Re: [PATCH 10/11] riscv: thead: Add support for the XTheadMemIdx ISA extension

["Christoph Müllner" <christoph.muellner@vrull.eu>]

On Wed, Jun 28, 2023 at 8:23 PM Jeff Law <jeffreyalaw@gmail.com> wrote:
>
>
>
> On 6/28/23 06:39, Christoph Müllner wrote:
>
> >>> +;; XTheadMemIdx overview:
> >>> +;; All peephole passes attempt to improve the operand utilization of
> >>> +;; XTheadMemIdx instructions, where one sign or zero extended
> >>> +;; register-index-operand can be shifted left by a 2-bit immediate.
> >>> +;;
> >>> +;; The basic idea is the following optimization:
> >>> +;; (set (reg 0) (op (reg 1) (imm 2)))
> >>> +;; (set (reg 3) (mem (plus (reg 0) (reg 4)))
> >>> +;; ==>
> >>> +;; (set (reg 3) (mem (plus (reg 4) (op2 (reg 1) (imm 2))))
> >>> +;; This optimization only valid if (reg 0) has no further uses.
> >> Couldn't this be done by combine if you created define_insn patterns
> >> rather than define_peephole2 patterns?  Similarly for the other cases
> >> handled here.
> >
> > I was inspired by XTheadMemPair, which merges two memory accesses
> > into a mem-pair instruction (and which got inspiration from
> > gcc/config/aarch64/aarch64-ldpstp.md).
> Right.  I'm pretty familiar with those.  They cover a different case,
> specifically the two insns being optimized don't have a true data
> dependency between them.  ie, the first instruction does not produce a
> result used in the second insn.
>
>
> In the case above there is a data dependency on reg0.  ie, the first
> instruction generates a result used in the second instruction.  combine
> is usually the best place to handle the data dependency case.

Ok, understood.

It is a bit of a special case here, because the peephole is restricted
to those cases, where reg0 is not used elsewhere (peep2_reg_dead_p()).
I have not seen how to do this for combiner optimizations.

I found sh_remove_reg_dead_or_unused_notes(), which tests for reg notes
on a given rtx_insn. In our case we have a pattern that matches two insns,
where we have to test if one operand (reg0) is dead or unused after the second
insn. The first insn can be accessed with "curr_insn", but I did not see how to
access the second matching insn. Any ideas or hints?

Thanks,
Christoph



>
>
> >
> > I don't see the benefit of using combine or peephole, but I can change
> > if necessary. At least for the provided test cases, the implementation
> > works quite well.
> Peepholes require the instructions to be consecutive in the stream while
> combine relies on data dependence links and can thus find these
> opportunities even when the two insn we care about are separated by
> unrelated other insns.
>
>
> Jeff