Efficient implementation of the OSI transport protocol checksum algorithm using 8/16-bit arithmetic
ACM SIGCOMM Computer Communication Review
ACM SIGCOMM Computer Communication Review
Computing the internet checksum
ACM SIGCOMM Computer Communication Review
ACM SIGCOMM Computer Communication Review
The Analysis of Diskless Workstation Traffic on an Ethernet
The Analysis of Diskless Workstation Traffic on an Ethernet
Practical trade-offs for open interconnection
CSC '92 Proceedings of the 1992 ACM annual conference on Communications
Performance of checksums and CRCs over real data
SIGCOMM '95 Proceedings of the conference on Applications, technologies, architectures, and protocols for computer communication
Fast software implementation of error detection codes
IEEE/ACM Transactions on Networking (TON)
Performance of checksums and CRC's over real data
IEEE/ACM Transactions on Networking (TON)
Hi-index | 0.00 |
It is known that using larger byte--sizes to access memory usually results in faster computations of checksum algorithms. This paper proposes two different ways to use larger byte--sizes to improve the performance of the OSI checksum. First, an algorithm is presented that computes the 8--bit checksum using 16-bit integers. It is shown that this algorithm yields a 5 to 20 percent performance improvement on many architectures. Second, the benefits of expanding the basic computation unit of the OSI checksum algorithm to 16--bits integers is considered. This change can yield an additional performance improvement of up to 50% and greatly extended error detection properties, although it is incompatible with the current standard. The measurements of these algorithms are compared with some taken of checksums in common use, such as IP and XNS†.