This patches adds a 16 bit register class for use with Zhinx
instructions. This makes them more similar to Zfh instructions and
allows us to only spill 16 bits.
I've added CodeGenOnly instructions for load/store using GPRF16 as that
gave better results than insert_subreg/extract_subreg. I'm using FSGNJ
for GPRF16 copy with Zhinx as that gave better results. Zhinxmin will
use ADDI+subreg operations.
Function arguments use this new GPRF16 register class for f16 arguments
with Zhinxmin. Eliminating the need to use RISCVISD::FMV* nodes.
I plan to extend this idea to Zfinx next.
Create an FP_EXTEND instead of handling the soft promote directly. This
FP_EXTEND will be visited and soft promoted itself.
This removes a zero extend from the generated code when the f32 type is
itself softened. Previously we softened it as an fp16_to_fp which sees
the operand as an integer type so we extend it. When we soften the
result as an fp_extend we see the source as f16 and don't extend. It
only becomes an integer inside call lowering not by type legalization.
If this extend is really necessary, then we have an issue when an
f16->f32 fp_extend exists in the source and f32 needs to be softened.
This simplifies part of #102503.
With Zfinx/Zdinx, f32/f64 are legal types for a GPR, we don't need a
bitcast.
This avoids turning fneg/fabs into bitwise operations purely because of
these bitcasts. If the bitwise operations are faster for some reason on
a Zfinx CPU, then that seems like it should be done for all fneg/fabs,
not just ones near function arguments/returns.
I don't have much interest in Zfinx, this just makes the code more
similar to what I proposed for Zhinx in #107446.
This reverts commit 16bd10a38730fed27a3bf111076b8ef7a7e7b3ee.
Re-applies:
b3c55b707110084a9f50a16aade34c3be6fa18da - "[SelectionDAG] Handle more opcodes in canCreateUndefOrPoison (#84921)"
8e2f6495c0bac1dd6ee32b6a0d24152c9c343624 - "[DAGCombiner] Do not always fold FREEZE over BUILD_VECTOR (#85932)"
73472c5996716cda0dbb3ddb788304e0e7e6a323 - "[SelectionDAG] Treat CopyFromReg as freezing the value (#85932)"
with a fix in DAGCombiner::visitFREEZE.
This reverts:
b3c55b707110084a9f50a16aade34c3be6fa18da - "[SelectionDAG] Handle more opcodes in canCreateUndefOrPoison (#84921)"
(because it updates a test case that I don't know how to resolve the conflict for)
8e2f6495c0bac1dd6ee32b6a0d24152c9c343624 - "[DAGCombiner] Do not always fold FREEZE over BUILD_VECTOR (#85932)"
73472c5996716cda0dbb3ddb788304e0e7e6a323 - "[SelectionDAG] Treat CopyFromReg as freezing the value (#85932)"
Due to a test suite failure on AArch64 when compiling for SVE.
https://lab.llvm.org/buildbot/#/builders/197/builds/13955
clang: ../llvm/llvm/include/llvm/CodeGen/ValueTypes.h:307: MVT llvm::EVT::getSimpleVT() const: Assertion `isSimple() && "Expected a SimpleValueType!"' failed.
The description of CopyFromReg in ISDOpcodes.h says that the input
valus is defined outside the scope of the current SelectionDAG. I
think that means that we basically can treat it as a FREEZE in the
sense that it can be seen as neither being undef nor poison.
Being able to fold freeze(CopyFromReg) into CopyFromReg seems
useful to avoid regressions if we start to introduce freeze
instruction in DAGCombiner/foldBoolSelectToLogic, e.g. to solve
https://github.com/llvm/llvm-project/issues/84653
Things _not_ dealt with in this patch:
- Depending on calling convention an input argument can be passed
also on the stack and not in a register. If it is allowed to treat
an argument received in a register as not being poison, then I think
we want to treat arguments received on the stack the same way. But
then we need to attribute load instructions, or add explicit FREEZE
when lowering formal arguments.
- A common pattern is that there is an AssertZext or AssertSext just
after CopyFromReg. I think that if we treat CopyFromReg as never
being poison, then it should be allowed to fold
(freeze(AssertZext(CopyFromReg))) -> AssertZext(CopyFromReg))
Machine scheduler will suppress register pressure when the scheduling
window is too small, but now it doesn't consider i64 register type,
and this MR extends it into i64 register type, so architecture like
RISCV64 that only supports i64 interger register will have the same
behavior like RISCV32.
Integer RISCVISD::SELECT_CC doesn't create poison. If none of the,
operands are poison, the result is not poison.
This allows ISD::FREEZE to be hoisted above RISCVISD::SELECT_CC.
