Xilinx, Inc.

U.S. Philips Corporation

Xilinix, Inc.

Ralph D Wittig

Sundararajarao Mohan

Philip Bryn James-Roxby

Bernard J New

Eric F Dellinger

L James Hwang

Henry E Styles

Sujoy Mitra

Juan J Noguera Serra

Vinod Kumar Kathail

Shail Aditya Gupta

Baris Ozgul

Richard A Carberry

Kornelis Antonius Vissers

Jan Langer

Richard Lewis Walke

Satish R Ganesan

Samuel R Bayliss

Goran H K Bilski

Mark Paluszkiewicz

Richard S Ballantyne

Christopher H Dick

Jennifer Wong

Cameron D Patterson

Goran Hk Bilski

David B Squires

Chia-Jui Hsu

Usha Prabhu

Tim Tuan

Sonal Santan

David W Bennett

David Clarke

Robert Anders Johnson

Goran Bilski

Akella Sastry

Fernando J Martinez Vallina

Sheng Zhou

Jeffrey M Fifield

Devadas Varma

Steven P Young

Ashish Sirasao

Alireza S Kaviani

Hem C Neema

Kumar Deepak

Jorge Ernesto Carrillo

Hamish T Fallside

Amit Kasat

Ehsan Ghasemi

Peter McColgan

Mukund Sivaraman

Kristof Denolf

Brendan K Bridgford

Jimmy Zhenming Wang

Sean Settle

Christoffel Wijenberg

Rishi Surendran

Navaneethan Sundaramoorthy

Zachary Blair

Sivakumar Velusamy

Ajit K Agarwal

Catalin Baetoniu

Vasanth Asokan

Bernardus L M Van Bakel

Sundarajarao Mohan

Charles Kwok-Wah Lo

Alireza Khodamoradi

Charles Kwah-Wah Lo

Robert M McGee

Richard DeFelice

Sathyanarayanan Thammanur

Kwok-Wah Lo

A method for operating a computing system includes determining a baseline accuracy of the computing system based on a baseline data transmission format comprising a baseline quantity of data bits and a baseline quantity of error correction (ECC) bits, determining sample accuracies of the computing system based on sample data transmission formats each including a quantity of data bits and a quantity of ECC bits that are different from the baseline quantity of data bits and the baseline quantity of ECC bits, and storing data in a memory device of the computing system using at least one data transmission format, wherein the at least one data transmission format is selected from a group of data transmission formats comprising the baseline data transmission format and the sample data transmission formats and the at least one data transmission is selected based on the baseline accuracy and the sample accuracies.

Reclamation of memory ECC bits for error tolerant number formats

A device includes a data processing engine array having a plurality of data processing engines organized in a grid having a plurality of rows and a plurality of columns. Each data processing engine includes a core, a memory module including a memory and a direct memory access engine. Each data processing engine includes a stream switch connected to the core, the direct memory access engine, and the stream switch of one or more adjacent data processing engines. Each memory module includes a first memory interface directly coupled to the core in the same data processing engine and one or more second memory interfaces directly coupled to the core of each of the one or more adjacent data processing engines.

Data processing engine arrangement in a device

Embodiments herein use control application programming interfaces (APIs) to control the execution of a dataflow graph in a heterogeneous processing system. That is, embodiments herein describe a programming model along with associated APIs and methods that can control, interact, and at least partially reconfigure a user application (e.g., the dataflow graph) executing on the heterogeneous processing system through a local executing control program. Using the control APIs, users can manipulate such remotely executing graphs directly as local objects and perform control operations on them (e.g., for loading and initializing the graphs; dynamically adjusting parameters for adaptive control; monitoring application parameters, system states and events; scheduling operations to read and write data across the distributed memory boundary of the platform; controlling the execution life-cycle of a subsystem; and partially reconfiguring the computing resources for a new subsystem).

Control and reconfiguration of data flow graphs on heterogeneous computing platform

A device may include a plurality of data processing engines. Each of the data processing engines may include a memory pool having a plurality of memory banks, a plurality of cores each coupled to the memory pool and configured to access the plurality of memory banks, a memory mapped switch coupled to the memory pool and a memory mapped switch of at least one neighboring data processing engine, and a stream switch coupled to each of the plurality of cores and to a stream switch of the at least one neighboring data processing engine.

