The growing impact of the network on the overall power consumption of many-core systems introduces a need for mechanisms that reduce the power required for data communication without significantly impacting performance. This paper proposes a low-overhead mechanism for frequency control of individual channels in a Network-on-Chip system. The proposed mechanism is low-overhead, distributed and easy to tune for varying traffic, which are crucial aspects in a many-core context. This is primarily achieved by the asymmetry of the controller, which defines different responses for increases and decreases in performance requirements, allowing a channel to operate at the minimum required frequency without adversely affecting stability, necessary for subsequent voltage scaling.

Implementing Dynamic Voltage and Frequency Scaling (DVFS) is a non-trivial task on FPGAs and requires knowledge about the feasible voltage and frequency (VF) ranges as a first step. The VF feasible ranges depend not only on the size of the critical path in the design but also on the inter- and intra-die variability on the FPGA die. Moreover, the variations in the configuration of the FPGA highly affect feasible VF ranges. Therefore, it is crucial to characterise feasibility by studying the relationship between feasible VF regions and these sources of variability in FPGAs. In this paper we employ a self-checking multiplier which uses residue codes and DVFS implemented on the programmable logic component of a Xilinx Zynq ZC702 device as an error-detection circuit to study these feasible regions. Results show that, as expected, feasible VF ranges vary with FPGA configuration. More interestingly, significant variation of the feasible VF regions is found for different dies. These results highlight the necessity of dynamic self-testing as a part of an adaptive DVFS implementation on FPGAs. Employing the techniques presented in this work enables the implementation of efficient adaptive on-line DVFS on programmable logic while ensuring reliability.

This paper details an extension to an architecture for robust bidirectional hetero-associative recall. Our proposed Protein Processor Associative Memory (PPAM) is fundamentally different from the traditional processing methods which use arithmetic operations and consequently Arithmetic and Logic Units (ALUs). In this paper, we improve on our initial work addressing concerns surrounding hardware implementation. We present the improved computational architecture, coupled with a corresponding hardware architecture for implementation. Results of applying the hardware implementation on a small dataset are included, along with reports from synthesis tools about hardware utilisation.

The evolution of Artificial Intelligence has passed through many phases over the years, going from rigorous mathematical grounding to more intuitive bio-inspired approaches. Despite the abundance of AI algorithms and machine learning techniques, the state of the art still fails to capture the rich analytical properties of biological beings or their robustness. Most parallel hardware architectures tend to combine Von Neumann style processors to make a multi-processor environment and computation is based on Arithmetic and Logic Units (ALU). This paper introduces an alternate architecture that is inspired from the biological world, and is fundamentally different from traditional processing which uses arithmetic operations. The architecture proposed here is targeted towards robust artificial intelligence applications.

In this article, we describe a novel hardware platform aimed at the realization of cellular architectures. The system is built hierarchically from a very simple computing unit, called ECell. Several of these units can then be connected, using a high-speed serial communication protocol, to a more complex structure called the UltraStack. Consisting of four different kinds of interconnected boards (computational, routing, power supply, and display), these stacks can then be joined together to form an arbitrarily large parallel network of programmable circuits. This structure, while theoretically universal in its operation, is however particularly suited for the implementation of cellular computing applications.

The multicellular structure of biological organisms and the interpretation in each of their cells of a chemical program (the DNA string or genome ) is the source of inspiration for the Embryonics (embryonic electronics) project, whose final objective is the design of highly robust integrated circuits, endowed with properties usually associated with the living world: self-repair and self-replication. In this article, we provide an overview of our latest research in the domain of the self-replication of processing elements within a programmable logic substrate, a key prerequisite for achieving system-level fault tolerance in our bio-inspired approach.

Fault tolerance is a crucial operational aspect of biological systems and the self-repair capabilities of complex organisms far exceeds that of even the most advanced electronic devices. While many of the processes used by nature to achieve fault tolerance cannot easily be applied to silicon-based systems, in this paper we show that mechanisms loosely inspired by the operation of multicellular organisms can be transported to electronic systems to provide self-repair capabilities. Features such as dynamic routing, reconfiguration, and on-chip reprogramming can be invaluable for the realization of adaptive hardware systems and for the design of highly complex systems based on the kind of unreliable components that are likely to be introduced in the not-too-distant future. In this paper, we describe the implementation of fault tolerant features that address error detection and recovery through dynamic routing, reconfiguration, and on-chip reprogramming in a novel application specific integrated circuit. We take inspiration from three biological models:phylogenesis, ontogenesis,andepigenesis(hence the POE in POEtic). As in nature, our approach is based on a set of separate and complementary techniques that exploit the novel mechanisms provided by our device in the particular context of fault tolerance.

