Intel Corporation

Kent D Glossop

Simon C Steely, Jr

Kermin Elliott Fleming, Jr

Dennis Ryan Bradford

Jesus Corbal

Paul Caprioli

Yongzhi Zhang

Robert Valentine

Gilbert A Neiger

Mark Jay Charney

Rajesh M Sankaran

Edward Thomas Grochowski

Eriko Nurvitadhi

Koichi Yamada

Thomas D Fletcher

Joseph Nuzman

Deborah T Marr

Stephen R Van Doren

Lokpraveen B Mosur

Narayan Ranganathan

Jonathan D Pearce

Niall D McDonnell

Richard J Greco

Jeffrey J Cook

Ganesh Venkatesh

Asit K Mishra

Dwight P Manley

David B Sheffield

Tracy Garrett Drysdale

Nicholas P Carter

Michael A O'Hanlon

Barry Tannenbaum

Samantika S Sury

Fabrizio Petrini

Rakesh Krishnaiyer

Benjamin Keen

Kermin ChoFleming

Mitchell Diamond

Rajiv Deodhar

Daniel Woodworth

Jinjie Tang

Jim Sukha

Alan G Gara

Pratik M Marolia

Aamer Jaleel

Michael C Adler

Ping Tak Peter Tang

Chinmay Ashok

Uma Srinivasan

Joshua Cranmer

Rohan Sharma

Chiachen Chou

Neal C Crago

Arvind Sudarsanam

Dounia Khaldi

Louise Huot

Sergey Dmitriev

Niall D Mcdonnell

Michael A O'HANLON

Embodiments of systems, methods, and apparatuses for heterogeneous computing are described. In some embodiments, a hardware heterogeneous scheduler dispatches instructions for execution on one or more plurality of heterogeneous processing elements, the instructions corresponding to a code fragment to be processed by the one or more of the plurality of heterogeneous processing elements, wherein the instructions are native instructions to at least one of the one or more of the plurality of heterogeneous processing elements.

Systems, methods, and apparatuses for heterogeneous computing

Systems, methods, and apparatuses relating to operations in a configurable spatial accelerator are described. In one embodiment, a configurable spatial accelerator includes a first processing element that includes a configuration register within the first processing element to store a configuration value that causes the first processing element to perform an operation according to the configuration value, a plurality of input queues, an input controller to control enqueue and dequeue of values into the plurality of input queues according to the configuration value, a plurality of output queues, and an output controller to control enqueue and dequeue of values into the plurality of output queues according to the configuration value.

Apparatuses, methods, and systems for operations in a configurable spatial accelerator

Systems, apparatuses and methods may provide for technology that detects one or more local variables in source code, wherein the local variable(s) lack dependencies across iterations of a loop in the source code, automatically generate pipeline execution code for the local variable(s), and incorporate the pipeline execution code into an output of a compiler. In one example, the pipeline execution code includes an initialization of a pool of buffer storage for the local variable(s).

Automatic compiler dataflow optimization to enable pipelining of loops with local storage requirements

Various embodiments are generally directed to optimizing dataflow in automated transformation frameworks (e.g., compiler, runtime, etc.) for spatial architectures (e.g., Configurable Spatial Accelerator) that translate high-level user code into forms that use 'streams' (e.g., Latency Insensitive Channels, line buffers) to reduce overhead, eliminate or improve the efficiency of redundant memory accesses, and improve overall throughput.

Integration of automated complier dataflow optimizations

Systems, methods, and apparatuses relating to debugging a configurable spatial accelerator are described. In one embodiment, a processor includes a plurality of processing elements and an interconnect network between the plurality of processing elements to receive an input of a dataflow graph comprising a plurality of nodes, wherein the dataflow graph is to be overlaid into the interconnect network and the plurality of processing elements with each node represented as a dataflow operator in the plurality of processing elements, and the plurality of processing elements are to perform an operation by a respective, incoming operand set arriving at each of the dataflow operators of the plurality of processing elements. At least a first of the plurality of processing elements is to enter a halted state in response to being represented as a first of the plurality of dataflow operators.

