A switch, switched architecture and process for transferring data through an FCAL switch is disclosed. The switch uses multiple switch control circuits each coupled to one FCAL network and all connected to a crossbar switch. The switch control circuits are coupled together by a protocol bus for coordination purposes. Local conversations can occur on each FCAL loop and crossing conversations through the switch can occur concurrently. The OPN primitive is used to establish the connection before any data is transferred thereby eliminating the need for buffer memory in the switch control circuits. The destination address of each OPN is used to address a lookup table in each switch control circuit to determine if the destination node is local. If not, the destination is looked up and a connection request made on the protocol bus. If the remote port is not busy, it sends a reply which causes both ports to establish a data path through the backplane crossbar switch.

Fibre channel arbitrated loop bufferless switch circuitry to increase bandwidth without significant increase in cost

A data processing apparatus including a multiplier unit forming a product from L bits of each two data buses of N bits each N is greater than L. The multiplier forms a N bit output having a first portion which is the L most significant bits of the of product and a second portion which is M other bits not including the L least significant bits of the product, where N is the sum of M and L. In the preferred embodiment the M other bits are derived from other bits of the two input data busses, such as the M other bits of the first input data bus. An arithmetic logic unit performs parallel operations (addition, subtraction, Boolean functions) controlled by the same instructions. This arithmetic logic unit is divisible into a selected number of sections for performing identical operations on independent sections of its inputs. The multiplier unit may form dual products from separate parts of the input data. A single instruction controlling both the multiplier unit and the arithmetic logic unit permits addition of dual products. The dual products are temporarily stored in a data register permitting the multiply and add operations to be pipelined. The dual products are formed in one data word and added by a rotate/mask and add operation in a three input arithmetic unit.

Long Instruction Word Controlling Plural Independent Processor Operations

Several modifications to the CORDIC method of computing angles and performing rotations are presented: (1) the use of redundant (carry-free) addition instead of a conventional (carry-propagate) one; (2) a representation of angles in a decomposed form to reduce area and communication bandwidth; (3) the use of on-line addition (left-to-right, digit-serial addition) to replace shifters by delays; and (4) the use of online multiplication, square root, and division to compute scaling factors and perform the scaling operations. The modifications improve the speed and the area of CORDIC implementations. The proposed scheme uses efficiently floating-point representations. The application of the modified CORDIC method to matrix triangularization by Givens' rotations and to the computation of the singular value decomposition (SVD) are discussed. >

Redundant and on-line CORDIC: application to matrix triangularization and SVD

This paper describes new methods for producing optimal binary signed-digit representations. This can be useful in the fast computation of exponentiations. Contrary to existing algorithms, the digits are scanned from left to right (i.e., from the most significant position to the least significant position). This may lead to better performances in both hardware and software.

Optimal left-to-right binary signed-digit recoding

Aspects of the invention may comprise receiving an incoming TCP packet at a TEEC (270) and processing at least a portion of the incoming packet once by the TEEC (270) without having to do any reassembly and/or retransmission by the TEEC (270). At least a portion of the incoming TCP packet may be buffered in at least one internal elastic buffer (280,290) of the TEEC (270). The internal elastic buffer (280,290) may comprise a receive internal elastic buffer (290) and/or a transmit internal elastic buffer (280). Accordingly, at least a portion of the incoming TCP packet may be buffered in the receive internal elastic buffer (290). At least a portion of the processed incoming packet may be placed in a portion of a host memory (230) for processing by a host processor or CPU (210). Furthermore, at least a portion of the processed incoming TCP packet may be DMA transferred to a portion of the host memory (230).

System and method for TCP offload

A high speed multiplier and divider for MOS LSI based on a new algorithm is presented. When we implement the multiplier and the divider in LSI, the features such as high speed operation, small number of transistors and easy layout are the most important factors. A computational algorithm using a redundant binary representation has several excellent features such as high speed addition operations. We improved the algorithm and the method of implementation, and designed an advanced multiplier and divider with the above mentioned features. We expect mat our multiplier and divider are excellent compared with multipliers using the Booth algorithm and the Wallace tree, and with divider using the SRT method, respectively.

Design of high speed MOS multiplier and divider using redundant binary representation

An arithmetic processor and an addition/subtraction circuit therefor are disclosed. The arithmetic processor comprises a plurality of the addition/subtraction units arranged in parallel, each unit being capable of carrying out addition (or subtraction) with respect to respective digits of two operands. An addition/subtraction unit comprises a first circuit and a second circuit coupled to receive binary signals each representing a respective digit of the operands. At least a first of the two binary signals is a 2-bit signal representing a signed digit expression, one bit of which ("the sign bit") represents the sign of one of the digits of the operands and the other bit of which ("the magnitude bit") represents the magnitude of that one digit of the operands. The first circuit provides a binary signal representing an intermediate carry (or borrow) and the second circuit provides a binary signal representing an intermediate sum (or difference) from the two binary signals representing the digits of the operands. The addition/subtraction unit further comprises a third circuit which is coupled to receive the intermediate sum (or difference) binary signal output from the second circuit and a binary signal representing an intermediate carry (or borrow) from a next-lower-order digit, and outputs a 2-bit binary signal representing an addend (or subtrahend). That 2-bit signal output by the third circuit represents a signed digit expression, one bit, i.e., the sign bit, represents the sign of the addend (or subtrahend) and the other bit, i.e., the magnitude bit, represents the magnitude of the addend (or subtrahend).

Arithmetic processor and multiplier using redundant signed digit arithmetic

A data processing device includes first and second blocks which have different processing times and which operate in synchronism with a clock signal. One of the first and second blocks is selected and enabled in accordance with an instruction representing which of the first and second blocks should be selected and enabled. A clock change signal is generated on the basis of the instruction. A period of the clock signal is changed in accordance with the clock change signal.

Method and apparatus for controlling a clock signal

High Speed MOS Multiplier and Divider Using Redundant Binary Representation and Their Implementation in a Microprocessor

This an arithmetic processor which represents internal arithmetic operands as signed-digit numbers, each digit of which may have either positive, zero, or negative values and which executes addition of a plurality of numbers each of whose most significant digit is offset with respect to the other numbers. The arithmetic processor includes an adder tree which is so constituted that a pair of said plurality of numbers are added to obtain a partial sum and further pairs of partial sums are successively added to obtain a final sum of all numbers. The arithmetic processor further comprises first means for adding a portion of the two numbers where both digits are present, second means for causing a lower order portion where only one of the numbers has a digit present to directly become part of the sum, third means for retaining or outputting a carry created by the first means, and fourth means for adding the carry created in each add stage of the adder tree to the later add stages of the adder tree to obtain the sum.

Takashi Taniguchi

Papers

Design of high speed MOS multiplier and divider using redundant binary representation

Arithmetic processor and multiplier using redundant signed digit arithmetic

Method and apparatus for controlling a clock signal

High Speed MOS Multiplier and Divider Using Redundant Binary Representation and Their Implementation in a Microprocessor

Arithmetic processor using signed-digit representation of external operands