterns for
rev32/rev16. And removed the (or (shl), (shr)) patterns that should be
combined to rotl by DAG combine.
There is at least one other grev pattern that probably needs a
another rotr pattern, but we need more test coverage first.
Differential Revision: https://reviews.llvm.org/D90575
ADDI often has a frameindex in operand 1, but consumers of this
interface, such as MachineSink, tend to call getReg() on the Destination
and Source operands, leading to the following crash when building
FreeBSD after this implementation was added in 8cf6778d30:
```
clang: llvm/include/llvm/CodeGen/MachineOperand.h:359: llvm::Register llvm::MachineOperand::getReg() const: Assertion `isReg() && "This is not a register operand!"' failed.
PLEASE submit a bug report to https://bugs.llvm.org/ and include the crash backtrace, preprocessed source, and associated run script.
Stack dump:
#0 0x00007f4286f9b4d0 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) llvm/lib/Support/Unix/Signals.inc:563:0
#1 0x00007f4286f9b587 PrintStackTraceSignalHandler(void*) llvm/lib/Support/Unix/Signals.inc:630:0
#2 0x00007f4286f9926b llvm::sys::RunSignalHandlers() llvm/lib/Support/Signals.cpp:71:0
#3 0x00007f4286f9ae52 SignalHandler(int) llvm/lib/Support/Unix/Signals.inc:405:0
#4 0x00007f428646ffd0 (/lib/x86_64-linux-gnu/libc.so.6+0x3efd0)
#5 0x00007f428646ff47 raise /build/glibc-2ORdQG/glibc-2.27/signal/../sysdeps/unix/sysv/linux/raise.c:51:0
#6 0x00007f42864718b1 abort /build/glibc-2ORdQG/glibc-2.27/stdlib/abort.c:81:0
#7 0x00007f428646142a __assert_fail_base /build/glibc-2ORdQG/glibc-2.27/assert/assert.c:89:0
#8 0x00007f42864614a2 (/lib/x86_64-linux-gnu/libc.so.6+0x304a2)
#9 0x00007f428d4078e2 llvm::MachineOperand::getReg() const llvm/include/llvm/CodeGen/MachineOperand.h:359:0
#10 0x00007f428d8260e7 attemptDebugCopyProp(llvm::MachineInstr&, llvm::MachineInstr&) llvm/lib/CodeGen/MachineSink.cpp:862:0
#11 0x00007f428d826442 performSink(llvm::MachineInstr&, llvm::MachineBasicBlock&, llvm::MachineInstrBundleIterator<llvm::MachineInstr, false>, llvm::SmallVectorImpl<llvm::MachineInstr*>&) llvm/lib/CodeGen/MachineSink.cpp:918:0
#12 0x00007f428d826e27 (anonymous namespace)::MachineSinking::SinkInstruction(llvm::MachineInstr&, bool&, std::map<llvm::MachineBasicBlock*, llvm::SmallVector<llvm::MachineBasicBlock*, 4u>, std::less<llvm::MachineBasicBlock*>, std::allocator<std::pair<llvm::MachineBasicBlock* const, llvm::SmallVector<llvm::MachineBasicBlock*, 4u> > > >&) llvm/lib/CodeGen/MachineSink.cpp:1073:0
#13 0x00007f428d824a2c (anonymous namespace)::MachineSinking::ProcessBlock(llvm::MachineBasicBlock&) llvm/lib/CodeGen/MachineSink.cpp:410:0
#14 0x00007f428d824513 (anonymous namespace)::MachineSinking::runOnMachineFunction(llvm::MachineFunction&) llvm/lib/CodeGen/MachineSink.cpp:340:0
```
Thus, check that operand 1 is also a register in the condition.
Reviewed By: arichardson, luismarques
Differential Revision: https://reviews.llvm.org/D89090
The code is looking for (sext_inreg (or (shl X, C2), (shr (and Y, C3), C1))).
We need to ensure X and Y are the same.
Differential Revision: https://reviews.llvm.org/D90580
When validating C3 in (sext_inreg (or (shl X, C2), (shr (and Y, C3), C1)), i32)
we are truncating it to 32 bits before checking its value. We need
to check all 64 bits.
The function is matching (sext_inreg (or (shl X, C2), (shr (and Y, C3), C1))),
with appropriate checks for the constants to be a rotate. But it
fails to check that X and Y are the same which is also necessary.
fshl/fshr intrinsics turn into rotl/rotr ISD opcodes and we don't
have a complete set of patterns.
