Abstract: A system and method for virtually addressing an array of accelerator tiles of a mixed-signal integrated circuit includes testing each of a plurality of distinct matrix multiply accelerator (MMA) tiles of a grid of MMA tiles, the grid of MMA tiles being defined by the plurality of distinct grid of MMA tiles being arranged in a plurality of rows and a plurality of columns along an integrated circuit, each of the plurality of distinct MMA tiles within the grid of MMA tiles having a distinct physical address on the integrated circuit; identifying one or more defective MMA tiles within the grid of MMA tiles based on the testing; and configuring the grid of MMA tiles with a plurality of virtual addresses for routing data to or routing data from one or more non-defective MMA tiles of grid of MMA tiles based on identifying the one or more defective MMA tiles.

Abstract: A system and method for virtually addressing an array of accelerator tiles of a mixed-signal integrated circuit includes testing each of a plurality of distinct matrix multiply accelerator (MMA) tiles of a grid of MMA tiles, the grid of MMA tiles being defined by the plurality of distinct grid of MMA tiles being arranged in a plurality of rows and a plurality of columns along an integrated circuit, each of the plurality of distinct MMA tiles within the grid of MMA tiles having a distinct physical address on the integrated circuit; identifying one or more defective MMA tiles within the grid of MMA tiles based on the testing; and configuring the grid of MMA tiles with a plurality of virtual addresses for routing data to or routing data from one or more non-defective MMA tiles of grid of MMA tiles based on identifying the one or more defective MMA tiles.

Abstract: A system and method for virtually addressing an array of accelerator tiles of a mixed-signal integrated circuit includes testing each of a plurality of distinct matrix multiply accelerator (MMA) tiles of a grid of MMA tiles, the grid of MMA tiles being defined by the plurality of distinct grid of MMA tiles being arranged in a plurality of rows and a plurality of columns along an integrated circuit, each of the plurality of distinct MMA tiles within the grid of MMA tiles having a distinct physical address on the integrated circuit; identifying one or more defective MMA tiles within the grid of MMA tiles based on the testing; and configuring the grid of MMA tiles with a plurality of virtual addresses for routing data to or routing data from one or more non-defective MMA tiles of grid of MMA tiles based on identifying the one or more defective MMA tiles.

Abstract: A system and method for virtually addressing an array of accelerator tiles of a mixed-signal integrated circuit includes testing each of a plurality of distinct matrix multiply accelerator (MMA) tiles of a grid of MMA tiles, the grid of MMA tiles being defined by the plurality of distinct grid of MMA tiles being arranged in a plurality of rows and a plurality of columns along an integrated circuit, each of the plurality of distinct MMA tiles within the grid of MMA tiles having a distinct physical address on the integrated circuit; identifying one or more defective MMA tiles within the grid of MMA tiles based on the testing; and configuring the grid of MMA tiles with a plurality of virtual addresses for routing data to or routing data from one or more non-defective MMA tiles of grid of MMA tiles based on identifying the one or more defective MMA tiles.

Abstract: A slave interface unit controls the exchange of data between a master processing unit and a plurality of slave processing units operating in the asynchronous transfer mode (ATM) of operation. The ATM slave interface unit has a receive unit and a transmit unit that exchange data cells and control signals with the ATM master processing unit. The receive unit and the transmit unit are coupled to a receive buffer storage unit and a transmit buffer storage unit, respectively. The receive buffer storage unit and the transmit buffer storage unit exchange data and control signals with the direct memory access unit. The ATM slave interface unit includes a configuration interface unit having a register that identifies the location in the data cell where the destination address is located and relates the destination address to the particular processing unit or memory location. The receive buffer unit uses the information in the register to determine the destination of the data cell.

Abstract: A data transfer control apparatus includes a channel controller and a transfer controller. The channel controller receives, prioritizes and queues data transfer requests. The transfer controller includes separate control of data source and data destination in a data transfer corresponding to the data transfer requests. The transfer controller includes a data transfer program register and active source and destination registers. The transfer controller operates from the active source and destination registers. Upon completion of a data transfer the transfer controller writes data transfer parameters from the data transfer program register to the active source and destination registers.