Processors, methods, and systems for debugging a configurable spatial accelerator

Systems, methods, and apparatuses relating to swizzle operations and disable operations in a configurable spatial accelerator (CSA) are described. Certain embodiments herein provide for an encoding system for a specific set of swizzle primitives across a plurality of packed data elements in a CSA. In one embodiment, a CSA includes a plurality of processing elements, a circuit switched interconnect network between the plurality of processing elements, and a configuration register within each processing element to store a configuration value having a first portion that, when set to a first value that indicates a first mode, causes the processing element to pass an input value to operation circuitry of the processing element without modifying the input value, and, when set to a second value that indicates a second mode, causes the processing element to perform a swizzle operation on the input value to form a swizzled input value before sending the swizzled input value to the operation circuitry of the processing element, and a second portion that causes the processing element to perform an operation indicated by the second portion the configuration value on the input value in the first mode and the swizzled input value in the second mode with the operation circuitry.

Apparatuses, methods, and systems for swizzle operations in a configurable spatial accelerator

Systems, methods, and apparatuses relating to in-network storage for a configurable spatial accelerator are described. In one embodiment, a configurable spatial accelerator includes a plurality of processing elements; a circuit switched interconnect network between the plurality of processing elements to receive an input of a dataflow graph comprising a plurality of nodes, wherein the dataflow graph is to be overlaid into the circuit switched interconnect network and the plurality of processing elements with each node represented as a dataflow operator in the plurality of processing elements, and the plurality of processing elements are to perform an operation by a respective, incoming operand set arriving at each of the dataflow operators of the plurality of processing elements; and an in-network storage element of the circuit switched interconnect network comprising a queue coupled to an output queue of a first processing element, and a controller that switches the in-network storage element into a first mode that provides a value stored in the queue of the in-network storage element by the output queue of the first processing element to an input queue of a second processing element when a configuration value is a first value, and into a second mode that bypasses the queue of the in-network storage element and provides a value from the output queue of the first processing element to the input queue of the second processing element when the configuration value is a second value.

Apparatuses, methods, and systems for in-network storage in a configurable spatial accelerator

An integrated circuit includes a memory interface, coupled to a memory to store data corresponding to instructions, and an operations queue to buffer memory operations corresponding to the instructions. The integrated circuit may include acceleration hardware to execute a sub-program corresponding to the instructions. A set of input queues may include an address queue to receive, from the acceleration hardware, an address of the memory associated with a second memory operation of the memory operations, and a dependency queue to receive, from the acceleration hardware, a dependency token associated with the address. The dependency token indicates a dependency on data generated by a first memory operation of the memory operations. A scheduler circuit may schedule issuance of the second memory operation to the memory in response to the dependency queue receiving the dependency token and the address queue receiving the address.

Memory ordering in acceleration hardware

Systems, methods, and apparatuses relating to a configurable spatial accelerator are described. In one embodiment, a processor includes a core with a decoder to decode an instruction into a decoded instruction and an execution unit to execute the decoded instruction to perform a first operation; a plurality of processing elements; and an interconnect network between the plurality of processing elements to receive an input of a dataflow graph comprising a plurality of nodes, wherein the dataflow graph is to be overlaid into the interconnect network and the plurality of processing elements with each node represented as a dataflow operator in the plurality of processing elements, and the plurality of processing elements is to perform a second operation when an incoming operand set arrives at the plurality of processing elements.

Processors, methods, and systems with a configurable spatial accelerator

Methods and apparatuses relating to distributed memory hazard detection and error recovery are described. In one embodiment, a memory circuit includes a memory interface circuit to service memory requests from a spatial array of processing elements for data stored in a plurality of cache banks; and a hazard detection circuit in each of the plurality of cache banks, wherein a first hazard detection circuit for a speculative memory load request from the memory interface circuit, that is marked with a potential dynamic data dependency, to an address within a first cache bank of the first hazard detection circuit, is to mark the address for tracking of other memory requests to the address, store data from the address in speculative completion storage, and send the data from the speculative completion storage to the spatial array of processing elements when a memory dependency token is received for the speculative memory load request.

Memory circuits and methods for distributed memory hazard detection and error recovery

Systems, methods, and apparatuses relating to a configurable spatial accelerator are described. In one embodiment, a processor includes a synchronizer circuit coupled between an interconnect network of a first tile and an interconnect network of a second tile and comprising storage to store data to be sent between the interconnect network of the first tile and the interconnect network of the second tile, the synchronizer circuit to convert the data from the storage between a first voltage or a first frequency of the first tile and a second voltage or a second frequency of the second tile to generate converted data, and send the converted data between the interconnect network of the first tile and the interconnect network of the second tile

Growing community of inventors

Merrimack, NH, United States of America

Kent D Glossop