Modern applications like Genomics and Machine Learning (ML) hold the potential to reshape our understanding of diseases’ genetic origins and guide machines in executing tasks and making predictions without our explicit programming. The successful, widespread integration of these modern applications can usher in advancements in di-agnostics, individualized medicine, and routine tasks such as language interpretation, image analysis, and object categorization. However, our traditional computing infrastructures fall short when accommodating the distinct characteristics of these new applications. Specifically, (1) these applications handle an immense and ever-expanding data working set, and (2) each succeeding version of these applications and their associated use cases necessitates quicker and more energy-efficient analysis of these vast data sets. This is because our traditional computing systems largely hinge on (1) the von-Neumann architecture, a design that distinctly positions processing entities (like CPUs and GPUs) away from storage components (like memories and flash drives), and (2) the CMOS-based technology. While attempting to meet the performance and energy demands of our modern applications, these fully CMOS-based systems based on von-Neumann architecture have increasingly struggled and hit inherent roadblocks, with data movement overhead being the predominant issue.
To alleviate the data movement bottleneck, contemporary research revisits a concept historically known as Computation-In-Memory (CIM) or, alternatively, Processing-In-Memory (PIM). At its core, CIM emphasizes positioning computational capabilities close to, or within, the memory units storing the data. This placement might be within memory chips, in memory controllers, amid caches, or embedded in the logic layers of 3D-stacked memories. As a computational model, architectures leveraging CIM (referred to as CIM architectures) stand to tackle the issue of data movement overhead inherent in the von-Neumann architecture by diminishing or outright eradicating the data movement between computational locales and data storage areas. Moreover, from a techno-logical perspective, emerging memory technologies, including memristive devices and circuits, show potential to replace traditional memory systems, addressing some of the challenges posed by CMOS-based designs.
Irrespective of the specific CIM architecture deployed to optimize performance or energy efficiency in modern applications, there are substantial practical challenges to address and ponder upon first. Both system designers and developers face these hurdles and design decisions, which are critical to surmount CIM’s widespread acceptance across various computational areas and application domains.
In this dissertation, our focus is twofold: (1) We delve into the acceleration and streamlined execution of various steps in two pivotal application realms: genomics and ML; and (2) We explore several emerging memory technologies alongside circuit and architectural strategies, that show promise in enhancing CIM designs, specifically tailored for modern applications.
Therefore, in this thesis, we identify and propose strategies and designs to ameliorate the constrained performance of key kernels in genomics and ML. Recognizing that applications within these realms consist of diverse functions or kernels, it is imperative for a designer to possess a thorough understanding of them. Each function/kernel can be characterized by distinct data and control flows, calling for varied features to be enabled in either a von-Neumann or a CIM architecture. To enhance the efficacy of each function/kernel, we first profile them individually and then within a larger context of their corresponding pipeline, followed by discerning the best avenues for their memory mapping in a CIM architecture. We then undertake a concurrent assessment of essential adjunct components alongside the memory array, commonly referred to as the peripheries. For a designer, proficiency in the applications executable on a CIM system leveraging emerging memory technologies is indispensable. Grasping the fundamental characteristics of CIM and having an overarching view of its scope becomes vital prior to its integration. We aim to aggregate critical application features, improvement opportunities, and design decisions and refine them to their core essence. Through this, we aspire to shed light on present design options and identify kernels demanding heightened attention. Such insights can be instrumental in revealing prospective directions, encompassing supported kernels along with their respective merits and trade-offs.
We exploit emerging technologies and architect state-of-the-art CIM designs that optimally serve the targeted kernels, keeping a holistic improvement perspective at the forefront. Delving into emerging (memory) technologies, such as memristive devices like PCM and STT-MRAM, is crucial. These devices provide a suite of advantages, including non-volatility, compactness, and a natural aptitude for conducting logical operations (for instance, the logical AND). Additionally, other emerging technologies, such as integrated photonics, have the potential to enhance the CIM paradigm further with their capacity for high-frequency and low-latency functions. Our ambition is to integrate multiple such technologies, harnessing their distinct attributes, to craft a CIM design that surpasses the SotA counterparts across key benchmarks, be it in execution speed or energy.
This thesis demonstrates that when CIM is fused with emerging (memory) technologies, there is a marked enhancement in the performance of several Genomics pipelines and Machine Learning applications. It is our aspiration and conviction that the evaluations, methodologies, and findings detailed in this dissertation will empower the broader community to comprehend and address contemporary and upcoming challenges that revolve around enhancing the performance and energy efficiency of modern applications through the integration of (re)emerging computing paradigms and technologies. Additionally, our work provides insights for adapting these technologies to novel applications, ensuring they deliver optimal benefits.