A HyperTransport Network Interface Controller For Ultra-low Latency Message Transfers
نویسندگان
چکیده
This white paper presents the implementation of a high-performance HyperTransport-enabled Network Interface Controller (NIC), named Virtualized Engine for Low Overhead (VELO). The direct connect architecture and efficiency of HyperTransport produce an NIC capable of sub-microsecond latency. The prototype implemented on a Field Programmable Gate Array (FPGA) delivers a communication latency of 970 ns between two computing nodes. Such low latency almost closes the gap between remote memory access and local memory access in distributed computing systems.
منابع مشابه
A Hypertransport based low-latency reconfigurable testbed for message-passing developments
High-bandwidth, low-latency MPI implementations are of key importance for clustered, parallel computing machines. The performance of message-passing is based on the underlying network hardware, the network-interface architecture as well as the software design of the message-passing library and ultimately the parallel applications itself. This paper analyzes the application of the HTX-Board, a H...
متن کاملA New Ultra-low Latency Message Transfer Mechanism
Cluster computing is still the most cost-effective solution to meet the increasing demand for computing power. Clusters are typically based on commodity computing hardware with specialized interconnection networks (IN). These cluster interconnects differ from commodity networks by higher bandwidth, lower latency, lower CPU utilization and improved scalability. But even with these sophisticated ...
متن کاملUltra-high performance communication with MPI and the Sun fireTM link interconnect
We present a new low-latency system area network that provides the ultra-high bandwidth needed to fuse a collection of large SMP servers into a capability cluster. The network adapter exports a remote shared memory (RSM) model that supports low latency kernel bypass messaging. The SunTM MPI library uses the RSM interface to implement a highly efficient memory-to-memory messaging protocol in whi...
متن کاملOptimal Polling for Latency-Throughput Tradeoffs in Queue-Based Network Interfaces for Clusters
We consider a networking subsystem for message–passing clusters that uses two unidirectional queues for data transfers between the network interface card (NIC) and the lower protocol layers, with polling as the primary mechanism for reading data off these queues. We suggest that for accurate mathematical analysis of such an organization, the values of the system’s states probabilities have to b...
متن کاملA comparative study of some network subsystem organizations
The impact of alternative network subsystem design for realizing low end–to–end latencies and high network throughput in a switched LAN are studied in detail through simulation. These alternatives include choices in the disposition of the network interface card (NIC), DMA priorities and OS services. Our simulation model captures the delays of OS services/software layers, message copying DMAs an...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008