Previously we used memory like we do to move between GPRs and FPR64 with
the D extension on RV32.
We can instead use REG_SEQUENCE/EXTRACT_SUBREG to inform register
allocation how to do the copy without memory.
No nans/infs in SelectionDAG is complicated. Hopefully I've captured
all of the cases. I've only applied to ConsiderFlags to the SDNodeFlags
since those are the only ones that will be droped by hoisting. The
condition code and TargetOptions would still be in effect.
Recovers some regression from #84232.
Select blocks poison, but AND/OR do not. We need to insert a freeze
to block poison propagation.
This creates suboptimal codegen which I will try to fix with other
patches. I'm prioritizing the correctness fix since we have 2 bug reports.
Fixes#84200 and #84350
R_RISCV_CALL/R_RISCV_CALL_PLT distinction is not necessary and
R_RISCV_CALL has been deprecated. Since https://reviews.llvm.org/D132530
`call foo` assembles to R_RISCV_CALL_PLT. The `@plt` suffix is not
useful and can be removed now (matching AArch64 and PowerPC).
GNU assembler assembles `call foo` to RISCV_CALL_PLT since 2022-09
(70f35d72ef04cd23771875c1661c9975044a749c).
Without this patch, unconditionally changing MO_CALL to MO_PLT could
create `jump .L1@plt, a0`, which is invalid in LLVM integrated assembler
and GNU assembler.
PR #66334 tried to renumber slot indexes before register allocation, but
the numbering was still affected by list entries for instructions which
had been erased. Fix this to make the register allocator's live range
length heuristics even less dependent on the history of how instructions
have been added to and removed from SlotIndexes's maps.
The motivation of this change is simply to reduce test duplication. As
can be seen in the (massive) test delta, we have many tests whose output
differ only due to the use of addi on rv32 vs addiw on rv64 when the
high bits are don't care.
As an aside, we don't need to worry about the non-zero immediate
restriction on the compressed variants because we're not directly
forming the compressed variants. If we happen to get a zero immediate
for the ADDI, then either a later optimization will strip the useless
instruction or the encoder is responsible for not compressing the
instruction.
As introduced in D99148, RISC-V uses the softPromoteHalf legalisation
for fp16 values without zfh, with logic ensuring that f16 values are
passed in lower bits of FPRs (see D98670) when F or D support is
present. This legalisation produces ISD::FP_TO_FP16 and ISD::FP16_TO_FP
nodes which (as described in ISDOpcodes.h) provide a "semi-softened
interface for dealing with f16 (as an i16)". i.e. the return type of the
FP_TO_FP16 is an integer rather than a float (and the arg of FP16_TO_FP
is an integer). The remainder of the description focuses primarily on
FP_TO_FP16 for ease of explanation.
FP_TO_FP16 is lowered to a libcall to `__truncsfhf2 (float)` or
`__truncdfhf2 (double)`. As of D92241, `_Float16` is used as the return
type of these libcalls if the host compiler accepts `_Float16` in a test
input (i.e. dst_t is set to `_Float16`). `_Float16` is enabled for the
RISC-V target as of D105001 and so the return value should be passed in
an FPR on hard float ABIs.
This patch fixes the ABI issue in what appears to be a minimally
invasive way - leaving the softPromoteHalf logic undisturbed, and
lowering FP_TO_FP16 to an f32-returning libcall, converting its result
to an XLen integer value.
As can be seen in the test changes, the custom lowering for FP16_TO_FP
means the libcall is no longer tail-callable.
Although this patch fixes the issue, there are two open items:
* Redundant fmv.x.w and fmv.w.x pairs are now somtimes produced during
lowering (not a correctness issue).
* Now coverage for STRICT variants of FP16 conversion opcodes.
Differential Revision: https://reviews.llvm.org/D151284
There wasn't previous coverage for rv32id-ilp32, rv64id-lp64,
rv32id-ilp32d, or rv64id-lp64d. This is needed as D151284 fixes a bug
related to the ABI used for libcalls for fp<->fp16 conversion when hard
FP support is present.
This results in improved codegen for half/bf16 libcalls on soft ABIs
Adds a RISCVSubtarget helper method for determining if a soft FP ABI is
being targeted (future bf16 related patches make use of this).
Differential Revision: https://reviews.llvm.org/D151434
This function gets called for vectors and ISD::SELECT_CC was never
intended to support vectors. Some updates were made to support
it when this function started getting used for vectors.
Overall, using separate ISD::SETCC and ISD::SELECT looks like an
improvement even for scalar.
Reviewed By: RKSimon
Differential Revision: https://reviews.llvm.org/D149481
We don't have very many compressible FP instructions, just load and store.
