We present Laplace, a microarchitecture for tracking machine representations of probability distributions paired with architectural state. We present two new methods for in-processor distribution representations which are approximations of probability distributions just as floating-point number representations are approximations of real-valued numbers. Laplace executes unmodified RISC-V binaries and can track uncertainty through them. We present two sets of ISA extensions to provide a mechanism to initialize distributional information in the microarchitecture and to allow applications to query statistics of the distributional information without exposing the uncertainty representations above the ISA.

Computing systems that can tolerate effects of errors in their communicated data values can trade this tolerance for improved resource efficiency. Many important applications of computing, such as embedded sensor systems, can tolerate errors that are bounded in their distribution of deviation from correctness (distortion). We present a channel adaptation technique which modulates properties of I/O channels typical in embedded sensor systems, to provide a tradeoff between I/O power dissipation and distortion of communicated data. We provide an efficient-to-compute formulation for the distribution of integer distortion accounting for the distribution of transmitted values. Using this formulation we implement our value-deviation-bounded (VDB) channel adaptation. We experimentally quantify the achieved reduction in power dissipation on a hardware prototype integrated with the required programmable channel modulation circuitry. We augment these experimental measurements with an analysis of the distributions of distortions. We show that our probabilistic VDB channel adaptation can provide up to a 2× reduction in I/O power dissipation. When synthesized for a miniature low-power FPGA intended for use in sensor interfaces, a register transfer level implementation of the channel adaptation control logic requires only 106 flip-flops and 224 4-input LUTs for implementing per-bit channel adaptation on serialized streams of 8-bit sensor data.

We introduce a new method for hardware nonuniform random number generation based on the transfer characteristics of graphene field-effect transistors (GFETs) which requires as few as two transistors and a resistor. We implement the method by fabricating multiple GFETs and experimentally validating that their transfer characteristics exhibit the nonlinearity on which our method depends. We use characterisation data in simulations of a proposed architecture for generating samples from dynamically selectable non-uniform probability distributions. The method we present has the potential for Gb/s sample rates, is reconfigurable for arbitrary target distributions, and has a wide range of possible applications. Using a combination of experimental measurements of GFETs under a range of biasing conditions and simulation of the GFET-based non-uniform random variate generator, we demonstrate a speedup of Monte Carlo integration by up to $2 \times$. This speedup assumes the analog-to-digital converters reading the outputs from the circuit can produce samples in the same amount of time that it takes to perform memory accesses.

Inspired by nature, molecular communications (MC), i.e., the use of molecules to encode, transmit, and receive information, stands as the most promising communication paradigm to realize the nanonetworks. Even though there has been extensive theoretical research toward nanoscale MC, there are no examples of implemented nanoscale MC networks. The main reason for this lies in the peculiarities of nanoscale physics, challenges in nanoscale fabrication, and highly stochastic nature of the biochemical domain of envisioned nanonetwork applications. This mandates developing novel device architectures and communication methods compatible with MC constraints. To that end, various transmitter and receiver designs for MC have been proposed in the literature together with numerable modulation, coding, and detection techniques. However, these works fall into domains of a very wide spectrum of disciplines, including, but not limited to, information and communication theory, quantum physics, materials science, nanofabrication, physiology, and synthetic biology. Therefore, we believe it is imperative for the progress of the field that an organized exposition of cumulative knowledge on the subject matter can be compiled. Thus, to fill this gap, in this comprehensive survey, we review the existing literature on transmitter and receiver architectures toward realizing MC among nanomaterial-based nanomachines and/or biological entities and provide a complete overview of modulation, coding, and detection techniques employed for MC. Moreover, we identify the most significant shortcomings and challenges in all these research areas and propose potential solutions to overcome some of them.