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 …

In recent years, there has been increasing adoption of FPGAs in datacenters as hardware
accelerators, where a large population of end users are software developers. While high …

The continued growth in the processing power of FPGAs coupled with high bandwidth
memories (HBM), makes systems like the **linx U280 credible platforms for linear solvers …

The identification and quantification of proteins through mass spectrometry (MS) are
foundational to proteomics, offering insights into biological systems and disease states …

Recent works established new High-Level Synthesis (HLS) solutions translating AI models
described in PyTorch to customized AI accelerators automatically. By adopting PyTorch as …

Over the past decade, much progress has been made to advance the acceleration of sparse
linear operators such as SpMM and SpMV on FPGAs. Nevertheless, few works have …

Transformer-based large language models (LLM) have been widely used in language
processing applications. However, most of them restrict the context window that permits the …

The multiplication of a sparse matrix with a dense vector is a vital operation in linear algebra,
with applications in numerous contexts. After earlier research on FPGA acceleration of this …

With the deployment of FPGAs in a data center, there is the opportunity to build large multi-
FPGA applications. In this paper, we design a partitioner to address the problem of efficiently …

Dataflow high-level synthesis (HLS) tools automatically map a high-level software program
to a dataflow hardware design. When testing the design, the HLS tool takes a testing …