Tuesday 30 June 2015

More OpenCL 2.0 goodness, DX12 & Vulkan news, clRNG beta released + more

AMD Developer News
WELCOME TO AMD DEVELOPER NEWSJune 2015 | Previous Issues
Benchmarking clBLAS SGEMM on the AMD FirePro™ Professional Graphics Card!
 
4.2 Teraflops of Performance? As part of an ongoing effort to raise the performance of open source math libraries, AMD added offline kernel compilation to clBLAS. Find out what the results were in this new blog.


 
OPENCL™ RANDOM NUMBER LIBRARY (CLRNG) BETA RELEASED
 
clRNG 1.0 is an OpenCL library that generates uniform random numbers. This library is now available as open-source. Since it’s in beta, we’re looking for feedback. Check it out, use it, and let us know your feedback.


 
MERKLE TREE HASHING USING OPENCL™ 2.0
 
You can use OpenCL™ 2.0’s features and GPU compute to get real performance improvements in your code. Curious whether those performance gains are worth the effort? See what we did with hashing algorithms.


 
Questions about HSA development? See what other developers have asked, and get answers in the HSA forum on DevGurus.
CONFERENCE & EVENTS◢
GDC Europe 2015
Cologne, Germany
Aug 3-4, 2015

SIGGRAPH 2015
Los Angeles, CA
Aug 9-13, 2015

TRAINING & EDUCATION◢
OpenCL™ 2.0 training in Amsterdam from StreamComputing, Sept 2, 2015

OpenCL™ Training for Altera FPGAs in Baltimore, MD, with Acceleware, Sept 22, 2015


On-Demand Webinars & Tutorials – From AMD Developer Central

Visit AMD's Training Partners for more training options or to schedule a customized training session
Software Engineer
Beijing, China

Software Engineer
Bangalore, India
DX12 & VULKAN AT GDC EUROPE – THE DAWN OF A NEW GENERATION OF GRAPHICS APIS 
 
Developing for DX12 or Vulkan can offer significant performance boosts but sometimes requires a new approach to graphics programming. Come see us at GDC Europe August 3-4 for a presentation that will show you how to work with the new APIs.


 
A BRAND NEW OPENCL BOOK
 
Heterogeneous Computing with OpenCL 2.0 teaches OpenCL and parallel programming for complex systems that may include a variety of device architectures: multi-core CPUs, GPUs, and fully-integrated Accelerated Processing Units (APUs). This fully-revised edition includes the latest enhancements in OpenCL 2.0 and much more. Best of all, it’s out of pre-order status and available now! 

 
CONCURRENCY IN MODERN 3D GRAPHICS APIS 
 
Over the past year or two AMD’s Mantle introduced the efficiency of low-level APIs to the PC gaming developer community. That sparked a trend leading to significant developments in graphics APIs like Vulkan™ and DirectX® 12. Why is concurrency the greatest feature of those new graphics APIs? Find out in this new blog post.


 
SUPERCHARGING WITH DIRECTX® 12 & ASYNC SHADERS 
 
Microsoft® DirectX® 12 is designed to substantially increase a PC’s ability to run visually complex games at playable framerates. This blog post looks at the major rendering features of DirectX® 12, early performance profiles of AMD products, and collaborating with developers to ensure peak performance and top-notch image quality in upcoming games.


 
 
 
 
Power Profiling, Shader Analysis & More with AMD CodeXL 1.7
 
 
Watch Video »
 
 
Debug your way through OpenGL, GLES, DX11 & DX12 using GPU PerfStudio
 
Watch Video »
 
 
AMD Asynchronous Shaders Demo
 

 
Watch Video »
 

Thursday 25 June 2015

Introducing AMD Radeon™ R9 Fury X graphics Memperkenalkan Kartu Grafis AMD Radeon™ R9 Fury X

AMD Radeon ™ graphics card R9 Fury X is a total revolution inside and out.


GPU is the most advanced and innovative today that can provide the highest GPU memory bandwidthever for gaming experience at resolutions of 4K and VR (Virtual Reality) is unmatched.

The world's first graphics card that uses High Bandwidth Memory (HBM) as innovations from AMD.
HBM has a 60% greater bandwidth than GDDR5. 1
4096-bit memory interface that has never existed before.
Designed for maximum gaming experience with technologies such as AMD Eyefinity, FreeSync ™, LiquidVR ™, DirectX® 12 support, Vulkan ™, and much more.
Equipped Tach GPU activity gauges and LED lighting.
An incredible new level in terms of scale and design flexibility.

Small size. Major changes. Graphics Card AMD Radeon ™ R9 Fury X. 
View the infographic LiquidVR

Medical Imaging Issue - AMD Embedded Solutions Newsletter

AMD Embedded Solutions News
AMD Embedded Radeon™ HD 7850 GPU Accelerates Medical Imaging

AMD Embedded Radeon HD 7850 Medical Imaging - Press Release
On January 12th, AMD announced that the
AMD Embedded Radeon™ HD 7850 GPU is enabling cutting-edge application performance for the BK Ultrasound, powered by Analogic bk3000™ ultrasound system. Analogic is a leader in developing healthcare and security technology solutions to advance the practice of medicine to save lives.

