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

We provide our perspective on X-Learning (XL), a novel distributed learning architecture that generalizes and extends the concept of decentralization. Our goal is to present a vision for XL, introducing its unexplored design considerations…

With the rapid increase in software exploits, the last few decades have seen several hardware-level features to enhance security (e.g., Intel MPX, ARM TrustZone, Intel SGX, Intel CET). Due to security, performance and/or usability issues…

Existing continual learning (CL) research regards catastrophic forgetting (CF) as almost the only challenge. This paper argues for another challenge in class-incremental learning (CIL), which we call cross-task class discrimination…

The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…

2.5D integration is an important technique to tackle the growing cost of manufacturing chips in advanced technology nodes. This poses the challenge of providing high-performance inter-chiplet interconnects (ICIs). As the number of chiplets…

Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when…

Cyber-physical systems (CPS) integrate sensing, computing, communication and actuation capabilities to monitor and control operations in the physical environment. A key requirement of such systems is the need to provide predictable…

Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and…

The widening gap between processor speed and storage latency has made data movement a dominant bottleneck in modern systems. Two lines of storage-layer innovation attempted to close this gap: persistent memory shortened the latency…

Next-generation supercomputers will feature more hierarchical and heterogeneous memory systems with different memory technologies working side-by-side. A critical question is whether at large scale existing HPC applications and emerging…

The design of distributed mechanisms for interference management is one of the key challenges in emerging wireless small cell networks whose backhaul is capacity limited and heterogeneous (wired, wireless and a mix thereof). In this paper,…

Many applications of computer vision require the ability to adapt to novel data distributions after deployment. Adaptation requires algorithms capable of continual learning (CL). Continual learners must be plastic to adapt to novel tasks…

This paper explores the performance envelope of "traditional" inverted indexing on modern hardware using the implementation in the open-source Lucene search library. We benchmark indexing throughput on a single high-end multi-core commodity…

We study the problem of controlling the interference created to an external observer by a communication processes. We model the interference in terms of its type (empirical distribution), and we analyze the consequences of placing…

One of the fundamental elements impacting the performance of a wireless system is interference, which has been a long-term issue in wireless networks. In the case of cognitive radio (CR) networks, the problem of interference is tremendously…

WCET (Worst-Case Execution Time) estimation on multicore architecture is particularly challenging mainly due to the complex accesses over cache shared by multiple cores. Existing analysis identifies possible contentions between parallel…

In-context Learning (ICL) is an emerging few-shot learning paradigm on Language Models (LMs) with inner mechanisms un-explored. There are already existing works describing the inner processing of ICL, while they struggle to capture all the…

Modern computer architectures share physical resources between different programs in order to increase area-, energy-, and cost-efficiency. Unfortunately, sharing often gives rise to side channels that can be exploited for extracting or…

Supported by their high power efficiency and recent advancements in High Level Synthesis (HLS), FPGAs are quickly finding their way into HPC and cloud systems. Large amounts of work have been done so far on loop and area optimizations for…

As multicore computing is now standard, it seems irresponsible for constraints researchers to ignore the implications of it. Researchers need to address a number of issues to exploit parallelism, such as: investigating which constraint…