From: Eray Ozkural <examachine@gmail.com>
To: "Mattias Engdegård" <mattias@virtutech.se>
Cc: jon@ffconsultancy.com, caml-list@yquem.inria.fr
Subject: Re: [Caml-list] How to write a CUDA kernel in ocaml?
Date: Wed, 16 Dec 2009 15:47:14 +0200 [thread overview]
Message-ID: <320e992a0912160547q7969ed30i129e5798456fbf84@mail.gmail.com> (raw)
In-Reply-To: <20091216134138.411322D08BF@kicki.hq.vtech>
On Wed, Dec 16, 2009 at 3:41 PM, Mattias Engdegård <mattias@virtutech.se> wrote:
>>And trampolines to eliminate tail calls that cannot be eliminated using goto.
>>However, trampolines are ~10x slower than TCO in the code gen.
>
> With some care, gcc's sibcall mechanism can be exploited. For example,
> by having one standard signature for all generated C functions, and
> taking care not to pass pointers to variables in the caller's stack
> frame. This should give fairly good performance (better than
> trampolines anyway), at the cost of portability (but gcc is good at
> that). It would give full TCO, even across compilation units. It
> should work well with a Cheney-on-the-MTA-style GC, too.
>
> How suitable it is depends on the reason why compilation to C is done in
> the first place. It might be one of:
>
> 1) portability to odd platforms with semi-decent performance (ie,
> better than interpreted bytecode)
> 2) a simple target for maintaining bootstrapping capability for the
> compiler (but bytecode works well for this too)
> 3) simpler (?) interfacing to libraries in C etc
> 4) flat-out maximum performance by exploiting the optimisations that
> modern C compilers are capable of
>
> Of course, these days we have llvm which has a lot going for it.
Well, the original question was to be able to use the CUDA or OpenCL
compiler on that generated C code.
Possible or impossible? :)
One trivial and low-performance solution that comes to mind is: make
an ocaml bytecode interpreter into a CUDA kernel and then pass the
bytecode to it, and then voila, at least we have some 512-way
parallelism on the GT300. How does that sound? We'd be losing some
performance but massive parallelism will cover up for some of that.
Best,
--
Eray Ozkural, PhD candidate. Comp. Sci. Dept., Bilkent University, Ankara
http://groups.yahoo.com/group/ai-philosophy
http://myspace.com/arizanesil http://myspace.com/malfunct
next prev parent reply other threads:[~2009-12-16 13:47 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-12-15 15:37 Eray Ozkural
2009-12-15 16:07 ` [Caml-list] " Basile STARYNKEVITCH
2009-12-15 16:20 ` Eray Ozkural
2009-12-15 16:29 ` Basile STARYNKEVITCH
2009-12-15 17:46 ` Eray Ozkural
2009-12-15 23:18 ` David Allsopp
2009-12-16 0:39 ` Jon Harrop
2009-12-16 13:41 ` Mattias Engdegård
2009-12-16 13:47 ` Eray Ozkural [this message]
2009-12-17 0:34 ` Philippe Wang
2009-12-17 6:45 ` Eray Ozkural
2009-12-17 10:59 ` Philippe Wang
2010-01-12 6:15 ` Eray Ozkural
2009-12-16 6:26 ` Basile STARYNKEVITCH
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=320e992a0912160547q7969ed30i129e5798456fbf84@mail.gmail.com \
--to=examachine@gmail.com \
--cc=caml-list@yquem.inria.fr \
--cc=jon@ffconsultancy.com \
--cc=mattias@virtutech.se \
/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).