Advanced Micro Devices Corporation

Ati Technologies Ulc

Foveon, Inc.

Allen H Rush

Sateesh Lagudu

Michael Mantor

Arun Vaidyanathan Ananthanarayan

Nuwan S Jayasena

Shaizeen Dilawarhusen Aga

Michael Ignatowski

Lei Zhang

Hui Zhou

Prasad Nagabhushanamgari

Maxim V Kazakov

Richard Francis Lyon

Gabor Sines

Mehdi Saeedi

Jiasheng Chen

YunXiao Zou

Thomas Daniel Perry

Yang Ling

Jiangli Ye

Razvan Florin Dan-Dobre

Michal Eugeniusz Gallus

An apparatus includes a processor and a collision detection unit operatively coupled to the processor. The collision detection unit is configured to process, using a machine learning model, one or more parameters associated with a ray cast in virtual environment comprising an object. The machine learning model is configured to approximate a mesh representing the object. The collision detection unit is further configured to determine if the ray collides with the object based on processing the one or more parameters. In response to determining if the ray collides with the object, the collision detection unit is configured to generate collision data associated with the ray and the object.

Machine-learning based collision detection for objects in virtual environments

An array processor includes processor element arrays distributed in rows and columns. The processor element arrays perform operations on parameter values. The array processor also includes memory interfaces that broadcast sets of the parameter values to mutually exclusive subsets of the rows and columns of the processor element arrays. In some cases, the array processor includes single-instruction-multiple-data (SIMD) units including subsets of the processor element arrays in corresponding rows, workgroup processors (WGPs) including subsets of the SIMD units, and a memory fabric configured to interconnect with an external memory that stores the parameter values. The memory interfaces broadcast the parameter values to the SIMD units that include the processor element arrays in rows associated with the memory interfaces and columns of processor element arrays that are implemented across the SIMD units in the WGPs. The memory interfaces access the parameter values from the external memory via the memory fabric.

Vertical and horizontal broadcast of shared operands

A processing device including a plurality of clusters of processor cores and a method for use in the processing device is disclosed. Each processor core in a cluster of processor cores is in communication with the other processor cores in the cluster and at least one processor core of each cluster is in communication with at least a processor core of a different cluster of processor cores. Each processor core is configured to store a product of a portion of a first matrix and a first portion of a second matrix in the memory, and store a product of the portion of the first matrix and a second portion of the second matrix in the memory, where the second portion of the second matrix is received from a processor core in the cluster of processor cores.

Device and method for accelerating matrix multiply operations

Systems, apparatuses, and methods for implementing a low power parallel matrix multiply pipeline are disclosed. In one embodiment, a system includes at least first and second vector register files coupled to a matrix multiply pipeline. The matrix multiply pipeline comprises a plurality of dot product units. The dot product units are configured to calculate dot or outer products for first and second sets of operands retrieved from the first vector register file. The results of the dot or outer product operations are written back to the second vector register file. The second vector register file provides the results from the previous dot or outer product operations as inputs to subsequent dot or outer product operations. The dot product units receive the results from previous phases of the matrix multiply operation and accumulate these previous dot or outer product results with the current dot or outer product results.

Stream processor with low power parallel matrix multiply pipeline

A processing system includes a first set and a second set of general-purpose registers (GPRs) and memory access circuitry that fetches nonzero values of a sparse matrix into consecutive slots in the first set. The memory access circuitry also fetches values of an expanded matrix into consecutive slots in the second set of GPRs. The expanded matrix is formed based on values of a vector and locations of the nonzero values in the sparse matrix. The processing system also includes a set of multipliers that concurrently perform multiplication of the nonzero values in slots of the first set of GPRs with the values of the vector in corresponding slots of the second set. Reduced sum circuitry accumulates results from the set of multipliers for rows of the sparse matrix.

Sparse matrix-vector multiplication

Systems, apparatuses, and methods for adaptively mapping a machine learning model to a multi-core inference accelerator engine are disclosed. A computing system includes a multi-core inference accelerator engine with multiple inference cores coupled to a memory subsystem. The system also includes a control unit which determines how to adaptively map a machine learning model to the multi-core inference accelerator engine. In one implementation, the control unit selects a mapping scheme which minimizes the memory bandwidth utilization of the multi-core inference accelerator engine. In one implementation, this mapping scheme involves having one inference core of the multi-core inference accelerator engine fetch given data and broadcast the given data to other inference cores of the inference accelerator engine. Each inference core fetches second data unique to the respective inference core. The inference cores then perform computations on the first and second data in order to implement the machine learning model.

