This change enables the use of RISCV's variable length vector registers for fixed length vectors in the IR, and implicitly enables various IR transforms which generate fixed length vectors if legal (e.g. LoopVectorize). Specifically, this enables fixed length vectors which are known to be inbounds of the underlying variable hardware size.
For context, remember that the +V extension provides a minimum VLEN of 128. The embedded variants provide lower minimums. The analogy here is essentially vectorizing for SSE on a machine which may or may not include AVX2/AVX512. We won't get full utilization by default, but we will get some benefit. And of course, with an explicit mcpu we can vectorize to the exact target hardware.
The LV impact is mostly related to vectorizer robustness. In cases we haven't yet fully implemented scalable vectorization support, we can fall back to fixed length vectorization.
SLP has been disabled for now, even when fixed vectors are enabled. See a310637 and associated review. There are a few addiitional code quality issues which need worked through before turning SLP on would be reasonable.
Differential Revision: https://reviews.llvm.org/D131508
This change implements a TTI query with the goal of disabling slp vectorization on RISCV. The current default configuration disables SLP already, but its current tied to the ability to lower fixed length vectors. Over in D131508, I want to enable fixed length vectors for purposes of LoopVectorizer, but preliminary analysis has revealed a couple of SLP specific issues we need to resolve before enabling it by default. This change exists to allow us to enable LV without SLP.
Differential Revision: https://reviews.llvm.org/D132680
In patch D121183, target abi is get from .ll file's target-abi
attribute and set in RISCVAsmPrinter::emitFunctionEntryLabel
function. In https://github.com/llvm/llvm-project/issues/57242,
an api mismatch error may be caused by failing to call function
RISCVAsmPrinter::emitFunctionEntryLabel to set target-abi to
correct one when the .ll is empty or a module has no function.
This patch move setting target-abi part to function
RISCVAsmPrinter::emitStartOfAsmFile, make sure all .ll file and
module in LTO read target-abi from module flag and set, with or
without function.
Signed-off-by: xiaojing.zhang <xiaojing.zhang@xcalibyte.com>
Signed-off-by: jianxin.lai <jianxin.lai@xcalibyte.com>
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D132204
Running on RISCV machine llvm-exegesis I faced with trouble: can't measure C_ADDI16SP, beacuse immediate has type simm10_lsb0000nonzero.
Patch adds support for processing this immediate operand type.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D132650
Saves a heap allocation and avoids an explicit call to the BitVector constructor.
Reviewed By: reames, myhsu
Differential Revision: https://reviews.llvm.org/D132674
SimplifyDemandedBits tries to agressively turn xor immediates into -1
to match a 'not' instruction. In this case, because X is a boolean, the
upper bits of (xor X, 1) are known to be 0. Because this is an AND
instruction, that means those bits aren't demanded from the other
operand, and thus SimplifyDemandedBits can turn (xor Y, 1) to (not Y).
We need to detect that this has happened to enable the DeMorgan
optimization. To do this we allow one of the xors to use -1 when
the outer operation is And.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D132671
This optimizes xors that appear due to legalizing setge/setle which
require an xor with 1. This reduces the number of xors and may
allow the xor to fold with a beqz or bnez.
Differential Revision: https://reviews.llvm.org/D132614
We may be requested to emit an unaligned nop sequence (e.g. 7-bytes or
3-bytes). These should be 0-filled even though that is not a valid
instruction. This matches the behaviour on other architectures like
ARM, X86, and MIPS. When a custom section is emitted, it may be
classified as text even though it may be a data section or we may be
emitting data into a text segment (e.g. a literal pool). In such cases,
we should be resilient to the emission request.
This was originally identified by the Linux kernel build and reported on
D131270 by Nathan Chancellor.
Differential Revision: https://reviews.llvm.org/D132482
Reviewed By: luismarques
Tested By: Nathan Chancellor
This patch adds a Type operand to the TLI isCheapToSpeculateCttz/isCheapToSpeculateCtlz callbacks, allowing targets to decide whether branches should occur on a type-by-type/legality basis.
For X86, this patch proposes to allow CTTZ speculation for i8/i16 types that will lower to promoted i32 BSF instructions by masking the operand above the msb (we already do something similar for i8/i16 TZCNT). This required a minor tweak to CTTZ lowering - if the src operand is known never zero (i.e. due to the promotion masking) we can remove the CMOV zero src handling.
Although BSF isn't very fast, most CPUs from the last 20 years don't do that bad a job with it, although there are some annoying passthrough EFLAGS dependencies. Additionally, now that we emit 'REP BSF' in most cases, we are tending towards assuming this will most likely be executed as a TZCNT instruction on any semi-modern CPU.
Differential Revision: https://reviews.llvm.org/D132520
This commit moves the information on whether a register is constant into
the Tablegen files to allow generating the implementaiton of
isConstantPhysReg(). I've marked isConstantPhysReg() as final in this
generated file to ensure that changes are made to tablegen instead of
overriding this function, but if that turns out to be too restrictive,
we can remove the qualifier.
