Abstract: Efficient computation of complex multiplication results and very efficient fast Fourier transforms (FFTs) are provided. A parallel array VLIW digital signal processor is employed along with specialized complex multiplication instructions and communication operations between the processing elements which are overlapped with computation to provide very high performance operation. Successive iterations of a loop of tightly packed VLIWs are used allowing the complex multiplication pipeline hardware to be efficiently used. In addition, efficient techniques for supporting combined multiply accumulate operations are described.

Abstract: Various approaches for motion search refinement in a processing element are discussed. A k/2+L+k/2 register stores an expanded row of an L×L macro block. A k-tap filter horizontally interpolates over the expanded row generating horizontal interpolation results. A transpose storage unit stores the interpolated results generated by the k-tap filter for k/2+L+k/2 entries, wherein rows or columns of data may be read out of the transpose storage unit in pipelined register stages. A k-tap filter vertically interpolates over the pipelined register stages generating vertical interpolation results.

Abstract: Hardware and software techniques for interrupt detection and response in a scalable pipelined array processor environment are described. Utilizing these techniques, a sequential program execution model with interrupts can be maintained in a highly parallel scalable pipelined array processing containing multiple processing elements and distributed memories and register files. When an interrupt occurs, interface signals are provided to all PEs to support independent interrupt operations in each PE dependent upon the local PE instruction sequence prior to the interrupt. Processing/element exception interrupts are supported and low latency interrupt processing is also provided for embedded systems where real time signal processing is required. Further, a hierarchical interrupt structure is used allowing a generalized debug approach using debut interrupts and a dynamic debut monitor mechanism.

Abstract: Hardware and software techniques for interrupt detection and response in a scalable pipelined array processor environment are described. Utilizing these techniques, a sequential program execution model with interrupts can be maintained in a highly parallel scalable pipelined array processing containing multiple processing elements and distributed memories and register files. When an interrupt occurs, interface signals are provided to all PEs to support independent interrupt operations in each PE dependent upon the local PE instruction sequence prior to the interrupt. Processing/element exception interrupts are supported and low latency interrupt processing is also provided for embedded systems where real time signal processing is required. Further, a hierarchical interrupt structure is used allowing a generalized debug approach using debug interrupts and a dynamic debut monitor mechanism.

Abstract: Techniques are described for efficient reordering of data and performing data exchanges within a register file or memory, or in general, any device storing data that is accessible through a set of addressable locations. An address translator is placed in the path of all or a selected set of address busses to a storage device to provide a programmable and selectable means of translating the storage device addresses. An effect of this translation is that the data stored in one pattern may be accessed and stored in another pattern or accessed, processed and stored in another pattern. The address translation operation may be carried out in a single cycle, does not involve the physical movement of data in swap operations, allows data to effectively be ordered more efficiently for algorithmic processing and therefore saves power.

Abstract: Various approaches for motion search refinement in a processing element are discussed. A k/2+L+k/2 register stores an expanded row of an L×L macro block. A k-tap filter horizontally interpolates over the expanded row generating horizontal interpolation results. A transpose storage unit stores the interpolated results generated by the k-tap filter for k/2+L+k/2 entries, wherein rows or columns of data may be read out of the transpose storage unit in pipelined register stages. A k-tap filter vertically interpolates over the pipelined register stages generating vertical interpolation results.

Abstract: Processor pipeline controlling techniques are described which take advantage of the variation in critical path lengths of different instructions to achieve increased performance. By examining a processor's instruction set and execution unit implementation's critical timing paths, instructions are classified into speed classes. Based on these speed classes, one pipeline is presented where hold signals are used to dynamically control the pipeline based on the instruction class in execution. An alternative pipeline supporting multiple classes of instructions is presented where the pipeline clocking is dynamically changed as a result of decoded instruction class signals. A single pass synthesis methodology for multi-class execution stage logic is also described. For dynamic class variable pipeline processors, the mix of instructions can have a great effect on processor performance and power utilization since both can vary by the program mix of instruction classes.

Abstract: Techniques are described for decoupling fetching of an instruction stored in a main program memory from earliest execution of the instruction. An indirect execution method and program instructions to support such execution are addressed. In addition, an improved indirect deferred execution processor (DXP) VLIW architecture is described which supports a scalable array of memory centric processor elements that do not require local load and store units.

Abstract: Details of a highly cost effective and efficient implementation of a manifold array (ManArray) architecture and instruction syntax for use therewith are described herein. Various aspects of this approach include the regularity of the syntax, the relative ease with which the instruction set can be represented in database form, the ready ability with which tools can be created, the ready generation of self-checking codes and parameterized test cases. Parameterizations can be fairly easily mapped and system maintenance is significantly simplified.

Abstract: Apparatus and methods for scalable block pixel filtering are described. A block filtering instruction is issued to a processing element (PE) to initiate block pixel filtering hardware by causing at least one command and at least one parameter be sent to a command and control function associated with the PE. A block of pixels is fetched from a PE local memory to be stored in a register file of a hardware assist module. A sub-block of pixels is processed to generate sub-block parameters and the block of pixels is filtered in a horizontal/vertical edge filtering computation pipeline using the sub-block parameters.

Abstract: A multi-node video signal processor (VSPN) is describes that tightly couples multiple multi-cycle state machines (hardware assist units) to each processor and each memory in each node of an N node scalable array processor. VSPN memory hardware assist instructions are used to initiate multi-cycle state machine functions, to pass parameters to the multi-cycle state machines, to fetch operands from a node's memory, and to control the transfer of results from the multi-cycle state machines.