We pattern match rotl, but we have a custom match for rori that gets
priority. We don't pattern match rotr and we don't have patterns
or custom code for rori from rotr.
The fshr intrinsic with same inputs produces rotr ISD node. The
fshl intrinsic produces rotl ISD node.
There were only test cases and isel patterns for the fshl/rotl case.
This patch adds fshr/rotr test cases.
This combine makes two calls to SimplifyDemandedBits, one for the LHS and one
for the RHS. If the LHS call returns true, we don't make the RHS call. When
SimplifyDemandedBits makes a change, it will add the nodes around the change to
the DAG combiner worklist. If the simplification happens on the first recursion
step, the N will get added to the worklist. But if the simplification happens
deeper in the recursion, then N will not be revisited until the next time the
DAG combiner runs.
This patch explicitly addes N to the worklist anytime a Simplification is made.
Without this we might miss additional simplifications on the LHS or never
simplify the RHS. Special care also needs to be taken to not add N if it has
been CSEd by the simplification. There are similar examples in DAGCombiner and
the X86 target, but I don't have a test for it for RISC-V. I've also returned
SDValue(N, 0) instead of SDValue() so DAGCombiner knows a change was made and
will update its Statistic variable.
The test here was constructed so that 2 simplifications happen to the LHS.
Without this fix one happens in the post type legalization DAG combine and the
other happens after LegalizeDAG. This prevents the RHS from ever being
simplified causing the left and right shift to clear the upper 32 bits of the
RHS to be left behind.
Differential Revision: https://reviews.llvm.org/D90339
Based on a discussion on D88783, if we're promoting a funnel shift to a width at least twice the size as the original type, then we can use the 'double shift' patterns (shifting the concatenated sources).
Differential Revision: https://reviews.llvm.org/D89139
Currenlty assume x18 is used as pointer to shadow call stack. User shall pass
flags:
"-fsanitize=shadow-call-stack -ffixed-x18"
Runtime supported is needed to setup x18.
If SCS is desired, all parts of the program should be built with -ffixed-x18 to
maintain inter-operatability.
There's no particuluar reason that we must use x18 as SCS pointer. Any register
may be used, as long as it does not have designated purpose already, like RA or
passing call arguments.
Differential Revision: https://reviews.llvm.org/D84414
The isTriviallyRematerializable hook is only called for instructions that are
tagged as isAsCheapAsAMove. Since ADDI 0 is used for "mv" it should definitely
be marked with "isAsCheapAsAMove". This change avoids one stack spill in most of
the atomic-rmw.ll tests functions. It also avoids stack spills in two of our
out-of-tree CHERI tests.
ORI/XORI with zero may or may not be the same as a move micro-architecturally,
but since we are already doing it for register == x0, we might as well
do the same if the immediate is zero.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D86480
PseudoBRIND had seemingly inherited incorrect annotations denoting it as
a call instruction and that it defines X1/ra. This caused excess
save/restore code to be emitted for ra.
Differential Revision: https://reviews.llvm.org/D86286
In SelectionDAGBuilder always translate the fshl and fshr intrinsics to
FSHL and FSHR (or ROTL and ROTR) instead of lowering them to shifts and
ORs. Improve the legalization of FSHL and FSHR to avoid code quality
regressions.
Differential Revision: https://reviews.llvm.org/D77152
This fixes the "Unable to insert indirect branch" fatal error sometimes
seen when generating position-independent code.
Patch by msizanoen1
Reviewed By: jrtc27
Differential Revision: https://reviews.llvm.org/D84833
Similarly as for pointers, even for integers a == b is usually false.
GCC also uses this heuristic.
Reviewed By: ebrevnov
Differential Revision: https://reviews.llvm.org/D85781
Similarly as for pointers, even for integers a == b is usually false.
GCC also uses this heuristic.
Reviewed By: ebrevnov
Differential Revision: https://reviews.llvm.org/D85781
Similarly as for pointers, even for integers a == b is usually false.
GCC also uses this heuristic.
Reviewed By: ebrevnov
Differential Revision: https://reviews.llvm.org/D85781
This patch provides optimization of bit manipulation operations by
enabling the +experimental-b target feature.
It adds matching of single block patterns of instructions to specific
bit-manip instructions from the ternary subset (zbt subextension) of the
experimental B extension of RISC-V.
It adds also the correspondent codegen tests.