This should be pretty much NFC, but I did notice that e.g. the AMDGPU
generated file also includes the LO16/HI16 registers now.
The new isConstant flag will also be used by D131958 to ensure that
constant registers are marked as call-preserved.
Differential Revision: https://reviews.llvm.org/D131962
This issue is found by build llvm-testsuite with `-Oz`, linker will complain
`dangerous relocation: %pcrel_lo missing matching %pcrel_hi` and that
turn out cause by we outlined pcrel-lo, but leave pcrel-hi there, that's
not problem in general, but the problem is they put into different section, they
pcrel-hi and pcrel-lo pair (e.g. AUIPC+ADDI) *MUST* put be present in same
section due to the implementation.
Outlined function will put into .text name, but the source functions
will put in .text.<function-name> if function-section is enabled or the
function has `comdat` attribute.
There are few solutions for this issue:
1. Always disallow instructions with pcrel-lo flags.
2. Only disallow instructions with pcrel-lo flags that when function-section is
enabled or this function has `comdat` attribute.
3. Check the corresponding instruction with pcrel-high also included in the
outlining candidate sequence or not, and allow that only when pcrel-high is
included in the outlining candidate.
First one is most conservative, that might lose some optimization
opportunities, and second one could save those opportunities, and last
one is hard to implement, and don't have any benefits since pcrel-high
are using different label even accessing same symbol.
Use custom section name might also cause this problem, but that already
filtered by RISCVInstrInfo::isFunctionSafeToOutlineFrom.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D132528
llvm-exegesis uses operand type information provided in tablegen files to initialize
immediate arguments of the instruction. Some of them simply don't have such information.
Thus we should set into relevant immediate operands their specific type.
Also create verification methods for them.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D131771
Add zihintntl compressed instructions and some files related to zihintntl.
This patch is base on {D121670}.
Reviewed By: kito-cheng
Differential Revision: https://reviews.llvm.org/D121779
In branch relaxation pass, `j`'s with offset over 1MiB will be relaxed
to `jump` pseudo-instructions.
This patch allocates a stack slot for functions with a size greater than
1MiB. If the register scavenger cannot find a scratch register for
`jump`, spill a register to the slot before the jump and restore it
after the jump.
.mbb:
foo
j .dest_bb
bar
bar
bar
.dest_bb:
baz
The above code will be relaxed to the following code.
.mbb:
foo
sd s11, 0(sp)
jump .restore_bb, s11
bar
bar
bar
j .dest_bb
.restore_bb:
ld s11, 0(sp)
.dest_bb:
baz
Depends on D129999.
Reviewed By: StephenFan
Differential Revision: https://reviews.llvm.org/D130560
This has the effect of exposing the power-of-two property for use in memory op costing, but no target actually uses it yet. The main point of this change is simple consistency with the recently changes getArithmeticInstrCost, and to remove the last (interface) use of OperandValueKind.
This is part of an ongoing transition to use OperandValueInfo which combines OperandValueKind and OperandValueProperties. This change adds some accessor methods and uses them to simplify backend code. The primary motivation of doing so is removing uses of the parameters so that an upcoming api change is less error prone.
Similar to D132211, we can optimize x <s -1 ? x : -1 -> x <s 0 ? x : -1
Also improve the unsigned case from D132211 to use x != 0 which
will give a bnez instruction which might be compressible.
Differential Revision: https://reviews.llvm.org/D132252
Don't macrofuse if the LUI has more than 1 user. That will likely
require the LUI to have a different destination register post-RA.
LUI+ADDI can only be fused if they write the same register.
if x == 1,
x > 1 ? x : 1 return x, which is also 1.
x > 0 ? x : 1 return 1.
Reduce the number of load 1 instructions.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D132211
Defaults to TCK_RecipThroughput - as most explicit calls were assuming TCK_RecipThroughput (vectorizers) or was just doing a before-vs-after comparison (vectorcombiner). Calls via getInstructionCost were just dropping the CostKind, so again there should be no change at this time (as getShuffleCost and its expansions don't use CostKind yet) - but it will make it easier for us to better account for size/latency shuffle costs in inline/unroll passes in the future.
Differential Revision: https://reviews.llvm.org/D132287
This patch enables expansion or custom lowering for some integer
condition codes so that any xori that is needed is created before
the last DAG combine to enable optimization.
I've seen cases where we end up with
(or (xori (setcc), 1), (xori (setcc), 1)) which we would ideally
convert to (xori (and (setcc), (setcc)), 1). This patch doesn't
accomplish that yet, but it should allow us to add DAG
combines as follow ups. Example https://godbolt.org/z/Y4qnvsq1b
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D131729
Add vector costs for ceil/floor/trunc/round. As can be seen in the tests, the prior default costs were a significant under estimate of the actual code generated.
These costs are computed by simply generating code with the current backend, and then counting the number of instructions. I discount one vsetvli, and ignore the return.
Differential Revision: https://reviews.llvm.org/D131967
Use it to the fix a bug in the fceil/ffloor lowerings. We were
setting the passthru to IMPLICIT_DEF before and using a mask
agnostic policy. This means where the incoming bits in
the mask were 0 they could be anything in the outgoing mask. We
want those bits in the outgoing mask to be 0. This means we need to
pass the input mask as the passthru.
