All of lore.kernel.org
 help / color / mirror / Atom feed
From: Samuel Pitoiset <samuel.pitoiset-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: Hans de Goede <hdegoede-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: "nouveau-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org"
	<nouveau-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: NV50 compute support questions
Date: Fri, 20 Nov 2015 17:07:06 +0100	[thread overview]
Message-ID: <564F452A.1010206@gmail.com> (raw)
In-Reply-To: <564EF7CA.4090809-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>



On 11/20/2015 11:36 AM, Hans de Goede wrote:
> Hi Samual, et al,

Hi Hans,

>
> In
> http://cgit.freedesktop.org/mesa/mesa/commit/src/gallium/drivers/nouveau?id=ff72440b40211326eda118232fabd53965410afd
>
> you write: "This compute support has been tested by
> Pierre Moreau and myself with some compute kernels."
>
> Can you provide testing instructions (and the
> necessary files) so that I can try to reproduce
> your tests ?
>
> And once I've reproduced your tests, the next
> question is where / how did you get the compute
> kernels for testing. I guess you manually wrote them ?

Yeah, I wrote those compute kernels directly in assembly by hand.

I already said few days ago, you have some examples in 
src/gallium/tests/trivial/compute.c which show how to use that compute 
support stuff with TGSI kernels and without clover. Because clover is 
not currently able to do OpenCL -> TGSI using Clang/LLVM, you can't 
really use your backend directly.

An other way to achieve what you need is to copy/paste your TGSI kernel 
in src/gallium/tests/trivial/compute.c, set up the global buffers and 
other stuff (maybe samplers, textures and so on) yourself. This is a bit 
painful but should work as expected.

>
> As you know I'm working on a llvm tgsi backend,
> it actually produces some output now, if you want
> to take a peek it lives here:
> http://cgit.freedesktop.org/~jwrdegoede/llvm

I'm currently building your TGSI branch. :-)

>
> Before working further on this I want to take
> a bottom up approach, so I want to first make
> sure we've working TGSI -> compute-kernel and
> compute-kernel -> hardware steps. So the next
> question is, do you know if we can go from
> (manually written) TGSI to a compute-kernel
> using say nouveau-compiler ?

Sure, you can use nouveau-compiler to convert TGSI to NV50 IR, but as I 
said, you can't directly execute your compute kernel without setting a 
ton of stuff before... That's a bunch of fun! :-)

Btw, do you still need compute support on your GK208? or did you have an 
other card for testing ?

>
> And if not, do you know what is missing to do
> this?
>
> Thanks & Regards,
>
> Hans
_______________________________________________
Nouveau mailing list
Nouveau@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/nouveau

  parent reply	other threads:[~2015-11-20 16:07 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-20 10:36 NV50 compute support questions Hans de Goede
     [not found] ` <564EF7CA.4090809-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-20 11:55   ` Pierre Moreau
2015-11-20 16:07   ` Samuel Pitoiset [this message]
     [not found]     ` <564F452A.1010206-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-11-20 16:29       ` Hans de Goede
     [not found]         ` <564F4A54.7050704-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-23 15:31           ` Samuel Pitoiset
     [not found]             ` <5653314D.7010905-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-12-02 15:34               ` Hans de Goede
     [not found]                 ` <565F0F82.9040300-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-12-02 18:33                   ` Samuel Pitoiset
     [not found]                     ` <565F3988.10500-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-12-02 18:37                       ` Ilia Mirkin
2015-12-04  8:45                       ` Hans de Goede
     [not found]                         ` <566152BE.1080107-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-12-04  8:54                           ` Samuel Pitoiset
     [not found]                             ` <566154C2.4090509-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-12-04  9:12                               ` Hans de Goede
     [not found]                                 ` <56615907.5070909-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-12-04  9:21                                   ` Samuel Pitoiset
2015-12-07 15:10                           ` Hans de Goede
     [not found]                             ` <5665A161.90400-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-12-07 16:18                               ` Samuel Pitoiset
2015-11-25 14:43       ` Hans de Goede
     [not found]         ` <5655C92E.5010605-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-25 16:50           ` Samuel Pitoiset
     [not found]             ` <5655E6CC.30905-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-11-25 16:54               ` Ilia Mirkin
2015-11-26  8:42           ` Samuel Pitoiset
     [not found]             ` <5656C5F1.2000406-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-11-26 12:21               ` Hans de Goede
     [not found]                 ` <5656F958.1030201-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-26 12:52                   ` Samuel Pitoiset
     [not found]                     ` <56570087.80800-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-11-30 13:27                       ` Hans de Goede
     [not found]                         ` <565C4EAD.8030508-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2015-11-30 15:13                           ` Samuel Pitoiset
     [not found]                             ` <565C67A3.2090609-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2015-12-01 16:00                               ` Samuel Pitoiset
2015-11-30 19:03                           ` Ilia Mirkin
     [not found]                             ` <CAKb7UvjviUPdMCMrmPCuKy65WkyTz7ehNKoxa0myFbQftcc5mw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2015-12-01  8:19                               ` Hans de Goede

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=564F452A.1010206@gmail.com \
    --to=samuel.pitoiset-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
    --cc=hdegoede-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=nouveau-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.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.