Abstract: A reconfigurable hardware accelerator for computers combines a high-speed dataflow processor, having programmable functional units rapidly reconfigured in a network of programmable switches, with a stream processor that may autonomously access memory in predefined access patterns after receiving simple stream instructions. The result is a compact, high-speed processor that may exploit parallelism associated with many application-specific programs susceptible to acceleration.

Abstract: A hardware accelerator for computers combines a stand-alone, high-speed, fixed program dataflow functional element with a stream processor, the latter of which may autonomously access memory in predefined access patterns after receiving simple stream instructions and provide them to the dataflow functional element. The result is a compact, high-speed processor that may exploit fixed program dataflow functional elements.

Abstract: A dataflow accelerator including a control/command core, a scratchpad and a coarse grain reconfigurable array (CGRA) according to an exemplary embodiment is disclosed. The scratchpad may include a write controller to transmit data to an input vector port interface and to receive data from the input vector port interface. The CGRA may receive data from the input vector port interface and includes a plurality of interconnects and a plurality of functional units.

Abstract: According to exemplary embodiments, a method, processor, and system for accelerating a recurrent neural network are presented. A method of accelerating a recurrent neural network may include distributing from a first master core to each of a plurality of processing cores a same relative one or more columns of weight matrix data for each of a plurality of gates in the neural network, broadcasting a current input vector from the first master core to each of the processing cores, and processing each column of weight matrix data in parallel, at each of the respective processing cores.

Abstract: A method for performing acceleration of simultaneous access to shared data may include providing a plurality of groups of cores and a plurality of shared memory structures, providing a pod comprising the plurality of groups of cores linked by a common broadcast channel, and coordinating each shared memory structure to provide a logically unified memory structure. Each memory structure may be associated with a group of cores, and each group of cores may include one or more cores. The common broadcast channel may be operatively coupled to each shared memory structure. The coordinating each shared memory structure may include identifying a simultaneous read-reuse load to a first shared memory structure, fetching data corresponding to the simultaneous read-reuse load, and forwarding the data to shared memory structures other than the first shared memory structure and to groups of cores other than a first group of cores via the broadcast channel.

Abstract: According to exemplary embodiments, a method, processor, and system for accelerating a recurrent neural network are presented. A method of accelerating a recurrent neural network may include distributing from a first master core to each of a plurality of processing cores a same relative one or more columns of weight matrix data for each of a plurality of gates in the neural network, broadcasting a current input vector from the first master core to each of the processing cores, and processing each column of weight matrix data in parallel, at each of the respective processing cores.

Abstract: A method for performing acceleration of simultaneous access to shared data may include providing a plurality of groups of cores and a plurality of shared memory structures, providing a pod comprising the plurality of groups of cores linked by a common broadcast channel, and coordinating each shared memory structure to provide a logically unified memory structure. Each memory structure may be associated with a group of cores, and each group of cores may include one or more cores. The common broadcast channel may be operatively coupled to each shared memory structure. The coordinating each shared memory structure may include identifying a simultaneous read-reuse load to a first shared memory structure, fetching data corresponding to the simultaneous read-reuse load, and forwarding the data to shared memory structures other than the first shared memory structure and to groups of cores other than a first group of cores via the broadcast channel.

Abstract: According to some embodiments, a dataflow accelerator comprises a control/command core, a scratchpad and a coarse grain reconfigurable array (CGRA). The scratchpad comprises a write controller to transmit data to an input vector port interface and to receive data from the input vector port interface. The CGRA receives data from the input vector port interface where the CGRA comprising a plurality of interconnects and a plurality of functional units.

Abstract: A dataflow computer processor is teamed with a general computer processor so that program portions of an application program particularly suited to dataflow execution may be transferred to the dataflow processor during portions of the execution of the application program by the general computer processor. During this time the general computer processor may be placed in partial shutdown for energy conservation.

