Featured Articles

Gainward GTX 970 Phantom previewed

Gainward GTX 970 Phantom previewed

Nvidia has released two new graphics cards based on its latest Maxwell GPU architecture. The Geforce GTX 970 and Geforce GTX…

More...
Snapdragon 400 is Qualcomm’s SoC for watches, wearables

Snapdragon 400 is Qualcomm’s SoC for watches, wearables

We wanted to learn a bit more about Qualcomm's plans for wearables and it turns out that the company believes its…

More...
Qualcomm sampling 20nm Snapdragon 810

Qualcomm sampling 20nm Snapdragon 810

We had a chance to talk to Michelle Leyden-Li, Senior Director of Marketing, QCT at Qualcomm and get an update on…

More...
EVGA GTX 970 SC ACX 2.0 reviewed

EVGA GTX 970 SC ACX 2.0 reviewed

Nvidia has released two new graphics cards based on its latest Maxwell GPU architecture. The Geforce GTX 970 and Geforce GTX…

More...
Nvidia GTX 980 reviewed

Nvidia GTX 980 reviewed

Nvidia has released two new graphics cards based on its latest Maxwell GPU architecture. The Geforce GTX 970 and Geforce GTX…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Thursday, 14 November 2013 21:15

Nvidia announces new CUDA 6

Written by Slobodan Simic

nvidia cuda-logo

Unified memory for CUDA

Ahead of the annual International Conference for High Performance Computing, Networking, Storage, and Analysis, better known as the SC, Nvidia announced its new version of CUDA, CUDA 6. While most recent updates to CUDA had quite a few new features, the CUDA 6 will mostly focus on a few elements that might be quite important.

The bigest news is definitely the unified memory support wihtin CUDA. While CUDA 4 already had unified virtual addressing support which allowed x86 and GPU memory to be addressed together in a single space, it only simplified memory management and did not solve some issues that such a solution had and still required memory copying that will allow GPU to work with it.

With CUDA 6, Nvidia moved towards removing issues like memory copying by implementing a unified memory system on top of the existing memory pool structure. Basically, unified memory allows programmers to access any resource or addres within the legal address space, regardless of the place where it is in and actually use it without the need to copy it over.

While it does not resolve technical limitations that require memory copying, like limited bandwidth and latency of the PCIe, it moves memory management to CUDA rather than other toolkit, thus simply making the life of the programmer much easier.

Basically it does not solve any performance issues but rather simplifes CUDA programming. This move is made in order to make CUDA programming more accessible to wider audiences.

Nvidia did not shed any light regarding performance impact at this time, and while manual memory management is still present, CUDA unified memory will definitely have some kind of performance penalty.

Nvidia also revealed that while we are currently seeing software implementation of unified memory with CUDA 6, Maxwell will most likely have some sort of hardware functionality for implementing unified memory thus removing any performance penalties and most likely doing it much better than software solution with CUDA 6. 

Via Anandtech.com.

nvidia CUDA6unifiedmemory-1

nvidia CUDA6unifiedmemory-2

Last modified on Friday, 15 November 2013 08:27
blog comments powered by Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments