Sandbridge Technologies, Inc.

International Business Machines Corporation

Qualcomm Incorporated

Aspen Acquisition Corporation

Erdem Hokenek

Mayan Moudgill

C John Glossner

Michael J Schulte

David Meltzer

Clair John Glossner, Iii

Shenghong Wang

Arthur Joseph Hoane

Hung Qui Le

Robert K Montoye

Victor V Zyuban

Erik Richter Altman

Daniel Sabin Iancu

Sean Matthew Dorward

Pablo Balzola

Jin Lu

John Glossner

Vladimir Kotlyar

Joon-Hwa Chun

Eko Lisuwandi

John C Glossner

A multithreaded processor comprises a plurality of hardware thread units, an instruction decoder coupled to the thread units for decoding instructions received therefrom, and a plurality of execution units for executing the decoded instructions. The multithreaded processor is configured for controlling an instruction issuance sequence for threads associated with respective ones of the hardware thread units. On a given processor clock cycle, only a designated one of the threads is permitted to issue one or more instructions, but the designated thread that is permitted to issue instructions varies over a plurality of clock cycles in accordance with the instruction issuance sequence. The instructions are pipelined in a manner which permits at least a given one of the threads to support multiple concurrent instruction pipelines.

Multithreaded processor with multiple concurrent pipelines per thread

A processor comprises a plurality of arithmetic units, an accumulator unit, and a reduction unit coupled between the plurality of arithmetic units and the accumulator unit. The reduction unit receives products of vector elements from the arithmetic units and a first accumulator value from the accumulator unit, and processes the products and the first accumulator value to generate a second accumulator value for delivery to the accumulator unit. The processor implements a plurality of vector multiply and reduce operations having guaranteed sequential semantics, that is, operations which guarantee that the computational result will be the same as that which would be produced using a corresponding sequence of individual instructions.

Processor having parallel vector multiply and reduce operations with sequential semantics

A processor comprises a memory, an instruction decoder coupled to the memory for decoding instructions retrieved therefrom, and a plurality of execution units for executing the decoded instructions. One or more of the instructions are in a compound instruction format in which a single instruction comprises multiple operation fields, with one or more of the operation fields each comprising at least an operation code field and a function field. The operation code field and the function field together specify a particular operation to be performed by one or more of the execution units.

Multi-threaded processor having compound instruction and operation formats

A system and method for processing operations that use data vectors each comprising a plurality of data elements, in accordance with the present invention, includes a vector data file comprising a plurality of storage elements for storing data elements of the data vectors. A pointer array is coupled by a bus to the vector data file. The pointer array includes a plurality of entries wherein each entry identifies at least one storage element in the vector data file. The at least one storage element stores at least one data element of the data vectors, wherein for at least one particular entry in the pointer array, the at least one storage element identified by the particular entry has an arbitrary starting address in the vector data file.

Vector register file with arbitrary vector addressing

An arithmetic unit for performing an arithmetic operation on at least first and second input operands, each of the input operands being separable into a first portion and a second portion, such as respective less significant and more significant portions. The arithmetic unit comprises first arithmetic circuitry, second arithmetic circuitry, selection circuitry and saturation circuitry. The first arithmetic circuitry, which may comprise a carry-propagate adder, processes the first portions of the input operands to generate at least a temporary sum and a carry output. The second arithmetic circuitry, which may comprise a dual adder and a preliminary saturation detector, processes the second portions of the input operands to generate one or more temporary sums and a number of saturation flags. The selection circuitry is configured to select one or more of the outputs of the second arithmetic circuitry based on the carry output of the first arithmetic circuitry. The saturation circuitry has inputs coupled to corresponding outputs of the first arithmetic circuitry and the selection circuitry, and is configured to generate a result of the arithmetic operation.

Arithmetic unit for addition or subtraction with preliminary saturation detection

A system and method is provided for processing a first instruction set and a second instruction set in a single processor. The method includes storing a plurality of instructions of the second instruction set in a plurality of buffers proximate to a plurality of execution units, executing an instruction of the first instruction set in response to a first counter, and executing at least one instruction of the second instruction set in response to at least a second counter, wherein the second counter is invoked by a branch instruction of the first instruction set.

System and method including distributed instruction buffers for storing frequently executed instructions in predecoded form

A digital signal processor (DSP) includes dual SIMD units that are connected in cascade, and wherein results of a first SIMD stage of the cascade may be stored in a register file of a second SIMD stage in the cascade. Each SIMD stage contains its own resources for storing operands and intermediate results (e.g., its own register file), as well as for decoding the operations that may be executed in that stage. Within each stage, hardware resources are organized to operate in SIMD manner, so that independent SIMD operations can be executed simultaneously, one in each stage of the cascade. Intermediate operands and results flowing through the cascade are stored at the register files of the stages, and may be accessed from those register files. Data may also be brought from memory directly into the register files of the stages in the cascade.

Digital signal processor with cascaded SIMD organization

A receiver includes a controller which receives A/D sampled input signals and shifts the sampled digital signal to compensate for Doppler effect in the input signal prior to demodulation. The controller compensates for a Doppler increased frequency by shifting the sampled digital signal so as to skip a sample period every n samples. This may be achieved by decreasing a cycle of m samples by one sample period every n samples. The controller compensates for a Doppler decreased frequency by shifting the sampled digital signal so as to add a sample period every n samples. This may be achieved by repeating a sample every n samples to shift the sampled digital signal. The compensation is performed in software on a multi-threaded processor.

Doppler compensated receiver

A method of decoding using a log posterior probability ratio L(u), which is a function of forward variable &#x3b1; (.) and backward variable &#x3b2; (.). The method comprises dividing the forward variable &#x3b1; (.) and the backward variable &#x3b2; (.) into, for example, two segments p and q, where p plus q equal the length of the code word U. The forward segments &#x3b1; (.) are parallel calculated, and the backward segments &#x3b2; (.) are parallel calculated. The ratio L(u) is calculated using the parallel calculated segments of &#x3b1; (.) and &#x3b2; (.).

Turbo decoder using parallel processing

A cache memory for use in a multithreaded processor includes a number of set-associative thread caches, with one or more of the thread caches each implementing a thread-based eviction process that reduces the amount of replacement policy storage required in the cache memory. At least a given one of the thread caches in an illustrative embodiment includes a memory array having multiple sets of memory locations, and a directory for storing tags each corresponding to at least a portion of a particular address of one of the memory locations. The directory has multiple entries each storing multiple ones of the tags, such that if there are n sets of memory locations in the memory array, there are n tags associated with each directory entry. The directory is utilized in implementing a set-associative address mapping between access requests and memory locations of the memory array. An entry in a particular one of the memory locations is selected for eviction from the given thread cache in conjunction with a cache miss event, based at least in part on at least a portion of a thread identifier of the given thread cache.

Method and apparatus for multithreaded cache with cache eviction based on thread identifier

An ultra low power adder with sum synchronization which provides a power reduction method in the binary carry propagate adders by using a carry skip technique. The invention eliminates glitches at the adder outputs by preventing signal transitions at the sum outputs until the corresponding carry signals have reached their final values, which is achieved by adding a synchronization circuitry to the sum calculation path.

Growing community of inventors

Yorktown Heights, NY, United States of America

Erdem Hokenek