Intel Corporation

Raanan Sade

Robert Valentine

Mark Jay Charney

Alexander F Heinecke

Elmoustapha Ould-Ahmed-Vall

Bret L Toll

Zeev Sperber

Menachem Adelman

Amit Gradstein

Jesus Corbal

Simon Rubanovich

Christopher J Hughes

Dan Baum

Igor Yanover

Stanislav Shwartsman

Joseph Nuzman

Ron Gabor

Shlomo Raikin

Michael J Espig

Rinat Rappoport

Ehud Cohen

Tomer Stark

Oleg Margulis

Yuri Gebil

Ronen Zohar

Liron Zur

Ren Wang

Gad Shlomo Sheaffer

Vadim Bassin

Vinodh Gopal

Wajdi K Feghali

James D Guilford

Robert G Blankenship

Andrew J Herdrich

Christopher B Wilkerson

Anil Vasudevan

Bryant E Bigbee

Vedaraman Geetha

Shrikant M Shah

Chyi-Chang Miao

Binh Q Pham

Venkata Krishnan

Roman S Dubtsov

Yiftach Gilad

Ron Shalev

Marshall A Millier

Jason W Brandt

Milind Baburao Girkar

Robert S Chappell

Ahmad Yasin

Larisa Novakovsky

Barukh Ziv

Chen Koren

Thierry Pons

Eyal Hadas

Enrico Perla

David M Durham

Gilbert A Neiger

Ravi L Sahita

Rajesh Poornachandran

Vedvyas Shanbhogue

Efraim Rotem

Tsung-Yuan Charles Tai

Guei-Yuan Lueh

Barry E Huntley

Baiju V Patel

Andrew V Anderson

Ravishankar Iyer

Nir Rosenzweig

Ravi Rajwar

Ronak Singhal

Sameh Gobriel

Theodros Yigzaw

Jonathan D Pearce

Jacob Doweck

Julius Yuli Mandelblat

Ido Ouziel

Nilesh K Jain

Leena K Puthiyedath

Deep K Buch

Yipeng Wang

Evangelos Georganas

Arijit Biswas

David W Burns

Sebastien Hily

Ady Tal

Vivekananthan Sanjeepan

Arumugam Thiyagarajah

Ryan Carlson

Gavri Berger

Bob Valentine

Omar M Shaikh

Gur Hildesheim

Alex Gerber

Roman Dementiev

Lev Makovsky

Michael D Tucknott

Assaf Zaltsman

Ron Rais

Muhammad Taher

Methods, apparatus, systems, and articles of manufacture to perform weight and activation compression and decompression are disclosed. An example apparatus includes memory, instructions in the apparatus, and processor circuitry to execute the instructions to execute a compression operation to obtain compressed data corresponding to weights in a weight matrix, and determine meta-data associated with the weight matrix, a first portion of the meta-data indicative of whether the weight matrix is compressed, a second portion of the meta-data indicative of a cache size of the compressed data, and a third portion of the meta-data indicative of the compression operation executed to obtain the compressed data.

Methods and apparatus to perform weight and activation compression and decompression

Embodiments detailed herein relate to systems and methods to store a tile register pair to memory. In one example, a processor includes: decode circuitry to decode a store matrix pair instruction having fields for an opcode and source and destination identifiers to identify source and destination matrices, respectively, each matrix having a PAIR parameter equal to TRUE; and execution circuitry to execute the decoded store matrix pair instruction to store every element of left and right tiles of the identified source matrix to corresponding element positions of left and right tiles of the identified destination matrix, respectively, wherein the executing stores a chunk of C elements of one row of the identified source matrix at a time.

Systems and methods to store a tile register pair to memory

Disclosed embodiments relate to accelerating multiplication of sparse matrices. In one example, a processor is to fetch and decode an instruction having fields to specify locations of first, second, and third matrices, and an opcode indicating the processor is to multiply and accumulate matching non-zero (NZ) elements of the first and second matrices with corresponding elements of the third matrix, and executing the decoded instruction as per the opcode to generate NZ bitmasks for the first and second matrices, broadcast up to two NZ elements at a time from each row of the first matrix and each column of the second matrix to a processing engine (PE) grid, each PE to multiply and accumulate matching NZ elements of the first and second matrices with corresponding elements of the third matrix. Each PE further to store an NZ element for use in a subsequent multiplications.

Systems and methods of instructions to accelerate multiplication of sparse matrices using bitmasks that identify non-zero elements

Embodiments detailed herein relate to matrix (tile) operations. For example, decode circuitry to decode an instruction having fields for an opcode and a memory address; and execution circuitry to execute the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers are discussed.

Systems, methods, and apparatus for tile configuration

Embodiments detailed herein relate to matrix (tile) operations. For example, decode circuitry to decode an instruction having fields for an opcode and a memory address, and execution circuitry to execute the decoded instruction to store configuration information about usage of storage for two-dimensional data structures at the memory address.

Systems, methods, and apparatuses for matrix operations

Embodiments detailed herein relate to systems and methods to load a tile register pair. In one example, a processor includes: decode circuitry to decode a load matrix pair instruction having fields for an opcode and source and destination identifiers to identify source and destination matrices, respectively, each matrix having a PAIR parameter equal to TRUE; and execution circuitry to execute the decoded load matrix pair instruction to load every element of left and right tiles of the identified destination matrix from corresponding element positions of left and right tiles of the identified source matrix, respectively, wherein the executing operates on one row of the identified destination matrix at a time, starting with the first row.

