摘要:
An address translator (126) translates addresses, acting like a register file or a table, as necessary. The address translator contains a number of entries for matching an input address to a stored tag. An entry outputs a stored translated address if its stored tag matches the input address. A decoder (138) selects a particular entry in which to store an input translated address when the address translator operates as a register file. In these cases, a register number is also stored in the particular entry's as the entry's tag. Later, when it is necessary to read the particular entry, the register number is compared to each entry's tag to find a match. The disclosed address translator is compatible with both hardware and software refill algorithms ("tablewalks") without impacting its critical read speed path.
摘要:
A processor including a plurality of execution pipeline stages where each stage accepts a plurality of operand inputs and generates a result. A pipefile having at least the same number of entries as the number of execution pipeline stages is included in the processor. A pointer register is associated with each execution pipeline stage. A value is stored in at least one of the pointer registers, the value indicating a particular one of the entries in the pipefile.
摘要:
A method for forwarding data within a pipeline of a pipelined data processor having a plurality of execution pipeline stages where each stage accepts a plurality of operand inputs and generates a result. The result generated by each execution pipeline stage is selectively coupled to an operand input of one of the execution pipeline stages.
摘要:
A fully associative address translator which includes a number of entries, each of said number of entries translating a received effective address into a real address, each received effective address including a segment identifier and a page identifier. Each of the entries within the fully associative address translator includes a first translation from an effective address segment identifier into a virtual address segment identifier and a second translation from a virtual address page identifier to a real address page identifier. A first valid bit cell is provided for storing a validity bit which indicates the validity of the first translation from the effective address segment identifier to the virtual address segment identifier and a second valid bit cell is also provided for storing a validity bit indicating the validity of the second translation from the virtual address page identifier to the real address page identifier wherein a process context switch will invalidate only a portion of each of the entries, thereby reducing the miss penalty associated with a context switch.
摘要:
A computing system includes at least one functional unit and a magnetic random access memory (MRAM) block coupled to the at least one functional unit. The MRAM block is configured to store a functional state of the at least one functional unit during a power down state of the at least one functional unit.
摘要:
Techniques for adaptively scaling voltage for a processing core are described. In one scheme, the logic speed and the wire speed for the processing core are characterized, e.g., using a ring oscillator having multiple signal paths composed of different circuit components. A target clock frequency for the processing core is determined, e.g., based on computational requirements for the core. A replicated critical path is formed based on the characterized logic speed and wire speed and the target clock frequency. This replicated critical path emulates the actual critical path in the processing core and may include different types of circuit components such as logic cells with different threshold voltages, dynamic cells, bit line cells, wires, drivers with different threshold voltages and/or fan-outs, and so on. The supply voltage for the processing core and the replicated critical path is adjusted such that both achieve the desired performance.
摘要:
A method of designing a circuit includes annotating relative positions of instantiated hierarchical macro cells, which include two or more instantiated standard cells. The relative positions of individual instantiated standard cells may also be annotated. Relative positions of instantiated hierarchical macro cells and individual instantiated standard cells may be altered to form a more compact standard cell configuration. Pin positions may also be annotated by relative position. Relative pin positions may be altered to promote dense signal line routing within the standard cell design. The relative positions of the instantiated hierarchical macro cells and individual instantiated standard cells are converted to absolute grid position locations to form a grid assigned circuit. The grid assigned circuit is then routed.
摘要:
Systems, circuits and methods for software programmable logic using Spin Transfer Torque Magnetoresistive Random Access Memory (STT-MRAM) technology are disclosed. Magnetic tunnel junction (MTJ) storage elements can be formed into input planes and output planes. The input planes and output planes can be coupled together to form complex arrays that allow for the realization of logic functions.
摘要:
A full-scan latch is provided that may be used to incorporate design for test functionality in an integrated circuit. The full-scan latch includes a shadow latch, a multiplexer, and a slave latch. The full-scan latch has a test mode and a normal mode. When in the normal mode, the device operates as a transparent latch, passing a data input to its output. When in test mode, the device is operable to pass scan data down a scan chain and to inject scan data into the data path.
摘要:
An interface circuit according to one embodiment of the present invention includes a clock signal, a first phase locked loop coupled to the clock signal line and generating a reference clock signal, a second phase locked loop receiving the reference clock signal, and in accordance therewith, generating one or more phase shifted reference clock signals, and a data transceiver circuit coupled to receive at least one of the clock signal, the reference clock signal, or one or more of the phase shifted reference clock signals to control the flow of data between a first circuit and a second circuit. An interface circuit according to one embodiment of the invention can be used advantageously for controlling the flow of data between a CPU and an external memory.