Intel Corporation

Dan Baum

Elmoustapha Ould-Ahmed-Vall

Robert Valentine

Mark Jay Charney

Bret L Toll

Alexander F Heinecke

Christopher J Hughes

Raanan Sade

Zeev Sperber

Jesus Corbal

Menachem Adelman

Simon Rubanovich

Milind Baburao Girkar

Vinodh Gopal

Wajdi K Feghali

James D Guilford

Efraim Rotem

Doron Rajwan

Prasoonkumar Surti

David M Durham

Gilbert A Neiger

Subramaniam M Maiyuran

Rajesh Poornachandran

Vedvyas Shanbhogue

Eliezer Weissmann

Varghese George

Amit Gradstein

Michael J Espig

Rinat Rappoport

Barukh Ziv

Yuri Gebil

Stanislav Shwartsman

Igor Yanover

Ronen Zohar

Chen Koren

Kosta Luria

Ronny Korner

Guei-Yuan Lueh

Michael E Kounavis

Alon Naveh

Santosh Ghosh

Karanvir S Grewal

Avinash N Ananthakrishnan

Nadav Shulman

Ron Gabor

Sergej Deutsch

Robert S Chappell

Jorge E Parra

Abhishek Basak

Jonathan D Pearce

Nilesh K Jain

Brinda Ganesh

Asit K Mishra

Salmin Sultana

Hisham Abu Salah

Stephen J Robinson

Evangelos Georganas

Michael D LeMay

Arik Narkis

Regev Shemy

Guy Boudoukh

Omer Vikinski

Andrew James Weiler

Yash Akhauri

Elmoustapha Ould-ahmed-vall

Yaroslav Pollak

Ould-Ahmed-Vall Elmoustapha

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

Embodiments detailed herein relate to matrix operations. For example, embodiments of instruction support for matrix (tile) dot product operations are detailed. Exemplary instructions including computing a dot product of signed words and accumulating in a double word with saturation; computing a dot product of bytes and accumulating in to a dword with saturation, where the input bytes can be signed or unsigned and the dword accumulation has output saturation; etc.

Systems, methods, and apparatuses for dot production operations

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

A processor, a system, a machine readable medium, and a method. The processor comprises first circuitry to: encrypt a first code image using a first code key; load the encrypted first code image into a memory area allocated in memory for the first code image by an operating system miming on the processor; and send to the operating system a substitute key that corresponds to the first code key, wherein the first code key is concealed from the operating system; and an instruction cache including control circuitry; and second circuitry coupled to the instruction cache, the second circuitry to: receive the substitute key from the operating system; in response to a first request from the operating system to execute the first code image to instantiate a first process, perform a first cryptographic function using a hardware key to generate the first code key from the substitute key; and program the control circuitry of the instruction cache with the first code key to enable the first code image to be decrypted using the first code key.

Cryptographic computing in multitenant environments

Embodiments detailed herein relate to matrix operations. In particular, support for matrix (tile) addition, subtraction, and multiplication is described. For example, circuitry to support instructions for element-by-element matrix (tile) addition, subtraction, and multiplication are detailed. In some embodiments, for matrix (tile) addition, decode circuitry is to decode an instruction having fields for an opcode, a first source matrix operand identifier, a second source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry is to execute the decoded instruction to, for each data element position of the identified first source matrix operand: add a first data value at that data element position to a second data value at a corresponding data element position of the identified second source matrix operand, and store a result of the addition into a corresponding data element position of the identified destination matrix operand.

Systems, methods, and apparatuses for matrix add, subtract, and multiply

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 matrix compress/decompress instructions. In one example, a processor includes fetch circuitry to fetch a compress instruction having a format with fields to specify an opcode and locations of decompressed source and compressed destination matrices, decode circuitry to decode the fetched compress instructions, and execution circuitry, responsive to the decoded compress instruction, to: generate a compressed result according to a compress algorithm by compressing the specified decompressed source matrix by either packing non-zero-valued elements together and storing the matrix position of each non-zero-valued element in a header, or using fewer bits to represent one or more elements and using the header to identify matrix elements being represented by fewer bits; and store the compressed result to the specified compressed destination matrix.

Systems and methods for performing matrix compress and decompress instructions

Embodiments detailed herein relate to matrix operations. In particular, matrix (tile) multiply accumulate and negated matrix (tile) multiply accumulate are discussed. For example, in some embodiments decode circuitry to decode an instruction having fields for an opcode, an identifier for a first source matrix operand, an identifier of a second source matrix operand, and an identifier for a source/destination matrix operand; and execution circuitry to execute the decoded instruction to multiply the identified first source matrix operand by the identified second source matrix operand, add a result of the multiplication to the identified source/destination matrix operand, and store a result of the addition in the identified source/destination matrix operand and zero unconfigured columns of identified source/destination matrix operand are detailed.

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

Embodiments detailed herein relate to matrix operations. In particular, support for a matrix transpose instruction is detailed. In some embodiments, decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry to execute the decoded instruction to transpose each row of elements of the identified source matrix operand into a corresponding column of the identified destination matrix operand are detailed.

Systems, methods, and apparatuses for tile transpose

Systems, methods, and apparatuses for matrix operations

Detailed herein are embodiment systems, processors, and methods for matrix move. For example, a processor comprising decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry to execute the decoded instruction to move each data element of the identified source matrix operand to corresponding data element position of the identified destination matrix operand is described.

Systems, methods, and apparatus for matrix move

Techniques to allow use of metadata in unused bits of virtual addresses are described. A processor of an aspect includes a decode circuit to decode a memory access instruction. The instruction to indicate one or more memory address operands that are to have address generation information and metadata. An execution circuit coupled with the decode circuit to generate a 64-bit virtual address based on the one or more memory address operands. The 64-bit virtual address having a bit, an X-bit address field starting at a bitto store an address generated from the address generation information, and one or more metadata bits to store the metadata. The execution circuit also to perform a canonicality check on the 64-bit virtual address that does not fail due to non-canonical values of the metadata stored in the one or more metadata bits. Other processors, methods, systems, and instructions are disclosed.

64-bit virtual addresses having metadata bit(s) and canonicality check that does not fail due to non-canonical values of metadata bit(s)

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

Growing community of inventors

Haifa, Israel

Dan Baum