Marger Johnson & Mccollom Pc

Richard Rubinstein

Stuart Hawkinson

Ron Coleman

Brent LeBack

An architecture is shown where an execution unit is tightly coupled to a shared, reconfigurable memory system. Sequence control signals drive a DMA controller and address generator to control the transfer of data from the shared memory to a bus interface unit (BIU). The sequence control signals also drive a data controller and address generator which controls transfer of data from the shared memory to an execution unit interface (EUI). The EUI is connected to the execution unit operates under control of the data controller and address generator to transfer vector data to and from the shared memory. The shared memory is configured to swap memory space in between the BIU and the execution unit so as to support continuous execution and I/O. A local fast memory is coupled to the execution unit. A local address generator controls the transfer of scalar data between the local fast memory and the execution unit. The execution unit, local fast memory and local address generator form a fast memory path that is not dependent upon the slower data path between the execution unit and shared memory. The fast memory path provides for fast execution of scalar operations in the execution unit and rapid state storage and retrieval for operations in the execution unit.

Tightly coupled and scalable memory and execution unit architecture

Methods and apparatus are disclosed for interfacing a processor bus or CPU to a computation engine to carry out selected tasks with improved efficiency in the computation engine. The computation engine is controlled by an MCC memory-centric controller that provides microcoded operation of the engine independently of the CPU. Essential interfacing between the processor bus and the computation engine includes storing microcode in a separate memory accessible to the MCC controller, or downloading microcode from the CPU/processor bus as needed for a specific task. The MCC controller can reconfigure the computation engine, such as memory block allocation, word size, etc. under microcode control, so that new or user-proprietary algorithms such as those used in dsp can be implemented using a standard computation engine without redesign. Execution of selected tasks on the computation engine is triggered automatically by decoding instructions that appear on the processor bus. Such tasks can include dsp, compression, decompression, encryption or other complex computations, and further can include downloading new or updated microcode into the computation engine desired.

Growing community of inventors

Santa Cruz, CA, United States of America

Richard Rubinstein