All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jan Bobek <jan.bobek@gmail.com>
To: "Alex Bennée" <alex.bennee@linaro.org>
Cc: Richard Henderson <richard.henderson@linaro.org>, qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] [RISU PATCH v3 00/18] Support for generating x86 SIMD test images
Date: Sun, 14 Jul 2019 19:08:10 -0400	[thread overview]
Message-ID: <71f1ca40-9457-62c1-f585-6b3d6c523e3c@gmail.com> (raw)
In-Reply-To: <87zhljcr6c.fsf@zen.linaroharston>


[-- Attachment #1.1: Type: text/plain, Size: 3990 bytes --]

On 7/12/19 9:34 AM, Alex Bennée wrote:
> 
> Jan Bobek <jan.bobek@gmail.com> writes:
> 
>> This is v3 of the patch series posted in [1] and [2]. Note that this
>> is the first fully-featured patch series implementing all desired
>> functionality, including (V)LDMXCSR and VSIB-based instructions like
>> VGATHER*.
>>
>> While implementing the last bits required in order to support VGATHERx
>> instructions, I ran into problems which required a larger redesign;
>> namely, there are no more !emit blocks as their functionality is now
>> implemented in regular !constraints blocks. Also, memory constraints
>> are specified in !memory blocks, similarly to other architectures.
>>
>> I tested these changes on my machine; both master and slave modes work
>> in both 32-bit and 64-bit modes.
> 
> Two things I've noticed:
> 
>   ./contrib/generate_all.sh -n 1 x86.risu testcases.x86
> 
> takes a very long time. I wonder if this is a consequence of constantly
> needing to re-query the random number generator?

I believe so. While other architectures can be as cheap as a single rand()
call per instruction, x86 does more like 5-10.

Even worse, there are some instructions which cannot be generated in
32-bit mode (those requiring REX.W prefix, e.g. MMX MOVQ). When I let
the script run for a little bit, risugen would get stuck in an
infinite loop, because it could only choose from a single instruction
which wasn't valid for 32-bit....

> The other is:
> 
>   set -x RISU ./build/i686-linux-gnu/risu
>   ./contrib/record_traces.sh testcases.x86/*.risu.bin
> 
> fails on the first trace when validating the playback. Might want to
> check why that is.

The SIMD registers aren't getting initialized; both master and
apprentice need an --xfeatures=XXX parameter for that. Right now the
default is 'none'; unless the instructions are filtered, you'd need
--xfeatures=avx (or --xfeatures=sse, and that only works because on my
laptop, the upper part of ymm registers seems to be always zeroed when
risu starts).

>>
>> Cheers,
>>  -Jan
>>
>> Changes since v2:
>>   Too many to be listed individually; this patch series might be
>>   better reviewed on its own.
>>
>> References:
>>   1. https://lists.nongnu.org/archive/html/qemu-devel/2019-06/msg04123.html
>>   2. https://lists.nongnu.org/archive/html/qemu-devel/2019-07/msg00001.html
>>
>> Jan Bobek (18):
>>   risugen_common: add helper functions insnv, randint
>>   risugen_common: split eval_with_fields into extract_fields and
>>     eval_block
>>   risugen_x86_asm: add module
>>   risugen_x86_constraints: add module
>>   risugen_x86_memory: add module
>>   risugen_x86: add module
>>   risugen: allow all byte-aligned instructions
>>   risugen: add command-line flag --x86_64
>>   risugen: add --xfeatures option for x86
>>   x86.risu: add MMX instructions
>>   x86.risu: add SSE instructions
>>   x86.risu: add SSE2 instructions
>>   x86.risu: add SSE3 instructions
>>   x86.risu: add SSSE3 instructions
>>   x86.risu: add SSE4.1 and SSE4.2 instructions
>>   x86.risu: add AES and PCLMULQDQ instructions
>>   x86.risu: add AVX instructions
>>   x86.risu: add AVX2 instructions
>>
>>  risugen                    |   27 +-
>>  risugen_arm.pm             |    6 +-
>>  risugen_common.pm          |  117 +-
>>  risugen_m68k.pm            |    3 +-
>>  risugen_ppc64.pm           |    6 +-
>>  risugen_x86.pm             |  518 +++++
>>  risugen_x86_asm.pm         |  918 ++++++++
>>  risugen_x86_constraints.pm |  154 ++
>>  risugen_x86_memory.pm      |   87 +
>>  x86.risu                   | 4499 ++++++++++++++++++++++++++++++++++++
>>  10 files changed, 6293 insertions(+), 42 deletions(-)
>>  create mode 100644 risugen_x86.pm
>>  create mode 100644 risugen_x86_asm.pm
>>  create mode 100644 risugen_x86_constraints.pm
>>  create mode 100644 risugen_x86_memory.pm
>>  create mode 100644 x86.risu
> 
> 
> --
> Alex Bennée
> 


