Related papers: PUSHtap: PIM-based In-Memory HTAP with Unified Dat…

Artificial intelligence (AI) application domains consist of a mix of tensor operations with high and low arithmetic intensities (aka reuse). Hierarchical (i.e. compute along multiple levels of memory hierarchy) and heterogeneous (multiple…

Large-scale HPC simulations of plasma dynamics in fusion devices require efficient parallel I/O to avoid slowing down the simulation and to enable the post-processing of critical information. Such complex simulations lacking parallel I/O…

In this paper, we propose TAPA, an end-to-end framework that compiles a C++ task-parallel dataflow program into a high-frequency FPGA accelerator. Compared to existing solutions, TAPA has two major advantages. First, TAPA provides a set of…

Data movement between memory and processors is a major bottleneck in modern computing systems. The processing-in-memory (PIM) paradigm aims to alleviate this bottleneck by performing computation inside memory chips. Real PIM hardware (e.g.,…

Efficient simulation of complex plasma dynamics is crucial for advancing fusion energy research. Particle-in-Cell (PIC) Monte Carlo (MC) simulations provide insights into plasma behavior, including turbulence and confinement, which are…

High Bandwidth Memory with Processing-in-Memory (HBM-PIM) offers an opportunity to reduce data movement by executing computation directly inside memory, but current commercial platforms expose limited instruction sets and require…

Processing-in-memory (PIM) reduces data movement by executing near memory, but our large-scale characterization on real PIM hardware shows that end-to-end performance is often limited by disjoint host and device address spaces that force…

Hybrid main memory systems combine both performance and capacity advantages from heterogeneous memory technologies. With larger capacities, higher associativities, and finer granularities, hybrid memory systems currently exhibit significant…

The advent of Transformers has revolutionized computer vision, offering a powerful alternative to convolutional neural networks (CNNs), especially with the local attention mechanism that excels at capturing local structures within the input…

This article presents the parallel implementation of the coupled harmonic oscillator. From the analytical solution of the coupled harmonic oscillator, the design parameters are obtained. After that, a numerical integration of the system…

Hash table is a fundamental data structure for quick search and retrieval of data. It is a key component in complex graph analytics and AI/ML applications. State-of-the-art parallel hash table implementations either make some simplifying…

Task and motion planning (TAMP) for multi-robot systems, which integrates discrete task planning with continuous motion planning, remains a challenging problem in robotics. Existing TAMP approaches often struggle to scale effectively for…

Pipeline parallelism (PP) has become a standard technique for scaling large language model (LLM) training across multiple devices. However, despite recent progress in reducing memory consumption through activation offloading, existing…

Modern hardware is abundantly parallel and increasingly heterogeneous. The numerous processing cores have non-uniform access latencies to the main memory and to the processor caches, which causes variability in the communication costs.…

The expansion of long-context Large Language Models (LLMs) creates significant memory system challenges. While Processing-in-Memory (PIM) is a promising accelerator, we identify that it suffers from critical inefficiencies when scaled to…

Query workloads and database schemas in OLAP applications are becoming increasingly complex. Moreover, the queries and the schemas have to continually \textit{evolve} to address business requirements. During such repetitive transitions, the…

Hive is the most mature and prevalent data warehouse tool providing SQL-like interface in the Hadoop ecosystem. It is successfully used in many Internet companies and shows its value for big data processing in traditional industries.…

Extreme-scale computing involves hundreds of millions of threads with multi-level parallelism running on large-scale hierarchical and heterogeneous hardware. In POSIX threads and OpenMP applications, some key behaviors occurring in runtime…

Processing-in-memory (PIM) promises to alleviate the data movement bottleneck in modern computing systems. However, current real-world PIM systems have the inherent disadvantage that their hardware is more constrained than in conventional…

Processing-using-memory (PuM) techniques leverage the analog operation of memory cells to perform computation. Several recent works have demonstrated PuM techniques in off-the-shelf DRAM devices. Since DRAM is the dominant memory technology…