Texas Instruments Corporation

Brooktree Corporation

Michael D Asal

Karl M Guttag

Richard D Simpson

Mark F Novak

Jeffrey L Nye

Jerry R Van Aken

Neil Tebbutt

James G Littleton

Iain Craig Robertson

Graham B Short

Thomas Preston

Gary L Swoboda

Thomas A Dye

David Cureton Baker

Anthony J Lell

Todd T Hahn

Eric J Stotzer

Derek Roskell

John Sharkey

Jonathan I Siann

Michael A Denio

Matthew Damian Bates

Paul B Wood

Carrell R Killebrew, Jr

Stephen G Glennon

William S Egr

Steven B Ehlers

Douglas C Crawford

Ian J Sherlock

Karl W Guttag

Graham Short

Novak Mark F

Systems and methods for transferring control between programs of different security levels are described herein. Some embodiments include a processor capable of operating at one or more security levels including a first and a second security level, a memory system coupled to the processor (the memory system stores a first program that executes on the processor at the first security level, and a second program that executes on the processor at the second security level), and a register configured to store an entry point address to the first program (wherein an instruction that executes on the processor at the second security level is blocked from writing values to the register). A transfer of control from the second program to the first program is executed if the register provides the entry point address. The transfer of control is blocked if the entry point address is not provided by the register.

Transferring control between programs of different security levels

Disclosed herein is a system and method of operating a processor before and after a reset has been asserted. Prior to a reset being asserted the processor operates in one of a plurality of states wherein primary code may be executed by the processor depending on said state. Upon a reset being asserted the processor begins executing code for a reset routine. The processor also executes a process such that the processor operates in the same state it was in prior to the reset upon the reset no longer being asserted.

Automatic halting of a processor in debug mode due to reset

This invention is useful in a very long instruction word data processor that fetches a predetermined plural number of instructions each operation cycle. A predetermined one of these instructions is used as a special header. This special header has a unique encoding different from any normal instruction. When decoded this special header instructs decode hardware to decode this fetch packet in a special way. In one embodiment a bit field in the header signals the decode hardware whether to decode each instruction word normally or in an alternative way. The header may include extension opcode bits corresponding to each of the other instruction slots. In another embodiment another bit field signals whether to decode an instruction field as one normal length instruction or as two half-length instructions.

VLIW optional fetch packet header extends instruction set space

This invention employs a 16-bit instruction set that has a subset of the functionality of the 32-bit instruction set. In this invention 16-bit instructions and 32-bit instructions can coexist in the same fetch packet. In the prior architecture 32-bit instructions may not span a 32-bit boundary. The 16-bit instruction set is implemented with a special fetch packet header that signals whether the fetch packet includes some 16-bit instructions. This fetch packet header also has special bits that tell the hardware how to interpret a particular 16-bit instruction. These bits essentially allow overlays on the whole or part of the 16-bit instruction space. This makes the opcode space larger permitting more instructions than with a pure 16-bit opcode space.

Software source transfer selects instruction word sizes

An access circuit for data swapping between two computers and a computer system including the access circuit. Each computer including an address bus for supplying addresses and a data bus for transferring data. The access circuit includes a register file and two address decoder circuits. The register file has a plurality of storage locations for storing data. The register file has dual data ports capable of simultaneous data transfer via the first data port with a first data storage location and via the second data port with a second, different storage location. Each address decoder is connected to the address bus of a corresponding computer and the register file. The address decoders translate an address received on the address bus to a storage location of the register file. Two handshakes circuits are connected to respective address decoders and digital computers. The first and second address decoders are connected to each other. When the storage location of the first address decoder equals the storage location of the second address decoder, one of the handshake circuits signals the corresponding digital computer a memory waitstate or memory fault. At least one of the decoders is be programmable to position in the address space of the corresponding computer. At least one the address decoders includes an autoincrement circuit advances the accessed storage location within the register file to a next storage location upon each data transfer.

