Abstract: A memory addressing device for data processing apparatus addresses in sequence and in a burst a series of memory locations in a single addressing period of a central processing unit. The device comprises enabling circuits to set a central processing unit (CPU) to a burst transfer cycle and to keep a memory control unit (MCU) in a waiting state during the burst transfer. An address generator circuit is capable of generating in sequence a series of memory address codes to address a series of locations in the memory (RAM) during the burst transfer cycle. A multiplexer circuit sends to the memory either the address code of the address generator or that of the memory control unit during the burst cycles and the normal cycles respectively. The device is particularly suitable for use in personal computers with high data transfer rates.

Abstract: A microcode controlled processor having an overwritable memory device for microcode storage includes a setting device for setting a virtual memory space and a conversion table device showing the relationship between the address information of the virtual memory space designated by the setting device and the address in a real memory space inclusive of the memory device. A predetermined address in the virtual memory space is designated to read out data and the contents of the conversion table device may be modified. In this manner, a large size program or a plurality of programs can be executed immediately without the size of the executable program being limited by the size of the real memory space.

Abstract: A nonvolatile memory and a method for controlling the nonvolatile memory to switch between first and second data widths are described. The nonvolatile memory includes a first memory array, a second memory array, a first plurality of data pads, and a second plurality of data pads. A data width control circuit selectively couples the first and second plurality of data pads to the first and second memory arrays. A data width configuration cell is provided for configuring data width of the nonvolatile memory. A data width select circuit controls the data width control circuit to selectively couple the first and second plurality of data pads to the first and second memory arrays under the control of the data width configuration cell. When the data width configuration cell is in a first state, the first and second memory arrays are coupled to the first and second plurality of data pads such that the nonvolatile memory has a first data width.

Abstract: A data processing system comprised of a memory, a translation lookaside buffer (TLB) providing access to the memory, and an instruction cache connected to the memory. A two entry translation write buffer (TWB) has a first entry that is a first logical register and an associated first physical address register and a second entry that is a second logical register and an associated second physical address register. A physical address bus is connected to the TWB and a logical address bus is connected to the TLB and to the TWB, the logical address bus presenting an instruction pointer to the TLB and to the TWB. The instruction pointer is comprised of logical address bits including upper order bits, lower order bits, and a single bit having a first value or a second value. The single bit provides for translation of even-number pages for which the single bit has the first value and for odd-number pages for which the single bit has the second value.

Abstract: A signal cache memory controller which includes line for inputting an index section of an address is formed with a branch line which is intervened by an address delay circuit. In each of banks X and Y, a switching circuit selects the data which has been delayed in response to a select signal Sse being outputted as a cache-access address to be outputted to a tag memory. An address comparator compares a tag section of the address input through a signal line for inputting the tag section with a reference address output from the tag memory and outputs an coincidence signal if there is a coincidence therebetween. When the coincidence signal is generated and the select signal Sse is not generated, a bank-hit signal generating circuit generated a bank-hit signal Sbh, in response to which a select-signal generating circuit generates the select signal Sse. The circuit for controlling a cache memory which is divided into a plurality of banks enables the writing of data in the cache in every cycle.

Abstract: A microcontroller device on a single integrated circuit including a central processing unit, an associated data bus and an electrically-programmable nonvolatile memory is disclosed. The nonvolatile memory contains the applications program and may be remotely programmed by way of a communication port, such as a universal asynchronous, receiver/transmitter (UART) device, utilizing a separate host computer. A second nonvolatile memory is provided which contains a control program which is executed by the central processing unit for carrying out the programming of the electrically-programmable nonvolatile memory utilizing data and address information received from the host computer over the communications port.

Abstract: Insures data integrity in process ownership indications by providing an ownership interlock on the data units in a pipeline to a store-in type of cache. An ownership interlock prevents any processor ownership change to occur (i.e. exclusive or readonly ownership) for a cache data unit until all outstanding stores have been made in the cache data unit, after which the ownership may be changed. An ownership change may be signalled by a cross-invalidate (XI) signal to a processor. Outstanding stores are received by the pipeline after the stores are completed by a processor, and the outstanding stores output from the pipeline into a store-in cache. A continuous flow of stores is enabled into and out of the pipeline to expedite a change of ownership requested of a data unit in the cache. The continuous flow avoids having to stop a processor from putting stores into the pipeline and avoids forcing all outstanding stores out of the pipeline into the cache before indicating a change of processor ownership.

Abstract: A memory access system for improving memory access when addressing dynamic random access modules (DRAMs). The memory access system includes a main memory and a memory controller. To improve memory access, both the memory controller and the main memory hardware remember the row address of the last access. Macro operation commands for fetch and store contain the last row address. The main memory hardware redrives that row address to the DRAMs after completion of an access, so that the memory controller need not provide a row address to the memory for each command of a command sequence.

Abstract: A knowledge acquisition tool for direct use by an expert in the automatic creation of a knowledge base derived from the knowledge of the expert, the knowledge acquisition tool including an input device usable by the expert for providing knowledge to the tool in response to questions, statements and/or prompts from the tool, a display for displaying the knowledge, questions, statements and prompts so that the expert can interact with the tool in creating the knowledge base, and a processor connected to the input device and the display for supplying the questions, statements and prompts to the display in order to extract the knowledge from the expert in the creation of the knowledge base incorporating the knowledge provided by the expert through use of the input device.

