Part 1 in this tutorial series showed that task-based parallelism using concurrent kernels can accelerate applications simply by plugging more GPUs into a system - just as the GPU strong scaling execution model can accelerate applications simply by installing a newer GPU containing more SMX (Streaming Multiprocessors). No recompilation required! NVIDIA nvvp timelines show very … [Read more...]
Pre-order Your NVIDIA Shield Tablet Now! (available July 29 in US)
The Tegra K1-powered NVIDIA Shield Tablet is here - available July 29 in the US! Pre-order here! For more information on the shield tablet, or go to shield.nvidia.com. http://youtu.be/VohrddwVQqg Those who are adventurous, Caonical has a dual-boot mode that will allow Ubuntu to run on tablets, and potentially other devices bringing full Linux and CUDA … [Read more...]
NVIDIA Shield 2 will be a tablet (with stylus) as well as a gaming device!
It's looks like it is true (and it can now be ordered), the K1-powered Shield 2 Gaming console will also be an 8" tablet! What a cool idea! This will be a CUDA/Gamers/Tablet/(cellphone?) honey of a device. (July 22: It's available now!). NVIDIA has created a tweet-based game "Ultimate Quest" in what is believed to be a promotion for the Shield 2. Click on the image below … [Read more...]
Part 1: Load-Balanced, Strong-Scaling Task-Based Parallelism on GPUs
Achieve a 7.4x speedup with 8 GPUs over the performance of a single GPU through the use of task-based parallelism and concurrent kernels! Traditional GPU programming typically views the GPU as a monolithic device that runs a single parallel kernel across the entire device. This approach is fantastic when one kernel can provide enough work to keep the GPU busy. The conundrum is … [Read more...]
Farber to Teach All-Day Tutorial At Supercomputing Nov 16 2014
Supercomputing 2014 recently approved my proposal for an all-day class "From 'Hello World' to Exascale Using x86, GPUs and Intel Xeon Phi Coprocessors" (tut106s1), at The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC14). I hope to see you on Sunday November 16, 2014 in New Orleans,! Abstract Both GPUs and Intel Xeon Phi … [Read more...]
ARM64 with CUDA Early Access Boards Now Available
The X-Gene™ ARM64 and CUDA Development Platform for High Performance Computing (HPC) is now available to order from Cirrascale, the US Applied Micro (APM) integration partner. This board represents an entry point for ARM64 + CUDA into the enterprise markets as well. The X-Gene™ board features custom high-performance ARM v8 processor based on an advanced 64-bit ARM … [Read more...]
Netflix Provides 4K Content – Good News for Low-Power, High-Flop GPU Designs
Netflix is now streaming the hugely popular Breaking Bad series in 4K Ultra HD resolution. The adoption of 4K content coupled with heavy demand for retina quality displays and long battery life in laptops, tablets and cellphones means that GPU technology companies such as AMD, NVIDIA, Qualcomm, and Intel have a strong incentive … [Read more...]
NVIDIA App Showcase, See What Performance is Possible
Considering utilizing GPUs in your application? The NVIDIA Application Showcase is a great place to examine a broad spectrum of applications that have been GPU accelerated and the speedups that have been achieved. The recently updated list now contains descriptions, links, and performance reports for over 270 GPU accelerated applications. … [Read more...]
NVIDIA Tegra K1 Powered Shield Should Soon Be Available
A revised "P2750" NVIDIA Shield gaming device has now appeared in an FCC filing. This suggests that suggests we will soon start seeing a number of NVIDIA Tegra K1 powered devices on store shelves.TechEnablement.com reported some early specifications and benchmark results for a K1-powered Shield that should perform well and can run android or be rooted to … [Read more...]
NVIDIA’s Women Who CUDA Campaign – May 30, 2014 Deadline!
On May 8, 2014 NVIDIA launched the Women Who CUDA campaign to highlight the work of innovative women in the area of GPU computing. Winning entries in the CUDA Women survey (click here to enter) - that is open until May 30, 2014, will be published on the high-visibility, high-volume NVIDIA website. Tweets during the campaign will provide visibility in the GPU computing community … [Read more...]