Related papers: Parallel Data Object Creation: Towards Scalable Me…
High Energy Physics (HEP) experiments, for example at the Large Hadron Collider (LHC) at CERN, store data at exabyte scale in sets of files. They use a binary columnar data format by the ROOT framework, that also transparently compresses…
To reduce training time of large-scale DNNs, scientists have started to explore parallelization strategies like data-parallelism, model-parallelism, and hybrid-parallelism. While data-parallelism has been extensively studied and developed,…
Object-oriented programming has long been regarded as too inefficient for SIMD high-performance computing, despite the fact that many important HPC applications have an inherent object structure. On SIMD accelerators, including GPUs, this…
Shared memory multiprocessors come back to popularity thanks to rapid spreading of commodity multi-core architectures. As ever, shared memory programs are fairly easy to write and quite hard to optimise; providing multi-core programmers…
We present algorithmic improvements to the loading operations of certain reduced data ensembles produced from neutron scattering experiments at Oak Ridge National Laboratory (ORNL) facilities. Ensembles from multiple measurements are…
The I/O access patterns of many parallel applications consist of accesses to a large number of small, noncontiguous pieces of data. If an application's I/O needs are met by making many small, distinct I/O requests, however, the I/O…
The Data Science domain has expanded monumentally in both research and industry communities during the past decade, predominantly owing to the Big Data revolution. Artificial Intelligence (AI) and Machine Learning (ML) are bringing more…
Parallel applications can spend a significant amount of time performing I/O on large-scale supercomputers. Fast near-compute storage accelerators called burst buffers can reduce the time a processor spends performing I/O and mitigate I/O…
Machine learning training pipelines consume data in batches. A single training step may require thousands of samples drawn from shards distributed across a storage cluster. Issuing thousands of individual GET requests incurs per-request…
This paper describes PlinyCompute, a system for development of high-performance, data-intensive, distributed computing tools and libraries. In the large, PlinyCompute presents the programmer with a very high-level, declarative interface,…
The evolution of the Internet and computer applications have generated colossal amount of data. They are referred to as Big Data and they consist of huge volume, high velocity, and variable datasets that need to be managed at the right…
Convolutional Neural Networks (CNNs) combine large amounts of parallelizable computation with frequent memory access. Field Programmable Gate Arrays (FPGAs) can achieve low latency and high throughput CNN inference by implementing dataflow…
Dataflow architectures are growing in popularity due to their potential to mitigate the challenges posed by the memory wall inherent to the Von Neumann architecture. At the same time, high-level synthesis (HLS) has demonstrated its efficacy…
L1 instruction (L1-I) cache misses are a source of performance bottleneck. Sequential prefetchers are simple solutions to mitigate this problem; however, prior work has shown that these prefetchers leave considerable potentials uncovered.…
The fast development of Internet-of-Things (IoT) devices and applications has led to vast data collection, potentially containing irrelevant, noisy, or redundant features that degrade learning model performance. These collected data can be…
Scalable and secure data management is important in Internet of Things (IoT) applications such as smart water meters, where traditional blockchain storage can be restrictive due to high data volumes. This paper investigates a hybrid…
The rapid adoption of large language models (LLMs) has shifted a substantial portion of inference workloads into throughput-oriented offline regimes, where fully utilizing GPU compute requires large batch sizes. However, existing…
The introduction of Intel(R) Xeon Phi(TM) coprocessors opened up new possibilities in development of highly parallel applications. The familiarity and flexibility of the architecture together with compiler support integrated into the Intel…
Filters approximately store a set of items while trading off accuracy for space-efficiency and can address the limited memory on accelerators, such as GPUs. However, there is a lack of high-performance and feature-rich GPU filters as most…
While detailed resource usage monitoring is possible on the low-level using proper tools, associating such usage with higher-level abstractions in the application layer that actually cause the resource usage in the first place presents a…