Intel Corporation

Richard L Coulson

Jawad Basit Khan

Knut Stener Grimsrud

Robert J Royer, Jr

Robert W Faber

Theodore L Willke

Jonathan C Lueker

Chetan Chauhan

Dipanjan Sengupta

Mariano Tepper

Sourabh Dongaonkar

Sanjeev N Trika

John I Garney

Jerrold Von Hauck

Eric Cabot Hannah

Rajesh Sundaram

Kirk D Brannock

Albert Fazio

Jeanna N Matthews

Randall K Webb

C Brendan Traw

Brian M Yablon

Martin Langhammer

Mahesh A Iyer

Ebrahim Andideh

Shigeki Tomishima

Ravi H Motwani

Ravi Prakash Gutala

Scott J Weber

Zion S Kwok

Andrew W Vogan

Srikanth T Srinivasan

Richard Paul Mangold

Aravind Raghavendra Dasu

Ilya K Ganusov

Bruce Querbach

Michael A Brown

Brian Leete

Brad W Hosler

David W LaFollette

Matthew I Adiletta

Brian Dees

Theodore Willke, Ii

Zion Kwok

Terence Magee

Andrew Wayne Vogan

Technologies for performing random sparse lifting and Procrustean orthogonal sparse hashing using column read-enabled memory include a device that has a memory that is column addressable and circuitry connected to the memory. The circuitry is configured to add a set of input data vectors to the memory as a set of binary dimensionally expanded vectors, including multiplying each input data vector with a projection matrix. The circuitry is also configured to produce a search hash code from a search data vector, including multiplying the search data vector with the projection matrix. Further, the circuitry is configured to determine a Hamming distance between the search hash code and each of the binary dimensionally expanded vectors.

Technologies for performing sparse lifting and procrustean orthogonal sparse hashing using column read-enabled memory

Technologies for refining stochastic similarity search candidates include a device having a memory that is column addressable and circuitry connected to the memory. The circuitry is configured to add a set of input data vectors to the memory as a set of binary dimensionally expanded vectors, including multiplying each input data vector with a projection matrix. The circuitry is also configured to produce a search hash code from a search data vector, including multiplying the search data vector with the projection matrix. Additionally, the circuitry is configured to identify a result set of the binary dimensionally expanded vectors as a function of a Hamming distance of each binary dimensionally expanded vector from the search hash code and determine, from the result set, a refined result set as a function of a similarity measure in an original input space of the input data vectors.

Technologies for refining stochastic similarity search candidates

A three dimensional circuit system includes a first integrated circuit die having a core logic region that has first memory circuits and logic circuits. The three dimensional circuit system includes a second integrated circuit die that has second memory circuits. The first and second integrated circuit dies are coupled together in a vertically stacked configuration. The three dimensional circuit system includes third memory circuits coupled to the first integrated circuit die. The third memory circuits reside in a plane of the first integrated circuit die. The logic circuits are coupled to access the first, second, and third memory circuits and data can move between the first, second, and third memories. The third memory circuits have a larger memory capacity and a smaller memory access bandwidth than the second memory circuits. The second memory circuits have a larger memory capacity and a smaller memory access bandwidth than the first memory circuits.

Three dimensional circuit systems and methods having memory hierarchies

Error correction values for a memory device include row error correction values and column error correction values for the same memory array. The memory device includes a memory array that is addressable in two spatial dimensions: a row dimension and a column dimension. The memory array is written as rows of data, and can be read as rows in the row dimension or read as columns in the column dimension. A data write triggers updates to row error correction values and to column error correction values.

Error correction for dynamic data in a memory that is row addressable and column addressable

Technologies for performing in-memory macro operations include a memory having a media access circuitry connected to a memory media. The media access circuitry is to receive a request to perform an in-memory macro operation indicative of a set of multiple in-memory operations. The media access circuitry is also to perform, in response to the request, the in-memory macro operation on data present in the memory media.

Technologies for performing macro operations in memory

Technologies for performing stochastic similarity searches in an online clustering space include a device having a column addressable memory and circuitry. The circuitry is configured to determine a Hamming distance from a binary dimensionally expanded vector to each cluster of a set of clusters of binary dimensionally expanded vectors in the memory, identify the cluster having the smallest Hamming distance from the binary dimensionally expanded vector, determine whether the identified cluster satisfies a target size, and add or delete, in response to a determination that the identified cluster does not satisfy the target size, the binary dimensionally expanded vector to or from the identified cluster.

Technologies for performing stochastic similarity searches in an online clustering space

Technologies for addressing individual bits in memory include a device having a memory that includes partitions that each have tiles, in which each tile stores an individual bit. The device also includes circuitry to receive a request to access (e.g., read or write) a sequence of bits in a partition. The request specifies a logical row or column address. A corresponding tile is determined from the logical row or column address and for each bit in the sequence. The corresponding tile is accessed to read or write the bit therein.

