qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Alex Bennée" <alex.bennee@linaro.org>
To: Richard Henderson <richard.henderson@linaro.org>
Cc: qemu-devel@nongnu.org, peter.maydell@linaro.org
Subject: Re: [Qemu-devel] [PATCH v11 00/20] tcg: generic vector operations
Date: Tue, 06 Feb 2018 11:24:38 +0000	[thread overview]
Message-ID: <87eflywebt.fsf@linaro.org> (raw)
In-Reply-To: <20180126045742.5487-1-richard.henderson@linaro.org>


Richard Henderson <richard.henderson@linaro.org> writes:

> Changes since v11:
>   * Use dup_const more.
>   * Cleanup some gvec 2i and 2s routines.
>   * Use more helpers and less gotos in target/arm/translate-a64.c.

I think this series is good to go.

A quick word on performance. I saw a slight dip for the string sort in
Emilio's dbt-bench/nbench:

  https://i.imgur.com/K5AFr1u.png

And:

                         NBench score; higher is better

  140 +-+-----+------+-------+-------+------+-------+-------+------+-----+-+
      |                           ****                                     |
      |                           *  *##               development         |
  120 +-+.........................*..*.#....................master.......+-+
      |                           *  * #                                   |
  100 +-+............####.........*..*.#.................................+-+
      |              #  #         *  * #                                   |
      |            ***  #         *  * #                                   |
   80 +-+..........*.*..#.........*..*.#.........****###.................+-+
      |            * *  #         *  * #         *  *  #                   |
   60 +-+..........*.*..#.........*..*.#..***###.*..*..#.........***###..+-+
      |            * *  # ****### *  * #  * *  # *  *  #         * *  #    |
      |            * *  # *  *  # *  * #  * *  # *  *  # ****##  * *  #    |
   40 +-+..........*.*..#.*..*..#.*..*.#..*.*..#.*..*..#.*..*.#..*.*..#..+-+
      |            * *  # *  *  # *  * #  * *  # *  *  # *  * #  * *  #    |
   20 +-+..........*.*..#.*..*..#.*..*.#..*.*..#.*..*..#.*..*.#..*.*..#..+-+
      |    ****##  * *  # *  *  # *  * #  * *  # *  *  # *  * #  * *  #    |
      |    *  * #  * *  # *  *  # *  * #  * *  # *  *  # *  * #  * *  #    |
    0 +-+--****##--***###-****###-****##--***###-****###-****##--***###--+-+
        NUMERIC STRING SOBITFIEFP EMULAASSIGNMENT IDEA   HUFFMAN gmean

We think this is likely the strajust function which hits a loop
utilising a single vector. We already know a single vector-op is a worse
case given the latency but this improves if the code is -funrolled or
ultimately re-built with support for bigger vectors ;-)

I certainly don't think it's a blocker to merging given the other
benchmarks look pretty good including slight wins on others.

>
>
> Richard Henderson (20):
>   tcg: Allow multiple word entries into the constant pool
>   tcg: Add types and basic operations for host vectors
>   tcg: Standardize integral arguments to expanders
>   tcg: Add generic vector expanders
>   tcg: Add generic vector ops for constant shifts
>   tcg: Add generic vector ops for comparisons
>   tcg: Add generic vector ops for multiplication
>   tcg: Add generic helpers for saturating arithmetic
>   tcg: Add generic vector helpers with a scalar operand
>   tcg/optimize: Handle vector opcodes during optimize
>   target/arm: Align vector registers
>   target/arm: Use vector infrastructure for aa64 add/sub/logic
>   target/arm: Use vector infrastructure for aa64 mov/not/neg
>   target/arm: Use vector infrastructure for aa64 dup/movi
>   target/arm: Use vector infrastructure for aa64 constant shifts
>   target/arm: Use vector infrastructure for aa64 compares
>   target/arm: Use vector infrastructure for aa64 multiplies
>   target/arm: Use vector infrastructure for aa64 orr/bic immediate
>   tcg/i386: Add vector operations
>   tcg/aarch64: Add vector operations
>
>  Makefile.target              |    4 +-
>  accel/tcg/tcg-runtime.h      |  118 +++
>  target/arm/cpu.h             |    2 +-
>  tcg/aarch64/tcg-target.h     |   25 +-
>  tcg/aarch64/tcg-target.opc.h |    3 +
>  tcg/i386/tcg-target.h        |   41 +-
>  tcg/i386/tcg-target.opc.h    |   13 +
>  tcg/tcg-gvec-desc.h          |   49 +
>  tcg/tcg-op-gvec.h            |  306 ++++++
>  tcg/tcg-op.h                 |   52 +-
>  tcg/tcg-opc.h                |   46 +
>  tcg/tcg.h                    |   87 ++
>  accel/tcg/tcg-runtime-gvec.c |  997 +++++++++++++++++++
>  target/arm/translate-a64.c   |  979 ++++++++++++++-----
>  tcg/aarch64/tcg-target.inc.c |  588 ++++++++++-
>  tcg/i386/tcg-target.inc.c    |  987 ++++++++++++++++++-
>  tcg/optimize.c               |  150 +--
>  tcg/tcg-op-gvec.c            | 2215 ++++++++++++++++++++++++++++++++++++++++++
>  tcg/tcg-op-vec.c             |  389 ++++++++
>  tcg/tcg-op.c                 |   42 +-
>  tcg/tcg-pool.inc.c           |  115 ++-
>  tcg/tcg.c                    |  125 ++-
>  accel/tcg/Makefile.objs      |    2 +-
>  configure                    |   48 +
>  tcg/README                   |   86 ++
>  25 files changed, 6973 insertions(+), 496 deletions(-)
>  create mode 100644 tcg/aarch64/tcg-target.opc.h
>  create mode 100644 tcg/i386/tcg-target.opc.h
>  create mode 100644 tcg/tcg-gvec-desc.h
>  create mode 100644 tcg/tcg-op-gvec.h
>  create mode 100644 accel/tcg/tcg-runtime-gvec.c
>  create mode 100644 tcg/tcg-op-gvec.c
>  create mode 100644 tcg/tcg-op-vec.c


