News for hackers. Stuff that matters.
Re:Postgres on the GPU by DiabloD3 on Tuesday April 23, 2013 @04:59PM (#5597980)
OpenCL is a standards compliant compute API that is supported by Nvidia, AMD, Intel, IBM, Sony, Apple, and several other companies.

Nvidia is in the slow process of eventually discontinuing further CUDA support, and it is recommended to write new code in OpenCL only.

Re:Postgres on the GPU by qb45 on Tuesday April 23, 2013 @06:18PM (#5598344)
> Nvidia is in the slow process of eventually discontinuing further CUDA support, and it is recommended to write new code in OpenCL only.

[Citation needed]

Their OpenCL support is still limited to v1.1 (released in 2010), while just few months ago they've released a new major version of CUDA with tons of features nowhere to be seen in (any vendor's) OpenCL.

Re:Postgres on the GPU by smosher on Tuesday April 23, 2013 @07:11PM (#5598572)
Yeah, you're going to have to back that up. CUDA is meant to be supported on all future nVidia cards.
Re:Postgres on the GPU by pjmlp on Wednesday April 24, 2013 @02:33AM (#5600193)
How come, given that only CUDA has direct support for C++ and FORTRAN compilers that target the GPU?
Re:Postgres on the GPU by m_mueller on Wednesday April 24, 2013 @04:08AM (#5600384)
Furthermore Python[1], Matlab[2], F#[3]. Furthermore parallel device debuggers (TotalView, Allinea), profilers (NVIDIA). There's a long way for OpenCL to catch up, if ever (because there might be a better standard coming further down the line).

[1] http://www.techpowerup.com/181585/NVIDIA-CUDA-Gets-Python-Su...

[2] http://www.mathworks.com/discovery/matlab-gpu.html

[3] https://www.quantalea.net/media/pdf/2012-11-29_Zurich_FSharp...