Abstract: Using scalable scribe regions for implementing a user circuit design includes generating a scribe region having a plurality of contours for a static top design of a circuit design for an integrated circuit. The static top design is configured to integrate with a user circuit design in the integrated circuit. Each contour defines a different size of the scribe region having a boundary that extends outward in at least one direction from a boundary of a floorplan area of the static top design on the IC. The scribe region can be translated into design constraints defining the plurality of contours of the scribe region and restrict placement of components of the user circuit design within the scribe region as sized according to a selected contour. The static top design and the plurality of design constraints can be stored in a memory for use in implementing the user circuit design.

Abstract: Systems and methods for automated systolic array design from a high-level program are disclosed. One implementation of a systolic array design supporting a convolutional neural network includes a two-dimensional array of reconfigurable processing elements arranged in rows and columns. Each processing element has an associated SIMD vector and is connected through a local connection to at least one other processing element. An input feature map buffer having a double buffer is configured to store input feature maps, and an interconnect system is configured to pass data to neighboring processing elements in accordance with a processing element scheduler. A CNN computation is mapped onto the two-dimensional array of reconfigurable processing elements using an automated system configured to determine suitable reconfigurable processing element parameters.

Abstract: The present invention provides a beamforming antenna (100, 200, 400) comprising a plurality of antenna elements (101, 102, 201, 202, 401, 402, 440), and a signal generator (103, 403) that is configured to generate for each one of the antenna elements (101, 102, 201, 202, 401, 402, 440) a calibration signal (106, 107, 206, 406, 335) for radiation by the respective antenna element (101, 102, 201, 202, 401, 402, 440) and to supply the generated calibration signals (106, 107, 206, 406, 335) to the respective antenna elements (101, 102, 201, 202, 401, 402, 440).

Abstract: Embodiments herein describe techniques for preventing a stall when transmitting data between a producer and a consumer in the same integrated circuit (IC). A stall can occur when there is a split point and a convergence point between the producer and consumer. To prevent the stall, the embodiments herein adjust the latencies of one of the paths (or both paths) such that a maximum latency of the shorter path is greater than, or equal to, the minimum latency of the longer path. When this condition is met, this means the shortest path has sufficient buffers (e.g., a sufficient number of FIFOs and registers) to queue/store packets along its length so that a packet can travel along the longer path and reach the convergence point before the buffers in the shortest path are completely full (or just become completely full).

Abstract: An antenna assembly is provided having passive cooling elements that enable compact design. In one example, an antenna assembly is provided that includes a heat sink assembly having an interior side and an exterior side, an antenna array, an antenna circuit board, and a radome. The antenna circuit board includes at least one integrated circuit (IC) die. The IC die has a conductive primary heat dissipation path to the interior side of the heat sink assembly. The radome is coupled to the heat sink assembly and encloses the antenna circuit board and the antenna array between the radome and the heat sink assembly. The heat sink assembly includes a metal base plate and at least a first heat pipe embedded with the metal base plate. The first heat pipe is disposed between the metal base plate and the IC die.

Abstract: Sharing integrated circuit (IC) resources can include receiving, within a communication endpoint of an IC, a plurality of packets from a plurality of different source virtual entities, determining packet handling data for each packet of the plurality of packets using an acceleration function table stored within the IC, routing each packet of the plurality of packets to one or more selected function circuit blocks of a plurality of function circuit blocks in the IC based on the packet handling data of each respective packet, and processing the plurality of packets using the one more selected function circuit blocks generating a plurality of results corresponding to respective ones of the plurality of packets. The plurality of results are queued within the communication endpoint. Each result is queued based on the packet handling data of the corresponding packet.

Abstract: Techniques and apparatus for reducing low frequency power supply spurs in clock signals. One example circuit generally includes a first power supply circuit configured to generate a first power supply voltage on a first power supply rail, a second power supply circuit configured to generate a second power supply voltage on a second power supply rail, a clock distribution network, and a feedback circuit coupled between the second power supply rail and at least one input of the first power supply circuit. The feedback circuit may be configured to sense the second power supply voltage, to process the sensed second power supply voltage, and to output at least one feedback signal to control the first power supply circuit based on the processed second power supply voltage. The clock distribution network may include first and second sets of clock drivers powered by the first and second power supply voltages, respectively.

Abstract: A device may include a processor system and an array of data processing engines (DPEs) communicatively coupled to the processor system. Each of the DPEs includes a core and a DPE interconnect. The processor system is configured to transmit configuration data to the array of DPEs, and each of the DPEs is independently configurable based on the configuration data received at the respective DPE via the DPE interconnect of the respective DPE. The array of DPEs enable, without modifying operation of a first kernel of a first subset of the DPEs of the array of DPEs, reconfiguration of a second subset of the DPEs of the array of DPEs.

Abstract: Predicting performance of a circuit design includes determining memory access patterns of kernels of the circuit design for implementation in an integrated circuit (IC) and generating a plurality of different floorplans. Each floorplan specifies a mapping of memory interfaces of the kernels to memories of the selected IC and an allocation of the kernels to a plurality of programmable pattern generator (PPG) circuit blocks of a circuit architecture implemented in the IC. The plurality of different floorplans are executed using the circuit architecture in the IC. The plurality of PPG circuit blocks mimic the memory access patterns of the kernels for each of the plurality of different floorplans during the executing. One or more design constraints are generated based on a selected floorplan. The selected floorplan is selected from the plurality of different floorplans based on one or more performance metrics determined from the executing.

