Ati International Srl

Ati Technologies Ulc

Other

Fujitsu Corporation

Seagate Technology Incorporated

Lsi Corporation

Ati International Srl, Beaumont House

Nital P Patwa

Stephen C Purcell

Parin Bhadrik Dalal

Korbin S Van Dyke

Chad Edward Fogg

Steve C Hale

Timothy Lawrence Canepa

Stephen C Hale

Changyou Xu

Yang Liu

Niteen Aravind Patkar

Sanjay Mansingh

James Vinh

Chien Chen

Korbin Van Dyke

Dee Tovey

Yimin Chen

A storage controller of a data storage system maintains, for each interrupt vector, (1) a pending status that indicates whether one or more completions are pending in the completion queue (CQ) associated with the interrupt vector, and (2) an in-progress status that indicates whether or not the storage controller is currently in the process of composing an interrupt. The storage controller utilizes these two statuses to reduce or eliminate spurious interrupts by preventing an interrupt from being composed if there are no completions in the CQ, by preventing an interrupt from being composed if the corresponding interrupt mask has been set before composition of the interrupt begins, and by preventing an interrupt from being sent to the host system in cases where the interrupt mask was set after composition of the interrupt began, but before the interrupt has been sent to the host system.

Methods and systems for reducing spurious interrupts in a data storage system

An apparatus includes at least one general purpose register and at least one special purpose register and an execution unit that executes at least two instructions in parallel, to decode variable length codes, wherein each of the instructions share use of the at least one general purpose register and the at least one special purpose register. In one example, a processor stores variable length code information among a plurality of general purpose registers and generates decoded variable length code information by decoding the at least one variable length code. The processor also stores the decoded variable length code information among the plurality of general purpose registers.

Variable-length code decoder

A method for processing a read sub-command in a secondary storage controller is disclosed. The method includes receiving the read sub-command from a primary storage controller; retrieving data in response to the read sub-command; utilizing a write request to write the retrieved data directly to a memory accessible by a host device; issuing an additional request to the same memory after the write request; receiving an indication of completion of the additional request; and reporting a sub-completion status to the primary storage controller.

Method to ensure data coherency in a scalable aggregate neighbor-device interface

A method that decodes serially received MPEG variable length codes by executing instructions in parallel. The method includes an execution unit which includes multiple pipelined functional units. The functional units execute at least two of the instructions in parallel. The instructions utilize and share general purpose registers. The general purpose registers store information used by at least two of the instructions.

An apparatus that provides configurable processing includes a fetch module, a decoder, and a dynamic arithmetic unit. The fetch module is operable to fetch at least one instruction and provide it to the decoder. The decoder receives the instruction and decodes it. The dynamic arithmetic logic unit receives the decoded instruction and configures at least one configurable arithmetic logic unit to perform an operation contained within the decoded instruction.

Method and apparatus of configurable processing

A carry save multiplier receives two input values having respective bit lengths A and B and provides sum and carry values, each having bit lengths A&plus;B&plus;1. A carry prediction circuit receives the most significant bit of the sum and carry values and provides an extension bit to be merged with less significant bits of the sum and carry bits. A carry save adder receives the altered sum and carry values, as well as a third input value to provide second sum and carry values. The second sum and carry values are added in a carry propagate adder to form a resulting value. This allows for a faster multiplication to form a product, and the faster addition of this product to another value such as an accumulator value.

Sign extension circuit and method for unsigned multiplication and accumulation

An adder tree is partitioned into two parts. One multiplexer provides a first bit group to the first part of the tree. A second multiplexer provides a second bit group to the second part of the tree. The two multiplexers provide the same bits groups to the respective parts in response to a first instruction, and provide different bit groups in response to a second instruction. Therefore, the first instruction allows for the single multiplication of the number represented by the first bit group by another number provided to collectively represented to both parts of the tree. The second instruction causes the multiplication of the first bit group by the third bit group in the first part of the adder tree, and causes another multiplication of the second bit group by the fourth bit group in the second part of the adder tree.