This patch is based on Claire Wolf's proposal for the bit manipulation
extension of RISCV:
https://github.com/riscv/riscv-bitmanip/blob/master/bitmanip-0.92.pdf
Differential Revision: https://reviews.llvm.org/D79875
This patch provides optimization of bit manipulation operations by
enabling the +experimental-b target feature.
It adds matching of single block patterns of instructions to specific
bit-manip instructions from the single-bit subset (zbs subextension) of
the experimental B extension of RISC-V.
It adds also the correspondent codegen tests.
This patch is based on Claire Wolf's proposal for the bit manipulation
extension of RISCV:
https://github.com/riscv/riscv-bitmanip/blob/master/bitmanip-0.92.pdf
Differential Revision: https://reviews.llvm.org/D79874
This patch provides optimization of bit manipulation operations by
enabling the +experimental-b target feature.
It adds matching of single block patterns of instructions to specific
bit-manip instructions belonging to both the permutation and the base
subsets of the experimental B extension of RISC-V.
It adds also the correspondent codegen tests.
This patch is based on Claire Wolf's proposal for the bit manipulation
extension of RISCV:
https://github.com/riscv/riscv-bitmanip/blob/master/bitmanip-0.92.pdf
Differential Revision: https://reviews.llvm.org/D79873
This patch provides optimization of bit manipulation operations by
enabling the +experimental-b target feature.
It adds matching of single block patterns of instructions to specific
bit-manip instructions from the permutation subset (zbp subextension) of
the experimental B extension of RISC-V.
It adds also the correspondent codegen tests.
This patch is based on Claire Wolf's proposal for the bit manipulation
extension of RISCV:
https://github.com/riscv/riscv-bitmanip/blob/master/bitmanip-0.92.pdf
Differential Revision: https://reviews.llvm.org/D79871
This patch provides optimization of bit manipulation operations by
enabling the +experimental-b target feature.
It adds matching of single block patterns of instructions to specific
bit-manip instructions from the base subset (zbb subextension) of the
experimental B extension of RISC-V.
It adds also the correspondent codegen tests.
This patch is based on Claire Wolf's proposal for the bit manipulation
extension of RISCV:
https://github.com/riscv/riscv-bitmanip/blob/master/bitmanip-0.92.pdf
Differential Revision: https://reviews.llvm.org/D79870
The existing code already considered this case. Unfortunately a typo in
the condition prevents it from triggering. Also the existing code, had
it run, forgot to do the folding.
This fixes PR42876.
Differential Revision: https://reviews.llvm.org/D65802
Because of the layout of stores (that don't have a destination operand)
this check is exactly the same as the one in
RISCVInstrInfo::isLoadFromStackSlot.
Differential Revision: https://reviews.llvm.org/D81805
Since the `RISCVExpandPseudo` pass has been split from
`RISCVExpandAtomicPseudo` pass, it would be nice to run the former as
early as possible (The latter has to be run as late as possible to
ensure correctness). Running earlier means we can reschedule these pairs
as we see fit.
Running earlier in the machine pass pipeline is good, but would mean
teaching many more passes about `hasLabelMustBeEmitted`. Splitting the
basic blocks also pessimises possible optimisations because some
optimisations are MBB-local, and others are disabled if the block has
its address taken (which is notionally what `hasLabelMustBeEmitted`
means).
This patch uses a new approach of setting the pre-instruction symbol on
the AUIPC instruction to a temporary symbol and referencing that. This
avoids splitting the basic block, but allows us to reference exactly the
instruction that we need to. Notionally, this approach seems more
correct because we do actually want to address a specific instruction.
This then allows the pass to be moved much earlier in the pass pipeline,
before both scheduling and register allocation. However, to do so we
must leave the MIR in SSA form (by not redefining registers), and so use
a virtual register for the intermediate value. By using this virtual
register, this pass now has to come before register allocation.
Reviewed By: luismarques, asb
Differential Revision: https://reviews.llvm.org/D82988
For an addition with an immediate in specific ranges, a pair of
addi-addi can be generated instead of the ordinary lui-addi-add serial.
Reviewed By: MaskRay, luismarques
Differential Revision: https://reviews.llvm.org/D82262
... to shift/add or shift/sub.
Do not enable it on riscv32 with the M extension where decomposeMulByConstant
may not be an optimization.
Reviewed By: luismarques, MaskRay
Differential Revision: https://reviews.llvm.org/D82660
We can often fold an ADDI into the offset of load/store instructions:
(load (addi base, off1), off2) -> (load base, off1+off2)
(store val, (addi base, off1), off2) -> (store val, base, off1+off2)
This is possible when the off1+off2 continues to fit the 12-bit immediate.
