EEDSP
Follow
Find tag "gpgpu"
13.5K views | +0 today
EEDSP
Digital Signal Processing, Data Analytics, Big Data, HPC, Deep Learning, GPGPU
Curated by Shiwon Cho
Your new post is loading...
Your new post is loading...
Scooped by Shiwon Cho
Scoop.it!

New G2 Instance Type with 4x More GPU Power | AWS Official Blog

New G2 Instance Type with 4x More GPU Power | AWS Official Blog | EEDSP | Scoop.it

The GPU-powered G2 instance family is home to molecular modeling,  rendering, machine learning, game streaming, and transcoding jobs that require massive amounts of parallel processing power.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Understanding Natural Language with Deep Neural Networks Using Torch

Understanding Natural Language with Deep Neural Networks Using Torch | EEDSP | Scoop.it
This post was co-written by Soumith Chintala and Wojciech Zaremba of Facebook AI Research. Language is the medium of human communication. Giving machines the ability to learn and understand languag...
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning

Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning | EEDSP | Scoop.it
I have been using GPUs for nearly two years now and for me it is again and again amazing to see how much speedup you get. Compared to CPUs 20x speedups are typical, but on larger problems one can a...
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Overview of current OpenCL 2.0 hardware support, samples, blogs and drivers - Blog - StreamComputing

Overview of current OpenCL 2.0 hardware support, samples, blogs and drivers - Blog - StreamComputing | EEDSP | Scoop.it

It already started, but we were too busy lately to tell you about it. OpenCL 2.0 makes use of the more recent hardware and is therefore more powerful than 1.x.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

OpenCL™ 2.0 is here! Download the Release 2 of Intel® SDK for OpenCL™ Applications 2014

Dear Developers,

We are happy to announce the availability of our latest and most advanced SDK for OpenCL: Release 2 of Intel® SDK for OpenCL SDK 2014 is the industry’s first SDK to provide an OpenCL 2.0 development environment with the new Intel® Core™ M Processors.

This major advance in graphics programmability and accessibility will help you make greater use of the graphics engine to deliver new experiences on Intel-based platforms 

New with SDK 2014 Release 2:
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Khronos Announces OpenCL SPIR 2.0

Khronos Announces OpenCL SPIR 2.0 | EEDSP | Scoop.it

Khronos released OpenCL SPIR 1.2 as a provisional specification, keeping it there over a protracted period to solicit feedback over the first version of the standard. Since that provisional release, Khronos finalized OpenCL 1.2 SPIR in early 2014 and has been working on building up their developer and user bases for SPIR.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Kyle Lutz: Boost.Compute v0.3 Released

Boost.Compute is a header-only C++ library for GPGPU and parallel-computing based on OpenCL. It is available on GitHub and instructions for getting started can be found in the documentation.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

NVIDIA GPUs Deliver a Shot in the ARM for HPC Industry

NVIDIA GPUs Deliver a Shot in the ARM for HPC Industry | EEDSP | Scoop.it
Among the most interesting announcements at this week’s ISC’14 is the emergence of a new class of system – one that marries the many advantages of ARM processors with the massively parallel processing power of NVIDIA Tesla GPU accelerators. This is great news for the industry. Initially designed for micro-servers and web servers, ARM64 server processors… Read More
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Managing GPUs by SLURM - insideHPC

In this video from the HPC Advisory Council Swiss Conference 2014, Massimo Benini from CSCS presents: Managing GPUs by SLURM.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

CUDA 6, Available as Free Download, Makes Parallel Programming Easier, Faster

CUDA 6, Available as Free Download, Makes Parallel Programming Easier, Faster | EEDSP | Scoop.it

Available now to all developers on the CUDA website, the CUDA 6 Release Candidate is packed with several new features that are sure to please developers

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

NVIDIA Announces CUDA 6: Unified Memory for CUDA

NVIDIA Announces CUDA 6: Unified Memory for CUDA | EEDSP | Scoop.it

The big news here – and the headlining feature for CUDA 6 – is that NVIDIA has implemented complete unified memory support within CUDA. The toolkit has possessed unified virtual addressing support since CUDA 4, allowing the disparate x86 and GPU memory pools to be addressed together in a single space. But unified virtual addressing only simplified memory management; it did not get rid of the required explicit memory copying and pinning operations necessary to bring over data to the GPU first before the GPU could work on it.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Towards Performance-Portable, Scalable and Convenient Linear Algebra :: GPGPU.org