This generates worse code because we are unable to allocate the
v0 register to the output due to an earlyclobber constraint. We
probably need a special TIED pseudoinstruction and probably custom
isel since you can't use V0 twice in the input pattern.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D132058
I have a couple data points that some microarchitectures prefer
the immediate 0 over x0. Does anyone know of microarchitectures
where the opposite is true?
Unfortunately, this is different than the vncvt.x.x.w alias
from the spec. Perhaps the alias was poorly chosen if x0 isn't
as optimal as immediate 0 on all microarchitectures.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D132041
In many cases constant buildvector results in a vector load from a
constant/data pool. Need to consider this cost too.
Differential Revision: https://reviews.llvm.org/D126885
The previous implementation translated from names like sifive-7-series
to sifive-7-rv32 or sifive-7-rv64. This also required sifive-7-rv32
and sifive-7-rv64 to be valid CPU names. As those are not real
CPUs it doesn't make sense to accept them in -mcpu.
This patch does away with the translation and adds sifive-7-series
directly to RISCV.td. Removing sifive-7-rv32 and sifive-7-rv64.
sifive-7-series is only allowed in -mtune.
I've also added "rocket" to RISCV.td but have not removed rocket-rv32
or rocket-rv64.
To prevent -mcpu=sifive-7-series or -mcpu=rocket being used with llc,
I've added a Feature32Bit to all rv32 CPUs. And made it an error to
have an rv32 triple without Feature32Bit. sifive-7-series and rocket
do not have Feature32Bit or Feature64Bit set so the user would need
to provide -mattr=+32bit or -mattr=+64bit along with the -mcpu to
avoid the error.
SiFive no longer names their newer products with 3, 5, or 7 series.
Instead we have p200 series, x200 series, p500 series, and p600 series.
Following the previous behavior would require a sifive-p500-rv32 and
sifive-p500-rv64 in order to support -mtune=sifive-p500-series. There
is currently no p500 product, but it could start getting confusing if
there was in the future.
I'm open to hearing alternatives for how to achieve my main goal
of removing sifive-7-rv32/rv64 as a CPU name.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D131708
On known hardware, reductions, gather, and scatter operations have execution latencies which correlated with the vector length (VL) of the operation. Most other operations (e.g. simply arithmetic) don't correlated in this way, and instead essentially fixed cost as VL varies.
When I'd implemented initial scalable cost model support for reductions, gather, and scatter operations, I had used an upper bound on the statically unknown VL. The argument at the time was that this prevented falsely low costs, and biased the vectorizer away from generating bad (on some hardware) code. Unfortunately, practical experience shows we were a bit too effective at that goal, and the high costs defacto prevents vectorization using these constructs at all.
This patch reverses course, and ties the returned cost not to the maximum possible VL, but the VL which would correspond to VScaleForTuning. This parameter is the same one the vectorizer uses when normalizing loop costs, so the term effectively cancels out. The result is that the vectorizer now sees these constructs as comparable in cost to their fixed length variants.
This does introduce the possibility of the cost for these operations being a significant under estimate on platforms where actual VLEN is far from that implied by VScaleForTuning. On such platforms, we might make poor heuristic choices. Probably not in LV itself (due to the cancellation mentioned above), but possibly during e.g. lowering. I'm not currently aware of any concrete examples of this, but this patch does open a concern which did not previously exist.
Previously, we had the problem of overestimating costs causing the same problem on machines much closer to default values for vscale for tuning. With this patch, we still have that problem potentially if vscale for tuning is set high (manually), and then the code is run on a narrow VLEN machine.
Differential Revision: https://reviews.llvm.org/D131519
* Replace getUserCost with getInstructionCost, covering all cost kinds.
* Remove getInstructionLatency, it's not implemented by any backends, and we should fold the functionality into getUserCost (now getInstructionCost) to make it easier for targets to handle the cost kinds with their existing cost callbacks.
Original Patch by @samparker (Sam Parker)
Differential Revision: https://reviews.llvm.org/D79483
This patch adds support for part of Zc extension which will be frozen soon.
This extension is designed to continue reducing the binary size of RISC-V programs.
In this patch:
`Zca` is a subset of C extension instructions that are compatible with the Zc extension.
The spec of Zc ext is [[ https://github.com/riscv/riscv-code-size-reduction/releases | Here ]]
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D130141
TragetLowering had two last InstructionCost related `getTypeLegalizationCost()`
and `getScalingFactorCost()` members, but all other costs are processed in TTI.
E.g. it is not comfortable to use other TTI members in these two functions
overrided in a target.
Minor refactoring: `getTypeLegalizationCost()` now doesn't need DataLayout
parameter - it was always passed from TTI.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D117723
Extracted from D131729 where we handled C==0. It's now generalized
to more constants.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D132000
This refactors the code into a separate function with early returns.