We remove the previous restriction where we would never fold the ADDIs if
the load/stores had nonzero offsets. We now do the fold the the resulting
constant still fits a 12-bit immediate, or if off1 is a variable's address
and we know based on that variable's alignment that off1+offs2 won't overflow.
Differential Revision: https://reviews.llvm.org/D79690
The pass to split atomic and non-atomic RISC-V pseudo-instructions was itself
split into two passes in D79635 / commit rG2cb0644f90b7, with the splitting of
non-atomic instructions being moved to the PreSched2 phase. A comment was
added to D79635 detailing a case where this caused problems, so this commit
moves the non-atomic split pass back to the PreEmitPass2 phase. This allows
the bulk of the changes from D79635 to remain committed, while addressing the
the reported problem (the pass split is now almost NFC). Once the root problem
is fixed we can move the (non-atomic) instruction splitting pass back to
earlier in the pipeline.
Summary:
This implements two hooks that attempt to avoid control flow for RISC-V. RISC-V
will lower SELECTs into control flow, which is not a great idea.
The hook `hasMultipleConditionRegisters()` turns off the following
DAGCombiner folds:
select(C0|C1, x, y) <=> select(C0, x, select(C1, x, y))
select(C0&C1, x, y) <=> select(C0, select(C1, x, y), y)
The second hook `setJumpIsExpensive` controls a flag that has a similar purpose
and is used in CodeGenPrepare and the SelectionDAGBuilder.
Both of these have the effect of ensuring more logic is done before fewer jumps.
Note: with the `B` extension, we may be able to lower select into a conditional
move instruction, so at some point these hooks will need to be guarded based on
enabled extensions.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D79268
Summary:
As shown, LLVM is keen to avoid logic and introduce selects (in DAGCombiner, and
other places). This leads to control flow on RISC-V which we should attempt to
avoid.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D79267
Extracts the atomic pseudo-instructions' splitting from `riscv-expand-pseudo`
/ `RISCVExpandPseudo` into its own pass, `riscv-expand-atomic-pseudo` /
`RISCVExpandAtomicPseudo`. This allows for the expansion of atomic operations
to continue to happen late (the new pass is added in `addPreEmitPass2`, so
those expansions continue to happen in the same place), while the remaining
pseudo-instructions can now be expanded earlier and benefit from more
optimization passes. The nonatomics pass is now added in `addPreSched2`.
Differential Revision: https://reviews.llvm.org/D79635
This patch adds tests for folds of ADDIs into load/stores, focusing on
load/stores with nonzero offsets. When the offset is nonzero we currently
don't do the fold. A follow-up patch will improve on that.
Differential Revision: https://reviews.llvm.org/D79689
Since i32 is not legal in riscv64,
it always promoted to i64 before emitting lib call and
for conversions like float/double to int and float/double to unsigned int
wrong lib call was emitted. This commit fix it using custom lowering.
Differential Revision: https://reviews.llvm.org/D80526
Let the codegen recognized the nomerge attribute and disable branch folding when the attribute is given
Differential Revision: https://reviews.llvm.org/D79537
Summary:
Verify that each DBG_VALUE has a debug location. This is required by
LiveDebugValues, and perhaps by other late passes.
There's an exception for tests: lots of tests use a two-operand form of
DBG_VALUE for convenience. There's no reason to prevent that.
This is an extension of D80665, but there's no dependency.
Reviewers: aprantl, jmorse, davide, chrisjackson
Subscribers: hiraditya, asb, rbar, johnrusso, simoncook, sabuasal, niosHD, jrtc27, MaskRay, zzheng, edward-jones, rogfer01, MartinMosbeck, brucehoult, the_o, PkmX, jocewei, Jim, lenary, s.egerton, pzheng, sameer.abuasal, apazos, luismarques, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D80670
Summary:
RISC-V uses a post-select peephole pass to optimise
`(load/store (ADDI $reg, %lo(addr)), 0)` into `(load/store $reg, %lo(addr))`.
This peephole wasn't firing for accesses to constant pools, which is how we
materialise most floating point constants.
This adds support for the constantpool case, which improves code generation for
lots of small FP loading examples. I have not added any tests because this
structure is well-covered by the `fp-imm.ll` testcases, as well as almost
all other uses of floating point constants in the RISC-V backend tests.
Reviewed By: luismarques, asb
Differential Revision: https://reviews.llvm.org/D79523
Craig Topper