Abstract: A hardware accelerator for computers combines a stand-alone, high-speed, fixed program dataflow functional element with a stream processor, the latter of which may autonomously access memory in predefined access patterns after receiving simple stream instructions and provide them to the dataflow functional element. The result is a compact, high-speed processor that may exploit fixed program dataflow functional elements.

Abstract: A reconfigurable hardware accelerator for computers combines a high-speed dataflow processor, having programmable functional units rapidly reconfigured in a network of programmable switches, with a stream processor that may autonomously access memory in predefined access patterns after receiving simple stream instructions. The result is a compact, high-speed processor that may exploit parallelism associated with many application-specific programs susceptible to acceleration.

Abstract: A dataflow computer processor is teamed with a general computer processor so that program portions of an application program particularly suited to dataflow execution may be transferred to the dataflow processor during portions of the execution of the application program by the general computer processor. During this time the general computer processor may be placed in partial shutdown for energy conservation.

Abstract: Skip based control logic for first in first out buffer is disclosed. In one embodiment, an isochronous data packet placed in an isochronous receive first in first out (IRFIFO) buffer coupled to an isochronous receive direct memory access (IRDMA) is detected. Further, a header of the isochronous data packet is read. Furthermore, a validity of the isochronous data packet is determined. Also, a read operation of remaining data of the isochronous data packet is skipped if the isochronous data packet is determined as invalid.

Abstract: Skip based control logic for first in first out buffer is disclosed. In one embodiment, a host controller interface (HCI) device includes an isochronous receive first in first out (IRFIFO) buffer. The IRFIFO buffer includes a storage for storing an isochronous data packet received from a guest device. Further, the IRFIFO buffer includes a write pointer for pointing to a write address of the storage for a write operation. Furthermore, the IRFIFO buffer includes a read pointer for pointing to a read address of the storage for a read operation. In addition, the IRFIFO includes a control logic for incrementing the read pointer by a value of a skip parameter of a skip register if the isochronous data packet is not valid for the read operation.

Abstract: Skip based control logic for first in first out buffer is disclosed. In one embodiment, a host controller interface (HCI) device includes an isochronous receive first in first out (IRFIFO) buffer. The IRFIFO buffer includes a storage for storing an isochronous data packet received from a guest device. Further, the IRFIFO buffer includes a write pointer for pointing to a write address of the storage for a write operation. Furthermore, the IRFIFO buffer includes a read pointer for pointing to a read address of the storage for a read operation. In addition, the IRFIFO includes a control logic for incrementing the read pointer by a value of a skip parameter of a skip register if the isochronous data packet is not valid for the read operation.

Abstract: Skip based control logic for first in first out buffer is disclosed. In one embodiment, an isochronous data packet placed in an isochronous receive first in first out (IRFIFO) buffer coupled to an isochronous receive direct memory access (IRDMA) is detected. Further, a header of the isochronous data packet is read. Furthermore, a validity of the isochronous data packet is determined. Also, a read operation of remaining data of the isochronous data packet is skipped if the isochronous data packet is determined as invalid.

Abstract: A system and method of a skip based control logic for a first in first out (FIFO) buffer is disclosed. In one embodiment, a FIFO buffer system includes a storage for storing data, a write pointer for pointing to a write address of the storage for a write operation, and a read pointer for pointing to a read address of the storage for a read operation. Further, the FIFO buffer system includes a control logic for incrementing the read pointer based on a skip parameter of a skip register. The skip parameter is used to characterize a validity of the data for the read operation.

Abstract: A system and method of a skip based control logic for a first in first out (FIFO) buffer is disclosed. In one embodiment, a FIFO buffer system includes a storage for storing data, a write pointer for pointing to a write address of the storage for a write operation, and a read pointer for pointing to a read address of the storage for a read operation. Further, the FIFO buffer system includes a control logic for incrementing the read pointer based on a skip parameter of a skip register. The skip parameter is used to characterize a validity of the data for the read operation.