NetDAM: Network Direct Attached Memory with Programmable In-Memory Computing ISA

10/28/2021
by   Kevin Fang, et al.
0

Data-intensive applications like distributed AI-training may require multi-terabytes memory capacity with multi-terabits bandwidth. We directly attach the memory to the ethernet controller with some programable logic to design an efficient hardware "template" for Memory pooling and in-memory / in-network computing. We built an FPGA prototype of the NetDAM, andwe demonstrate MPI-Allreduce communication case, the NetDAM can be used as a software and hardware friendly programmable architeture with high performance alternative for RDMA.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/21/2021

Programmable FPGA-based Memory Controller

Even with generational improvements in DRAM technology, memory access la...
research
04/19/2022

HMT: A Hardware-Centric Hybrid Bonsai Merkle Tree Algorithm for High-Performance Authentication

Bonsai Merkle tree (BMT) is a widely used data structure for authenticat...
research
12/08/2017

Nintendo Super Smash Bros. Melee: An "Untouchable" Agent

Nintendo's Super Smash Bros. Melee fighting game can be emulated on mode...
research
10/11/2021

Zero-CPU Collection with Direct Telemetry Access

Programmable switches are driving a massive increase in fine-grained mea...
research
10/18/2020

Optimizing Memory Performance of Xilinx FPGAs under Vitis

Plenty of research efforts have been devoted to FPGA-based acceleration,...
research
04/22/2022

FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems

Rapid advances in artificial intelligence (AI) technology have led to si...
research
05/21/2021

Conduit: A C++ Library for Best-effort High Performance Computing

Developing software to effectively take advantage of growth in parallel ...

Please sign up or login with your details

Forgot password? Click here to reset