Related papers: Sprinkler: Maximizing Resource Utilization in Many…

Speculative Decoding (SD) is a recently proposed technique for faster inference using Large Language Models (LLMs). SD operates by using a smaller draft LLM for autoregressively generating a sequence of tokens and a larger target LLM for…

Optimizing the performance of stencil algorithms has been the subject of intense research over the last two decades. Since many stencil schemes have low arithmetic intensity, most optimizations focus on increasing the temporal data access…

Convolutional Neural Networks (CNNs) are widely employed to solve various problems, e.g., image classification. Due to their compute- and data-intensive nature, CNN accelerators have been developed as ASICs or on FPGAs. Increasing…

Datacenter applications demand both low latency and high throughput; while interactive applications (e.g., Web Search) demand low tail latency for their short messages due to their partition-aggregate software architecture, many…

We present two novel optimizations that accelerate clock-based spiking neural network (SNN) simulators. The first one targets spike timing dependent plasticity (STDP). It combines lazy- with event-driven plasticity and efficiently…

For a write request, today flash storage cannot distinguish the logical object it comes from. In such object-oblivious flash devices, concurrent writes from different objects are simply packed in their arrival order to flash memory blocks;…

We propose ZnG, a new GPU-SSD integrated architecture, which can maximize the memory capacity in a GPU and address performance penalties imposed by an SSD. Specifically, ZnG replaces all GPU internal DRAMs with an ultra-low-latency SSD to…

This paper introduces the first low-power hardware accelerator for Spiking Transformers, an emerging alternative to traditional artificial neural networks. By modifying the base Spikformer model to use IAND instead of residual addition, the…

NAND flash memory is ubiquitous in everyday life today because its capacity has continuously increased and cost has continuously decreased over decades. This positive growth is a result of two key trends: (1) effective process technology…

In recent years, SSDs have gained tremendous attention in computing and storage systems due to significant performance improvement over HDDs. The cost per capacity of SSDs, however, prevents them from entirely replacing HDDs in such…

This paper describes a new benchmark tool, Spatter, for assessing memory system architectures in the context of a specific category of indexed accesses known as gather and scatter. These types of operations are increasingly used to express…

ISP minimizes data transfer for analytics but faces challenges in adaptation and disaggregation. We propose DockerSSD, an ISP model leveraging OS-level virtualization and lightweight firmware to enable containerized data processing directly…

While blockchains initially gained popularity in the realm of cryptocurrencies, their widespread adoption is expanding beyond conventional applications, driven by the imperative need for enhanced data security. Despite providing a secure…

Hardware accelerators such as GPUs are required for real-time, low-latency inference with Deep Neural Networks (DNN). However, due to the inherent limits to the parallelism they can exploit, DNNs often under-utilize the capacity of today's…

Runtime variability in computing systems causes some tasks to straggle and take much longer than expected to complete. These straggler tasks are known to significantly slowdown distributed computation. Job execution with speculative…

Network programmability is an area of research both defined by its potential and its current limitations. While programmable hardware enables customization of device operation, tailoring processing to finely tuned objectives, limited…

As the landscape of deep neural networks evolves, heterogeneous dataflow accelerators, in the form of multi-core architectures or chiplet-based designs, promise more flexibility and higher inference performance through scalability. So far,…

Inference-time scaling has proven effective in boosting large language model (LLM) performance through increased test-time computation. Yet, its practical application is often hindered by reliance on external verifiers or a lack of…

While Transformers and other sequence-parallelizable neural network architectures seem like the current state of the art in sequence modeling, they specifically lack state-tracking capabilities. These are important for time-series tasks and…

Data processing systems offer an ever increasing degree of parallelism on the levels of cores, CPUs, and processing nodes. Query optimization must exploit high degrees of parallelism in order not to gradually become the bottleneck of query…