D132000 adds an additional operation to the if/else that selects
NewLHS, but can otherwise share the rest of the code.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D132002
If the success value of a cmpxchg is used in a branch, the expanded
cmpxchg sequence ends up with a redundant branch-to-branch (as the
backend atomics expansion happens as late as possible, passes to
optimise such cases have already run). This patch identifies this case
and avoid it when expanding the cmpxchg.
Note that a similar optimisation is possible for a BEQ on the cmpxchg
success value. As it's hard to imagine a case where real-world code may
do that, this patch doens't handle that case.
Differential Revision: https://reviews.llvm.org/D130192
Add scheduling resource for vector segment load/store instructions in D128886.
I miss to add scheduling resource for pseudo segment instructions.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D130222
This time using N1 instead of N0 since N1 points to the original
setcc. This now affects scheduling as I expected.
Original commit message:
We change seteq<->setne but it doesn't change the semantics
of the setcc. We should keep original debug location. This is
consistent with visitXor in the generic DAGCombiner.
We change seteq<->setne but it doesn't change the semantics
of the setcc. We should keep original debug location. This is
consistent with visitXor in the generic DAGCombiner.
While (sub 0, X) can use x0 for the 0, I believe (add X, -1) is
still preferrable. (addi X, -1) can be compressed, sub with x0 on
the LHS is never compressible.
This introduce an xori in some cases. I don't believe it was the
intention of the original patch. This was an accident because
nonan FP equality compares also use SETEQ/SETNE.
Also pass the correct type to getSetCCInverse.
-Rename variable NnzC -> N0C.
-Use SelectionDAG::getSetCC to reduce code.
-Use SDValue::getOperand instead of operator-> and SDNode::getOperand.
Initial steps to add another similar combine to this code.
We have a good selection of W instructions, so promoting a truncated
value back to i64 is often free.
This appears to be a net code size reduction on SPECINT2006.
This has been split from D130397 as one of the patches needed to
complete that.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D131819
(setcc x, y, eq/neq) are seqz, snez that set rd = 0/1.
addi is used to process immediate, which can save instructions for load immediate.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D131471
Including patterns to select addiw if only the lower 32 bits are used.
I'm not excited about adding this many patterns. I'm looking at whether
we can create the xori during lowering and move the ineg patterns to
DAGCombiner.
The patch uses peephole method to fold merge.vvm and unmasked intrinsics to
masked intrinsics. Using peephole intead of tablegen patterns is to avoid large
auto gnerated code.
Note: The patch ignores segment loads since I don't know how to test them.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D130442
Commit 8922adf646 recently made JITTargetMachineBuilder honor the
hasJIT property of the target. LLVM supports just-in-time compilation
on RISC-V, so set the flag.
Differential Revision: https://reviews.llvm.org/D131617
As extending from or truncating to mask vector do not use the same instructions as the normal cast, this path changed it to 2 which is the number of instructions we used.
Differential Revision: https://reviews.llvm.org/D131552
Prior to this patch, libcalls inserted by the SelectionDAG legalizer
could never be tailcalled. The eligibility of libcalls for tail calling
is is partly determined by checking TargetLowering::isInTailCallPosition
and comparing the return type of the libcall and the calleer.
isInTailCallPosition in turn calls TargetLowering::isUsedByReturnOnly
(which always returns false if not implemented by the target).
This patch provides a minimal implementation of
TargetLowering::isUsedByReturnOnly - enough to support tail calling
libcalls on hard float ABIs. Soft-float ABIs are left for a follow on
patch. libcall-tail-calls.ll also shows missed opportunities to tail
call integer libcalls, but this is due to issues outside of
the isUsedByReturnOnly hook.
Differential Revision: https://reviews.llvm.org/D131087
The cost of convert from or to mask vector is different from other cases. We could not use PowDiff to calculate it. This patch set it to 3 as we use 3 instruction to make it.
Differential Revision: https://reviews.llvm.org/D131149
This adds a +forced-atomics target feature with the same semantics
as +atomics-32 on ARM (D130480). For RISCV targets without the +a
extension, this forces LLVM to assume that lock-free atomics
(up to 32/64 bits for riscv32/64 respectively) are available.
This means that atomic load/store are lowered to a simple load/store
(and fence as necessary), as these are guaranteed to be atomic
(as long as they're aligned). Atomic RMW/CAS are lowered to __sync
(rather than __atomic) libcalls. Responsibility for providing the
__sync libcalls lies with the user (for privileged single-core code
they can be implemented by disabling interrupts). Code using
+forced-atomics and -forced-atomics are not ABI compatible if atomic
variables cross the ABI boundary.
For context, the difference between __sync and __atomic is that the
former are required to be lock-free, while the latter requires a
shared global lock provided by a shared object library. See
https://llvm.org/docs/Atomics.html#libcalls-atomic for a detailed
discussion on the topic.
This target feature will be used by Rust's riscv32i target family
to support the use of atomic load/store without atomic RMW/CAS.
Differential Revision: https://reviews.llvm.org/D130621
The floating point stores use a different register class, it
probably makes sense to have a different SchedRead.