--
Alex Bennée

  parent reply	other threads:[~2018-02-06 11:24 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-26  4:57 [Qemu-devel] [PATCH v11 00/20] tcg: generic vector operations Richard Henderson
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 01/20] tcg: Allow multiple word entries into the constant pool Richard Henderson
2018-02-06  8:51   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 02/20] tcg: Add types and basic operations for host vectors Richard Henderson
2018-02-06  8:53   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 03/20] tcg: Standardize integral arguments to expanders Richard Henderson
2018-02-06  8:57   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 04/20] tcg: Add generic vector expanders Richard Henderson
2018-02-06 10:59   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 05/20] tcg: Add generic vector ops for constant shifts Richard Henderson
2018-02-06 11:00   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 06/20] tcg: Add generic vector ops for comparisons Richard Henderson
2018-02-06 11:01   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 07/20] tcg: Add generic vector ops for multiplication Richard Henderson
2018-02-06 11:02   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 08/20] tcg: Add generic helpers for saturating arithmetic Richard Henderson
2018-02-06 11:03   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 09/20] tcg: Add generic vector helpers with a scalar operand Richard Henderson
2018-02-06 11:04   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 10/20] tcg/optimize: Handle vector opcodes during optimize Richard Henderson
2018-02-06 11:07   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 11/20] target/arm: Align vector registers Richard Henderson
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 12/20] target/arm: Use vector infrastructure for aa64 add/sub/logic Richard Henderson
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 13/20] target/arm: Use vector infrastructure for aa64 mov/not/neg Richard Henderson
2018-02-06 11:08   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 14/20] target/arm: Use vector infrastructure for aa64 dup/movi Richard Henderson
2018-02-06 11:09   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 15/20] target/arm: Use vector infrastructure for aa64 constant shifts Richard Henderson
2018-02-05 11:14   ` Peter Maydell
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 16/20] target/arm: Use vector infrastructure for aa64 compares Richard Henderson
2018-02-06 11:10   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 17/20] target/arm: Use vector infrastructure for aa64 multiplies Richard Henderson
2018-02-06 11:11   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 18/20] target/arm: Use vector infrastructure for aa64 orr/bic immediate Richard Henderson
2018-02-06 11:13   ` Alex Bennée
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 19/20] tcg/i386: Add vector operations Richard Henderson
2018-01-26  4:57 ` [Qemu-devel] [PATCH v11 20/20] tcg/aarch64: " Richard Henderson
2018-02-06 11:15   ` Alex Bennée
2018-01-26 17:25 ` [Qemu-devel] [PATCH v11 00/20] tcg: generic " no-reply
2018-02-06 11:24 ` Alex Bennée [this message]
2018-02-06 12:07   ` Philippe Mathieu-Daudé
2018-02-06 12:36     ` Alex Bennée
2018-02-06 16:24 ` Alex Bennée
2018-02-06 20:57   ` Alex Bennée

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=87eflywebt.fsf@linaro.org \
    --to=alex.bennee@linaro.org \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.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).