Title: Fusion System Architecture: Hardware and Software Directions
Phil Rogers, AMD Corporate Fellow
It's a well-understood maxim in the technology industry that software and hardware must evolve in
parallel. AMD introduced the world's first APU, combining different processing engines in
single-chip combinations in January 2011. Using this approach, APUs strike a unique balance
between the dimensions of performance, power consumption and price for a variety of applications.
In this presentation, Phil Rogers will review AMD's architectural direction as well as AMD work to
ease the programmer's access to this new level of compute horsepower and dramatically expand the
processing resources available to modern applications.
About the speaker: Phil Rogers, AMD Corporate Fellow, is the lead architect for AMD Fusion System Architecture,
focused on optimizing the APU for system power and performance, and enabling the software
ecosystem for heterogeneous computing.
Rogers joined AMD with the ATI acquisition in 2006, became an AMD Senior Fellow shortly
thereafter, and was promoted to Corporate Fellow in 2007.
Rogers was instrumental in the development of all of ATI Radeon[tm] GPUs
since the introduction of the series in 2000.
Title: Developing Portable, High Performance Kernels with
Microway's OpenCL Tools and Services
Michael Fried, GPGPU Unit Manager, Microway
This presentation will demonstrate how to optimizize GPU kernels utilizing
state-of-the-art tools and techniques.
About the speaker: As GPGPU Business Unit Manager and resident GPU expert at
Microway, Michael Fried works on OpenCL and CUDA development tools and assists
customers with technical issues. Prior to joining Microway, he spent 8 years
as a software design engineer at Microsoft, working on the Office 2003,
2007, and 2010 products in the PowerPoint and Office Graphics
development teams.
Title: GPUs: A Disruptive Technology Goes Mainstream
Glenn Lupton, Technical Lead of the Accelerator Team
GPUs have gone from graphics cards used primarily for gaming to extremely
powerful computational devices with the capabilities needed for demanding
compute applications. The hardware and software infrastructure around these
devices has been maturing as GPUs find their way into major industries and
top spots in the TOP500 supercomputers. This presentation discusses the
adoption of GPUs as computing devices and describes some of the efforts at
HP to help bring GPUs into the mainstream of high-performance computing.
About the speaker: Glenn serves as the Technical Lead on the Accelerator
Team at HP. In the past he has served as the Technical Director for the
Advanced Visualization and Computing Division at HP.
He was also a senior member
of the Technical Staff at Compaq, and a Consulting Engineer at Digital
Equipment Corporation.