Reviewed By: monkchiang
Differential Revision: https://reviews.llvm.org/D131379
If we're adding a constant that can't use addi we try a few tricks,
one of which is using li+sh3add. We should not do this if lui+add
would work. For example adding 8192. Using sh3add prevents folding
a sext.w to form addw, thus increasing instruction count.
This fixes a bug reported privately by @craig.topper. Here's an example which illustrates the problem:
vsetivli a1, a0, e32, m1, ta, mu # both DefInfo and PrevInfo
vsetivli a2, a1, e32, m4, ta, mu
With the unsound result being:
vsetivli a1, a0, e32, m1, ta, mu
vsetivli a2, a0, e32, m4, ta, mu
Consider the case where this is running on a machine with VLEN=512,. For this case, the VLMAXs are 16 and 64 respectively.
Consider for a0 = 33. The correct result is: a1 = 16, and a2 = 16
After the unsound optimization: a1 = 16 and a2 = 33
This particular example used VLMAXs which differed by more than a power of two. With a difference of only one power of two, there's another form of this bug which involves the AVL < 2 x VLMAX special case, but that ones more complicated to construct as many examples turn out accidentally sound.
This patch takes the approach of simply removing the unsound optimization, but there are multiple sound sub-cases of it. I plan to return to at least a couple of them, but figured it was cleaner to remove the unsound optimization (for ease of backporting), and then review the new optimizations on their own.
Differential Revision: https://reviews.llvm.org/D131264
When folding (sra (add (shl X, 32), C1), 32 - C) -> (shl (sext_inreg (add X, C1), i32), C)
it's possible that the add is used by multiple sras. We should
allow the combine if all the SRAs will eventually be updated.
After transforming all of the sras, the shls will share a single
(sext_inreg (add X, C1), i32).
This pattern occurs if an sra with 32 is used as index in multiple
GEPs with different scales. The shl from the GEPs will be combined
with the sra before we get a chance to match the sra pattern.
When folding (sra (add (shl X, 32), C1), 32 - C) -> (shl (sext_inreg (add X, C1), C)
ignore the use count on the (shl X, 32).
The sext_inreg after the transform is free. So we're only making
2 new instructions, the add and the shl. So we only need to be
concerned with replacing the original sra+add. The original shl
can have other uses. This helps if there are multiple different
constants being added to the same shl.
In RVV, we use vwredsum.vs and vwredsumu.vs for vecreduce.add(ext(Ty A)) if the result type's width is twice of the input vector's SEW-width. In this situation, the cost of extended add reduction should be same as single-width add reduction. So as the vector float widenning reduction.
Differential Revision: https://reviews.llvm.org/D129994
D129980 converts (seteq (i64 (and X, 0xffffffff)), C1) into
(seteq (i64 (sext_inreg X, i32)), C1). If bit 31 of X is 0, it
will be turned back into an 'and' by SimplifyDemandedBits which
can cause an infinite loop.
To prevent this, check if bit 31 is 0 with computeKnownBits before
doing the transformation.
Fixes PR56905.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D131113
This patch ensures consistency in the construction of FP_ROUND nodes
such that they always use ISD::TargetConstant instead of ISD::Constant.
This additionally fixes a bug in the AArch64 SVE backend where patterns
were matching against TargetConstant nodes and sometimes failing when
passed a Constant node.
Reviewed By: paulwalker-arm
Differential Revision: https://reviews.llvm.org/D130370
An unnecessary sext.w is generated when masking the result of the
riscv_masked_cmpxchg_i64 intrinsic. Implementing handling of the
intrinsic in ComputeNumSignBitsForTargetNode allows it to be removed.
Although this isn't a particularly important optimisation, removing the
sext.w simplifies implementation of an additional cmpxchg-related
optimisation in D130192.
Although I can't produce a test with different codegen for the other
atomics intrinsics, these are added as well for completeness.
Differential Revision: https://reviews.llvm.org/D130191
This used to print from the ADDI where the operand number was
correct. It recently changed to print from the LUI or AUIPC which
needs to use operand 1 instead of 2.
This shows up as a crash with -debug.
I think these pseudos will exist when the post-RA scheduler runs
so they should have sched classes.
Reviewed By: monkchiang
Differential Revision: https://reviews.llvm.org/D130945
* TargetFrameLowering has a TransientStackAlignment field that "returns
the number of bytes to which the stack pointer must be aligned at all
times, even between calls.
* As explained in the [RISC-V calling
convention](https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc),
the stack pointer must remain fully aligned throughout execution for
compliant code. This is important for embedded targets that might avoid
realigning the stack pointer for interrupt service routines. Systems
running full OSes may always realign the stack anyway.
* TransientStackAlignment is used in estimateStackSize in
MachineFrameInfo and in PEI::calculateFrameObjectOffsets.
* estimateStackSize is only used in the RISC-V backend for scavenging
slots. It may be possible to craft a function where the difference
is observable, but it wouldn't be a meaningful test.