Technologies to address individual bits in memory

Technologies for efficiently performing memory augmented neural network (MANN) update operations includes a device with circuitry configured to obtain a key usable to search a memory associated with a memory augmented neural network for one or more data sets. The circuitry is also configured to perform a stochastic associative search to identify a group of data sets within the memory that satisfy the key and write to the identified group of data sets concurrently to update the memory augmented neural network.

Technologies for performing efficient memory augmented neural network update operations

Technologies for scrambling functions in a column-addressable memory architecture includes a device having a memory and a circuitry. The memory includes a matrix storing individually addressable bit data, and the matrix is formed by rows and columns. The circuitry is to receive a request to perform a write operation of one or more bit values to one of the columns. The circuitry is further to determine a scrambler state at each location of the column, the location corresponding to a respective row and column index. The scrambler state is indicative of a function used to determine a value at the respective column location. Each of the bit values is scrambled as a function of the scrambler state for the respective column location and written thereto.

Technologies for performing column architecture-aware scrambling

Technologies for tuning performance and/or accuracy of similarity search using stochastic associative memories (SAM). Under a first subsampling approach, columns associated with set bits in a search key comprising a binary bit vector are subsampled. Matching set bits for the subsampled columns are aggregated on a row-wise basis to generate similarity scores, which are then ranked. A similar scheme is applied for all the columns with set bits in the search key and the results for top ranked rows are compared to evaluate a tradeoff between throughput boost versus lost accuracy. A second approach called continuous column read, and iterative approach is employed that continuously scores the rows as each new column read is complete. The similarity scores for an N-1 and Nth-1 iteration are ranked, a rank correlation is calculated, and a determination is made to whether the rank correlation meets or exceeds a threshold.

Technologies for tuning performance and/or accuracy of similarity search using stochastic associative memories

Technologies for efficiently accessing data columns and rows in a memory include a device with circuitry configured to receive a request to access memory in which each bit of a logical column of bits is located in a different physical row and a different physical column than any other bit in the logical column. The circuitry is additionally configured to access, in response to the request, the memory. In accessing the memory, the circuitry rotates one or more bit positions in a data set read from or written to the memory.

Technologies for efficiently accessing data columns and rows in a memory

Technologies for directly performing read and write operations on matrix data in a data storage device are disclosed. The data storage device receives a request to perform a read or write operation on matrix data stored in one or more memory units of the data storage device. Each memory unit is associated with a column address for the matrix data. The data storage device determines whether the request specifies to read or write a column or a row in the matrix data. The data storage device performs, in response to a determination that the request specifies to read or write a column in the matrix data, the read or write operation on the matrix data on the column.

Technologies for direct matrix read and write operations

Technologies for stochastic associative search operations in memory (e.g., a three-dimensional cross-point memory) using error correction codes include a compute device. The compute device has a memory including a matrix that stores individually addressable bit data and is formed by rows and columns. The compute device receives a request to retrieve a subset of the bit data stored in the matrix. The compute device identifies, based on a search performed on the columns in the matrix, one or more candidate data sets. Each candidate data set corresponds to one of the rows in the matrix. The compute device performs an error correction operation on the identified one or more candidate data sets to determine whether the identified one or more candidate data sets is an exact match with the subset of the bit data.

Technologies for efficient stochastic associative search operations with error-correcting code

Technologies for stochastic associative search operations in memory (e.g., a three-dimensional cross-point memory) include a compute device. The compute device has a memory including a matrix that stores individually addressable bit data and is formed by rows and columns. The compute device receives a request to retrieve a subset of the bit data stored in the matrix. The request includes a search key indicative of the subset of bit data, and the search key is formed on a same axis as the rows. The compute device identifies one or more candidate data sets in the matrix based on a search for matching bit data of the search key with bit data in one or more of the columns. The compute device outputs the identified candidate data sets.

Technologies for efficient stochastic associative search operations

Technologies for performing a hyper-dimensional operation in a memory of the compute device include a memory and a memory controller. The memory controller is configured to receive a query from a requestor and determine, in response to a receipt of the query, a key hyper-dimensional vector associated with the query, perform a hyper-dimensional operation to determine a reference hyper-dimensional vector associated with a value to the key. The memory controller is further configured to perform a nearest neighbor search by searching columns of a stochastic associative array of a hyper-dimensional vector table in the memory, identify a closest matching row in the stochastic associative array relative to the reference hyper-dimensional vector, wherein the closest matching row indicates a closest matching value hyper-dimensional vector, and output a value associated with the closest matching value hyper-dimensional vector.

Technologies for providing stochastic key-value storage

Growing community of inventors

Porland, OR, United States of America

Richard L Coulson