Examples herein describe techniques for generating dataflow graphs using source code for defining kernels and communication links between those kernels. In one embodiment, the graph is formed using nodes (e.g., kernels) which are communicatively coupled by edges (e.g., the communication links between the kernels). A compiler converts the source code into a bit stream and/or binary code which configure a heterogeneous processing system of a SoC to execute the graph. The compiler uses the graph expressed in source code to determine where to assign the kernels in the heterogeneous processing system. Further, the compiler can select the specific communication techniques to establish the communication links between the kernels and whether synchronization should be used in a communication link. Thus, the programmer can express the dataflow graph at a high-level (using source code) without understanding about how the operator graph is implemented using the heterogeneous hardware in the SoC.

Dataflow graph programming environment for a heterogenous processing system

Examples herein describe techniques for communicating between data processing engines in an array of data processing engines. In one embodiment, the array is a 2D array where each of the DPEs includes one or more cores. In addition to the cores, the data processing engines can include a memory module (with memory banks for storing data) and an interconnect which provides connectivity between the engines. To transmit processed data, a data processing engine identifies a destination processing engine in the array. Once identified, the data processing engine can transmit the processed data using a reserved point-to-point communication path in the interconnect that couples the source and destination data processing engines.

Streaming interconnect architecture for data processing engine array

A device may include a plurality of data processing engines. Each of the data processing engines may include a core and a memory module. The plurality of data processing engines may be organized in a plurality of rows. Each core may be configured to communicate with other neighboring data processing engines of the plurality of data processing engines by shared access to the memory modules of the neighboring data processing engines.

An example method of implementing an application for a system-on-chip (SOC) having a data processing engine (DPE) array includes determining a graph representation of the application, the graph representation including nodes representing kernels of the application and edges representing communication between the kernels, mapping, based on the graph, the kernels onto DPEs of the DPE array and data structures of the kernels onto memory in the DPE array, routing communication channels between DPEs and circuitry of the application configured in programmable logic of the SOC, and generating implementation data for programming the SOC to implement the application based on results of the mapping and the routing.

Compilation flow for a heterogeneous multi-core architecture

Examples described herein relate to dynamically structured single instruction, multiple data (SIMD) instructions, and systems and circuits implementing such dynamically structured SIMD instructions. An example is a method for processing data. A first SIMD structure is determined by a processor. A characteristic of the first SIMD structure is altered by the processor to obtain a second SIMD structure. An indication of the second SIMD structure is communicated from the processor to a numerical engine. Data is packed by the numerical engine into an SIMD instruction according to the second SIMD structure. The SIMD instruction is transmitted from the numerical engine.

Dynamically structured single instruction, multiple data (SIMD) instructions

A device may include a plurality of data processing engines. Each data processing engine may include a core and a memory module. Each core may be configured to access the memory module in the same data processing engine and a memory module within at least one other data processing engine of the plurality of data processing engines.

Device with data processing engine array

An integrated circuit (IC) includes a first region being static and providing an interface between the IC and a host processor. The first region includes a first interconnect circuit block having a first master interface and a second interconnect circuit block having a first slave interface. The IC includes a second region coupled to the first region. The second region implements a kernel of a heterogeneous, multiprocessor design and includes a slave interface coupled to the first master interface of the first interconnect circuit block and configured to receive commands from the host processor. The second region also includes a master interface coupled the first slave interface of the second interconnect circuit block, wherein the master interface of the second region is a master for a memory controller.

Heterogeneous multiprocessor platform targeting programmable integrated circuits

OpenCL program compilation may include generating, using a processor, a register transfer level (RTL) description of a first kernel of a heterogeneous, multiprocessor design and integrating the RTL description of the first kernel with a base platform circuit design. The base platform circuit design provides a static interface within a programmable integrated circuit to a host of the heterogeneous, multiprocessor design. A first configuration bitstream may be generated from the RTL description of the first kernel using the processor. The first configuration bitstream specifies a hardware implementation of the first kernel and supporting data for the configuration bitstream. The first configuration bitstream and the supporting data may be included within a binary container.

Heterogeneous multiprocessor program compilation targeting programmable integrated circuits

An embodiment of a method for a high-assurance operation is disclosed. For this embodiment of the method, a first processor and a second processor are clocked for lockstep operation. A first physical address and a first transaction request are provided to a shared bus from the first processor. A second physical address and a second transaction request are provided to the shared bus from the second processor. The first physical address, the first transaction request, the second physical address, and the second transaction request are passed to a proxy device coupled to the shared bus. The first processor and the second processor are proxy served by the proxy device including generation of a third transaction request and a third physical address by the proxy device.

Transaction-level lockstep

Growing community of inventors

Menlo Park, CA, United States of America

Ralph D Wittig