Abstract:
Variable-length instructions are prepared for simultaneous decoding and execution of a plurality of instructions in parallel by reading multiple variable-length instructions from an instruction source and determining the starting point of each instruction so that multiple instructions are presented to a decoder simultaneously for decoding in parallel. Immediately upon accessing the multiple variable-length instructions from an instruction memory, a predecoder derives predecode information for each byte of the variable-length instructions by determining an instruction length indication for that byte, assuming each byte to be an opcode byte since the actual opcode byte is not identified. The predecoder associates an instruction length to each instruction byte. The instructions and predecode information are applied to an instruction buffer circuit in a memory-aligned format. The instruction buffer circuit prepares the variable-length instructions for decoding by converting the instruction alignment from a memory alignment to an instruction alignment on the basis of the instruction length indication. The instruction buffer circuit also assists the preparation of variable-length instructions for decoding of multiple instructions in parallel by facilitating a conversion of the instruction length indication to an instruction pointer.
Abstract:
A novel interconnect layout method and metallization scheme is provided. The process of the present invention provides a multilevel interconnect structure formed solely from patterned metal layers (32, 36) stacked on top of each other. Both interconnect lines which form electrical connections along horizontal paths, as well as contacts which form electrical connections along vertical paths, can be formed using patterned metal interconnects as building-blocks. To form thicker metal layers for the purpose of constructing thick interconnect lines, two or more patterned metal layers may be stacked on each other.
Abstract:
The electromigration lifetime of a metal interconnection line is increased by adjusting the length of the interconnection line or providing longitudinally spaced apart holes or vias to optimize the backflow potential capacity of the metal interconnection line. In addition, elongated slots are formed through the metal interconnection line so that the total width of metal across the interconnection line is selected for optimum electromigration lifetime in accordance with the Bamboo Effect for that metal.
Abstract:
A system and method for providing a flexible medium access control device (32). The medium access control (MAC) device includes four configurable transmit and receive modes for communicating with a physical layer signaling control device. The four modes are controlled by a processor (36) and a transceiver interface (38). In operation, the modes enable the MAC device to transmit and receive MAC data to and from the physical layer signaling control device, and to optionally transmit and receive PHY data to and from the physical layer signaling control device, thereby providing compatibility between a MAC device and a radio (34), regardless of the physical layer functionality of the radio.
Abstract:
A supply voltage detect circuit is described which generates a control signal indicating the status of VCC to be at 5.0 or 3.3 volts. This control signal is used to generate analog reference signals used by A/D and/or D/A circuitry in an audio processing integrated circuit and by other circuitry to control clock frequencies or current drive. An input buffer is also described which is configurable depending on whether a 5.0 or 3.3 volt supply voltage is present. The input buffer includes two input buffer circuits. The output of a first input buffer circuit is output as valid data when VCC equals 5.0 volts. The output of the second input buffer circuit is output as valid data when VCC equals 3.3 volts.
Abstract:
A strip of a semiconductor material (for example, P type silicon) is oxidized and the resulting strip of oxide is removed leaving a depression in the upper surface of the semiconductor material which has steep sidewalls. The steep sidewalls do not have significant ion impact damage because they are formed by oxidation and not by reactive ion etching of the semiconductor material. A high quality tunnel oxide (115) can therefore be grown on the steep sidewalls. Floating gates (123-132) are then formed on the tunnel oxide (115), corresponding word lines are formed over the floating gates, a conductive region (114) (for example, N type silicon) is formed into the bottom of the depression, and a number of conductive regions (150) (for example, N type silicon) corresponding with the floating gates are formed above the rim of the depression. The resulting bit transistors have channel regions which extend in a vertical dimension under floating gates along the surface ofthe sidewall. Because the depth and profile of the depression is determined primarily by oxidation and not by lithography, very small geometry bit transistors can be made.
Abstract:
Methods and apparatus are disclosed for testing integrated circuits at the wafer level and for integrating test results, calculation of lifetimes and generation of trend charts in a common data base following testing. A wafer tester controller is supplemented with additional hardware and software to avoid data transfer errors and facilitate processing and storage of test results. The data base is available over a network to all areas of an organization.
Abstract:
An FPGA including SRAM memory cells (400), each having a latch configured so that both read and write signals are provided through the data path connection. By providing both read and write through the data path, the FPGA further includes only a single decoder to control pass gates connected to the memory cells (400) during read and write. To prevent voltages during write from damaging pass gates in the data path, the FPGA further includes a modified power supply to provide voltages ranging from VDD to VSS to the memory cell transistors (414, 416, 418, 420) during read, while providing a reduced voltage range during write to enable memory cell states to more easily be altered.
Abstract:
An apparatus and method for reducing the time required to supply a processor core with instructions uses a cache memory, a cache controller, and an instruction predecoding unit. When a line of instructions is retrieved into the cache memory, the instruction predecoding unit inspects the instructions in the line to determine if the line contains any non-sequential instructions. The cache controller stores an indication of whether the line contains non-sequential instructions with the line of instructions in the cache memory. If a given line of instructions does not contain any non-sequential instructions, the line of instructions following the given line is retrieved into the cache memory when one of the instructions in the given line is requested by the processor core.
Abstract:
A secure repeater (20) implementing data packet masking includes a programmable and selective, on a per port basis, disrupt response responsive to any of several selectable qualifying conditions. A disrupt controller (70) receives signals indicating various characteristics of fields of a data packet, and other conditions. A register bank (76) includes a plurality of memories, one associated with each port and some of the conditions, assists the disrupt controller to determine the associated port's disrupt response to the data packet. Each memory stores a disrupt control code. When the disrupt control code for a particular port has a value indicating that the associated port is enabled, deassertion of a condition signal associated with that control code results in disruption of a data packet. A cell array (200) permits simple, efficient scaling and formation of integrated semiconductor structures to implement complex disrupt logic equations.