qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: Paolo Bonzini <pbonzini@redhat.com>, qemu-devel@nongnu.org
Cc: paul@nowt.org
Subject: Re: [PATCH v2 30/37] target/i386: reimplement 0x0f 0x10-0x17, add AVX
Date: Sat, 24 Sep 2022 21:16:44 +0000	[thread overview]
Message-ID: <a01bb109-a386-593a-9b54-dacd661448ae@linaro.org> (raw)
In-Reply-To: <20220920172507.95568-31-pbonzini@redhat.com>

On 9/20/22 17:25, Paolo Bonzini wrote:
> These are mostly moves, and yet are a total pain.  The main issue
> is that:
> 
> 1) some instructions are selected by mod==11 (register operand)
> vs. mod=00/01/10 (memory operand)
> 
> 2) stores to memory are two-operand operations, while the 3-register
> and load-from-memory versions operate on the entire contents of the
> destination; this makes it easier to separate the gen_* function for
> the store case
> 
> 3) it's inefficient to load into xmm_T0 only to move the value out
> again, so the gen_* function for the load case is separated too
> 
> The manual also has various mistakes in the operands here, for example
> the store case of MOVHPS operates on a 128-bit source (albeit discarding
> the bottom 64 bits) and therefore should be Mq,Vdq rather than Mq,Vq.
> Likewise for the destination and source of MOVHLPS.
> 
> VUNPCK?PS and VUNPCK?PD are the same as VUNPCK?DQ and VUNPCK?QDQ,
> but encoded as prefixes rather than separate operands.  The helpers
> can be reused however.
> 
> For MOVSLDUP, MOVSHDUP and MOVDDUP I chose to reimplement them as
> helpers.  I named the helper for MOVDDUP "movdldup" in preparation
> for possible future introduction of MOVDHDUP and to clarify the
> similarity with MOVSLDUP.
> 
> Signed-off-by: Paolo Bonzini<pbonzini@redhat.com>
> ---
>   target/i386/ops_sse.h            |   7 ++
>   target/i386/ops_sse_header.h     |   3 +
>   target/i386/tcg/decode-new.c.inc | 126 ++++++++++++++++++++++++++++++
>   target/i386/tcg/emit.c.inc       | 127 +++++++++++++++++++++++++++++++
>   target/i386/tcg/translate.c      |   1 +
>   5 files changed, 264 insertions(+)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


  reply	other threads:[~2022-09-24 21:21 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-20 17:24 [PATCH v2 00/37] target/i386: new decoder + AVX implementation Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 01/37] target/i386: Define XMMReg and access macros, align ZMM registers Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 02/37] target/i386: make ldo/sto operations consistent with ldq Paolo Bonzini
2022-09-24 15:00   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 03/37] target/i386: REPZ and REPNZ are mutually exclusive Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 04/37] target/i386: introduce insn_get_addr Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 05/37] target/i386: add core of new i386 decoder Paolo Bonzini
2022-09-24 15:09   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 06/37] target/i386: add ALU load/writeback core Paolo Bonzini
2022-09-24 15:13   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 07/37] target/i386: add CPUID[EAX=7, ECX=0].ECX to DisasContext Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 08/37] target/i386: add CPUID feature checks to new decoder Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 09/37] target/i386: add AVX_EN hflag Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 10/37] target/i386: validate VEX prefixes via the instructions' exception classes Paolo Bonzini
2022-09-24 20:19   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 11/37] target/i386: validate SSE prefixes directly in the decoding table Paolo Bonzini
2022-09-24 20:23   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 12/37] target/i386: move scalar 0F 38 and 0F 3A instruction to new decoder Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 13/37] target/i386: Prepare ops_sse_header.h for 256 bit AVX Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 14/37] target/i386: extend helpers to support VEX.V 3- and 4- operand encodings Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 15/37] target/i386: support operand merging in binary scalar helpers Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 16/37] target/i386: provide 3-operand versions of unary " Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 17/37] target/i386: implement additional AVX comparison operators Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 18/37] target/i386: Introduce 256-bit vector helpers Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 19/37] target/i386: reimplement 0x0f 0x60-0x6f, add AVX Paolo Bonzini
2022-09-24 20:31   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 20/37] target/i386: reimplement 0x0f 0xd8-0xdf, 0xe8-0xef, 0xf8-0xff, " Paolo Bonzini
2022-09-24 20:32   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 21/37] target/i386: reimplement 0x0f 0x50-0x5f, " Paolo Bonzini
2022-09-24 20:37   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 22/37] target/i386: reimplement 0x0f 0x78-0x7f, " Paolo Bonzini
2022-09-24 20:43   ` Richard Henderson
2022-09-26  7:24     ` Paolo Bonzini
2022-09-26  7:46       ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 23/37] target/i386: reimplement 0x0f 0x70-0x77, " Paolo Bonzini
2022-09-24 20:53   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 24/37] target/i386: reimplement 0x0f 0xd0-0xd7, 0xe0-0xe7, 0xf0-0xf7, " Paolo Bonzini
2022-09-24 20:56   ` Richard Henderson
2022-09-26  7:56     ` Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 25/37] target/i386: clarify (un)signedness of immediates from 0F3Ah opcodes Paolo Bonzini
2022-09-24 20:57   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 26/37] target/i386: reimplement 0x0f 0x3a, add AVX Paolo Bonzini
2022-09-24 21:02   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 27/37] target/i386: Use tcg gvec ops for pmovmskb Paolo Bonzini
2022-09-24 21:08   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 28/37] target/i386: reimplement 0x0f 0x38, add AVX Paolo Bonzini
2022-09-24 21:14   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 29/37] target/i386: reimplement 0x0f 0xc2, 0xc4-0xc6, " Paolo Bonzini
2022-09-20 17:25 ` [PATCH v2 30/37] target/i386: reimplement 0x0f 0x10-0x17, " Paolo Bonzini
2022-09-24 21:16   ` Richard Henderson [this message]
2022-09-20 17:25 ` [PATCH v2 31/37] target/i386: reimplement 0x0f 0x28-0x2f, " Paolo Bonzini
2022-09-24 21:18   ` Richard Henderson
2022-09-20 17:25 ` [PATCH v2 32/37] target/i386: implement XSAVE and XRSTOR of AVX registers Paolo Bonzini
2022-09-24 21:19   ` Richard Henderson
2022-09-20 17:25 ` [PATCH v2 33/37] target/i386: implement VLDMXCSR/VSTMXCSR Paolo Bonzini
2022-09-24 21:20   ` Richard Henderson
2022-09-20 17:25 ` [PATCH v2 34/37] target/i386: Enable AVX cpuid bits when using TCG Paolo Bonzini
2022-09-20 17:25 ` [PATCH v2 35/37] tests/tcg: extend SSE tests to AVX Paolo Bonzini
2022-09-20 17:25 ` [PATCH v2 36/37] target/i386: move 3DNow to the new decoder Paolo Bonzini
2022-09-24 21:24   ` Richard Henderson
2022-09-20 17:25 ` [PATCH v2 37/37] target/i386: remove old SSE decoder Paolo Bonzini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=a01bb109-a386-593a-9b54-dacd661448ae@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=paul@nowt.org \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).