Related papers: MemPool Flavors: Between Versatility and Specializ…
Over a past few decades, VM's or Virtual machines have sort of gained a lot of momentum, especially for large scale enterprises where the need for resource optimization & power save is humongous, without compromising with performance or…
As emerging deep neural network (DNN) models continue to grow in size, using large GPU clusters to train DNNs is becoming an essential requirement to achieving acceptable training times. In this paper, we consider the case where future…
The POOL project is the common persistency framework for the LHC experiments to store petabytes of experiment data and metadata in a distributed and grid enabled way. POOL is a hybrid event store consisting of a data streaming layer and a…
With phenomenal growth of high speed and complex computing applications, the design of low power and high speed logic circuits have created tremendous interest. Conventional computing devices are based on irreversible logic and further…
Based on the two observations that diverse applications perform better on different multicore architectures, and that different phases of an application may have vastly different resource requirements, Pal et al. proposed a novel…
Pipeline parallelism is widely used to scale the training of transformer-based large language models, various works have been done to improve its throughput and memory footprint. In this paper, we address a frequently overlooked issue: the…
IT based scientific research requires high computational resources. The limitation on funding and infrastructure led the high performance computing era from supercomputer to cluster and grid computing technology. Parallel application…
High-Performance Computing (HPC) processors are nowadays integrated Cyber-Physical Systems demanding complex and high-bandwidth closed-loop power and thermal control strategies. To efficiently satisfy real-time multi-input multi-output…
As RISC-V architectures proliferate across embedded and high-performance domains, developers face persistent challenges in performance optimization due to fragmented tooling, immature hardware features, and platform-specific defects. This…
The POOL project has been created to implement a common persistency framework for the LHC Computing Grid (LCG) application area. POOL is tasked to store experiment data and meta data in the multi Petabyte area in a distributed and grid…
Analysis of asset liability management (ALM) strategies especially for long term horizon is a crucial issue for banks, funds and insurance companies. Modern economic models, investment strategies and optimization criteria make ALM studies…
Performance modeling of parallel applications on multicore processors remains a challenge in computational co-design due to multicore processors' complex design. Multicores include complex private and shared memory hierarchies. We present a…
Cryptographic techniques have the potential to enable distrusting parties to collaborate in fundamentally new ways, but their practical implementation poses numerous challenges. An important class of such cryptographic techniques is known…
Developers face a wide choice of programming languages and libraries supporting multicore computing. Ever more diverse paradigms for expressing parallelism and synchronization become available while their influence on usability and…
Emerging agentic LLM workloads are driving rapidly growing demand on both memory capacity and bandwidth, with different phases of inference (e.g., prefill and decode) imposing distinct requirements. Industry is responding by composing…
Systems that require high-throughput and fault tolerance, such as key-value stores and databases, are looking to persistent memory to combine the performance of in-memory systems with the data-consistent fault-tolerance of nonvolatile…
Large language models (LLMs) training or inference across multiple nodes introduces significant pressure on GPU memory and interconnect bandwidth. The Compute Express Link (CXL) shared memory pool offers a scalable solution by enabling…
The ability to dynamically allocate memory is fundamental in modern programming languages. However, this feature is not adequately supported in current general-purpose PIM devices. To identify key design principles that PIM must consider,…
Flexible electronics offer unique advantages for conformable, lightweight, and disposable healthcare wearables. However, their limited gate count, large feature sizes, and high static power consumption make on-body machine learning…
As a current trend in Artificial Intelligence (AI), large foundation models are increasingly employed as the core of AI services. However, even after training, serving such models at scale remains a challenging task due to their heavy…