Abstract: 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.

Abstract: Embodiments herein describe techniques for interfacing a neural network application with a neural network accelerator using a library. The neural network application may execute on a host computing system while the neural network accelerator executes on a massively parallel hardware system, e.g., a FPGA. The library operates a pipeline for submitting the tasks received from the neural network application to the neural network accelerator. In one embodiment, the pipeline includes a pre-processing stage, an FPGA execution stage, and a post-processing stage which each correspond to different threads. When receiving a task from the neural network application, the library generates a packet that includes the information required for the different stages in the pipeline to perform the tasks. Because the stages correspond to different threads, the library can process multiple packets in parallel which can increase the utilization of the neural network accelerator on the hardware system.

Abstract: Supporting multiple clients on a single programmable integrated circuit (IC) can include implementing a first image within the programmable IC in response to a first request for processing to be performed by the programmable IC, wherein the request is from a first process executing in a host data processing system coupled to the programmable IC, receiving, using a processor of the host data processing system, a second request for processing to be performed on the programmable IC from a second and different process executing in the host data processing system while the programmable IC still implements the first image, comparing, using the processor, a second image specified by the second request to the first image, and, in response to determining that the second image matches the first image based on the comparing, granting, using the processor, the second request for processing to be performed by the programmable IC.

Abstract: 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.

Abstract: An integrated circuit (IC) may include a scheduler for hardware acceleration. The scheduler may include a command queue having a plurality of slots and configured to store commands offloaded from a host processor for execution by compute units of the IC. The scheduler may include a status register having bit locations corresponding to the slots of the command queue. The scheduler may also include a controller coupled to the command queue and the status register. The controller may be configured to schedule the compute units of the IC to execute the commands stored in the slots of the command queue and update the bit locations of the status register to indicate which commands from the command queue are finished executing.

Abstract: An integrated circuit (IC) can include a command queue having a plurality of slots corresponding to commands from a host processor for execution by a plurality of compute units of the IC and a command request register having a plurality of locations corresponding to the plurality of slots in the command queue. The command request register is configured to generate an interrupt indicating a new command stored within the command queue. The IC can include a controller configured to, in response to the interrupt from the command request register, determine a selected compute unit that is idle from the plurality of compute units to execute the new command. The IC can also include a compute unit direct memory access circuit configured to provide the new command to the available compute unit.

Abstract: An integrated circuit (IC) can include a command queue having a plurality of slots corresponding to commands from a host processor for execution by a plurality of compute units of the IC and a command request register having a plurality of locations corresponding to the plurality of slots in the command queue. The command request register is configured to generate an interrupt indicating a new command stored within the command queue. The IC can include a controller configured to, in response to the interrupt from the command request register, determine a selected compute unit that is idle from the plurality of compute units to execute the new command. The IC can also include a compute unit direct memory access circuit configured to provide the new command to the available compute unit.

Abstract: An integrated circuit (IC) may include a scheduler for hardware acceleration. The scheduler may include a command queue having a plurality of slots and configured to store commands offloaded from a host processor for execution by compute units of the IC. The scheduler may include a status register having bit locations corresponding to the slots of the command queue. The scheduler may also include a controller coupled to the command queue and the status register. The controller may be configured to schedule the compute units of the IC to execute the commands stored in the slots of the command queue and update the bit locations of the status register to indicate which commands from the command queue are finished executing.

Abstract: A heterogeneous computing system can include a host memory and a host processor. The host memory is configured to maintain a write task queue and a read task queue. The host processor is coupled to the host memory and a processing device. The host processor is adapted to store write tasks in the write task queue. The write tasks cause transfer of input data to the processing device. The processing device is adapted to perform offloaded functions. The host processor is adapted to store read tasks in the read task queue. The read tasks cause transfer of results from the offloaded functions from the processing device. The host processor is further adapted to maintain a number of direct memory access (DMA) worker threads corresponding to concurrent data transfer capability of the processing device. Each DMA worker thread is preconfigured to execute tasks from the write task queue or the read task queue.