Two computer access circuit using address translation into common register file

A multifunction access circuit for use with first and second digital computers each having an address bus for supplying addresses and a data bus for supplying data. The access circuit has an address decoder with inputs for the address bus from the first computer, and an address translator circuit having address inputs for addresses supplied by the address bus of the first computer and outputs for translated addresses to the address bus of the second computer. The address translator circuit also has registers selectable by the address decoder and data inputs to program the registers so selected with data from the data bus from the first computer. Also in the access circuit is a port circuit with registers controlled by the address decoder for entry of address information from the data bus of the first computer and assertion of the address information on the address bus of the second computer. Further, a mode control circuit is connected to the address decoder and connected to the data bus to program the mode control circuit to selectively establish operation of the address translator circuit and of the port circuit. Other access circuits, devices, systems and methods are also described.

Multifunctional access devices, systems and methods

Multimedia information (e.g. graphics, video, sound, control information) passes through a system bus from a CPU main memory to a display memory in accordance with CPU commands. The information may be packetized with associated packet types identifying the different media. A media stream controller processes the information and passes the processed information to the display memory. Controllers in the media stream controller individually pass multimedia information to the display memory. A PACDAC controller in the media stream controller causes media (e.g. graphics, video) in the display memory to be transferred to a PACDAC for display. The format, sequence, and rate of this transfer may be flexibly controlled by software on a frame by frame basis. Arbitration logic establishes priorities for the different controllers in the media stream controller so they may share a single bus for accessing the display memory. A single interrupt controller coordinates interrupts (e.g. at a single level) to provide priorities based upon the type of interrupt cause or media. Each interrupt cause activates only the appropriate callback functions. Two different virtual machine sessions (e.g. Windows, DOS) share an interrupt line to process interrupt requests form one (1) session (e.g. Windows) before processing interrupt requests from the other.

Using prioritized interrupt callback routines to process different types

The graphics data processor of the present invention offers as a single instruction in its instruction set a draw and advance operation. A first data register stores a set of X and Y coordinates. In a first embodiment, a predetermined color code is stored at the pixel address of a bit mapped display memory indicated by the X and Y coordinates the first data register upon execution of the the draw and advance instruction. The X and Y coordinates stored in the first data register are then advanced by addition of X and Y coordinates stored in a second data register. A second embodiment is similar except that the color code stored at the X and Y coordinates of the first date register is recalled for combining with the predetermined color code and the combined result stored at that pixel location. The predetermined color code is preferrably stored in another data register. By proper selection of the X and Y coordinate data stored in the second data register either the X or the Y coordinate may be altered alone or both may by simultaneously changed. Provision of signed X and Y coordinate values in the second register enables either the X or Y coordinate to be incremented of decremented. This instruction serves to inhance the speed at which a line or computed curve may by drawn in the bit mapped display.

Process of processing graphics data

A system for processing a stream of data and automatically selecting a portion or all of the data stream for block writing to a memory. The memory is capable of storing data in response to a block write command and a normal write command. The system contains a first data register and a second data register having the same data width. The first data register accepts data from the data stream in accordance with the its data width. Data stored in the first data register is transferred to the second data register. The first data register is then loaded with a portion of the data stream which is contiguous to the data stored in the first data register prior to the transferring. The data in the first and the second data registers is then compared. If the data in the first and the second registers is the same, then the content of a data counter is increased by one. When the content of the data counter exceeds a predetermined value, the system executes a block write command.

