Abstract:
A system, apparatus and a method for routing data over fewer switches and interconnections among reconfigurable logic elements, and for adapting routing resources to dynamically perform complex bit-level permutations, such as shifting and bit reversal operations. In one embodiment, an exemplary silo routing circuit is formed upon a semiconductor substrate and routes data among a number of reconfigurable computational elements. The silo routing circuit comprises a plurality of input terminals and a plurality of output terminals. Further, the silo routing circuit includes a multi-stage interconnection network (“MIN”) of switches configurable to form data paths from any input terminal to any output terminal.
Abstract:
A novel architecture for a multi-scale programmable logic array (MSA) to be used in the design of complex digital systems allows digital logic to be programmed using both small-scale blocks (also called gate level blocks) as well as medium scale blocks (also called Register Transfer Level or RTL blocks). The MSA concept is based on a bit sliceable Arithmetic Logic Unit (ALU). Each bit-slice may be programmed to perform a basic Boolean logic operation or may be programmed to contribute to higher-level functions that are further programmed by an ALU controller circuit. The ALU controller level in this new approach also allows the primitive logic operations computed at the bit-slice level to be combined to perform complex random logic operations. The data shifting capability of this new programmable logic architecture reduces the complexity of the programmable routing needed to implement shift operations including multiplier arrays. The new array also allows logic variables under program control to dynamically modify the micro-program of each ALU. This technique is called configuration overlay and simplifies the programming of complex arithmetic and random logic functions.
Abstract:
A system, apparatus and a method for implementing multifunctional memories is disclosed. The multifunctional memories perform a variety of functions during execution of extended instructions in a reconfigurable data path processor composed of processing nodes. In one embodiment, a processing node can be comprised of modular processing elements to perform computations associated with an extended instruction. Also, such a node includes at least two multifunctional memories and a data flow director configured to selectably couple the first multifunctional memory and the second multifunctional memory. The data flow director is configured to route data out from a first multifunctional memory of the two multifunctional memories while data is being routed into a second multifunctional memory. In another embodiment, a processing node is configured to compute a function output based on a number of Boolean functions, wherein at least one of the multifunctional memories is configured as a look-up table (“LUT”).