The number of bugs in a chip is relatively proportional to the number of transistors - Bob Colwell, former Intel chief architect
CHIP DESIGNER AMD launched its highest performing second generation embedded R-series accelerated processing unit (APU) and CPU lines on Tuesday, codenamed Bald Eagle.
Made for embedded applications, the 28nm chip is aimed at bringing 4K quality displays to gaming machines, medical imaging, digital signage, industrial control and automation, and communications and networking infrastructure that are increasingly relying on compute and graphics processing technology.
"Bald Eagle is our first implementation of our Heterogeneous Systems Architecture (HSA) that allows us to unlock the power of the GPU for non-traditional graphics workloads," AMD CVP and GM of Embedded Solutions Scott Aylor said in a briefing call.
"In the evolution of our next wave of processing and graphics technology, we are able to support 4K, the advent of ultra high definition (UHD). [This] is a big part of what we are bringing forward in this device."
AMD R-series APU and CPU chips are designed for mid to high-end visual and parallel compute-intensive embedded applications with support for Linux, RTOS and Windows operating systems. AMD said Bald Eagle is the very top end of performance in the R-series family.
"We have the vertical segments that we are focusing on in terms of establishing a vertical market system level value propositions. Areas like digital signage, for example is a great one where this device is our first that actually has 4K display capability," Aylor added.
"What we see happening in the digital signage market is enormous growth in quick-service restaurant and video walls, where people are replacing digital signage with rich interactive signage," Aylor explained.
"The Bald Eagle device is the first device that enables those innovations in display."
The second generation R-series ranges from 2.2GHz to 3.6GHz CPU frequency with max boost, based on AMD's latest CPU architecture codenamed Steamroller, and 533MHz to 686MHz GPU frequency based on AMD's latest Graphics Core Next (GCN) architecture, designed to boost the growth and parallel processing capabilities of embedded applications.
The R-series family is also designed for embedded applications with dual-channel memory including error-correcting code (ECC), DDR3-2133 support and configurable thermal design power (TDP) for system design flexibility to optimise the processor at a lower TDP, AMD said. µ
Sign up for INQbot – a weekly roundup of the best from the INQ