Systems and methods to load a tile register pair

Embodiments detailed herein relate to matrix operations. In particular, the loading of a matrix (tile) from memory. For example, support for a loading instruction is described in the form of decode circuitry to decode an instruction having fields for an opcode, a destination matrix operand identifier, and source memory information, and execution circuitry to execute the decoded instruction to load groups of strided data elements from memory into configured rows of the identified destination matrix operand to memory.

Systems, methods, and apparatuses for tile load, multiplication and accumulation

Disclosed embodiments relate to systems and methods for performing instructions to convert to 16-bit floating-point format. In one example, a processor includes fetch circuitry to fetch an instruction having fields to specify an opcode and locations of a first source vector comprising N single-precision elements, and a destination vector comprising at least N 16-bit floating-point elements, the opcode to indicate execution circuitry is to convert each of the elements of the specified source vector to 16-bit floating-point, the conversion to include truncation and rounding, as necessary, and to store each converted element into a corresponding location of the specified destination vector, decode circuitry to decode the fetched instruction, and execution circuitry to respond to the decoded instruction as specified by the opcode.

Systems and methods for performing instructions to convert to 16-bit floating-point format

Disclosed embodiments relate to systems and methods for performing 16-bit floating-point vector dot product instructions. In one example, a processor includes fetch circuitry to fetch an instruction having fields to specify an opcode and locations of first source, second source, and destination vectors, the opcode to indicate execution circuitry is to multiply N pairs of 16-bit floating-point formatted elements of the specified first and second sources, and accumulate the resulting products with previous contents of a corresponding single-precision element of the specified destination, decode circuitry to decode the fetched instruction, and execution circuitry to respond to the decoded instruction as specified by the opcode.

Systems and methods for performing 16-bit floating-point vector dot product instructions

Embodiments detailed herein relate to matrix operations. In particular, the loading of a matrix (tile) from memory. For example, support for a loading instruction is described in at least a form of decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and destination memory information, and execution circuitry to execute the decoded instruction to store each data element of configured rows of the identified source matrix operand to memory based on the destination memory information.

Systems, methods, and apparatuses for tile store

An embodiment of the invention is a processor including execution circuitry to calculate, in response to a decoded instruction, a result of a complex multiplication of a first complex number and a second complex number. The calculation includes a first operation to calculate a first term of a real component of the result and a first term of the imaginary component of the result. The calculation also includes a second operation to calculate a second term of the real component of the result and a second term of the imaginary component of the result. The processor also includes a decoder, a first source register, and a second source register. The decoder is to decode an instruction to generate the decoded instruction. The first source register is to provide the first complex number and the second source register is to provide the second complex number.

Apparatus and method for complex multiplication

Disclosed embodiments relate to systems for performing instructions to quickly convert and use matrices (tiles) as one-dimensional vectors. In one example, a processor includes fetch circuitry to fetch an instruction having fields to specify an opcode, locations of a two-dimensional (2D) matrix and a one-dimensional (1D) vector, and a group of elements comprising one of a row, part of a row, multiple rows, a column, part of a column, multiple columns, and a rectangular sub-tile of the specified 2D matrix, and wherein the opcode is to indicate a move of the specified group between the 2D matrix and the 1D vector, decode circuitry to decode the fetched instruction; and execution circuitry, responsive to the decoded instruction, when the opcode specifies a move from 1D, to move contents of the specified 1D vector to the specified group of elements.

Systems for performing instructions to quickly convert and use tiles as 1D vectors

Systems, methods, and apparatuses relating to circuitry to precisely monitor memory store accesses are described. In one embodiment, a system includes a memory, a hardware processor core comprising a decoder to decode an instruction into a decoded instruction, an execution circuit to execute the decoded instruction to produce a resultant, a store buffer, and a retirement circuit to retire the instruction when a store request for the resultant from the execution circuit is queued into the store buffer for storage into the memory, and a performance monitoring circuit to mark the retired instruction for monitoring of post-retirement performance information between being queued in the store buffer and being stored in the memory, enable a store fence after the retired instruction to be inserted that causes previous store requests to complete within the memory, and on detection of completion of the store request for the instruction in the memory, store the post-retirement performance information in storage of the performance monitoring circuit.

Apparatuses, methods, and systems to precisely monitor memory store accesses

Disclosed embodiments relate to computing dot products of nibbles in tile operands. In one example, a processor includes decode circuitry to decode a tile dot product instruction having fields for an opcode, a destination identifier to identify a M by N destination matrix, a first source identifier to identify a M by K first source matrix, and a second source identifier to identify a K by N second source matrix, each of the matrices containing doubleword elements, and execution circuitry to execute the decoded instruction to perform a flow K times for each element (m, n) of the specified destination matrix to generate eight products by multiplying each nibble of a doubleword element (M,K) of the specified first source matrix by a corresponding nibble of a doubleword element (K,N) of the specified second source matrix, and to accumulate and saturate the eight products with previous contents of the doubleword element.

Systems and methods for performing 16-bit floating-point matrix dot product instructions

Growing community of inventors

Kibutz Sarid, Israel

Raanan Sade