* calculateFrameObjectOffsets makes use of TransientStackAlignment,
but then sets the stack alignment to the max of that alignment and
MaxAlign, which is unconditionally set to 16 in
RISCVFrameLowering::processFunctionBeforeFrameFinalized
* I've changed this logic to only set MaxAlign if there are RVV frame
objects. There should be no functional change here for either RVV
targets (MaxAlign is set as before) or non-RVV targets
(TransientStackAlign is now 16 anyway).
Differential Revision: https://reviews.llvm.org/D130068
It's possible we have:
lui a0, %hi(sym)
addi a0, %lo(sym)
addi a0, <offset1>
lw a0, <offset2>(a0)
We want to arrive at
lui a0, %hi(sym+offset1+offset2)
lw a0, %lo(sym+offset1+offset2)
We currently fail to do this because we only consider loads/stores
if we didn't find any arithmetic.
This patch splits arithmetic folding and load/store folding into
two separate phases. The load/store folding can no longer assume
the offset in hi/lo is 0 so we must combine the offsets. I've applied
the same simm32 limit that we applied in the arithmetic folding.
Reviewed By: luismarques
Differential Revision: https://reviews.llvm.org/D130931
At least based on the lit tests, the coalescer sometimes fails to
propagate the copy from X0 into the branch instruction. This patch
does it manually during isel. The majority of the changes are from
the select patterns.
Some of the changes are just register allocation changes. Only
the Select change affects the whether a b*z instruction is generated
in the tests. I changed the branch pattern for consistency.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D130809
The only iterator we're holding points to HiLUI and we never
delete that so I think it is safe to delete everything else
immediately.
I want to split detectAndFoldOffset into two phases. First, combine
LUI+ADDI with any ADD/ADDI/SHXADD that comes after it. This may
open opportunities to fold the ADDI from the LUI+ADDI into a
load/store address. So the load/store folding should run as a
second phase even if the ADD/ADDI/SHXADD made changes.
In order to do this we need to eagerly delete instructions in the
first phase so that we don't have dead users of the LUI+ADDI
when we start the second phase.
Patches to split the phases will come later.
Reviewed By: asb, luismarques
Differential Revision: https://reviews.llvm.org/D130119
Builds upon D123264, adding support for merging the low part of the LLA
address into the load/store instruction offsets.
Differential Revision: https://reviews.llvm.org/D123265
Expand load address pseudo-instructions earlier (pre-ra) to allow follow-up
patches to fold the addi of PseudoLLA instructions into the immediate
operand of load/store instructions.
Differential Revision: https://reviews.llvm.org/D123264
This adds a merge operand to all of the binary _VL nodes. Including
integer and widening. They all share multiclasses in tablegen
so doing them all at once was easiest.
I plan to use FADD_VL in an upcoming patch. The rest are just for
consistency to keep tablegen working.
This does reduce the isel table size by about 25k so that's nice.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D130816
For constants in the range [-2047, 2048] we use addi. If the constant
is -2048 we can use xori. If we don't match this explicitly, we'll
emit an LI for the -2048 followed by an XOR.
This avoids a vmerge at the end and avoids spurious fflags updates.
This isn't used for constrained intrinsic so we technically don't have
to worry about fflags, but it doesn't cost much to support it.
To support I've extend our FCOPYSIGN_VL node to support a passthru
operand. Similar to what was done for VRGATHER*_VL nodes.
I plan to do a similar update for trunc, floor, and ceil.
Reviewed By: reames, frasercrmck
Differential Revision: https://reviews.llvm.org/D130659
InstCombine and DAGCombine prefer to keep shl before binops.
This patch teaches isel to convert to (shl (and/or/xor X, C1 >> C2), C2)
if (C1 >> C2) is a simm12. The idea was taken from X86's isel code.
There's a special case implemented for a sext_inreg between the
shift and the binop.
Differential Revision: https://reviews.llvm.org/D130610
This change enables vectorization (using scalable vectorization only, fixed vectors are not yet enabled) for RISCV when vector instructions are available for the target configuration.
At this point, the resulting configuration should be both stable (e.g. no crashes), and profitable (i.e. few cases where scalar loops beat vector ones), but is not going to be particularly well tuned (i.e. we emit the best possible vector loop). The goal of this change is to align testing across organizations and ensure the default configuration matches what downstreams are using as closely as possible.
This exposes a large amount of code which hasn't otherwise been on by default, and thus may not have been fully exercised. Given that, having issues fall out is not unexpected. If you find issues, please make sure to include as much information as you can when reverting this change.
Differential Revision: https://reviews.llvm.org/D129013
We can use slli.uw by C followed by sh1add. Similar can be done
for multiples of 5 and 9. We need to make sure that C is less than
32 to stay in bounds of the 5-bit immediate for slli.uw.
We have existing patterns for (mul X, 3<<C) that use sh1add
followed by slli. That order doesn't allow the and to be folded.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D130146
A mul by a negated power of 2 is a slli followed by neg. This doesn't
require any constant materialization and may be lower latency than mul.
The neg may also be foldable into other arithmetic.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D130047
These are aliases that allow the immediate offset to be ommitted.
We had predicates for the RV64, RV32+F, and D versions, but
not the base versions.
