Topic
TCP offload engine
About: TCP offload engine is a research topic. Over the lifetime, 440 publications have been published within this topic receiving 8496 citations.
Papers published on a yearly basis
Papers
Book•
1 Jan 1995
TL;DR: This volume is the only one to cover the de facto standard implementation from the 4.4BSD-Lite release, the foundation for TCP/IP implementations run daily on hundreds of thousands of systems worldwide.
Abstract: TCP/IP Illustrated, Volume 2 contains a thorough explanation of how TCP/IP protocols are implemented. There isn't a more practical or up-to-date bookothis volume is the only one to cover the de facto standard implementation from the 4.4BSD-Lite release, the foundation for TCP/IP implementations run daily on hundreds of thousands of systems worldwide.Combining 500 illustrations with 15,000 lines of real, working code, TCP/IP Illustrated, Volume 2 uses a teach-by-example approach to help you master TCP/IP implementation. You will learn about such topics as the relationship between the sockets API and the protocol suite, and the differences between a host implementation and a router. In addition, the book covers the newest features of the 4.4BSD-Lite release, including multicasting, long fat pipe support, window scale, timestamp options, and protection against wrapped sequence numbers, and many other topics.Comprehensive in scope, based on a working standard, and thoroughly illustrated, this book is an indispensable resource for anyone working with TCP/IP.
424 citations
TL;DR: A TCP processor for Gigabit Ethernet with a circuit size suitable for implementing on a single Field Programmable Gate Array allows adoption of TCP/Ethernet in small devices that have hardware size limitations.
Abstract: Transmission control protocol (TCP) and Ethernet have been widely used in readout systems. These protocols are de facto standards and have been implemented on standard operating systems. However, some small devices, e.g., front-end devices and detectors, are not capable of employing these protocols because of hardware size limitations. This paper describes a TCP processor for gigabit Ethernet with a circuit size suitable for implementing on a single field programmable gate array. The only peripheral device required is a single Ethernet physical layer device. The hardware was implemented and its TCP throughput was measured. The throughputs in both directions simultaneously were at the upper limits of gigabit Ethernet. A mechanism for slow control over user datagram protocol (UDP) is also provided. The processor described here allows adoption of TCP/Ethernet in small devices that have hardware size limitations.
256 citations
Proceedings Article•
18 May 2003TL;DR: In the context of the replacement of storage-specific interconnect via commoditized network hardware, TCP offload (and more generally, offloading the transport protocol) appropriately solves an important problem.
Abstract: Network interface implementors have repeatedly attempted to offload TCP processing from the host CPU These efforts met with little success, because they were based on faulty premises TCP offload per se is neither of much overall benefit nor free from significant costs and risks But TCP offload in the service of very specific goals might actually be useful In the context of the replacement of storage-specific interconnect via commoditized network hardware, TCP offload (and more generally, offloading the transport protocol) appropriately solves an important problem
252 citations
4 Feb 2004
TL;DR: This paper discusses three different ways to connect sensor networks with TCP/IP networks: proxy architectures, DTN overlays, and tcp/IP for sensor networks, and concludes that the methods are in some senses orthogonal and that combinations are possible, but that TCP/ IP for Sensor networks currently has a number of issues that require further research.
Abstract: Wireless sensor networks are based on the collaborative efforts of many small wireless sensor nodes, which collectively are able to form networks through which sensor information can be gathered. Such networks usually cannot operate in complete isolation, but must be connected to an external network through which monitoring and controlling entities can reach the sensornet. As TCP/IP, the Internet protocol suite, has become the de-facto standard for large-scale networking, it is interesting to be able to connect sensornets to TCP/IP networks. In this paper, we discuss three different ways to connect sensor networks with TCP/IP networks: proxy architectures, DTN overlays, and TCP/IP for sensor networks. We conclude that the methods are in some senses orthogonal and that combinations are possible, but that TCP/IP for sensor networks currently has a number of issues that require further research before TCP/IP can be a viable protocol family for sensor networking.
199 citations
Patent•
3 Dec 2004
TL;DR: A TCP Offload Engine (TOE) as mentioned in this paper is a state machine that performs TCP/IP protocol processing operations in parallel without performing sequential processor instructions or sequential memory accesses.
Abstract: A TCP Offload Engine (TOE) device includes a state machine that performs TCP/IP protocol processing operations in parallel. In a first aspect, the state machine includes a first memory, a second memory, and combinatorial logic. The first memory stores and simultaneously outputs multiple TCP state variables. The second memory stores and simultaneously outputs multiple header values. In contrast to a sequential processor technique, the combinatorial logic generates a flush detect signal from the TCP state variables and header values without performing sequential processor instructions or sequential memory accesses. In a second aspect, a TOE includes a state machine that performs an update of multiple TCP state variables in a TCB buffer all simultaneously, thereby avoiding multiple sequential writes to the TCB buffer memory. In a third aspect, a TOE involves a state machine that sets up a DMA move in a single state machine clock cycle.
188 citations
Related Topics (5)
Performance Metrics
| Year | Papers |
|---|---|
| 2020 | 4 |
| 2019 | 5 |
| 2018 | 3 |
| 2017 | 3 |
| 2016 | 12 |
| 2015 | 14 |