Xilinx, Inc.

Agilent Technologies, Inc.

Agilent Technoloiges, Inc.

Stephen P Rozum

Sonal Santan

Sudipto Chakraborty

Hem C Neema

David A Knol

Soren T Soe

Kyle Corbett

Pradip Jha

Yenpang Lin

Fernando J Martinez Vallina

Ryan Linderman

Susheel Kumar Puthana

Nik Cimino

Paul R Schumacher

Nabeel Shirazi

Sebastian Turullols

David T Crook

Salil Ravindra Raje

Pramod Chandraiah

Khang Kim Dao

Ravi Nagarajarao Kurlagunda

Ravinder Sharma

Henry E Styles

Jayaram Pvss

Eddie L Williamson

Julian M Kain

Sumit Roy

Suman Kumar Timmireddy

Yu Liu

Dinesh K Monga

Heera Nand

Yau-Tsun Steven Li

Kevin Lee Wible

Pradip Kar

Yong Li

Ch Vamshi Krishna

Anurag Dubey

Kaustuv Manji

Jeffrey M Fifield

Derrick S Woods

Siva Santosh Kumar Pyla

Steven K List

Bennet An

Michael Keilson

Eddie L Williamson, Jr

Fei Rui

Ethan T Parker

Remote kernel execution in a heterogeneous computing system can include executing, using a device processor of a device communicatively linked to a host processor, a device runtime and receiving from the host processor within a hardware submission queue of the device, a command. The command requests execution of a software kernel and specifies a descriptor stored in a region of a memory of the device shared with the host processor. In response to receiving the command, the device runtime, as executed by the device processor, invokes a runner program associated with the software kernel. The runner program can map a physical address of the descriptor to a virtual memory address corresponding to the descriptor that is usable by the software kernel. The runner program can execute the software kernel. The software kernel can access data specified by the descriptor using the virtual memory address as provided by the runner program.

Transparent and remote kernel execution in a heterogeneous computing system

Using a flat shell for an accelerator card includes reading a flat shell from one or more computer readable storage media using computer hardware, wherein the flat shell is a synthesized, unplaced, and unrouted top-level circuit design specifying platform circuitry. A kernel specifying user circuitry is synthesized using the computer hardware. The kernel is obtained from the one or more computer readable storage media. The synthesized kernel is linked, using the computer hardware, to the flat shell forming a unified circuit design. The unified circuit design is placed and routed, using the computer hardware, to generate a placed and routed circuit design specifying the platform circuitry and the user circuitry for implementation in an integrated circuit.

Flat shell for an accelerator card

A unified container file can be selected using computer hardware. The unified container file can include a plurality of files embedded therein used to configure a programmable integrated circuit (IC). The plurality of files can include a first partial configuration bitstream and a second partial configuration bitstream. The unified container file also includes metadata specifying a defined relationship between the first partial configuration bitstream and the second partial configuration bitstream for programming the programmable IC. The defined relationship can be determined using computer hardware by reading the metadata from the unified container file. The programmable IC can be configured, using the computer hardware, based on the defined relationship specified by the metadata using the first partial configuration bitstream and the second partial configuration bitstream.

Unified container for hardware and software binaries

An example computing system includes: a processing system, a hardware accelerator coupled to the processing system, and a software platform executing on the processing system. The hardware accelerator includes: a programmable integrated circuit (IC) configured with an acceleration circuit having a static region and a programmable region; a memory in the programmable IC configured to store metadata describing interface circuitry in at least one of the static region and the programmable region of the acceleration circuit. The software platform includes program code executable by the processing system to read the metadata from the memory of the hardware accelerator.

Data-driven platform characteristics capture and discovery for hardware accelerators

A computer program product can include a non-transitory computer readable storage medium storing a unified container. The unified container can include a header structure, wherein the header structure has a fixed length and specifies a number of section headers included in the unified container. The unified container can include a plurality of section headers equivalent to the number of section headers specified in the header structure. The unified container can include a plurality of data sections corresponding to the plurality of section headers on a one-to-one basis. The plurality of data sections includes a first data section including a hardware binary and a second data section including a software binary. The hardware binary and the software binary are configured to program a programmable integrated circuit. Each section header specifies a type of data stored in the corresponding data section and specifies a mapping for the corresponding data section.