Abstract: A semiconductor microcontroller device is adapted to control the operation of an external system. The device includes a CPU, program memory for storing instructions to be executed by the CPU to perform its control functions, and data memory for storing data for selective retrieval by the CPU. The contents of either memory are code protected by an EEPROM fuse, and are automatically erased if the code protect state of the EEPROM fuse is sought to be reset, and the EEPROM fuse is reset only after the erasure of the memory contents.

Abstract: Method and apparatus for reducing the access time required to write to memory and read from memory in a computer system having a cache-based memory. A dynamic determination is made on a cycle by cycle basis of whether data should be written to the cache with a dirty bit asserted, or the data should be written to both the cache and main memory. The write-through method is chosen where the write-through method is approximately as fast as the write-back method. Where the write-back method is substantially faster than the write-through method, the write-back method is chosen.

Abstract: A security system is used for programmable read-only memory locations within a very large scale integrated (VLSI) circuit. In a first security bit memory location there is stored a first security data bit. The first security data bit has a first value when the first security bit memory location is unprogrammed and a second value when the first security bit memory location is programmed. In a second security bit memory location there is stored a second security data bit. The second security data bit has the first value when the second security bit memory location is unprogrammed and the second value when the second security bit memory location is programmed. A selection logic is electrically coupled to the first security bit memory location and the second security bit memory location. The selection logic selects no security data bit, the first security data bit or the second security data bit to be used to generate a security access signal.

Abstract: A command state machine for control circuitry associated with a memory array which control circuitry includes apparatus for programming and erasing the memory array including first state machine logic apparatus for providing control signals for reading the memory array and for initiating operations of the apparatus for programming and erasing the memory array in response to commands, and second state machine logic apparatus for controlling information derived from the memory array, the first and second state machine logic apparatus being adapted to assume predetermined states in response to any invalid command which have no adverse affect on the memory array or the control circuitry.

Abstract: A queue pointer manager contained in an integrated data controller is capable of controlling high speed data transfers between a high speed controlled data channel, a local processor bus and a dedicated local data bus. The overall design utilizes enhanced features of the Micro Channel architecture and data buffering to achieve maximum burst rates of 80 megabytes and to allow communications with 8, 16, 32 and 64 bit Micro Channel devices. Queued demands allow flexible programming of the Micro Channel master operations and reporting of completion statuses. The hardware control of command and status queuing functions increases the processing speed of control operations and reduces the need for software queuing. Extensive error checking/reporting, programming parameters, internal wrap self-test capability give the integrated data controller advanced functions as an input/output processor. The queue pointer manager also manages queue read and write pointers.

Abstract: An associative memory system using an associative memory circuit, capable of performing hit judgment on cache data at a high speed. The associative memory system comprises a virtual-address holding CAM circuit 2 for outputting a hit signal 5 when the data previously stored in a supplied address coincides with a supplied virtual address 4, a cache-tag memory circuit 1 for outputting cache-tag data coinciding with the supplied virtual address 4 when the data is present, and a physical-address holding CAM circuit 3 which connects with an output line for outputting the hit signal 5 given from the CAM circuit 2 and outputs the hit signal 6 when a physical address previously stored in the memory area from which the hit signal is outputted coincides with cache tag data supplied from the cache-tag memory circuit 1.

Abstract: A high-performance central processing unit (CPU) of the reduced instruction set (RISC) type employs a standardized, fixed instruction size, and permits only simplified memory access data width and addressing modes. The instruction set is limited to register-to-register operations and register load/store operations. The processor can employ a variable memory page size, so that the entries in a translation buffer for implementing virtual addressing can be optimally used. A granularity hint is added to the page table entry to define the page size for this entry.

Abstract: An improved internal memory address mapping apparatus repositions a lower priority memory resource when two or more memory resources are located at the same address space. Upon receipt of a signal indicating that two memory resources have been mapped to the same address space, an internal address mapping decoder assigns the conflicting portion of the memory resource with the lower priority a different address range. The portion of the memory resource with the lower priority not conflicting with another memory resource is accessed without being repositioned. This internal memory address mapping apparatus assures that all portions of conflicting memory resources remain accessible to the user.

Abstract: An efficient organization for microcoded instruction sets which have processor operations in which not all the bits of an instruction word are required. The organization has two registers for receiving and holding the first and second byte of instructions at a time, a first ROM connected to the register for decoding the first byte into control signals for operation of said microprocessor. One of these control signals is generated whenever the portion of the second instruction byte is required. The organization also has a second ROM connected to the register for decoding the portion of the second byte into control signals. Connected to said first and second ROMs is a multiplexer which selects the decoded second byte control signals for operation of the microprocessor responsive to the first ROM control signal.

Abstract: A system for compressing bilevel data includes a first cache memory having a plurality of assigned levels of usage, a first usage level assigned to a most recently used data segments and a second level assigned to a plurality of less recently used data segments. A processor determines if a received data segment is found in the cache memory and, if not, it assigns the received data segment to the cache memory's first level in place of a previous data segment stored therein. The previous data segment is assigned to a position in the second level in place of a less recently used data segment. The less recently used data segment that is displaced is chosen by a pseudo-random method. A not-found indication is then transmitted to a receiving station along with the identity of the received data segment. The receiving station contains identical cache structures and updates its caches in response to received code words and data segments.

Abstract: Cache memory input/output apparatus that allows transfer of a single data word and transfer of consecutive sequences of data words in a row of memory, using two independent serial ports and a random access port whose actions are controlled in part by a memory address signal. Data transferred by the serial ports are double buffered, each serial port having two independent registers; and the two registers associated with a serial port may be ganged together to transfer data sequences having word lengths from 16, or multiples thereof, up to arbitrary multiples of the length of a row of data words.