Read More

 
AMD Eyes the Medical Device Segment In The Embedded Market
AMD Eyes the medical device segment in the embedded market
As written by Forbes: The embedded market is a very competitive market and AMD’s strategy is to play to its strengths. The company is focusing on efficient computing and very strong visualization, factors that it believes differentiates it from other players and will fuel its growth in the embedded market. The company is a key player in digital signage, and has admitted in the past that medical devices is a segment of considerable focus and interest.

Read More
June Partner Focus: congatec
June Partner Focus: Congatec
congatec has integrated AMD’s G-Series SoC processors on Computer-on-Modules (COMs) in a move to round off the company’s range of high-graphics, low-power modules for compact form factors. The focus is on the multitude of embedded applications, such as medical imaging, where high graphics performance and open x86 programmability are required in a small form factor.

Learn More

AMD performance powers Samsung thin clients

AMD Embedded G-Series SoC Powers New Line of Samsung All-In-One Thin Client Solutions.

AMD Embedded SolutionsAMD recently announced that Samsung Electronics Co., Ltd. selected the AMD Embedded G-Series SoC (system on chip) for a new line of all-in-one cloud monitors featuring integrated thin client technology. The Samsung 21.5-inch TC222W and 23.6-inch TC242W are powered by AMD Embedded G-Series SoCs that couple high-performance compute and graphics capability in a highly integrated, low power design. The AMD SoC improves data transfer rates and saves space on the motherboard, which makes it a perfect fit for the compact form factors required by thin clients.

Samsung TC222WPlanned availability starting in Q3 2015, the Windows®-supported Samsung cloud monitors will provide customers with expanded choice, capability and configuration flexibility. Complete with Samsung's professional-grade display panel, the cloud monitors will create a superior user experience through easy connectivity and high-quality reliability. As a superior option for effective desktop virtualization, Samsung's thin-client monitors will also enable improved productivity and optimized end-to-end performance.

Tuesday 23 June 2015

HPC User Support Tools (HUST15): Call for Papers

HPC User Support Tools (HUST15): Call for Papers
HUST 2015
====================
Second Annual Workshop on HPC User Support Tools
Held in conjunction with SC15, in cooperation with SIGHPC.
November 20, 2015, Austin, TX, USA.
http://hust15.github.io/


Call For Papers
--------------------
Supercomputing centers exist to drive scientific discovery by
supporting researchers in computational science fields. To make users
more productive in the complex HPC environment, HPC centers employ
user support teams. These teams serve many roles, from setting up
accounts, to consulting on math libraries and code optimization, to
managing HPC software stacks. Adequately supporting scientists can
often be a struggle for the support teams. HPC environments are
extremely complex, and combined with the complexity of multi-user
installations, exotic hardware, and maintaining research software,
supporting HPC users can be extremely demanding. Meeting all of these
competing demands of the scientist often results in the creation of
new tools and establishment of new policies and best practices.

With the second HUST workshop, we will continue to provide a necessary
forum for system administrators, user support team members, tool
developers, policy makers and end users to discuss support issues. We
solicit papers on user support experiences, best practices, tools, and
any efforts to streamline support at supercomputing centers.


Topics of Interest
--------------------
Topics of interest include, but are not limited to:

  * Defining and customising the user environment
  * Software build and installation tools
  * Tools and frameworks for using performance analysis tools
  * Workflow and pipeline tools
  * Collaboration tools
  * Novel environments: cloud, etc.
  * Tools and frameworks for supporting Hadoop and Big Data
  * Establishing baseline configuration efforts for HPC
  * Software development/system testing
  * Documentation: creating, maintaining and updating


We invite authors to submit original, high-quality work with
sufficient background material to be clear to the HPC
community. Papers should be submitted in PDF format and should not
exceed 10 pages including tables, figures and appendices, but
excluding references. They should be formatted according to the ACM
SIG Proceedings format. Similar to the SC15 policy, margins and font
sizes should not be modified. We kindly refer authors to the necessary
templates.

All submissions should be made electronically through the EasyChair
website. Submissions must be double blind, i.e., authors should remove
their names, institutions or hints found in references to earlier
work. When discussing past work, they need to refer to themselves in
the third person, as if they were discussing another researcher¹s
work. Furthermore, authors must identify any conflict of interest with
the PC chair or PC members.

Proceedings will be published in both IEEE Xplore and the ACM Digital
library through collaboration with ACM SIGHPC.


Important Dates
--------------------
  * Submission deadline: August 7
  * Workshop paper reviews due: September 21
  * Acceptance notifications: October 1
  * Camera-ready papers: October 8
  * Workshop: November 20, at SC15. 8:30AM - 12:00PM.


More Information
--------------------
Further details, as well as a link to the submission site, can be
found at the HUST'15 website:

  http://hust15.github.io/

Also, be sure to visit the SC15 site at http://sc15.supercomputing.org