Abstract: Predicting performance of a circuit design includes determining memory access patterns of kernels of the circuit design for implementation in an integrated circuit (IC) and generating a plurality of different floorplans. Each floorplan specifies a mapping of memory interfaces of the kernels to memories of the selected IC and an allocation of the kernels to a plurality of programmable pattern generator (PPG) circuit blocks of a circuit architecture implemented in the IC. The plurality of different floorplans are executed using the circuit architecture in the IC. The plurality of PPG circuit blocks mimic the memory access patterns of the kernels for each of the plurality of different floorplans during the executing. One or more design constraints are generated based on a selected floorplan. The selected floorplan is selected from the plurality of different floorplans based on one or more performance metrics determined from the executing.

Abstract: Implementing a design for a heterogeneous device can include mapping, using computer hardware, a plurality of applications of a design for a device to a plurality of domains of the device, wherein each domain includes a different compute unit, performing, using the computer hardware, validity checking on the plurality of applications, detecting, using the computer hardware, a conflict between two or more of the plurality of applications from the validity checking, and, in response to the detecting, generating a notification of the conflict using the computer hardware. Operations such as automatically generating a boot image, debugging, and/or performing system level performance analysis may also be performed.

Abstract: 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.

Abstract: Using multiple overlays with a data processing array includes loading an application in a data processing array. The data processing array includes a plurality of compute tiles each having a processor. The application specifies kernels executable by the processors and implements stream channels that convey data to the plurality of compute tiles. During runtime of the application, a plurality of overlays are sequentially implemented in the data processing array. Each overlay implements a different mode of data movement in the data processing array via the stream channels. For each overlay implemented, a workload is performed by moving data to the plurality of compute tiles based on the respective mode of data movement.

Abstract: An integrated circuit includes a data processing array. The data processing array includes a plurality of compute tiles each having a processor. The integrated circuit includes an array controller coupled to the data processing array. The array controller is adapted to configure the plurality of compute tiles of the data processing array to implement an application. The application specifies kernels executable by the processors and stream channels that convey data to the plurality of compute tiles. The array controller is configured to initiate execution of workloads by the data processing array as configured with the application.

Abstract: Systems and methods for training a neural network model includes providing a quantization function including a quantization log threshold parameter associated with a log value of a quantization threshold. A quantization training to a neural network model is performed to generate quantized neural network parameters. The quantization training includes: generating first values with a first precision for the neural network parameters; performing a first optimization process to generate an updated quantization log threshold parameter; and generating quantized values with a second precision lower than the first precision for the neural network parameters by applying the quantization function with the updated quantization log threshold parameter to the first values. The neural network model with the quantized values for the neural network parameters is provided for performing a task.

Abstract: Examples herein describe an accelerator device that shares the same coherent domain as hardware elements in a host computing device. The embodiments herein describe a mix of hardware and software coherency which reduces the overhead of managing data when large chunks of data are moved from the host into the accelerator device. In one embodiment, an accelerator application executing on the host identifies a data set it wishes to transfer to the accelerator device to be processed. The accelerator application transfers ownership from a home agent in the host to the accelerator device. A slave agent can then take ownership of the data. As a result, any memory operation requests received from a requesting agent in the accelerator device can gain access to the data set in local memory via the slave agent without the slave agent obtaining permission from the home agent in the host.

Abstract: Examples herein describe a peripheral I/O device with a hybrid gateway that permits the device to have both I/O and coherent domains. As a result, the compute resources in the coherent domain of the peripheral I/O device can communicate with the host in a similar manner as CPU-to-CPU communication in the host. The dual domains in the peripheral I/O device can be leveraged for machine learning (ML) applications. While an I/O device can be used as an ML accelerator, these accelerators previously only used an I/O domain. In the embodiments herein, compute resources can be split between the I/O domain and the coherent domain where a ML engine is in the I/O domain and a ML model is in the coherent domain. An advantage of doing so is that the ML model can be coherently updated using a reference ML model stored in the host.

Abstract: Circuits and methods involve an integrated circuit (IC) device, a plurality of application-specific sub-circuits, and a plurality of instances of a measuring circuit. The application-specific sub-circuits are disposed within respective areas of the IC device. Each instance of the measuring circuit is associated with one of the application-specific sub-circuits and is disposed within a respective one of the areas of the device. Each instance of the measuring circuit further includes a ring oscillator and a register for storage of a value indicative of an interval of time. Each instance of the measuring circuit is configured to measure passage of the interval of time based on a first clock signal, count oscillations of an output signal of the ring oscillator during the interval of time, and output a value indicating a number of oscillations counted during the interval of time.

Abstract: Approaches for visualizing data buses in a circuit design include determining ones of the data buses that satisfy selection criteria. For each element connected to a data bus of the ones of the data buses, a method and system determine whether the element is of interest or the element is not of interest. A graphical representation of the ones of the data buses and each element of interest is generated, and data buses of the circuit design determined to not satisfy the selection criteria and elements not of interest are excluded from the graphical representation. The graphical representation is displayed on a display device.

Abstract: Approaches for placing logic of a circuit design include determining respective relative activation rates of control paths in a high-level language (HLL) program by a design tool. The HLL program specifies a circuit design. The design tool compiles the HLL program into logic functions and determines respective relative activation rates of signal connections between the logic functions based on the relative activation rates of the control paths in the HLL program. The design tool selects placement locations on an integrated circuit device for the logic functions using a placement cost minimization function that factors the relative activation rates of the signal connections into placement costs.