On Sunday, 26 February 2017 at 08:37:29 UTC, Nicholas Wilson
wrote:
DCompute is an extension to LDC capable of generating code
(with no language changes*) for NVIDIA's NVPTX for use with
CUDA, SPIRV for use with the OpenCL runtime, and of course the
host, all at the same time! It is also possib
On Monday, 27 February 2017 at 23:02:43 UTC, Nicholas Wilson
wrote:
Interesting to write kernels in D, since a limitation of CUDA
is that you need to multiply the entry points to instantiate a
template differently, and a limitation of OpenCL C is that you
need templates and includes in the firs
On Monday, 27 February 2017 at 13:55:23 UTC, Guillaume Piolat
wrote:
On Sunday, 26 February 2017 at 08:37:29 UTC, Nicholas Wilson
wrote:
This will enable writing kernels in D utilising all of D's
meta programming goodness across the device divide and will
allow launching those kernels with a le
On Sunday, 26 February 2017 at 08:37:29 UTC, Nicholas Wilson
wrote:
This will enable writing kernels in D utilising all of D's meta
programming goodness across the device divide and will allow
launching those kernels with a level of ease on par with CUDA's
<<<...>>> syntax.
Interesting to wri
On Monday, 27 February 2017 at 13:19:00 UTC, Nicholas Wilson
wrote:
Actually I've got the submodules working so feel free to go
ahead, the release is only for OSX for ldc's CI. If you could
let me know when that window is I could post an AMA if I'm
awake then.
Direct your AMA here:
https
On Monday, 27 February 2017 at 13:19:00 UTC, Nicholas Wilson
wrote:
Actually I've got the submodules working so feel free to go
ahead, the release is only for OSX for ldc's CI. If you could
let me know when that window is I could post an AMA if I'm
awake then.
Now is a great time.
On Monday, 27 February 2017 at 09:13:22 UTC, Mike Parker wrote:
On Monday, 27 February 2017 at 08:37:56 UTC, Nicholas Wilson
wrote:
On Sunday, 26 February 2017 at 08:37:29 UTC, Nicholas Wilson
wrote:
DCompute is an extension to LDC capable of generating code
(with no language changes*) for NVID
On Monday, 27 February 2017 at 09:13:22 UTC, Mike Parker wrote:
On Monday, 27 February 2017 at 08:37:56 UTC, Nicholas Wilson
wrote:
On Sunday, 26 February 2017 at 08:37:29 UTC, Nicholas Wilson
wrote:
DCompute is an extension to LDC capable of generating code
(with no language changes*) for NVID
On Monday, 27 February 2017 at 08:37:56 UTC, Nicholas Wilson
wrote:
On Sunday, 26 February 2017 at 08:37:29 UTC, Nicholas Wilson
wrote:
DCompute is an extension to LDC capable of generating code
(with no language changes*) for NVIDIA's NVPTX for use with
Hmm, I appear to have really mucked up
On Sunday, 26 February 2017 at 08:37:29 UTC, Nicholas Wilson
wrote:
DCompute is an extension to LDC capable of generating code
(with no language changes*) for NVIDIA's NVPTX for use with
Hmm, I appear to have really mucked up the git submodules.
Unfortunately I have a cold at the moment and fi
On Sunday, 26 February 2017 at 08:37:29 UTC, Nicholas Wilson
wrote:
DCompute is an extension to LDC capable of generating code
(with no language changes*) for NVIDIA's NVPTX for use with
CUDA, SPIRV for use with the OpenCL runtime, and of course the
host, all at the same time! It is also possib
On Sun, Feb 26, 2017 at 10:37 AM, Nicholas Wilson via
Digitalmars-d-announce wrote:
> DCompute is an extension to LDC capable of generating code (with no language
> changes*) for NVIDIA's NVPTX for use with CUDA, SPIRV for use with the
> OpenCL runtime, and of course the host, all at the same time
DCompute is an extension to LDC capable of generating code (with
no language changes*) for NVIDIA's NVPTX for use with CUDA, SPIRV
for use with the OpenCL runtime, and of course the host, all at
the same time! It is also possible to share implementation of
algorithms across the host and device.
13 matches
Mail list logo