Related papers: Memory Centric Characterization and Analysis of SP…

We investigate and characterize the performance of an important class of operations on GPUs and Many Integrated Core (MIC) architectures. Our work is motivated by applications that analyze low-dimensional spatial datasets captured by high…

Multicore CPU architectures have been established as a structure for general-purpose systems for high-performance processing of applications. Recent multicore CPU has evolved as a system architecture based on non-uniform memory…

Scientific communities are increasingly adopting machine learning and deep learning models in their applications to accelerate scientific insights. High performance computing systems are pushing the frontiers of performance with a rich…

Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor Processing Unit (TPU)---deployed in datacenters since 2015 that…

Processing-in-memory (PIM) has emerged as a promising solution for accelerating memory-intensive workloads as they provide high memory bandwidth to the processing units. This approach has drawn attention not only from the academic community…

This work studies the behavior of state-of-the-art memory controller designs when executing scale-out workloads. It considers memory scheduling techniques, memory page management policies, the number of memory channels, and the address…

Phase-based statistical sampling methods such as SimPoints have proven to be effective at dramatically reducing the long time for architectural simulators to run large workloads such as SPEC CPU2017. However, generating and validating them…

High-end ARM processors are emerging in data centers and HPC systems, posing as a strong contender to x86 machines. Memory-centric profiling is an important approach for dissecting an application's bottlenecks on memory access and guiding…

Big data analytics applications play a significant role in data centers, and hence it has become increasingly important to understand their behaviors in order to further improve the performance of data center computer systems, in which…

High-Performance Computing (HPC) and Artificial Intelligence (AI) workloads typically demand substantial memory bandwidth and, to a degree, memory capacity. CXL memory expansion modules, also known as CXL "type-3" devices, enable…

Modern microarchitectures are some of the world's most complex man-made systems. As a consequence, it is increasingly difficult to predict, explain, let alone optimize the performance of software running on such microarchitectures. As a…

AI workloads, particularly those driven by deep learning, are introducing novel usage patterns to high-performance computing (HPC) systems that are not comprehensively captured by standard HPC benchmarks. As one of the largest academic…

This article features extended summaries and retrospectives of some of the recent research done by our research group, SAFARI, on (1) various critical problems in memory systems and (2) how memory system bottlenecks affect graphics…

Soft real-time applications such as multimedia applications often show bursty memory access patterns---regularly requiring a high memory bandwidth for a short duration of time. Such a period is often critical for timely data processing.…

General trends in computer architecture are shifting more towards parallelism. Multicore architectures have proven to be a major step in processor evolution. With the advancement in multicore architecture, researchers are focusing on…

Many modern and emerging applications must process increasingly large volumes of data. Unfortunately, prevalent computing paradigms are not designed to efficiently handle such large-scale data: the energy and performance costs to move this…

In a modern GPU architecture, all threads within a warp execute the same instruction in lockstep. For a memory instruction, this can lead to memory divergence: the memory requests for some threads are serviced early, while the remaining…

Graphics Processing Units (GPUs) have become an integral part of High-Performance Computing to achieve an Exascale performance. The main goal of application developers of GPU is to tune their code extensively to obtain optimal performance,…

Graph processing is typically considered to be a memory-bound rather than compute-bound problem. One common line of thought is that more available memory bandwidth corresponds to better graph processing performance. However, in this work we…

This paper presents a systematic review of mapping and scheduling strategies within the High-Performance Computing (HPC) compute continuum, with a particular emphasis on heterogeneous systems. It introduces a prototype workflow to establish…