Today’s embedded solutions are driving higher performance applications in smaller form factors, from sophisticated industrial control and automation applications that require complex processing algorithms to digital signage applications that require high-performance graphics processing. These applications often require low power consumption and support for open standards in order to provide the highest levels of design flexibility. To enable these applications, developers need embedded processing platforms that deliver advanced performance while helping to reduce time-to-market and development costs.
New highly integrated system-on-chip (SOC) processors are available that feature a high-performance x86 multicore processor, a discrete-class graphics processing unit (GPU), an I/O controller, and error-correction code (ECC) memory support for high reliability – all on a single die. With increased chip-level integration, developers can achieve new levels of processing efficiency, while retaining a low power design and a significant footprint reduction to reduce manufacturing costs and minimize design complexity.
This article will describe the benefits, technology, and target markets for single-chip SOCs so developers can make informed decisions about whether this type of solution is right for their next embedded design projects.
Typical processing SOCs are comprised of one or more microcontroller or DSP cores, memory blocks, timing sources, peripherals, external interfaces, analog interfaces, voltage regulators, and power management circuits. The processor is usually powerful enough to run a Windows, Linux, Android, or RTOS operating system.
Traditionally, SOC processor architectures have not been widely utilized for graphics-intensive applications. For these applications, developers typically design a system whereby CPUs and GPUs are separate processing elements, and therefore they usually do not work together efficiently. Each has a separate memory space, requiring an application to copy data from the CPU to GPU and then back again. Additional chips are required to make a complete system.
The accelerated processing unit (APU), pioneered by AMD, is comprised of a low power CPU and a discrete-class GPU with a companion I/O unit in a two-chip architecture (Figure 1). The APU was the first step toward the realization of a new generation of SOC processors. APUs enable a large amount complex data processing more efficiently than either a CPU or GPU alone, but in a larger footprint than a single-chip SOC.
Figure 1: New generations of embedded SoCs targeting graphics incorporate a low power microprocessor with a dedicated graphics processor unit and a companion I/O acceleration unit.
Single-chip SOCs, like their APUpredecessors, enable “heterogeneous computing”, which refers to systemscomprised of multiple processor types, typically CPUs and GPUs, andusually on the same silicon die. There are numerous advantages toheterogeneous computing but most importantly, heterogeneous computingenables each processor element to perform efficiently at what it doesbest, and to work cooperatively. With heterogeneous computing theprocessors share memory space so there is no need for them to copy databack and forth.
Using its high-performance vector processingcapabilities, the onboard GPU is free to perform parallel operations onvery large sets of data at much lower power consumption than a CPUcould. Meanwhile, the onboard CPU handles scalar processing tasks thatsupport general-purpose functions such as running the operating system.Heterogeneous computing via an integrated single-chip SOC results indramatic performance increases per watt as compared to ad hoc CPU+GPUchipsets. Figure 1, a block diagram of the AMD G-Series single-chip SOC,illustrates components found on these solutions.
Target applications for SOCs
Digitalsignage systems are optimized to provide immersive HD visualexperiences across multiple displays for a wide range of environmentssuch as supermarkets, shopping centers, and transportation hubs. Thesesystems require the high-speed delivery of HD multimedia content,typically in a small form factor design. Low power consumption iscritical for these types of systems, as it helps designers alleviatethermal dissipation challenges within the system.
Thin clientsrely heavily upon HD video and graphics, and are dependent upon improveddata transfer rates in order to create enhanced Internet experiences.Industrial control and automation systems, from headless control systemsto complex display systems and human-machine interfaces, also dependupon high-performance, low-power processor architectures. Industrialcontrol and automation applications typically require software to besupported across a broad spectrum of devices. The single-chip SOC is anattractive option for this application domain due to its support foropen standards such as the Open Computing Language (OpenCL).
Anotherkey enabler for heterogeneous computing is a system’s ability tooperate in multivendor environments. OpenCL, which enables parallelprogramming of GPUs, CPUs, and other processors, provides a uniformprogramming environment for developers to write efficient, portable codeacross different hardware and software platforms. With OpenCL,programmers can preserve their expensive source-code investments,re-using code across platforms.
Inorder to provide visually stunning graphics for a broad range ofapplications, GPUs often include hardware acceleration capabilities. TheUnified Video Decoder, which is included in advanced GPUs from AMD,decodes H.264, VC-1, and MPEG-4 video formats natively at the processorlevel. AMD’s Video Codec Engine, included in the AMD G-Series SOC’sintegrated GPU, encodes videos using H.264 compression with full, customhardware acceleration. Dedicated hardware acceleration engines forvideo decode and encode are particularly beneficial formultimedia-intensive applications such as digital gaming and digitalsignage.
Standard API support is also an important considerationfor HD video applications, as it enables developers to expand theirsoftware development options. The OpenGL API (the latest version isOpenGL 4.3) enables 2D and 3D graphics and is often used for digitalgaming applications. The DirectX API (the latest version is DirectX11.1), enables support for multimedia-related tasks within Microsoftplatforms, delivers 2D and 3D rendering, GPU compute, and even powerefficiency, and is especially useful for games and video, among otherapplication areas.
Electronic gaming systems, which oftenfeature vibrant 3D graphics displayed across multiple monitors, canbenefit from the significant performance boost enabled with video- andgraphics-optimized SOC processors. SOC processors that feature DirectXsupport with a scalable, x86-based architecture can help systemdesigners meet aggressive performance targets.
Withhigher integration (including the I/O controller), the single-chip SOCoccupies less real estate than comparably-performing CPU+GPU chipsets.As mentioned earlier, a single-chip SOC can save more than 30% spacecompared to a two-chip solution, requiring fewer board layers. Theperformance-per-watt profiles provided by SOCs can also enabledevelopers to eliminate mechanical fans from their designs in manycases. With fewer moving parts, there is less risk of failure and asignificant reduction in noise.
The small footprint of asingle-chip SOC makes it ideal for numerous application areas, improvingnot only power consumption but also price/performance. The smallfootprint and power savings also make single-chip SOCs ideal candidatesfor smaller single-board computer (SBC) and computer-on-module (COM)designs, including PC/104, Pico-ITX, Q-Seven, nanoEXTexpress, and MobileITX.
Single-chip SOC solutions, such as AMDEmbedded G-Series SOCs, are smaller in size, offer dramatic performanceimprovements, and are more energy efficient than most CPU+GPU chipsets.With a high level of integration, SOC processors can save designersvaluable time and cost while helping them achieve advanced systemcapabilities.
David Beck is director of technical marketing, Symmetry Electronics.