Related papers: apenext: A Multi-Tflops LQCD Computing Project
The rapid growth of Machine Learning (ML) has increased demand for DNN hardware accelerators, but their embodied carbon footprint poses significant environmental challenges. This paper leverages approximate computing to design sustainable…
The CP-PACS project is a five year plan, which formally started in April 1992 and has been completed in March 1997, to develop a massively parallel computer for carrying out research in computational physics with primary emphasis on lattice…
We present results for the performance of QCD code on ALiCE, the Alpha-Linux Cluster Engine at Wuppertal. We describe the techniques employed to optimise the code, including the metaprogramming of assembler kernels, the effects of data…
The march toward developing relevant and robust CPU benchmarks continues with the introduction of SPEC CPU 2026, the next generation suite for measuring processor performance. This paper details the methodology behind its creation,…
We describe the construction of a high performance parallel computer composed of PC components, present some physical results for light hadron and hybrid meson masses from lattice QCD. We also show that the smearing technique is very useful…
Deploying large language models (LLMs) on edge devices is crucial for delivering fast responses and ensuring data privacy. However, the limited storage, weight, and power of edge devices make it difficult to deploy LLM-powered applications.…
The scan-based testing has been widely used as a Design-for-Test (DfT) mechanism for most recent designs. It has gained importance not only in manufacturing testing but also in online testing and debugging. However, the multiplexer-based…
Multivariate long-term time series forecasting (LTSF) supports critical applications such as traffic-flow management, solar-power scheduling, and electricity-transformer monitoring. The existing LTSF paradigms follow a three-stage pipeline…
We motivate the design and implementation of a platform-neutral compute intermediate language (PENCIL) for productive and performance-portable accelerator programming.
Real-time Deep Neural Network (DNN) inference with low-latency requirement has become increasingly important for numerous applications in both cloud computing (e.g., Apple's Siri) and edge computing (e.g., Google/Waymo's driverless car).…
High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…
Large Language Models (LLMs) impose massive computational demands, driving the need for scalable multi-chiplet accelerators. However, existing mapping space exploration efforts for such accelerators primarily focus on traditional…
A CW-compatible, pulsed H- superconducting linac is envisaged as a possible path for upgrading Fermilab's injection complex. To validate the concept of the front- end of such a machine, a test accelerator (a.k.a. PXIE) is under…
General aviation fault diagnosis and efficient maintenance are critical to flight safety; however, deploying deep learning models on resource-constrained edge devices poses dual challenges in computational capacity and interpretability.…
Flow Matching models achieve state-of-the-art image generation quality but incur substantial inference cost due to iterative denoising through large Transformer networks. We observe that different layer groups within a Transformer exhibit…
Novel use cases and verticals such as connected cars and human-robot cooperation in the areas of 5G and Tactile Internet can significantly benefit from the flexibility and reduced latency provided by Network Function Virtualization (NFV)…
Matrix Distributed Processing is a collection of classes and functions written in C++ for fast development of efficient parallel algorithms for the most general lattice/grid application. FermiQCD is an Object Oriented Lattice QCD…
One of the outstanding challenges in contemporary science and technology is building a quantum computer that is useful in applications. By starting from an estimate of the algorithm success rate, we can explicitly connect gate fidelity to…
As users and developers, we are witnessing the opening of a new computing scenario: the introduction of hybrid processors into a single die, such as an accelerated processing unit (APU) processor, and the plug-and-play of additional…
Current PC processors are equipped with vector processing units and have other advanced features that can be used to accelerate lattice QCD programs. Clusters of PCs with a high-bandwidth network thus become powerful and cost-effective…