Abstract: Hardware and software techniques for interrupt detection and response in a scalable pipelined array processor environment are described. Utilizing these techniques, a sequential program execution model with interrupts can be maintained in a highly parallel scalable pipelined array processing containing multiple processing elements and distributed memories and register files. When an interrupt occurs, interface signals are provided to all PEs to support independent interrupt operations in each PE dependent upon the local PE instruction sequence prior to the interrupt. Processing/element exception interrupts are supported and low latency interrupt processing is also provided for embedded systems where real time signal processing is required. Further, a hierarchical interrupt structure is used allowing a generalized debug approach using debut interrupts and a dynamic debut monitor mechanism.

Abstract: Apparatus and methods for scalable block pixel filtering are described. A block filtering instruction is issued to a processing element (PE) to initiate block pixel filtering hardware by causing at least one command and at least one parameter be sent to a command and control function associated with the PE. A block of pixels is fetched from a PE local memory to be stored in a register file of a hardware assist module. A sub-block of pixels is processed to generate sub-block parameters and the block of pixels is filtered in a horizontal/vertical edge filtering computation pipeline using the sub-block parameters.

Abstract: A Wings array system for communicating between nodes using store and load instructions is described. Couplings between nodes are made according to a 1 to N adjacency of connections in each dimension of a G×H matrix of nodes, where G?N and H?N and N is a positive odd integer. Also, a 3D Wings neural network processor is described as a 3D G×H×K network of neurons, each neuron with an N×N×N array of synaptic weight values stored in coupled memory nodes, where G?N, H?N, K?N, and N is determined from a 1 to N adjacency of connections used in the G×H×K network. Further, a hexagonal processor array is organized according to an INFORM coordinate system having axes at 60 degree spacing. Nodes communicate on row paths parallel to an FM dimension of communication, column paths parallel to an IO dimension of communication, and diagonal paths parallel to an NR dimension of communication.

Abstract: Various approaches for motion search refinement in a processing element are discussed. A k/2+L+k/2 register stores an expanded row of an L×L macro block. A k-tap filter horizontally interpolates over the expanded row generating horizontal interpolation results. A transpose storage unit stores the interpolated results generated by the k-tap filter for k/2+L+k/2 entries, wherein rows or columns of data may be read out of the transpose storage unit in pipelined register stages. A k-tap filter vertically interpolates over the pipelined register stages generating vertical interpolation results.

Abstract: Hardware and software techniques for interrupt detection and response are provided in a scalable pipelined array processor environment. Utilizing these techniques, a sequential program execution model with interrupts can be maintained in a highly parallel scalable pipelined array processing containing multiple processing elements and distributed memories and register files. When an interrupt occurs, interface signals are provided to all PEs to support independent interrupt operations in each PE dependent upon the local PE instruction sequence prior to the interrupt. Processing/element exception interrupts are supported and low latency interrupt processing is also provided for embedded systems where real time signal processing is required. Further, a hierarchical interrupt structure is used allowing a generalized debug approach using debug interrupts and a dynamic debug monitor mechanism.

Abstract: A multi-node video signal processor (VSPN) is describes that tightly couples multiple multi-cycle state machines (hardware assist units) to each processor and each memory in each node of an N node scalable array processor. VSPN memory hardware assist instructions are used to initiate multi-cycle state machine functions, to pass parameters to the multi-cycle state machines, to fetch operands from a node's memory, and to control the transfer of results from the multi-cycle state machines.

Abstract: A Wings array system for communicating between nodes using store and load instructions is described. Couplings between nodes are made according to a 1 to N adjacency of connections in each dimension of a G×H matrix of nodes, where G?N and H?N and N is a positive odd integer. Also, a 3D Wings neural network processor is described as a 3D G×H×K network of neurons, each neuron with an N×N×N array of synaptic weight values stored in coupled memory nodes, where G?N, H?N, K?N, and N is determined from a 1 to N adjacency of connections used in the G×H×K network. Further, a hexagonal processor array is organized according to an INFORM coordinate system having axes at 60 degree spacing. Nodes communicate on row paths parallel to an FM dimension of communication, column paths parallel to an IO dimension of communication, and diagonal paths parallel to an NR dimension of communication.

Abstract: Processor pipeline controlling techniques are described which take advantage of the variation in critical path lengths of different instructions to achieve increased performance. By examining a processor's instruction set and execution unit implementation's critical timing paths, instructions are classified into speed classes. Based on these speed classes, one pipeline is presented where hold signals are used to dynamically control the pipeline based on the instruction class in execution. An alternative pipeline supporting multiple classes of instructions is presented where the pipeline clocking is dynamically changed as a result of decoded instruction class signals. A single pass synthesis methodology for multi-class execution stage logic is also described. For dynamic class variable pipeline processors, the mix of instructions can have a great effect on processor performance and power utilization since both can vary by the program mix of instruction classes.

Abstract: Details of a highly cost effective and efficient implementation of a manifold array (ManArray) architecture and instruction syntax for use therewith are described herein. Various aspects of this approach include the regularity of the syntax, the relative ease with which the instruction set can be represented in database form, the ready ability with which tools can be created, the ready generation of self-checking codes and parameterized test cases. Parameterizations can be fairly easily mapped and system maintenance is significantly simplified.