Software Programmable Memories, or SPMs, are raw on-chip memories that are not implicitly managed by the processor hardware, but explicitly by software. For example, while caches fetch data from memories automatically and maintain coherence with other caches, SPMs explicitly manage data movement between memories and other SPMs through software instructions. SPMs make the design of on-chip memories simpler, more scalable, and power efficient, but also place additional burden for programming of SPM-based processors. Traditionally, SPMs have been utilised in embedded systems, especially multimedia and gaming systems, but recently research on SPM-based systems has seen increased interest as a means to solve the memory scaling challenges of many-core architectures. This study presents an overview of the state-of-the-art in SPM management techniques in many-core processors, summarises some recent research on SPM-based systems, and outlines future research directions in this field.

The inner workings of the brain as a biological information processing system remain largely a mystery to science. Yet there is a growing interest in applying what is known about the brain to the design of novel computing systems, in part to explore hypotheses of brain function, but also to see if brain-inspired approaches can point to novel computational systems capable of circumventing the limitations of conventional approaches, particularly in the light of the slowing of the historical exponential progress resulting from Moore's Law. Although there are, as yet, few compelling demonstrations of the advantages of such approaches in engineered systems, a number of large-scale platforms have been developed recently that promise to accelerate progress both in understanding the biology and in supporting engineering applications. SpiNNaker (Spiking Neural Network Architecture) is one such large-scale example, and much has been learnt in the design, development and commissioning of this machine that will inform future developments in this area.

This study introduces an inexact, but ultra-low power, computing architecture devoted to the embedded analysis of bio-signals. The platform operates at extremely low voltage supply levels to minimise energy consumption. In this scenario, the reliability of static RAM (SRAM) memories cannot be guaranteed when using conventional 6-transistor implementations. While error correction codes and dedicated SRAM implementations can ensure correct operations in this near-threshold regime, they incur in significant area and energy overheads, and should therefore be employed judiciously. Herein, the authors propose a novel scheme to design inexact computing architectures that selectively protects memory regions based on their significance, i.e. their impact on the end-to-end quality of service, as dictated by the bio-signal application characteristics. The authors illustrate their scheme on an industrial benchmark application performing the power spectrum analysis of electrocardiograms. Experimental evidence showcases that a significance-based memory protection approach leads to a small degradation in the output quality with respect to an exact implementation, while resulting in substantial energy gains, both in the memory and the processing subsystem.

Long timescales and complex design processes require that CPU architects and microarchitects have early access to information about future manufacturing processes. In some cases, this means that future technology must be predicted in advance of it actually being developed. In addition, close collaboration with the foundries, known as ‘Design-Technology Co-Optimisation’, or DTCO, allows the mutual influence during development of microarchitecture, physical IP (standard cells and memories), and process technology. This predictive technology, in conjunction with early technology information or not, allow design exploration in the form of trial runs of synthesis, place and route to determine the predicted effects of various technology choices on CPU power, performance, and area.