These instruction require the FP register to be f8-f15.
This patch changes the FP allocation order to prioritize f10-f15 first.
These are also the FP argument registers. So I allocated them in reverse
order starting at f15 to avoid taking the first argument registers.
This appears to match gcc allocation order.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D146488
We don’t have W versions of AND/OR/XOR/ANDN/ORN/XNOR so we should recursively check their users. We should limit the recursion to SelectionDAG::MaxRecursionDepth levels.
We need to add a Depth argument, all existing callers should pass 0 to the Depth. The new recursive calls should increment it by 1. At the top of the function we should give up and return false if Depth >= SelectionDAG::MaxRecursionDepth.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D139462
The Zfhmin subset only has FLH, FSH, FMV.X.H, FMV.H.X, FCVT.S.H, and FCVT.H.S.
If the D extension is present, the FCVT.D.H and FCVT.H.D instructions are also included.
Since most instructions are not included for Zfhmin, so most operations are promoted.
The patch primarily about making f16 a legal type.
RISC-V ISA info:
https://wiki.riscv.org/display/HOME/Recently+Ratified+Extensions
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D139391
These instructions requires both register operands to be compressible
so I've only applied the hint if we already have a GPRC physical register
assigned for the other register operand.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D139079
Compressed instructions usually require one of the source registers
to also be the source register. The register allocator doesn't have
that bias on its own.
This patch adds register allocation hints to introduce this bias.
I've started with ADDI, ADDIW, and SLLI. These all have a 5-bit
field for the register. If the source and dest register are the
same they are guaranteed to compress as long as the immediate is
also 6 bits.
This code was inspired by similar code from the SystemZ target.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D138242
Same with (select C, X, -1), (select C, 0, X), and (select C, X, 0).
There's a DAGCombine after we turn the select into select_cc, but
that may introduce a setcc that didn't previously exist. We could
add more DAGCombines to remove the extra setcc, but this seemed lower
effort.
Reviewed By: reames
Differential Revision: https://reviews.llvm.org/D135833
Continuing the theme of adding branchless lowerings for simple selects, this time handle the 0 arm case. This is very common for various umin idioms, etc..
Differential Revision: https://reviews.llvm.org/D135600
We can lower these as an or with the negative of the condition value. This appears to result in significantly less branch-y code on multiple common idioms (as seen in tests).
Differential Revision: https://reviews.llvm.org/D135316
We use the saturating behavior of fcvt.wu.h/s/d but forgot to
take into account that fcvt.wu will sign extend the saturated
result. According to computeKnownBits a promoted FP_TO_UINT_SAT
is expected to zero extend the saturated value.
In many case the upper bits aren't be demanded so this wouldn't
be an issue. But if we computeKnownBits caused an AND to be removed
it would be a bug.
This patch inserts an AND during to zero the upper bits.
Unfortunately, this pessimizes code if we aren't able to tell if
the upper bits are demanded. To fix that we could custom type
promote the FP_TO_UINT_SAT with SEXT_INREG after it, but I'll
leave that for future work.
I haven't found a failure from this, I was revisiting the code to
add vector support and spotted it.
Differential Revision: https://reviews.llvm.org/D133746
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
Using AArch64's original implementation for reference, this patch
implements a pass to remove unneeded copies of X0. This pass runs
after register allocation and looks to see if a register is implied
to be 0 by a branch in the predecessor basic block.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D118160
`__gnu_h2f_ieee` and `__gnu_f2h_ieee` are introduce by ARM and set that as
default name for fp16 and fp32 conversion in LLVM.
However RISC-V GCC using default naming scheme for that, which is
`__extendhfsf2` and `__truncsfhf2` for that, that cause runtime ABI
incompatible issue.
Although we didn't have formal runtime ABI spec to specify those naming
convention yet, but I think it would be great to fix the incompatible
issue first.
And I've plan to create a runtime ABI spec undere psABI spec this year.
Reviewed By: asb
Differential Revision: https://reviews.llvm.org/D118207
After D86836, we can define multiple cost values for
different cost models. So here we set CostPerUse to
1 iff RVC is enabled to avoid potential impact on RA.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D117741
Now AND is used for zero extension when both Zbb and Zbp are not enabled.
It may be better to use shift operation if the trailing ones mask exceeds simm12.
This patch optimzes LUI+ADDI+AND to SLLI+SRLI.
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D116720
These nodes should saturate to their saturating VT. We can use this
information to know the bits past the VT are all zeros or all sign bits.
I think we might only have test coverage for the unsigned case. I'll
verify and add tests.
Reviewed By: nikic
Differential Revision: https://reviews.llvm.org/D116870
