Intel Corporation

Jose Yallouz

Amit Gradstein

Simon Rubanovich

Zeev Sperber

Regev Shemy

Vinodh Gopal

Wajdi K Feghali

Ittai Anati

Sean M Gulley

Jacob Doweck

Ilya Albrekht

Sagi Meller

Gavri Berger

Ron Schneider

Saeed Kharouf

Robert Valentine

Ron Gabor

Igor Yanover

Arkady Bramnik

Eyal Hadas

Onkar P Desai

Systems, methods, and apparatuses relating to performing hashing operations on packed data elements are described. In one embodiment, a processor includes a decode circuit to decode a single instruction into a decoded single instruction, the single instruction including at least one first field that identifies eight 32-bit state elements A, B, C, D, E, F, G, and H for a round according to a SM3 hashing standard and at least one second field that identifies an input message; and an execution circuit to execute the decoded single instruction to: rotate state element C left by 9 bits to form a rotated state element C, rotate state element D left by 9 bits to form a rotated state element D, rotate state element G left by 19 bits to form a rotated state element G, rotate state element H left by 19 bits to form a rotated state element H, perform two rounds according to the SM3 hashing standard on the input message and state element A, state element B, rotated state element C, rotated state element D, state element E, state element F, rotated state element G, and rotated state element H to generate an updated state element A, an updated state element B, an updated state element E, and an updated state element F, and store the updated state element A, the updated state element B, the updated state element E, and the updated state element F into a location specified by the single instruction.

Apparatuses, methods, and systems for hashing instructions

Systems, methods, and apparatuses relating to a matrix operations accelerator are described. In one embodiment, a processor includes a matrix operations accelerator circuit that includes a two-dimensional grid of fused multiply accumulate circuits that is switchable to a scheduling mode for execution of a decoded single instruction where the matrix operations accelerator circuit loads a first buffer of the two-dimensional grid of fused multiply accumulate circuits from a first plurality of registers that represents a first input two-dimensional matrix, checks if a second buffer of the two-dimensional grid of fused multiply accumulate circuits stores an immediately prior input two-dimension matrix that is the same as a second input two-dimensional matrix from a second plurality of registers that represents the first input two-dimensional matrix, and when the second buffer of the two-dimensional grid of fused multiply accumulate circuits stores the immediately prior input two-dimension matrix, from execution of a previous instruction, that is the same as the second input two-dimensional matrix: prevents reclamation of the second buffer between execution of the previous instruction and the decoded single instruction, performs an operation on the first input two-dimensional matrix from the first buffer and the immediately prior input two-dimension matrix from the second buffer to produce a resultant, and stores the resultant in resultant storage, and when the second buffer of the two-dimensional grid of fused multiply accumulate circuits does not store the immediately prior input two-dimension matrix, from execution of the previous instruction, that is the same as the second input two-dimensional matrix: loads the second input two-dimensional matrix into the second buffer of the two-dimensional grid of fused multiply accumulate circuits, performs the operation on the first input two-dimensional matrix from the first buffer and the second input two-dimension matrix from the second buffer to produce a resultant, and stores the resultant in the resultant storage.

Apparatuses, methods, and systems for instructions of a matrix operations accelerator

Integrated circuits to compute a result of summing m values, rotating the sum by k bits, and adding a summation of n values Bto Bto the rotated sum. An embodiment includes: a first carry save adder to add up the m values to generate a first carry and a first sum; rotator circuitry to rotate both the first carry and the first sum by k bits to generate a second carry and a second sum; a second carry save adder to add up the second carry, the second sum, and the summation of values Bto Bto generate a third carry and a third sum; two parallel adders to generate a first intermediate result and a second intermediary result based on the third carry and the third sum; and a multiplexer to generate the result utilizing various portions of the first and second intermediate results.

Efficient rotate adder for implementing cryptographic basic operations

Systems, methods, and apparatuses relating to a matrix operations accelerator are described. In one embodiment, a processor includes a matrix operations accelerator circuit that includes a two-dimensional grid of fused multiply accumulate circuits; a first plurality of registers that represents an input two-dimensional matrix coupled to the matrix operations accelerator circuit; a decoder, of a core coupled to the matrix operations accelerator circuit, to decode an instruction into a decoded instruction; and an execution circuit of the core to execute the decoded instruction to cause the two-dimensional grid of fused multiply accumulate circuits to form a transpose of the input two-dimensional matrix when the matrix operations accelerator circuit is in a transpose mode.

Apparatuses, methods, and systems for transpose instructions of a matrix operations accelerator

The present disclosure is directed to systems and methods for performing one or more operations on a two dimensional tile register using an accelerator that includes a tiled matrix multiplication unit (TMU). The processor circuitry includes reservation station (RS) circuitry to communicatively couple the processor circuitry to the TMU. The RS circuitry coordinates the operations performed by the TMU. TMU dispatch queue (TDQ) circuitry in the TMU maintains the operations received from the RS circuitry in the order that the operations are received from the RS circuitry. Since the duration of each operation is not known prior to execution by the TMU, the RS circuitry maintains shadow dispatch queue (RS-TDQ) circuitry that mirrors the operations in the TDQ circuitry. Communication between the RS circuitryand the TMU provides the RS circuitry with notification of successfully executed operations and allows the RS circuitry to cancel operations where the operations are associated with branch mispredictions and/or non-retired speculatively executed instructions.

Accelerator systems and methods for matrix operations

A method includes calculating, by a processor core, a first residue code of a first packed vector stored in a first vector register of a set of vector registers; calculating a second residue code of a second packed vector stored in a second vector register of the set of vector registers; calculating, from an addition of the first residue code and the second residue code, a reference residue code for a SIMD arithmetic operation; performing an element-by-element execution of the SIMD arithmetic operation between data elements of the first packed vector and of the second packed vector, resulting in an output packed vector; calculating an output residue code of the output packed vector; and detecting an error in the SIMD arithmetic operation based on comparison of the reference residue code with the output residue code.

Advanced error detection for integer single instruction, multiple data (SIMD) arithmetic operations

Growing community of inventors

Haifa, Israel

Jose Yallouz