Embodiments herein describe reconfigurable integrated circuits (ICs) which include programmable logic that can be configured to perform a user task. In one embodiment, the programmable logic is configured as an accelerator. The user may want to gather debug data or profiling data when executing the accelerator. Rather than using debug/profile circuitry disposed in a static region of the IC, the user can provide preferences to a linker which then dynamically configures debug/profile circuitry in a dynamic region of the IC. That is, based on user preferences, the linker can generate customized debug/profile circuitry for monitoring the performance of the accelerator. In one embodiment, the debug/profile circuitry is implemented in the dynamic region of the IC and is tailored to user preferences rather than relying on static, or fixed, debug/profile circuitry. Moreover, the user can retrieve the debug/profiling data on demand using a call back and a device driver.

Customizable debug and profile monitoring of reconfigurable systems

Modifying initialization data for a memory array of a circuit design can include providing, using a processor, portions of an incoming stream of data for initializing the memory array to emulation objects of a memory array emulator. The memory array emulator is configured to emulate an implementation of the memory array and the emulation objects represent block random access memories (block RAMs) of the memory array. Using the processor, the data can be formatted using the emulation objects to generate initialization data, wherein the data is formatted based upon configuration settings of the block RAMs emulated by the respective emulation objects. A configuration bitstream can be updated, using the processor, with the initialization data.

Updating block random access memory contents using memory emulation

Hardware acceleration for a kernel can include selecting, using a processor, a kernel, determining, using the processor, a clock frequency for the selected kernel, and programming, using the processor, a clock circuit to generate a clock signal having a clock frequency compatible with the clock frequency of the selected kernel. Using the processor, the selected kernel can be implemented as a kernel circuit within a region of programmable circuitry. The kernel circuit can be clocked using the clock signal from the clock circuit having the compatible clock frequency.

Adaptive compilation and execution for hardware acceleration

Implementing hardware accelerators using programmable integrated circuits may include performing, using a processor, a design flow on a static circuit design. The static circuit design may specify a region reserved for a hardware accelerator and a static region comprising interface circuitry configured to couple the hardware accelerator with an external node. The design flow may generate an implemented static circuit design. Metadata describing the interface circuitry may be generated using a processor. A device support archive including the implemented static circuit design and the metadata may be written, using the processor, to a computer readable storage medium.

Hardware acceleration device handoff for using programmable integrated circuits as hardware accelerators

A software development-based compilation flow for circuit design may include executing, using a processor, a makefile including a plurality of rules for hardware implementation. Responsive to executing a first rule of the plurality of rules, a source file including a kernel specified in a high level programming language may be selected; and, an intermediate file specifying a register transfer level implementation of the kernel may be generated using the processor. Responsive to executing a second rule of the plurality of rules, a configuration bitstream for a target integrated circuit may be generated from the intermediate file using the processor. The configuration bitstream includes a compute unit circuit implementation of the kernel.

Software development-based compilation flow for hardware implementation

Constraint handling for a circuit design may include determining, using a processor, instances of parameterizable modules of a circuit design associated with constraints based upon a predefined hardware description language attribute within the instances, extracting, using the processor, parameter values from the instances of the parameterizable modules, and generating, using the processor, static constraint files for the instances of the parameterizable modules using the extracted parameter values.

Constraint handling for parameterizable hardware description language

A method, non-transitory computer readable medium and apparatus for using an out-of-context sub-block in a hierarchical design flow for an integrated circuit are disclosed. For example, the method identifies one or more sub-blocks in the hierarchical design flow that are eligible for creating the out-of-context sub-block, receives a selection of one of the one or more sub-blocks that are eligible and creates the out-of-context sub-block for the one of the one or more sub-blocks that is selected.

Method and apparatus for unified out-of-context flow and automation for IP reuse and hierarchical design flows

A data accelerator for use in a test vector sequencer includes a data translator, a plurality of sequence memory devices, and a switch. The data translator and the switch are configured via a control signal responsive to an indication that a first sequence memory device is prepared to receive a data segment and that a second sequence memory device is prepared to transfer a previously stored data segment. The test sequencer forwards a first application segment to a first memory device and acquires a subsequent application with a second memory device, detects a condition responsive to the completion of the segment acquisition and forwarding tasks, switches the roles of the first and second memory devices, and repeatedly switches and detects until all application segments have been processed.

Data accelerator and methods for increasing data throughput

A method and system is presented for optimizing the number of required measurements to obtain in real-time by an automated tester that tests a device under test. During a test run, historical measurements are obtained and tracked. Each subsequent iteration the test attempts to re-measure the fewest number of measurements in real-time to obtain an accurate reflection of whether the device being tested passes or fails based on the real-time measurements and substituting historical measurements for those required measurements that were not taken in real-time.

Method and apparatus for adaptively learning test error sources to reduce the total number of test measurements required in real-time

Growing community of inventors

Loveland, CO, United States of America

Stephen P Rozum