Related papers: CXL-Interference: Analysis and Characterization in…

Information retrieval in Large Language Models (LLMs) is increasingly recognized as intertwined with generation capabilities rather than mere lookup. While longer contexts are often assumed to improve retrieval, the effects of intra-context…

In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing…

Notwithstanding the significant traction gained by ultra-reliable and low-latency communication (URLLC) in both academia and 3GPP standardization, fundamentals of URLLC remain elusive. Meanwhile, new immersive and high-stake control…

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

In our work we analyze computational aspects of the problem of numerical integration in finite element calculations and consider an OpenCL implementation of related algorithms for processors with wide vector registers. As a platform for…

In the rapidly evolving domain of high-performance computing (HPC), heterogeneous architectures such as the SX-Aurora TSUBASA (SX-AT) system architecture, which integrate diverse processor types, present both opportunities and challenges…

We present the Cuckoo Trie, a fast, memory-efficient ordered index structure. The Cuckoo Trie is designed to have memory-level parallelism -- which a modern out-of-order processor can exploit to execute DRAM accesses in parallel -- without…

In-memory computing is a promising alternative to traditional computer designs, as it helps overcome performance limits caused by the separation of memory and processing units. However, many current approaches struggle with unreliable…

We propose using reinforcement learning to address the challenges of discovering microarchitectural vulnerabilities, such as Spectre and Meltdown, which exploit subtle interactions in modern processors. Traditional methods like random…

There are many approaches is use today to either prevent or minimize the impact of inter-query interactions on a shared cluster. Despite these measures, performance issues due to concurrent executions of mixed workloads still prevail…

As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware…

This paper summarizes the ideas and key concepts in MISE (Memory Interference-induced Slowdown Estimation), which was published in HPCA 2013 [97], and examines the work's significance and future potential. Applications running concurrently…

It is known that data rates in standard cellular networks are limited due to inter-cell interference. An effective solution of this problem is to use the multi-cell cooperation idea. In Cloud Radio Access Network (C-RAN), which is a…

Concurrent computation and communication (C3) is a pervasive paradigm in ML and other domains, making its performance optimization crucial. In this paper, we carefully characterize C3 in ML on GPUs, which are most widely deployed for ML…

Memory latencies and bandwidth are major factors, limiting system performance and scalability. Modern CPUs aim at hiding latencies by employing large caches, out-of-order execution, or complex hardware prefetchers. However, software-based…

This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's ability to adapt to later tasks. Using synthetic regression tasks over linear and…

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of…

Aligning future system design with the ever-increasing compute needs of large language models (LLMs) is undoubtedly an important problem in today's world. Here, we propose a general performance modeling methodology and workload analysis of…

Federated Learning (FL) has become a viable technique for realizing privacy-enhancing distributed deep learning on the network edge. Heterogeneous hardware, unreliable client devices, and energy constraints often characterize edge computing…

Tiny machine learning (TinyML) aims to run ML models on small devices and is increasingly favored for its enhanced privacy, reduced latency, and low cost. Recently, the advent of tiny AI accelerators has revolutionized the TinyML field by…