Partitioned adder tree supported by a multiplexer configuration

An apparatus for high speed signal propagation across a net in an integrated circuit operates with a driver that is coupled to the net, for driving signals across the net. A first transition assist driver (TAD) is coupled to a first node in the net and is capable of pulling the voltage level of the first node in response to the voltage level of the first node reaching a threshold value. The threshold value can be adjusted in order to increase the switching speed or, alternatively, the noise immunity of the first TAD. A second TAD is coupled to a second node in the net and is capable of pulling the voltage level of the second node in response to the voltage level of the second node reaching the threshold value. The apparatus is used for increasing the propagation speed of signals that are transmitted in a microprocessor block or other stages in an integrated circuit. A method for high speed signal propagation in an integrated circuit by use of a signal propagation system includes the steps of: (a) sensing a voltage level of a first node in a net; and (b) pulling the voltage level of the first node in response to the voltage level of the first node reaching a threshold value. This method is applicable without any modification when the net can be driven by one of the multiple drivers attached to the net. In other words, the method allows bi-directional signal propagation.

Method and apparatus for high speed on-chip signal propagation

An adder tree includes several partial product generators, each generating a bit of equal weight. An adder receives the bits and provides a carry bit to a logic unit. The logic unit propagates the carry bit to the next more significant column in response to a carry enable instruction. The logic unit outputs a bit that is independent of the carry bit in response to a lack of a carry enable instruction.

Selective carry boundary

A combination has a booth recoder with at least three input lines; two input lines corresponding to two bits of a multiplier and one input line being an increment select line. In one embodiment, signals representing the two bits of the multiplier are provided on the two input lines corresponding to the two bits. A controller selectively asserts a increment select signal on an increment select line, thereby incrementing the multiplier. Therefore, the present invention has the advantage of incrementing a multiplier while performing booth multiplication without requiring an additional adder for incrementing.

Booth multiplication structure which selectively integrates the function

In accordance with the present invention, an adder tree structure includes at least two adder stages. In the circuit and method according to the present invention, the first of the two adder stages generates two bits of a common weight and other more significant bits of a weight one bit more significant than the two bits of the common weight. The second of the two adder stages includes an adder that receives the more significant bits generated in the first of the two adder stages. The second adder stage also includes an AND gate which receives and logically AND's the two bits of the common weight to generate a carry-in bit for the adder in the second stage. The above adder tree structure and adding method have an advantage of permitting more input terminals of adders to contain information about the input values to the adder tree structure. Therefore, the adders are used more efficiently and less adders are required to perform a specific function.

Modified adder tree structure and method using logic and gates to

A multiplier has two input value terminals which receive two signed input bit groups. The multiplier also has two output terminals configured to carry a sum and carry bit group representing, in redundant form, a product of the two signed input values. A sign determining circuit generates a sign bit representing a sign of the product of the two input signed values. An extension unit has three input terminals configured to receive the most significant bit of the sum bit group, the most significant bit of the carry bit group, and the sign bit generated by the sign determining circuit. The extension unit is structure to generate a least significant extension bit and a more significant extension bit. The least significant extension bit has one binary state if the sum most significant bit, the sign bit, and the carry most significant bit have the same binary state. The least significant extension bit otherwise has the opposite binary state.

Circuit and method for wrap-around sign extension for signed numbers

A multiplier is configured to multiply two signed values to generate sum and carry bit groups representing, in redundant form, a product of the first and second signed values. A sign determining circuit is configured generate a sign bit representing a sign of the product. An extension unit is configured to receive the sum most significant bit, the sign bit, and the carry most significant bit. The extension output terminal configured to carry a replacement bit and an extension bit, the replacement bit having a same weight as the sum most significant bit. The extension unit is structured such that the replacement bit has one binary state only if the sum most significant bit and the carry most significant bit are different. The extension unit is structured such that the extension bit has one binary state only if the sign bit is a binary zero and the sum most significant bit and the carry most significant bit are the same.

Growing community of inventors

San Jose, CA, United States of America

Nital P Patwa