The rise of multi- and many-core architectures also gave birth to a plethora of new parallel programming models. Among these, the open industry standard OpenCL addresses this heterogeneity of programming environments by providing a unified programming framework. The price to pay, however, is that OpenCL requires additional low-level boilerplate code, when compared to vendor-specific solutions, even if only simple operations are to be performed. Also, the unified programming framework does not automatically provide any guarantees on performance portability of a particular implementation. Thus, device-specific compute kernels are still required for obtaining good performance across different hardware architectures.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

High Scalability - High Scalability - Strategy: Stop Using Linked-Lists

High Scalability - High Scalability - Strategy: Stop Using Linked-Lists | EEDSP | Scoop.it
What data structure is more sacred than the link list? If we get rid of it what silly interview...
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

cuDNN v2: Higher Performance for Deep Learning on GPUs

cuDNN v2: Higher Performance for Deep Learning on GPUs | EEDSP | Scoop.it

The cuDNN library team is excited to announce the second version of cuDNN, NVIDIA’s library of GPU-accelerated primitives for deep neural networks (DNNs). We are proud that the cuDNN library has se...

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Speech: Accurate Speech Recognition with GPU-Accelerated Deep Learning

Deep Speech: Accurate Speech Recognition with GPU-Accelerated Deep Learning | EEDSP | Scoop.it

Speech recognition is an established technology, but it tends to fail when we need it the most, such as in noisy or crowded environments, or when the speaker is far away from the microphone. At Bai...

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Learning on the NVIDIA Developer Zone

Developer resources for deep learning, deep neural networks, and more. Find research, presentations, articles, educational links, events, and more.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Facebook open sources tools for bigger, faster deep learning models

Facebook open sources tools for bigger, faster deep learning models | EEDSP | Scoop.it
Facebook on Friday open sourced a handful of software libraries that it claims will help users build bigger, faster deep learning models than existing tools allow. The libraries, which is calling modules, are alternatives for the default ones in a popular machine learning development environment called Torch, and are optimized to run on graphics processing…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Unified Memory: Now for CUDA Fortran Programmers

Unified Memory: Now for CUDA Fortran Programmers | EEDSP | Scoop.it
Unified Memory is a CUDA feature that we've talked a lot about on Parallel Forall. CUDA 6 introduced Unified Memory, which dramatically simplifies GPU programming by giving programmers a single poi...
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Accelerate R Applications with CUDA

Accelerate R Applications with CUDA | EEDSP | Scoop.it

In this article, I will introduce the computation model of R with GPU acceleration, focusing on three topics:

accelerating R computations using CUDA libraries;calling your own parallel algorithms written in CUDA C/C++ or CUDA Fortran from R; andprofiling GPU-accelerated R applications using the CUDA Profiler.

 

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Echelon Blog

Echelon Blog | EEDSP | Scoop.it

In preparation for my C++Now talk entitled The Future of Accelerator Programming in C++ I am currently reviewing numerous C++ libraries. I put together a catalogue of questions for these reviews. The questions are intended to gauge scope, use-cases, performance, quality and level of abstraction of each library.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

CUDA Spotlight: GPU-Accelerated Speech Recognition

CUDA Spotlight: GPU-Accelerated Speech Recognition | EEDSP | Scoop.it
This week's Spotlight is on Dr. Ian Lane of Carnegie Mellon University. Ian is an Assistant Research Professor and leads a speech and language processing research group based in Silicon Valley. He ...
more...
Topiary eDiscovery LLC's curator insight, March 12, 2014 10:30 AM

Carnegie Mellon... the Incubator.

Scooped by Shiwon Cho
Scoop.it!

How New Features in CUDA 6 Make GPU Acceleration Easier - insideHPC

In this video from the Nvidia booth at SC13, Mark Harris from Nvidia presents: New Features in CUDA 6 Make GPU Acceleration Easier.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

New Guide: Dependency Injection with Unity - Grigori Melnik: Thoughts on Agile Software Engineering and Beyond - Site Home - MSDN Blogs

New Guide: Dependency Injection with Unity - Grigori Melnik: Thoughts on Agile Software Engineering and Beyond - Site Home - MSDN Blogs | EEDSP | Scoop.it

dependency injection – a design pattern that allows the removal of hard-coded dependencies and makes it possible to assemble a service by changing dependencies easily, whether at run-time or compile-time. It promotes code reuse and loosely-coupled design which leads to more easily maintainable and flexible code.

more...
No comment yet.