[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH 1/1] target/i386: fix phadd* with identical destination and s
From: |
Paolo Bonzini |
Subject: |
Re: [PATCH 1/1] target/i386: fix phadd* with identical destination and source register |
Date: |
Thu, 21 May 2020 18:04:54 +0200 |
User-agent: |
Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101 Thunderbird/68.6.0 |
On 02/04/20 00:52, Janne Grunau wrote:
> Detected by asm test suite failures in dav1d
> (https://code.videolan.org/videolan/dav1d). Can be reproduced by
> `qemu-x86_64 -cpu core2duo ./tests/checkasm --test=mc_8bpc 1659890620`.
>
> Signed-off-by: Janne Grunau <address@hidden>
> ---
> target/i386/ops_sse.h | 53 +++++++++++++++++++++++++++----------------
> 1 file changed, 33 insertions(+), 20 deletions(-)
>
> diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
> index ec1ec745d0..2f41511aef 100644
> --- a/target/i386/ops_sse.h
> +++ b/target/i386/ops_sse.h
> @@ -1435,34 +1435,47 @@ void glue(helper_pshufb, SUFFIX)(CPUX86State *env,
> Reg *d, Reg *s)
>
> void glue(helper_phaddw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
> {
> - d->W(0) = (int16_t)d->W(0) + (int16_t)d->W(1);
> - d->W(1) = (int16_t)d->W(2) + (int16_t)d->W(3);
> - XMM_ONLY(d->W(2) = (int16_t)d->W(4) + (int16_t)d->W(5));
> - XMM_ONLY(d->W(3) = (int16_t)d->W(6) + (int16_t)d->W(7));
> - d->W((2 << SHIFT) + 0) = (int16_t)s->W(0) + (int16_t)s->W(1);
> - d->W((2 << SHIFT) + 1) = (int16_t)s->W(2) + (int16_t)s->W(3);
> - XMM_ONLY(d->W(6) = (int16_t)s->W(4) + (int16_t)s->W(5));
> - XMM_ONLY(d->W(7) = (int16_t)s->W(6) + (int16_t)s->W(7));
> +
> + Reg r;
> +
> + r.W(0) = (int16_t)d->W(0) + (int16_t)d->W(1);
> + r.W(1) = (int16_t)d->W(2) + (int16_t)d->W(3);
> + XMM_ONLY(r.W(2) = (int16_t)d->W(4) + (int16_t)d->W(5));
> + XMM_ONLY(r.W(3) = (int16_t)d->W(6) + (int16_t)d->W(7));
> + r.W((2 << SHIFT) + 0) = (int16_t)s->W(0) + (int16_t)s->W(1);
> + r.W((2 << SHIFT) + 1) = (int16_t)s->W(2) + (int16_t)s->W(3);
> + XMM_ONLY(r.W(6) = (int16_t)s->W(4) + (int16_t)s->W(5));
> + XMM_ONLY(r.W(7) = (int16_t)s->W(6) + (int16_t)s->W(7));
> +
> + *d = r;
> }
>
> void glue(helper_phaddd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
> {
> - d->L(0) = (int32_t)d->L(0) + (int32_t)d->L(1);
> - XMM_ONLY(d->L(1) = (int32_t)d->L(2) + (int32_t)d->L(3));
> - d->L((1 << SHIFT) + 0) = (int32_t)s->L(0) + (int32_t)s->L(1);
> - XMM_ONLY(d->L(3) = (int32_t)s->L(2) + (int32_t)s->L(3));
> + Reg r;
> +
> + r.L(0) = (int32_t)d->L(0) + (int32_t)d->L(1);
> + XMM_ONLY(r.L(1) = (int32_t)d->L(2) + (int32_t)d->L(3));
> + r.L((1 << SHIFT) + 0) = (int32_t)s->L(0) + (int32_t)s->L(1);
> + XMM_ONLY(r.L(3) = (int32_t)s->L(2) + (int32_t)s->L(3));
> +
> + *d = r;
> }
>
> void glue(helper_phaddsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
> {
> - d->W(0) = satsw((int16_t)d->W(0) + (int16_t)d->W(1));
> - d->W(1) = satsw((int16_t)d->W(2) + (int16_t)d->W(3));
> - XMM_ONLY(d->W(2) = satsw((int16_t)d->W(4) + (int16_t)d->W(5)));
> - XMM_ONLY(d->W(3) = satsw((int16_t)d->W(6) + (int16_t)d->W(7)));
> - d->W((2 << SHIFT) + 0) = satsw((int16_t)s->W(0) + (int16_t)s->W(1));
> - d->W((2 << SHIFT) + 1) = satsw((int16_t)s->W(2) + (int16_t)s->W(3));
> - XMM_ONLY(d->W(6) = satsw((int16_t)s->W(4) + (int16_t)s->W(5)));
> - XMM_ONLY(d->W(7) = satsw((int16_t)s->W(6) + (int16_t)s->W(7)));
> + Reg r;
> +
> + r.W(0) = satsw((int16_t)d->W(0) + (int16_t)d->W(1));
> + r.W(1) = satsw((int16_t)d->W(2) + (int16_t)d->W(3));
> + XMM_ONLY(r.W(2) = satsw((int16_t)d->W(4) + (int16_t)d->W(5)));
> + XMM_ONLY(r.W(3) = satsw((int16_t)d->W(6) + (int16_t)d->W(7)));
> + r.W((2 << SHIFT) + 0) = satsw((int16_t)s->W(0) + (int16_t)s->W(1));
> + r.W((2 << SHIFT) + 1) = satsw((int16_t)s->W(2) + (int16_t)s->W(3));
> + XMM_ONLY(r.W(6) = satsw((int16_t)s->W(4) + (int16_t)s->W(5)));
> + XMM_ONLY(r.W(7) = satsw((int16_t)s->W(6) + (int16_t)s->W(7)));
> +
> + *d = r;
> }
>
> void glue(helper_pmaddubsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
>
Queued, thanks.
Paolo
[Prev in Thread] |
Current Thread |
[Next in Thread] |
- Re: [PATCH 1/1] target/i386: fix phadd* with identical destination and source register,
Paolo Bonzini <=