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

  reply	other threads:[~2019-07-14 23:08 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-11 22:32 [Qemu-devel] [RISU PATCH v3 00/18] Support for generating x86 SIMD test images Jan Bobek
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 01/18] risugen_common: add helper functions insnv, randint Jan Bobek
2019-07-12  5:48   ` Richard Henderson
2019-07-14 21:55     ` Jan Bobek
2019-07-12 12:41   ` Alex Bennée
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 02/18] risugen_common: split eval_with_fields into extract_fields and eval_block Jan Bobek
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 03/18] risugen_x86_asm: add module Jan Bobek
2019-07-12 14:11   ` Richard Henderson
2019-07-14 22:04     ` Jan Bobek
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 04/18] risugen_x86_constraints: " Jan Bobek
2019-07-12 14:24   ` Richard Henderson
2019-07-14 22:39     ` Jan Bobek
2019-07-21  1:54   ` Richard Henderson
2019-07-22 13:41     ` Jan Bobek
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 05/18] risugen_x86_memory: " Jan Bobek
2019-07-21  1:58   ` Richard Henderson
2019-07-22 13:53     ` Jan Bobek
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 06/18] risugen_x86: " Jan Bobek
2019-07-21  2:02   ` Richard Henderson
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 07/18] risugen: allow all byte-aligned instructions Jan Bobek
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 08/18] risugen: add command-line flag --x86_64 Jan Bobek
2019-07-17 17:00   ` Richard Henderson
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 09/18] risugen: add --xfeatures option for x86 Jan Bobek
2019-07-17 17:01   ` Richard Henderson
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 10/18] x86.risu: add MMX instructions Jan Bobek
2019-07-20  4:30   ` Richard Henderson
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 11/18] x86.risu: add SSE instructions Jan Bobek
2019-07-20 17:50   ` Richard Henderson
2019-07-22 13:57     ` Jan Bobek
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 12/18] x86.risu: add SSE2 instructions Jan Bobek
2019-07-20 21:19   ` Richard Henderson
2019-07-22 14:12     ` Jan Bobek
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 13/18] x86.risu: add SSE3 instructions Jan Bobek
2019-07-20 21:27   ` Richard Henderson
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 14/18] x86.risu: add SSSE3 instructions Jan Bobek
2019-07-20 21:52   ` Richard Henderson
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 15/18] x86.risu: add SSE4.1 and SSE4.2 instructions Jan Bobek
2019-07-20 22:28   ` Richard Henderson
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 16/18] x86.risu: add AES and PCLMULQDQ instructions Jan Bobek
2019-07-20 22:35   ` Richard Henderson
2019-07-11 22:32 ` [Qemu-devel] [RISU PATCH v3 17/18] x86.risu: add AVX instructions Jan Bobek
2019-07-21  0:04   ` Richard Henderson
2019-07-22 14:23     ` Jan Bobek
2019-07-11 22:33 ` [Qemu-devel] [RISU PATCH v3 18/18] x86.risu: add AVX2 instructions Jan Bobek
2019-07-21  0:46   ` Richard Henderson
2019-07-22 14:41     ` Jan Bobek
2019-07-12 13:34 ` [Qemu-devel] [RISU PATCH v3 00/18] Support for generating x86 SIMD test images Alex Bennée
2019-07-14 23:08   ` Jan Bobek [this message]
2019-07-15 10:14     ` 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=71f1ca40-9457-62c1-f585-6b3d6c523e3c@gmail.com \
    --to=jan.bobek@gmail.com \
    --cc=alex.bennee@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.