lowenz Posted September 20, 2010 Share Posted September 20, 2010 (edited) Pubblico qui la notizia perchè magari a qualche uber-user interessa! Per conto mio erano mesi che aspettavo e non perchè sia fan boy ma perchè per uno sviluppatore il framework offerto da nvidia è moooooooooooolto completo. E con questo step direi che siamo veramente a buon punto. AMD svegliati a fare qualcosa di simile! (non basta l'ATI Stream, ci vuole un framework che invogli gli sviluppatori a lavorarci sopra integrandosi in VS!) NVIDIA Announces Parallel Nsight Support for Visual Studio 2010 and Up to 300% Performance Increase in CUDA Toolkit Libraries – Real Time Press Release Distribution Santa Clara, CA – September 15, 2010 – Today NVIDIA extended its leadership in GPU computing with the announcement of new versions of its two industry-leading developer tools: Parallel Nsight and the CUDA Toolkit. Parallel Nsight is the only integrated development environment for creating GPU-accelerated applications for a range of desktop and supercomputing platforms. Parallel Nsight version 1.5 includes support for Microsoft Visual Studio 2010, Tesla Compute Cluster (TCC) debugging, the updated CUDA Toolkit version 3.2, full support for NVIDIA’s recently announced, high-performance Fermi GPU architecture, and other advanced debugging and analysis capabilities. The new CUDA Toolkit 3.2 release includes two new math libraries, significant performance improvements and support for the new 6GB Tesla and Quadro products. A short video overview of the new features in CUDA Toolkit 3.2 and Parallel Nsight 1.5 is available at: http://developer.download.nvidia.com/CUDA/training/CUDAToolkit_and_ParallelNsight_Update_Sept2010.mp4 Parallel Nsight 1.5 Standard edition will be available as a free update on September 22. In addition, a release candidate of the Professional edition, which includes all Standard edition features plus additional capabilities, including the System Analysis functionality, will also be available. For more information about Parallel Nsight 1.5, please visit: NVIDIA Parallel Nsight. The CUDA Toolkit includes all the tools, libraries and documentation developers need to build CUDA C/C++ applications, and is the foundation for many other GPU computing language solutions. In addition to delivering up to 300 percent faster FFT and BLAS performance compared with the previous release, the new CUDA Toolkit 3.2 release includes new libraries for sparse matrix multiplication, random number generation, H.264 encode/decode, and new cluster management features. For more information on the free CUDA Toolkit please visit: CUDA Toolkit 3.2 RC (September 2010). CUDA and Parallel Nsight at GTC With more than 280 hours of GPU-focused sessions, six sessions on Parallel Nsight and more than 25 sessions on CUDA C/C++ development, NVIDIA’s GPU Technology Conference (GTC) will provide a wealth of information on GPU computing news, developments and achievements. In addition, experts from NVIDIA and Microsoft will be providing hands-on training and educational sessions on Parallel Nsight, Visual Studio 2010, Windows HPC Server 2008, and CUDA C/C++ development at the Parallel Nsight Lounge by Microsoft (Sept. 20-23, 10 a.m. – 8 p.m.). For more information about the Lounge and GTC please visit GPU Technology Conference. Edited September 20, 2010 by lowenz Quote Link to comment Share on other sites More sharing options...
lowenz Posted September 23, 2010 Author Share Posted September 23, 2010 Aggiungo la notizia di oggi (che è presente anche nelle news del sito): RICORDANDO CHE LA ST E' ITALIANA Nvidia and Portland Group Announce CUDA C x86 Compiler - X-bit labs The Portland Group, a wholly-owned subsidiary of STMicroelectronics and a leading independent supplier of compilers for high-performance computing, on Tuesday announced it is developing a CUDA C compiler targeting systems based on the industry-standard general-purpose 64- and 32-bit x86 architectures. The PGI CUDA C compiler for x86 platforms will allow developers using CUDA to compile and optimize CUDA applications to run on x86-based workstations, servers and clusters with or without an Nvidia GPU accelerator. When run on x86-based systems without a GPU, PGI CUDA C applications will use multiple cores and the streaming SIMD (single instruction multiple data) capabilities of Intel and AMD CPUs for parallel execution. "CUDA C for x86 is a perfect complement to CUDA Fortran and PGI’s optimizing parallel Fortran and C compilers for multi-core x86. It is another important element in our on-going strategy of providing HPC programmers with development tools that give PGI users a full range of options for optimizing compute-intensive applications, while allowing them to leverage the latest technical innovations from AMD, Intel and Nvidia," said Douglas Miles, the director of the Portland Group. The announcement by Portland and Nvidia appears to be pretty important for the whole industry in general and the graphics chip designer in particular. On the one hand, it will be possible to recompile almost every software designed for Nvidia CUDA-compliant hardware to run at x86 architectures. On the other hand, it will be possible to easily port a multi-threaded x86 program onto CUDA-compliant platform. As a result, it will be easier for developers to realize benefits of Nvidia's multi-threaded architecture. In addition, with the new compiler it should be easier for software developers to write applications that use both CPUs and GPUs. "With the CUDA for x86 CPU compiler, PGI is responding to the need of developers who want to use a single parallel programming model to target many core GPUs and multi-core CPUs," said Sanford Russell, general manager of GPU Computing software at Nvidia. A big question is how well it is possible to recompile an originally x86 applications for CUDA architecture and vice versa. Intel is currently working on its MIC architecture that will result into explicitly multi-core x86 chips, which can potentially compete against Nvidia's graphics chips with hundreds of stream processors. The new PGI CUDA C compiler for x86 platforms will be demonstrated at the SC10 Supercomputing conference taking place in New Orleans, LA, November 13-15, 2010. Già ora cmq è possibile usare come "target" nella compilazione la CPU, ma probabilmente i nuovi compilatori del PGI permettono una maggiore efficienza! Quote Link to comment Share on other sites More sharing options...
Slime Posted September 23, 2010 Share Posted September 23, 2010 Attualmente la vera novità è sul fatto che i programmatori possono usare un singolo compilatore e quindi un unico modello di computazione parallela. Quindi un solo codice scritto. A livello di prestazioni non credo ci siano miracoli, semplicemente i software saranno più leggeri e meno complicati da realizzare. Questo passo è un ulteriore dimostrazione di quanto Nvidia voglia penetrare in qualsiasi fascia di mercato. Avere un software che gira in CPU multi-core già GPGPU ready significa infliggere un bel colpo alla concorrenza. ATI Stream comincia a non bastare più... è ora di muoversi. (imho). Quote Link to comment Share on other sites More sharing options...
lowenz Posted September 23, 2010 Author Share Posted September 23, 2010 CUDA 3.2 RC2: CUDA Toolkit 3.2 RC (September 2010) Nsight 1.5 RC: NVIDIA Developer Tools Support Center Quote Link to comment Share on other sites More sharing options...
lowenz Posted October 28, 2010 Author Share Posted October 28, 2010 BON, hanno rilasciato tutto ora! CUDA 3.2 RC2 con relativi driver (vanno bene i 260.99, non penso servano per forza i 261.00) ed Nsight 1.5 PER TUTTI per l'integrazione con Visual Studio 2010!!!!!! CUDA Toolkit 3.2 RC 2 (October 2010) E' UN GIORNO LUNGAMENTE ATTESO! Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.