[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [PATCH 07/10] target/arm: Implement v8.1M low-overhead-loop instruct

From: Richard Henderson
Subject: Re: [PATCH 07/10] target/arm: Implement v8.1M low-overhead-loop instructions
Date: Tue, 13 Oct 2020 15:31:29 -0700
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101 Thunderbird/68.10.0

On 10/12/20 8:37 AM, Peter Maydell wrote:
> +    nextlabel = gen_new_label();
> +    tcg_gen_brcondi_i32(TCG_COND_NE, cpu_R[a->rn], 0, nextlabel);
> +    gen_jmp(s, read_pc(s) + a->imm);
> +
> +    gen_set_label(nextlabel);
> +    tmp = load_reg(s, a->rn);
> +    store_reg(s, 14, tmp);
> +    gen_jmp(s, s->base.pc_next);
> +    return true;

Oh, fwiw, with the tcg optimization patches just posted, this branch is better
inverted.  That way the load of rn can be reused on the non-taken branch path.

Maybe sometime I'll try to propagate the data to the taken path, but that
automatically requires extra memory allocation, so it'll be difficult to do
that without a tcg slowdown.


reply via email to

[Prev in Thread] Current Thread [Next in Thread]