Deep Learning Recommendation Models (DLRMs) are important applications in various
domains and have evolved into one of the largest and most important machine learning …

Communication switches have sometimes been augmented to process collectives, eg, in the
IBM BlueGene and Mellanox SHArP switches. In this work, we find that there is a great …

While FPGA is a suitable platform for implementing cryptographic algorithms, there are
several challenges associated with implementing Optimal Ate pairing on FPGA, such as …

In this paper, we investigate the benefits of hardware-aware quantization in the gFADES
hardware accelerator targeting Graph Convolutional Networks (GCNs). GCNs are a type of …

Offload of MPI collectives to network devices, eg, NICs and switches, is being implemented
as an effective mechanism to improve application performance by reducing inter-and intra …

Network performance has contributed fundamentally to the growth of supercomputing over
the past decades. In parallel, High Performance Computing (HPC) peak performance has …

For the last three decades a core use of FPGAs has been for processing communication:
FPGA-based SmartNICs are in widespread use from the datacenter to IoT. Augmenting …

Communication capabilities of FPGAs, combined with programmability in hardware
(reconfigurable logic) and software (soft-processors), often provide FPGAs a competitive …

Abstract Field Programmable Gate Arrays (FPGAs) can fulfill many critical and contrasting
roles in modern computing due to their combination of powerful computing and …

A long-standing goal, which is increasingly important in the post-Moore era, is to augment
system performance by building more intelligent compilers. One of our motivating …