Related papers: Inherent Limitations of Hybrid Transactional Memor…
Memory performance is often the main bottleneck in modern computing systems. In recent years, researchers have attempted to scale the memory wall by leveraging new technology such as CXL, HBM, and in- and near-memory processing. Developers…
We present a general methodology for establishing the impossibility of implementing certain concurrent objects on different (weak) memory models. The key idea behind our approach lies in characterizing memory models by their mergeability…
Memory trace analysis is an important technology for architecture research, system software (i.e., OS, compiler) optimization, and application performance improvements. Hardware-snooping is an effective and efficient approach to monitor and…
Software Transactional memory (STM) is an emerging abstraction for concurrent programming alternative to lock-based synchronizations. Most STM models admit only isolated transactions, which are not adequate in multithreaded programming…
Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to inefficient memory management. Existing approaches face a fundamental trade-off between efficiency…
Transactional Memory (TM) is an approach to concurrency control that aims to make writing parallel programs both effective and simple. The approach is started in non-distributed multiprocessor systems, but is gaining popularity in…
Software transactional memory (STM) allows programmers to easily implement concurrent data structures. STMs simplify atomicity. Recent STMs can achieve good performance for some workloads but they have some limitations. In particular, STMs…
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…
Homomorphic encryption (HE) enables computation over encrypted data, offering strong privacy guarantees for untrusted computing environments. Practical adoption remains limited by high computational complexity, large ciphertext sizes, and…
A wide range of evidence points toward the existence of a common algorithm underlying the processing of information throughout the cerebral cortex. Several hypothesized features of this cortical algorithm are reviewed, including sparse…
High-Bandwidth Memory (HBM) delivers exceptional bandwidth and energy efficiency for AI workloads, but its high cost per bit, driven in part by stringent on-die reliability requirements, poses a growing barrier to scalable deployment. This…
The rapid advancement of Large Language Models (LLMs) necessitates a deep understanding of their fundamental performance limits. This paper investigates the limits of LLM inference, focusing on hardware-imposed bottlenecks in…
Memory tiering provides a cost-effective solution to increase memory capacity, utilization, and even bandwidth. Memory tiering relies on system software for memory profiling, detection of frequently accessed pages, and page migration. Such…
A large language model (LLM) is one of the most important emerging machine learning applications nowadays. However, due to its huge model size and runtime increase of the memory footprint, LLM inferences suffer from the lack of memory…
AI clusters today are one of the major uses of High Bandwidth Memory (HBM). However, HBM is suboptimal for AI workloads for several reasons. Analysis shows HBM is overprovisioned on write performance, but underprovisioned on density and…
Despite the recent improvements in supporting Persistent Hardware Transactions (PHTs) on emerging persistent memories (PM), the poor performance of Read-Only (RO) transactions remains largely overlooked. We propose DUMBO, a new design for…
Hybrid manufacturing (HM) technologies combine additive and subtractive manufacturing (AM/SM) capabilities in multi-modal process plans that leverage the strengths of each. Despite the growing interest in HM technologies, software tools for…
Modern blockchains increasingly rely on parallel execution to improve throughput. We show several industry and academic transaction fee mechanisms (TFMs) struggle to simultaneously account for execution parallelism while remaining…
Processing-in-Memory (PIM) architectures offer promising solutions for efficiently handling AI applications in energy-constrained edge environments. While traditional PIM designs enhance performance and energy efficiency by reducing data…
Byte-addressable persistent memory, such as Intel/Micron 3D XPoint, is an emerging technology that bridges the gap between volatile memory and persistent storage. Data in persistent memory survives crashes and restarts; however, it is…