Abstract: A data transfer control apparatus includes a channel controller and plural transfer controllers. The channel controller receives, prioritizes and queues data transfer requests. An event to transfer controller table enables recall of a transfer controller number corresponding to the data transfer request. The plural transfer controllers are independent and can operate simultaneously in parallel. Each transfer controller includes a read bus interface and a write bus interface which arbitrate with other bus masters in the case of blocking accesses directed to interfering devices or address ranges.

Abstract: The configurable multiple write-enhanced EDMA of this invention processes multiple priority channels and utilizes as much write data bus as practical. A write queue stores write requests with their corresponding data width and priority. A dispatch circuit dispatches a highest priority maximum data width write request if that is the highest priority stored write request or if the prior dispatch was not a maximum data width write request. The dispatch circuit dispatches two write requests if their total data width is less than or equal to the maximum data width and they both have a priority higher than the highest priority maximum data width write request.

Abstract: A data transfer control apparatus includes a channel controller and a transfer controller. The channel controller receives, prioritizes and queues event signals and predetermined memory writes which trigger data transfer requests controlling the transfer controller. The event queue stores event numbers mapped to parameter memory locations storing data transfer parameters. The mapping table and the parameter memory are writeable via a memory mapped write operation. Memory protection registers store data indicative of permitted data accesses to the memory map.

Abstract: A data processing system with a microprocessor that has an instruction execution pipeline that includes fetch and decode stages and several functional execution units. Fetch packets contain a plurality of instruction words. Execution packets include a plurality of instruction words that can be executed in parallel by two or more execution units. An execution packet can span two or more fetch packets. An add (k) constant to program counter (ADDKPC) instruction is provided, such that a parameter specified by the ADDKPC instruction is combined with a value provided by a program counter of microprocessor. The ADDKPC instruction can also specify a number of delay slots after a branch instruction to be filled with virtual NOP instructions such that memory is not wasted with useless NOP instructions. An ADDKPC instruction can provide a relative address for use as a return address. A plurality of predicated ADDKPC instructions can provide a return address selected from a plurality of return addresses.

Abstract: The invention describes a modification of FIFO hardware to allow improved use of FIFOs for burst reading from or writing to a processor direct memory access unit via either an expansion bus or an external memory interface using FIFO flag initiated bursts. The hardware and FIFO signal modifications make the FIFO-DMA interface immune to deadlock conditions and generation of spurious interrupt events in the process of initiating burst transfers. The FIFO function is modified to synchronize the frame transfer on the digital signal processor even if the digital signal processor lacks this functionality. By delaying the programmable flag assertions within the FIFO until after the current burst is complete the DSP-FIFO interface may be made immune to deadlock conditions and generation of spurious events.

Abstract: A microprocessor 1 is described which includes a multi-channel serial port (MCSP) 120. MCSP 120 includes clock generation and frame sync generation circuitry 300, multi-channel selection circuitry 310, and companding circuitry 320. The clock generation and frame sync generation circuitry is configurable by means of a Serial Port Control Register SPCR, and Receive Control Register RCR, a Transmit Control Register XCR, a Sample Rate Generator Register SRGR, and Pin Control Register PCR. The multi-channel selection circuitry is configurable by means of a Multi-Channel Register MCR, a Receive Channel Enable Register RCER and a Transmit Channel Enable Register XCER. Companding circuitry 320 performs optional expansion or compression of received or transmitted data using &mgr;-LAW or A-LAW, as selected by the Receive Control Register or the Transmit Control Register.

Abstract: A slave interface unit controls the exchange of data between a master processing unit and a plurality of slave processing units operating in the asynchronous transfer mode (ATM) of operation. The ATM slave interface unit has a receive unit and a transmit unit that exchange data cells and control signals with the ATM master processing unit. The receive unit and the transmit unit are coupled to a receive buffer storage unit and a transmit buffer storage unit, respectively. The receive buffer storage unit and the transmit buffer storage unit exchange data and control signals with the direct memory access unit. The ATM slave interface unit includes a configuration interface unit having a register that identifies the location in the data cell where the destination address is located and relates the destination address to the particular processing unit or memory location. The receive buffer unit uses the information in the register to determine the destination of the data cell.