I've also re-ordered them to share Predicate lines to improve
readability.
(abs(i32 X, i1 1) always produces a positive result. The 'i1 1'
means INT_MIN input produces poison. If the result is sign extended,
InstCombine will convert it to zext. This does not produce ideal
code for RISCV.
This patch reverses the zext back to sext which can be folded
into a subw or negw. Ideally we'd do this in SelectionDAG, but
we lose the INT_MIN poison flag when llvm.abs becomes ISD::ABS.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D130412
This patch adds shouldScalarizeBinop to RISCV target in order to convert an extract element of a vector binary operation into an extract element followed by a scalar binary operation.
Differential Revision: https://reviews.llvm.org/D129545
We can always fold zext.b since it is just andi. The others require
Zba/Zbb.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D130302
(srl (and X, 1<<C), C) is the form we receive for testing bit C.
An earlier combine removed the setcc so it wasn't there to match
when we created the SELECT_CC. This doesn't happen for BR_CC because
generic DAG combine rebuilds the setcc if it is used by BRCOND.
We can shift X left by XLen-1-C to put the bit to be tested in the
MSB, and use a signed compare with 0 to test the MSB.
The only difference between the combines were the calls to getNode
that include the true/false values for SELECT_CC or the chain
and branch target for BR_CC.
Wrap the rest of the code into a helper that reads LHS, RHS, and
CC and outputs new values and a bool if a new node needs to be
created.
If C > 10, this will require a constant to be materialized for the
And. To avoid this, we can shift X left by XLen-1-C bits to put the
tested bit in the MSB, then we can do a signed compare with 0 to
determine if the MSB is 0 or 1. Thanks to @reames for the suggestion.
I've implemented this inside of translateSetCCForBranch which is
called when setcc+brcond or setcc+select is converted to br_cc or
select_cc during lowering. It doesn't make sense to do this for
general setcc since we lack a sgez instruction.
I've tested bit 10, 11, 31, 32, 63 and a couple bits betwen 11 and 31
and between 32 and 63 for both i32 and i64 where applicable. Select
has some deficiencies where we receive (and (srl X, C), 1) instead.
This doesn't happen for br_cc due to the call to rebuildSetCC in the
generic DAGCombiner for brcond. I'll explore improving select in a
future patch.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D130203
This patch implements recently ratified extension Zmmul, a subextension
of M (Integer Multiplication and Division) consisting only
multiplication part of it.
Differential Revision: https://reviews.llvm.org/D103313
Reviewed By: craig.topper, jrtc27, asb
(and X, 0xffffffff) requires 2 shifts in the base ISA. Since we
know the result is being used by a compare, we can use a sext_inreg
instead of an AND if we also modify C1 to have 33 sign bits instead
of 32 leading zeros. This can also improve the generated code for
materializing C1.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D129980
setge/le/uge/ule selected by themselves require an xori with 1.
If we're negating the setcc, we can fold the xori with the neg
to create an addi with -1.
This works because xori X, 1 is equivalent to 1 - X if X is either
0 or 1. So we're doing -(1 - X) which is X-1 or X+-1.
This improves the code for selecting between 0 and -1 based on a
condition for some conditions.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D129957
We can use lw to load 4 bytes from the stack and sign extend them
instead of loading all 8 bytes.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D129948
This patch replaces some foreach with Arrayref, and abstract some same literal array with a variable.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D125656
This patch extends D124824. It uses SHXADD+SLLI to emit 3, 5, or 9 multiplied by a power 2.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D129179
If X is known positive by a dominating condition, we can fill in
ones into the upper bits of C1 if that would allow it to become an
simm12 allowing the use of ANDI.
This pattern often occurs in unrolled loops where the induction
variable has been widened.
To get the best benefit from this, I had to move the pass above
ConstantHoisting which is in addIRPasses. Otherwise the AND constant
is often hoisted away from the AND.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D129888
We're creating single instruction to replace another instruction.
We can insert using the InsertBefore operand of the constructor.
Then copy the debug location.
Initial optimization is to convert (i64 (zext (i32 X))) to
(i64 (sext (i32 X))) if the dominating condition for the basic block
guaranteed the sign bit of X is zero.
This frequently occurs in loop preheaders where a signed induction
variable that can never be negative has been widened. There will be
a dominating check that the 32-bit trip count isn't negative or zero.
The check here is not restricted to that specific case though.
A i32->i64 sext is cheaper than zext on RV64 without the Zba
extension. Later optimizations can often remove the sext from the
preheader basic block because the dominating block also needs a sext to
evaluate the greater than 0 check.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D129732
We previously enabled subregister liveness by default when compiling
with RVV. This has been shown to cause miscompilations where RVV
register operand constraints are not met. A test was added for this in
D129639 which explains the issue in more detail.
Until this issue is fixed in some way, we should not be enabling
subregister liveness unless the user asks for it.
Reviewed By: craig.topper, rogfer01, kito-cheng
Differential Revision: https://reviews.llvm.org/D129646
D25618 added a method to verify the instruction predicates for an
emitted instruction, through verifyInstructionPredicates added into
<Target>MCCodeEmitter::encodeInstruction. This is a very useful idea,
but the implementation inside MCCodeEmitter made it only fire for object
files, not assembly which most of the llvm test suite uses.