In this article, we describe the application of an enhanced genetic algorithm to the problem of hardware-software codesign. Starting from a source code written in a high level language our algorithm determines, using a dynamically-weighted fitness function, the most interesting code parts of the program to be implemented in hardware, given a limited amount of resources, in order to achieve the greatest overall execution speedup. The novelty of our approach resides in the tremendous reduction of the search space obtained by specific optimizations passes that are conducted on each generation. Moreover, by considering different granularities during the evolution process, very fast and effective convergence (in the order of a few seconds) can thus be attained. The partitioning obtained can then be used to build the different functional units of a processor well suited for a large customization, thanks to its architecture that uses only one instruction, Move.

In 1953, Crick and Watson published their landmark paper revealing the detailed structure of the DNA double helix. Several years earlier, von Neumann embedded a very complex configuration, a universal interpreter-copier, into a cellular array. Astoundingly, the structure of this configuration, able to realize the self-replication of any computing machine, including a universal Turing machine, shares several common traits with the structure of living cells as defined by Crick and Watson's discovery. To commemorate the 100th anniversary of von Neumann's birth, this paper presents a macroscopic analysis of self-replication in computing machines using three examples. After describing self-replication in von Neumann's universal interpreter-copier, we will revisit the famous self-replicating loop designed by Langton in 1984. In order to overcome some of the major drawbacks of Langton's loop, namely, its lack of functionality and the fact that it is ill-adapted for a realization in electronic circuits, we present a novel self-replicating loop, the Tom Thumb loop. Endowed with the same capabilities as von Neumann's interpreter-copier, i.e., the possibility of replicating computing machines of any complexity, our loop is moreover specifically designed for the implementation of self-replicating structures in programmable digital logic.

The growth and operation of all living beings are directed by the interpretation, in each of their cells, of a chemical program, the DNA string or genome. This process is the source of inspiration for the Embryonics (embryonic electronics) project, whose final objective is the design of highly robust integrated circuits, endowed with properties usually associated with the living world: self-repair (cicatrization) and self-replication. The Embryonics architecture is based on four hierarchical levels of organization. (1) The basic primitive of our system is the molecule, a multiplexer-based element of a novel programmable circuit. (2) A finite set of molecules makes up a cell, essentially a small processor with an associated memory. (3) A finite set of cells makes up an organism, an application-specific multiprocessor system. (4) The organism can itself replicate, giving rise to a population of identical organisms. We begin by describing in detail the implementation of an artificial cell characterized by a fixed architecture, showing that multicellular arrays can realize a variety of different organisms, all capable of self-replication and self-repair. In order to allow for a wide range of applications, we then introduce a flexible architecture, realized using a new type of fine-grained field-programmable gate array whose basic element, our molecule, is essentially a programmable multiplexer. We describe the implementation of such a molecule, with built-in self-test, and illustrate its use in realizing two applications: a modulo-4 reversible counter (a unicellular organism) and a timer ( a complex multicellular organism). We describe our ongoing research efforts to meet three challenges: a scientific challenge, that of implementing the original specifications formulated by John von Neumann for the conception of a self-replicating automaton; a technical challenge, that of realizing very robust integrated circuits capable of self-repair and self-replication; and a biological challenge, that of attempting to show that the microscopic architectures of artificial and natural organisms, i.e., their genomes, share common properties.

Biological organisms are among the most intricate structures known to man, exhibiting highly complex behavior through the massively parallel cooperation of numerous relatively simple elements, the cells. As the development of computing systems approaches levels of complexity such that their synthesis begins to push the limits of human intelligence, engineers are starting to seek inspiration in nature for the design of computing systems, both at the software and at hardware levels. We present one such endeavor, notably an attempt to draw inspiration from biology in the design of a novel digital circuit: a field-programmable gate array (FPGA). This reconfigurable logic circuit will be endowed with two features motivated and guided by the behavior of biological systems: self-replication and self-repair.

The growth and the operation of all living beings are directed through the interpretation, in each of their cells, of a chemical program, the DNA string or genome. This process is the source of inspiration for the Embryonics (embryonic electronics) project, whose final objective is the conception of very large scale integrated circuits endowed with properties usually associated with the living world: self-repair (cicatrization) and self-replication. We begin by showing that any logic system can be represented by an ordered binary decision diagram (OBDD), and then embedded into a fine-grained field-programmable gate array (FPGA) whose basic cell is a multiplexer with programmable connections. The cellular array thus obtained is perfectly homogeneous: the function of each cell is defined by a configuration (or gene) and all the genes in the array, each associated with a pair of coordinates, make up the blueprint (or genome) of the artificial organism. In the second part of the project, we add to the basic cell a memory and an interpreter to, respectively, store and decode the complete genome. The interpreter extracts from the genome the gene of a particular cell as a function of its position in the array (its coordinates) and thus determines the exact configuration of the relative multiplexer. The considerable redundancy introduced by the presence of a genome in each cell has significant advantages: self-replication (the automatic production of one or more copies of the original organism) and self-repair (the automatic repair of one or more faulty cells) become relatively simple operations. The multiplexer-based FPGA cell and the interpreter are finally embedded into an electronic module; an array of such modules make it possible to demonstrate self-repair and self-replication.