Demanding big-time graphics in little packages

March 1, 2012 OpenSystems Media

3The demand for graphics performance in small form factor embedded devices is continuing to grow to the next level. This push has created new challenges for designers in a broad array of vertical markets. Silicon platforms available today enable the creation of small devices with enhanced embedded graphics capabilities.

Embedded PCs are being pushed to excel like never before. Much of this pressure is generated by user requirements stemming from the consumer market and its vast array of computing devices. Today, it’s hard to find a vertical market that doesn’t have a need for more powerful graphics capabilities. At the same time, the push for low-power smaller form factors compels embedded PCs to keep up with shrinking board sizes. Many years ago, the future of embedded computing was defined with a focus on “smaller is better.” Now that objective seems to have been redefined as “smaller, with more capabilities, is better.”

To achieve high-quality video in an embedded system, designers have traditionally needed to incorporate peripheral-based graphics engines in the form of a plug-in card or module. This increased the overall hardware component count in the system and often led to additional form factors and heat concerns.

Today, major silicon vendors are providing embedded graphics processors powerful enough to tackle multiple application requirements. One such processor is the Accelerated Processing Unit (APU), which combines the functionality of a Central Processing Unit (CPU) and a Graphics Processing Unit (GPU) into one chip.

Processes run mostly serially on a standard CPU. Under these circumstances, parallelization can only occur in multiprocessor systems or virtually via time-splicing control of relatively large processes. On the contrary, with a GPU, tasks are distributed over many small and highly specialized engines. These engines are linked to one another according to their respective tasks, which they manage in each time step in parallel. With another type of processor, the General-Purpose GPU (GPGPU), the individual processor tasks are not hardwired, as is the case with the Vertex Shader Unit using a simple GPU. Instead, the particular tasks are freely configurable, similar to a network processor within a certain range.

An APU such as the AMD Fusion distinguishes itself from a standard GPU with its flexible parallel processing units. Its GPGPU can be used for compute-intensive parallel operations and can considerably increase performance in the non-graphics sphere. This APU not only provides a powerful graphics engine, it also gives developers the freedom to use it for other purposes as well.

Qseven addresses graphics needs

When it comes to implementing the latest APU silicon in a system, the best choice is often a small form factor module. One example of a small form factor module utilizing AMD’s Fusion APU is congatec’s latest Qseven module, the conga-QAF (Figure 1). The Qseven standard is an off-the-shelf, multivendor Computer-On-Module (COM) that integrates all the core components of a common PC. It is mounted to a carrier board that enables designers to match their I/O requirements with their footprint requirements.

21
Figure 1: The conga-QAF Qseven module combines high graphics performance, dual-core processing power, and low power consumption in a small form factor.

Measuring 70 mm x 70 mm, the Qseven form factor utilizes a high-speed MXM system connector that has a standardized pinout regardless of the vendor. The Qseven specification defines an ultra-low overall height of 13.9 mm for the carrier board, Qseven module, and flat heat spreader combination when using the lowest-profile MXM connector.

In addition to offering a compact design, the Qseven module allows designers to address the challenge of potentially running the system on battery power. To obtain the most uptime from batteries, designers need to focus on keeping total system power draw as low as possible. Depicted in the block diagram in Figure 2, the AMD G-Series APUs found on congatec’s conga-QAF modules have a clock speed of 1.0 GHz and a Thermal Design Power (TDP) of 5.5 W in the single-core version and 6.4 W in the dual-core version. Either model enables the Qseven module to fall under the specified 12 W ceiling for Qseven modules.

22
Figure 2: AMD’s Embedded G-Series architecture integrates a low-power processor and advanced GPU into a single embedded APU.

APUs in action

One area of the embedded market where APUs and modules like Qseven are beginning to play a major role is medical equipment. Geared by the consumer market, the efficiency of the graphics core has steadily increased in the medical equipment market. In particular, the 3D representation of virtual worlds has advanced the specialization of graphic cards to the highest parallel of computing power. Due to the variety of graphics data such as computations of textures, volumes, and 3D modeling for collision queries, as well as Vertex Shader for geometry computations, the functionalities are no longer cast firmly in hardware, but rather can be freely programmed. Therefore, modern graphics cores offer flexible and enormous potential.

A specific example in the medical equipment industry is the computational requirements found in today’s portable 3D ultrasound devices. Certain data forms from sensors, gauge heads, transceivers, or video cameras are processed more efficiently and faster with dedicated processing cores than with the generic, serial computing power of x86 processors. With the GPGPU, it is irrelevant if program codes are virtually produced or forwarded from external sources. Thus, there is an advantage in uniting the CPU and GPU in an APU to create an even stronger team.

These days, portable computing-based devices, regardless of whether they are used in medical, automation, logistics, or kiosk systems, require higher graphical and computing performance than what is offered by previous embedded technologies. Users can easily upgrade their machines and devices by changing modules to enable future performance gains. This leads to new possibilities in portable devices, particularly in regard to imaging technology and analysis devices, where the APU architecture can fully exploit the advantages of parallel processing. In addition, the excellent ratio of computing power to power consumption enables battery-operated devices with higher performance. Moving forward, it is inevitable that more and more applications will take advantage of future developments around APUs, with Qseven modules available to help designers turn their ideas into reality.

Dan Demers is sales and marketing manager at congatec Inc.

congatec 858-457-2600 info@congatec.com www.linkedin.com/company/congatec-ag www.congatec.us

Dan Demers (congatec)
Previous Article
Programmable perks: Tallying the benefits of FPGAs
Programmable perks: Tallying the benefits of FPGAs

Leaders in the field of FPGAs share their thoughts on how FPGA technology can simplify and add functionalit...

Next Article
Pitfalls of multicore software: Why data races are never benign
Pitfalls of multicore software: Why data races are never benign

Static analysis tools build models to help single out race conditions that would otherwise run away with so...