Abstract: In a data processing system have a master-state data processing unit and at least one slave-state data processing unit, the data processing units can be provided with an asynchronous transfer mode interface unit 18 for transferring data cells there between. The interface unit 18 provides and receives signals formatted in the Utopia protocol. The interface unit 18 includes processor acting as a state machine 181, 184 and a buffer out memory unit 182, 183 for buffering the data groups between the interface unit processor and the direct memory access unit of the data processing unit. The interface unit 18 can act in a receive mode and a transmit mode for a master-state data processing unit and can act in a receive mode 181, 182 and transmit mode 184, 183 in a slave-state data processing unit. An event signal provides an efficient exchange of transfer of data between the direct memory access unit 14 and the buffer memory storage unit 182, 183 in the slave mode.

Abstract: In a data processing system have a master-state data processing unit and at least one slave-state data processing unit, the data processing units can be provided with an asynchronous transfer mode interface unit for transferring data cells there between. The interface unit provides and receives signals formatted in the UTOPIA protocol. The interface unit includes processor acting as a state machine and a buffer out memory unit for buffering the data groups between the interface unit processor and the direct memory access unit of the data processing unit. The interface unit can act in a receive mode and a transmit mode for a master-state data processing unit and can act in a receive mode, and transmit mode in a slave-state data processing unit. An event signal provides an efficient exchange of transfer of data between the direct memory access unit and the buffer memory storage unit in the slave mode.

Abstract: A general purpose microprocessor architecture enabling more efficient computations of a type in which Boolean operations and arithmetic operations conditioned on the results of the Boolean operations are interleaved. The microprocessor is provided with a plurality of general purpose registers (“GPRs” 102)and an arithmetic logic unit (“ALU” 104), capable of performing arithmetic operations and Boolean operations. The ALU has a first input (108) and a second input (110), and an output (112), the first and second inputs receiving values stored in the GPRs. The output stores the results of the arithmetic logic unit operations in the GPRs. At least one of the GPRs is capable of receiving directly from the ALU a result of a Boolean operation. In one embodiment, at least one of the GPRs (PN)capable of receiving directly from the ALU a result of a Boolean operation is configured so as to cause the conditioning of an arithmetic operation of the ALU based on the value stored in the GPR.

Abstract: The present invention provide a method of implementing bit reversal using a subtree lookup table. In another aspect of the invention, a subtree lookup table is used to implement digit reversal.

Abstract: A microprocessor 1 is described which includes a direct memory access (DMA) circuitry 143. DMA 143 is interconnected with a program memory 23 and a data memory 22 and is operational to transfer data to or from these memories. DMA 143 is interconnected with a peripheral bus 110 and thereby to various peripherals internal to microprocessor 1. DMA 143 is also interconnected with an external memory interface 103 and thereby to various external memory circuits and peripherals external to microprocessor 1. An auxiliary channel control circuitry 160 provides DMA transfers by interacting with a peripheral such as host port 150 which has its own address generation circuitry. DMA 143 provides frame synchronization for triggering a frame transfer, or group of transfers. DMA 143 is auto-initialized through registers. DMA action complete pins DMAC0-3 indicate DMA status to external devices.

Abstract: A microprocessor, comprising a first set of functional units capable of performing parallel data operations, a second set of functional units capable of performing parallel data operations, and a data interconnection path connecting the first and second functional units.

Abstract: A microprocessor 1 is described which includes a multi-channel serial port (MCSP) 120. MCSP 120 includes clock generation and frame sync generation circuitry 300, multi-channel selection circuitry 310, and companding circuitry 320. The clock generation and frame sync generation circuitry is configurable by means of a Serial Port Control Register SPCR, and Receive Control Register RCR, a Transmit Control Register XCR, a Sample Rate Generator Register SRGR, and Pin Control Register PCR. The multi-channel selection circuitry is configurable by means of a Multi-Channel Register MCR, a Receive Channel Enable Register RCER and a Transmit Channel Enable Register XCER. Companding circuitry 320 performs optional expansion or compression of received or transmitted data using .mu.-LAW or A-LAW, as selected by the Receive Control Register or the Transmit Control Register.