Abstract: Embodiments herein describe techniques for interfacing a neural network application with a neural network accelerator using a library. The neural network application may execute on a host computing system while the neural network accelerator executes on a massively parallel hardware system, e.g., a FPGA. The library operates a pipeline for submitting the tasks received from the neural network application to the neural network accelerator. In one embodiment, the pipeline includes a pre-processing stage, an FPGA execution stage, and a post-processing stage which each correspond to different threads. When receiving a task from the neural network application, the library generates a packet that includes the information required for the different stages in the pipeline to perform the tasks. Because the stages correspond to different threads, the library can process multiple packets in parallel which can increase the utilization of the neural network accelerator on the hardware system.

Abstract: A PLD is configurable to efficiently implement a wide variety of user functions. The PLD includes a programmable interconnect circuit, programmable logic circuits, one-bit registers, selector circuits, and input/output blocks. The programmable interconnect circuit is configurable to connect the signal lines of its output ports to the signal lines of its input ports. The programmable logic circuits are configurable to implement a programmable function generating one-bit signal values from a respective output port of the programmable interconnect circuit. The one-bit registers store a respective one of these one-bit signal values. The programmable selector circuits are each coupled to output ports of a plurality of the one-bit registers, with each of these one-bit registers coupled to a respective one of the programmable logic circuits.

Abstract: A PLD is configurable to efficiently implement a wide variety of user functions. The PLD includes a programmable interconnect circuit, programmable logic circuits, one-bit registers, selector circuits, and input/output blocks. The programmable interconnect circuit is configurable to connect the signal lines of its output ports to the signal lines of its input ports. The programmable logic circuits are configurable to implement a programmable function generating one-bit signal values from a respective output port of the programmable interconnect circuit. The one-bit registers store a respective one of these one-bit signal values. The programmable selector circuits are each coupled to output ports of a plurality of the one-bit registers, with each of these one-bit registers coupled to a respective one of the programmable logic circuits.

Abstract: Fast logic sharing is created using a feedback path from the output logic macrocell of one functional block to the product term inputs of another function block without going through an advanced interconnect matrix (AIM). The fast feedback path may be provided from the macrocell after the product terms XOR gate without registering, and/or after the register in the macrocell. The fast logic sharing avoids the slow AIM for feedback logic, and allows additional resources to be borrowed from other function blocks with a limited delay penalty. In particular, delay penalties resulting from dividing wide operations requiring multiple product terms between the product terms of multiple functional blocks are significantly reduced.

Abstract: A method and apparatus for implementing incremental design changes. In various embodiments, primary outputs of a new design are compared for logical equivalence to corresponding primary outputs of a prior implementation. If the logic is equivalent, the implementation of the primary outputs from the prior implementation is reused to implement the corresponding primary outputs of the new design.

Abstract: A method and apparatus for implementing type-safe, heterogeneous object-oriented property lists. A library of classes and template classes implementing a heterogeneous property list is defined, wherein each object of the property list includes a property name and an associated property value of a selected property type. Instantiation of objects having equal property names and unequal property types is prevented with a constructor, and template functions are provided each of which accesses the objects of the property list according to a type of data passed to the function.

Abstract: A method for programming programmable logic devices (PLDs) having multiple function block types to implement a logic function, whereby the logic function is mapped into one of the function block types before being mapped into the remaining function block types. In one embodiment, a PLD containing both "fast" function blocks (FFBs) and "high density" function blocks (HDFBs) are programmed such that the FFBs are programmed prior to the HDFBs. This method maximizes the overall speed of an implemented logic function.

Abstract: A method for programming programmable logic devices (PLDs) having multiple function block types to implement a logic function, whereby the logic function is mapped into one of the function block types before being mapped into the remaining function block types. In one embodiment, a PLD containing both "fast" function blocks (FFBs) and "high density" function blocks (HDFBs) are programmed such that the FFBs are programmed prior to the HDFBs. This method maximizes the overall speed of an implemented logic function.