This patch moves the code into the <Target>_MC::verifyInstructionPredicates
method, inside the InstrInfo. The allows it to be called from other
places, such as in this patch where it is called from the
<Target>AsmPrinter::emitInstruction methods which should trigger for
both assembly and object files. It can also be called from other places
such as verifyInstruction, but that is not done here (it tends to catch
errors earlier, but in reality just shows all the mir tests that have
incorrect feature predicates). The interface was also simplified
slightly, moving computeAvailableFeatures into the function so that it
does not need to be called externally.
The ARM, AMDGPU (but not R600), AVR, Mips and X86 backends all currently
show errors in the test-suite, so have been disabled with FIXME
comments.
Recommitted with some fixes for the leftover MCII variables in release
builds.
Differential Revision: https://reviews.llvm.org/D129506
The former pattern will select as slliw+sraiw while the latter
will select as slli+srai. This can enable the slli+srai to be
compressed.
Differential Revision: https://reviews.llvm.org/D129688
When doing scalable vectorization, the loop vectorizer uses a urem in the computation of the vector trip count. The RHS of that urem is a (possibly shifted) call to @llvm.vscale.
vscale is effectively the number of "blocks" in the vector register. (That is, types such as <vscale x 8 x i8> and <vscale x 1 x i8> both fill one 64 bit block, and vscale is essentially how many of those blocks there are in a single vector register at runtime.)
We know from the RISCV V extension specification that VLEN must be a power of two between ELEN and 2^16. Since our block size is 64 bits, the must be a power of two numbers of blocks. (For everything other than VLEN<=32, but that's already broken.)
It is worth noting that AArch64 SVE specification explicitly allows non-power-of-two sizes for the vector registers and thus can't claim that vscale is a power of two by this logic.
Differential Revision: https://reviews.llvm.org/D129609
This reverts commit e2fb8c0f4b as it does
not build for Release builds, and some buildbots are giving more warning
than I saw locally. Reverting to fix those issues.
D25618 added a method to verify the instruction predicates for an
emitted instruction, through verifyInstructionPredicates added into
<Target>MCCodeEmitter::encodeInstruction. This is a very useful idea,
but the implementation inside MCCodeEmitter made it only fire for object
files, not assembly which most of the llvm test suite uses.
This patch moves the code into the <Target>_MC::verifyInstructionPredicates
method, inside the InstrInfo. The allows it to be called from other
places, such as in this patch where it is called from the
<Target>AsmPrinter::emitInstruction methods which should trigger for
both assembly and object files. It can also be called from other places
such as verifyInstruction, but that is not done here (it tends to catch
errors earlier, but in reality just shows all the mir tests that have
incorrect feature predicates). The interface was also simplified
slightly, moving computeAvailableFeatures into the function so that it
does not need to be called externally.
The ARM, AMDGPU (but not R600), AVR, Mips and X86 backends all currently
show errors in the test-suite, so have been disabled with FIXME
comments.
Differential Revision: https://reviews.llvm.org/D129506
This patch was split off from D126465, where an early-exit is necessary
as it checks the VLEN and that asserts that V instructions are present.
Since this makes logical sense on its own, I think it's worth landing
regardless of D126465.
Reviewed By: kito-cheng
Differential Revision: https://reviews.llvm.org/D129617
Only one caller didn't already have an MVT and that was easy to
fix. Since the return type is MVT and it uses MVT::getVectorVT,
taking an MVT as input makes the most sense.
This custom isel was used to split the lo12 bits of the imm so that
they could be folded into load/store addresses via a post-isel
peephole.
This patch instead splits the immediate during isel and folds the
lo12 removing the need for the post-isel peephole to do anything.
After this we'll be able to remove the post-isel peephole.
Reviewed By: asb, luismarques
Differential Revision: https://reviews.llvm.org/D129450
This restores the old behavior before D129402 when
enableUnalignedScalarMem is false. This fixes a regression spotted
by @asb.
To fix this correctly, we need to consider alignment of the load
we'd be replacing, but that's not possible in the current interface.
Currently, for vectorised loops that use the get.active.lane.mask
intrinsic we only use the mask for predicated vector operations,
such as masked loads and stores, etc. The loop itself is still
controlled by comparing the canonical induction variable with the
trip count. However, for some targets this is inefficient when it's
cheap to use the mask itself to control the loop.
This patch adds support for using the active lane mask for control
flow by:
1. Generating the active lane mask for the next iteration of the
vector loop, rather than the current one. If there are still any
remaining iterations then at least the first bit of the mask will
be set.
2. Extract the first bit of this mask and use this bit for the
conditional branch.
I did this by creating a new VPActiveLaneMaskPHIRecipe that sets
up the initial PHI values in the vector loop pre-header. I've also
made use of the new BranchOnCond VPInstruction for the final
instruction in the loop region.
Differential Revision: https://reviews.llvm.org/D125301
Philip Reames