Machine learning inference engine scalability

An array processor includes processor element arrays (PEAs) distributed in rows and columns. The PEAs are configured to perform operations on parameter values. A first sequencer received a first direct memory access (DMA) instruction that includes a request to read data from at least one address in memory. A texture address (TA) engine requests the data from the memory based on the at least one address and a texture data (TD) engine provides the data to the PEAs. The PEAs provide first synchronization signals to the TD engine to indicate availability of registers for receiving the data. The TD engine provides second synchronization signals to the first sequencer in response to receiving acknowledgments that the PEAs have consumed the data.

Broadcast synchronization for dynamically adaptable arrays

Systems, apparatuses, and methods for implementing a low latency long short-term memory (LSTM) machine learning engine using sequence interleaving techniques are disclosed. A computing system includes at least a host processing unit, a machine learning engine, and a memory. The host processing unit detects a plurality of sequences which will be processed by the machine learning engine. The host processing unit interleaves the sequences into data blocks and stores the data blocks in the memory. When the machine learning engine receives a given data block, the machine learning engine performs, in parallel, a plurality of matrix multiplication operations on the plurality of sequences in the given data block and a plurality of coefficients. Then, the outputs of the matrix multiplication operations are coupled to one or more LSTM layers.

Low latency long short-term memory inference with sequence interleaving

A processing device is provided which comprises memory configured to store data and a plurality of processor cores in communication with each other via first and second hierarchical communication links. Processor cores of a first hierarchical processor core group are in communication with each other via the first hierarchical communication links and are configured to store, in the memory, a sub-portion of data of a first matrix and a sub-portion of data of a second matrix. The processor cores are also configured to determine a product of the sub-portion of data of the first matrix and the sub-portion of data of the second matrix, receive, from another processor core, another sub-portion of data of the second matrix and determine a product of the sub-portion of data of the first matrix and the other sub-portion of data of the second matrix.

A system and method for controlling characteristics of collected image data are disclosed. The system and method include performing pre-processing of an image using GPUs, configuring an optic based on the pre-processing, the configuring being designed to account for features of the pre-processed image, acquiring an image using the configured optic, processing the acquired image using GPUs, and determining if the processed acquired image accounts for feature of the pre-processed image, and the determination is affirmative, outputting the image, wherein if the determination is negative repeating the configuring of the optic and re-acquiring the image.

Computational optics

An array processor includes processor element arrays distributed in rows and columns. The processor element arrays perform operations on parameter values. The array processor also includes memory interfaces that are dynamically mapped to mutually exclusive subsets of the rows and columns of the processor element arrays based on dimensions of matrices that provide the parameter values to the processor element arrays. In some cases, the processor element arrays are vector arithmetic logic unit (ALU) processors and the memory interfaces are direct memory access (DMA) engines. The rows of the processor element arrays in the subsets are mutually exclusive to the rows in the other subsets and the columns of the processor element arrays in the subsets are mutually exclusive to the columns in the other subsets. The matrices can be symmetric or asymmetric, e.g., one of the matrices can be a vector having a single column.

Dynamically adaptable arrays for vector and matrix operations

Computational sensor

Systems, apparatuses, and methods for implementing memory bandwidth reduction techniques for low power convolutional neural network inference applications are disclosed. A system includes at least a processing unit and an external memory coupled to the processing unit. The system detects a request to perform a convolution operation on input data from a plurality of channels. Responsive to detecting the request, the system partitions the input data from the plurality of channels into 3D blocks so as to minimize the external memory bandwidth utilization for the convolution operation being performed. Next, the system loads a selected 3D block from external memory into internal memory and then generates convolution output data for the selected 3D block for one or more features. Then, for each feature, the system adds convolution output data together across channels prior to writing the convolution output data to the external memory.

Growing community of inventors

Santa Clara, CA, United States of America

Allen H Rush