National Semiconductor Corporation

Gary D Phillips

Christopher M Hall

David W Weinrich

Robert M Salter, Iii

William E Miller

Richard E Crippen

Thomas W Thomson

Ralph W Haines

D Kevin Covey

An architecture for a serial multi-chip package digital controller including a controller oriented processor die and a separate non-volatile memory die. The architecture provides for a low pin count on the package, minimal electrical connections on and between the dice, and a minimal number of registers by making use of significant multiplexing to allow many of the registers and signal lines to serve multiple functions responsive to the mode of operation and other control signals. An input data register on the non-volatile memory die and a related multiplexer allows data from different sources to be loaded into the input data register depending on the mode of operation. Also, the output of the input data register is coupled to plural locations so that the destination of the data can also be switched responsive to the mode of operation. Particularly, the output of the input data register is coupled to an output port, a program data register (through which program data can be loaded into the program memory), and a control register for setting various control bits for performing specific integrity tests which can be performed following fabrication. Accordingly, the input data register is used for programming the memory from an external source, setting control bits from an external device, and sending data from the processor to the R port and on to external devices.

Non-volatile memory control and data loading architecture for multiple

An architecture for a serial multi-chip package digital controller including a controller oriented processor die and a separate non-volatile memory die. The architecture provides for a low pin count on the package, minimal electrical connections on and between the dice, and a minimal number of registers by making use of significant multiplexing to allow many of the registers and signal lines to serve multiple functions responsive to the mode of operation and other control signals.

Serial register multi-input multiplexing architecture for multiple chip

An architecture for a serial multi-chip package digital controller including a controller oriented processor die and a separate non-volatile memory die. The architecture provides for a low pin count on the package, minimal electrical connections on and between the dice, and a minimal number of registers by making use of significant multiplexing to allow many of the registers and signal lines to serve multiple functions responsive to the mode of operation and other control signals. A plurality of feed-throughs are provided on the non-volatile memory die to provide communication paths from the processor die to package pads which are in the shadow of the non-volatile memory die relative to the processor die and thus prevent direct connection from the processor die to the package pad. In normal run mode, these pads are exclusively used as feed-through, providing a direct connection between a specific pad on the processor die and a specific pad on the package. In other modes of operation, however, the signals input from (or output to) the feed-through package pads are re-routed by transfer gates to the non-volatile memory die.

Multiple chip package processor having feed through paths on one die

An architecture for a serial multi-chip package digital controller including a controller oriented processor die and a separate non-volatile memory die. The architecture provides for a low pin count on the package, minimal electrical connections on and between the dice, and a minimal number of registers by making use of significant multiplexing to allow many of the registers and signal lines to serve multiple functions responsive to the mode of operation and other control signals. A reset intercept circuit is provided on the non-volatile memory die for intercepting the signal which is provided to the reset input of the non-volatile memory die from external of the multi chip package. The reset intercept circuit provides a modified version thereof to the processor die. Particularly, the reset intercept circuit performs the function of sending a modified version of the reset signal to the processor die responsive to the present mode of operation of the multi chip package at the time the reset signal is received.

Multiple chip processor architecture with reset intercept circuit

An architecture for a serial multi-chip package digital controller including a controller oriented processor die and a separate non-volatile memory die. The architecture provides for a low pin count on the package, minimal electrical connections on and between the dice, and a minimal number of registers by making use of significant multiplexing to allow many of the registers and signal lines to serve multiple functions responsive to the mode of operation and other control signals. The processor includes an in-system programming mode including first and second memory interface control registers on the processor die and the memory die, respectively, for receiving control bits from the processor core for controlling multiplexers on the dies. The various bit output lines of the first memory interface control register are coupled to the control inputs of the multiplexers.

Multiple chip processor architecture with memory interface control

An architecture for a serial multi-chip package digital controller including a controller oriented processor die and a separate non-volatile memory die. The architecture provides for a low pin count on the package, minimal electrical connections on and between the dice, and a minimal number of registers by making use of significant multiplexing to allow many of the registers and signal lines to serve multiple functions responsive to the mode of operation and other control signals. The processor can be programmed internally or externally. In the in-system programming mode, the processor program counter is used to fetch running instructions out of an on-board ROM instruction memory on the processor die. The processor core outputs an address into which data is to be programmed on its output data bus. The processor core then receives from an external device the data which is to be programmed into the selected address and outputs it serially onto the data bus and therefrom to the memory die. The address and program data are then parallel output from separate registers on the memory die along with a program pulse to program the memory core.

In-system programming architecture for a multiple chip processor

An arithmetic unit for multiplying and accumulating signed binary data and indicating an occurrence of a signed arithmetic overflow includes a multiplier-accumulator and an overflow flag register. The multiplier-accumulator receives and selectively multiples and accumulates signed binary data, and provides output data representing the multiplied and accumulated data and a sign bit representing its polarity, i.e. positive or negative. The flag register provides two 'sticky' flag bits for indicating whether a signed arithmetic overflow (positive or negative) of the multiplied and accumulated data has occurred. The flag bits are 'sticky' in that once a flag has been set, it cannot be reset by another arithmetic overflow condition. Instead, it must be specifically reset. The sign bit is used to selectively set one of the two sticky flag bits to a true state to indicate the direction (positive or negative) of the first arithmetic overflow. The sticky flag bits have mutually exclusive true states in that once a flag bit has been set true, the other flag bit cannot be set true until both flag bits have been specifically reset.

Signed overflow sticky bits

An integrated circuit (IC) processor architecture is disclosed that implements hardware, signal processing (DSP) functions with less digital improved speed and a more efficient layout. The resources of the central processing unit (CPU) are used in conjunction with an integrated multiply/accumulate unit to perform DSP operations. Internal registers of the CPU are used to store pointers which reference a circular sample buffer. The CPU thus manages the selection and transfer of coefficients from the sample buffer to the multiply/accumulate unit, thereby allowing a minimum amount of lower speed hardware to be used for the multiply/accumulate unit and permitting DSP operations to be performed in parallel with CPU operations.

CPU with integrated multiply/accumulate unit

An integrated circuit processor architecture that implements digital signal processing (DSP) functions with less hardware, improved speed and a more efficient layout. The central processing unit (CPU) resources are used in conjunction with an integrated multiply/accumulate unit to perform DSP operations. Use of the CPU's internal register for the circular buffer of the DSP multiply/accumulate function allows a minimum amount of lower speed hardware to be used for the multiply/accumulate unit and permits DSP operations to be performed in parallel. The multiply/accumulate unit takes advantage of the inherent accumulating properties of conventional multiplier designs to perform multiplication of two signed binary numbers using the modified Booth's algorithm but in both reduced cycle time and hardware requirements. This is accomplished by using the adder within the multiplier to sum the product terms. Instead of clearing the adder of the result of one multiplication before beginning another, the result is maintained and all subsequent partial products are added to it to generate a final output. The placement of the 32-bits of the multiply/accumulate unit's multiplicand register is arranged in two rows of 8 even bits and two rows of 8 odd bits to allow left shift by two with a single loop around and to provide direct interface with the 16-bit data latch register on its input and the rest of the 32-bit arithmetic logic unit (ALU) on its output.

Growing community of inventors

San Jose, CA, United States of America

Gary D Phillips