p data/results
> there if there is further processing to do.
> > > >
> > > > things like martix multiplication and other similar tasks are 10x to
> 100x faster (iirc) including the round trip back to cpu.
> > > >
> > > >
> > > >
via General <gene...@jsoftware.com>
> Sent: Tuesday, June 21, 2016 8:26 PM
> Subject: Re: [Jgeneral] GPU APL compiler work
>
> INO benefit of using GPU for implementing APL (and J) primiivies
> is questionable. Most primitives are simple and the efficiency
> of APL/J com
10x to 100x
faster (iirc) including the round trip back to cpu.
- Original Message -
From: bill lam <bbill@gmail.com>
To: 'Pascal Jasmin' via General <gene...@jsoftware.com>
Sent: Tuesday, June 21, 2016 8:26 PM
Subject: Re: [Jgeneral] GPU APL compiler work
INO benef
INO benefit of using GPU for implementing APL (and J) primiivies
is questionable. Most primitives are simple and the efficiency
of APL/J comes the processing large arrays. The time needed to
read/write GPU memory for large array is not justified
unless the job is highly looped eg,
Sent: Monday, June 20, 2016 8:27 PM
Subject: Re: [Jgeneral] GPU APL compiler work
Thanks.
Q: How do these projects relate to GNU APL? As far as I can tell,
they're independent research.
On Mon, Jun 20, 2016 at 8:58 AM, 'Pascal Jasmin' via General
<gene...@jsoftware.com> wrote:
> Intere