Apparatus and methods for automatically controlling block writes

A CPU introduces software commands to a first limited capacity memory (e.g. FIFO), on an integrated circuit chip. Data (e.g. graphics) from a first portion of a second memory (off chip) is processed in accordance with such commands. A second portion (e.g. FIFO) of the second memory may also store commands normally passing from the CPU through the first memory. When the first memory becomes full, the commands may pass from the CPU through the second portion of the second memory (which may have a storage capacity considerably greater than that of the first memory) and then through the first memory. The commands may continue to flow in this auxiliary path until the second portion of the second memory becomes empty. A third memory of a limited capacity on the chip may pass the commands from the CPU to the first memory in the normal operation or to the second portion of the second memory when the first memory becomes full. The CPU may also pass commands to other peripheral equipment while a ready line is high. When low, the ready line prevents commands from passing to the peripheral equipment while the third memory is full. However, a command may pass from the third memory to the first or second memory to make the ready line high. A counter indicates the number of commands in the first and third memories and the second portion of the second memory. Software occasionally interrogates the counter to update in the software the number of commands in the counter.

System for, and method of, processing in hardware commands received from

A computer graphics system includes a host computer and a graphics processor. The graphics processor includes a control register. When the graphics processor writes to the control register it simultaneously generates a predetermined address on a local address bus and supplies data on a local data bus identical to data to be written into the control register. A shadow register circuit connected to both the host computer and the graphics processor includes a shadow register and first and second address decoders. The first address decoder enables a write from a local data bus into the shadow register upon detection of the predetermined address. The second address decoder enables a read from the shadow register via a host data bus upon detection of the predetermined address on a host address bus. The shadow register optionally includes a message in plurality of bits and a message out plurality of bits, the first and second address decoders enabling message passing between the host computer and the graphics processor. The shadow register circuit optionally includes a host interrupt bit and a buffer circuit. The buffer circuit generates a host interrupt signal to the host computer if either the graphics processor generates a host interrupt signal or the host interrupt bit of the shadow register has a predetermined state.

Graphics processor writing to shadow register at predetermined address

A memory access system for use with a graphics processor having an address bus, a data bus and a set of control lines. An address translator circuit connected to the address bus of the graphics processor supplies a translated address to a memory upon receipt of an address from the graphics processor. A logic circuit responds to a write signal to automatically increment the translated address and responds to a control signal to return to the translated address. Control circuitry connected to the logic circuit responds to a read signal to supply the control signal to the logic circuit.

Memory access circuit with address translation performing auto increment

A graphics computer system including a host computer and a graphics processor. The host computer has a host data bus and a host address bus. A first video memory stores color codes corresponding to a display. The first video memory is connected to the host computer permitting it to specify the color codes. A first palette connected to the first video memory has a first look-up table memory for recalling color data words corresponding to color codes received from the first video memory. The first palette is connected to the host computer permitting it to specify the color data words stored in the first look-up table memory. The graphics processor has a local data bus and a local address bus. A second video memory stores color codes corresponding to a display, the graphics processor specifying the color codes stored in the second video memory. A second palette connected to the second video memory has a second look-up table memory. The second palette is connected to the graphics processor permitting it to specify the color data words stored in the second look-up table memory. An interface circuit connects to the host data bus, the host address bus and the second palette. The interface circuit writes data received from the host data bus into the second palette upon detecting predetermined addresses on the host address bus. This causes at least a portion of the second palette to store identical data as stored in corresponding locations of the first palette.

Graphics computer system having a second palette shadowing data in a

A display buffer includes a plurality of memory banks, each said bank having a plurality of ordered rows of data storage locations. Circuitry controls the storage of a plurality of sequenced lines of display data in said display buffer. A first set of lines of display data is stored at contiguous locations in a first memory bank with the first word of a first line being stored in a location offset from the first location of the first row so a last word of a last line is stored in the last location of the last row. A second set of lines is stored at contiguous locations starting at the first row of the second memory bank. A last line of the second set of lines is stored so that the last word of this last line is stored in the last location of a selected row of the second bank. A third set of lines is stored in a third memory bank starting at a memory line other than the first memory line. If additional space is needed, the display lines wrap around to the first location of the first line of the third bank of memories. A graphics processor may provide the memory addressing and bank selection logic.

Growing community of inventors

Sugarland, TX, United States of America

Michael D Asal