Abstract: According to at least one embodiment, a system comprises means for performing an operation utilizing a clock signal. The system further comprises means for supplying a variable operating voltage to the performing means, and means for dynamically varying the frequency of the clock signal responsive to observed changes in the variable operating voltage.

Abstract: A circuit and method for receiving data signals over a data signal line are disclosed. In one embodiment, a receiver circuit is provided for receiving data signals transmitted over a signal line. The receiver circuit comprises an inverter circuit having an input that forms an input of the receiver circuit and an output coupled to an internal node, an output circuit having an input coupled to the internal node and an output that provides an output of the receiver circuit, and a charge adding circuit that provides at least a portion of a temporary logic transition at the input of the receiver circuit, induced by a logic transition on an adjacent signal line, to the internal node to mitigate erroneous logic transitions associated with the receiver circuit.

Abstract: Systems and methods are disclosed for providing a temporarily modified output. A waveform control provides a control output that temporarily adjusts to an intermediate level between normal high and low levels during a first operating mode. The waveform control provides the control output to transition periodically between the high and low levels during a second operating mode. A delay network controls the waveform control to provide the output at the intermediate level for a duration during the first operating mode.

Abstract: The present invention is directed to a system and method for measuring a current in an integrated circuit comprising measuring a first output count from a first voltage controlled oscillator (VCO) using a first measurement voltage, simultaneously measuring a second output count from a second VCO using a second measurement voltage, and calculating the current in the integrated circuit using a voltage proportional to a difference between the first and second output counts.

Abstract: The invention provides a processor architecture that bypasses data hazards. The architecture has an array of pipelines and a register file. Each of the pipelines includes an array of execution units. The register file has a first section of n registers (e.g., 128 registers) and a second section of m registers (e.g., 16 registers). A write mux couples speculative data from the execution units to the second set of m registers and non-speculative data from a write-back stage of the execution units to the first section of n registers. A read mux couples the speculative data from the second set of m registers to the execution units to bypass data hazards within the execution units. The register file preferably includes column decode logic for each of the registers in the second section of m registers to architect speculative data without moving data. The decode logic first decodes, and then selects, an age of the producer of the speculative state; the newest producer enables the decode.

Abstract: According to at least one embodiment, a system comprises means for performing an operation utilizing a clock signal. The system further comprises means for supplying a variable operating voltage to the performing means, and means for dynamically varying the frequency of the clock signal responsive to observed changes in the variable operating voltage.

Abstract: A multiple dispatch processor has several instruction fetch units, each for providing a stream of instructions to an instruction decode and dispatch unit. The processor also has an resource allocation unit, and multiple resources such as combined integer and address execution pipelines and floating point execution pipelines. Each instruction decode and dispatch unit requests resources needed to perform an instruction of the resource allocation unit, which arbitrates among the multiple instruction decode and dispatch units.

Abstract: The invention provides a method and circuit for measuring on-chip, cycle-to-cycle, jitter. Copies of a circuit comprising a programmable delay line, a programmable phase comparator, and two counters are placed at different locations on an IC near a clock signal. The programmable delay line creates a clock signal that is delayed by one clock cycle. This delayed clock signal is compared in time to the original clock signal by the programmable phase comparator. If the difference in time between the delayed clock signal and the clock signal is greater than the dead time, the first counter is triggered. If the difference in time is negative and the absolute value is greater than the dead time, the second counter is triggered. A statistical distribution, based on the values of the counters, is created. This distribution is used to predict on-chip, cycle-to-cycle jitter.

Abstract: An embodiment of the invention provides a circuit and method for reducing silent data corruption in storage arrays with no increase in read and write access times. An N bit parity encoder is connected to an N bit storage array. When the N bit array is written, the data used to write into the storage array is also used to generate a parity value by the N bit parity encoder. This parity value is stored in a latch. When the N bit array is read, the current parity value of the parity encoder is presented to the state machine. The state machine compares the current value of the parity encoder to the stored value in the latch. If the parity values, stored and observed, don't match, the state machine indicates that data corruption may have occurred.

Abstract: A system and method are disclosed which allow unstored computed results to be accessed without the normal overhead associated with traditional data forwarding and bypass techniques. Through the use of multiplexers and bi-directional OR controllers the unstored data is readily accessible for use before it is stored in a register file. The circuitry used also allows bi-directional travel across a register file or bank as information is passed between the bi-directional controllers used. Latches can also be used in the circuitry. Additionally, the features of the invention allow the required number of select signals fed to the multiplexers used to be reduced over conventional methods. These reductions are possible through circuitry disclosed herein.

Abstract: A system and method are disclosed which allow unstored computed results to be accessed without the normal overhead associated with traditional data forwarding and bypass techniques. Through the use of multiplexers and bi-directional OR controllers the unstored data is readily accessible for use before it is stored in a register file. The circuitry used also allows bi-directional travel across a register file or bank as information is passed between the bi directional controllers used. Latches can also be used in the circuitry. Additionally, the features of the invention allow the required number of select signals fed to the multiplexers used to be reduced over conventional methods. These reductions are possible through circuitry disclosed herein.

Abstract: A circuit for reducing power in SRAMS and DRAMS is implemented by dynamically controlling a voltage applied to Nwells containing PFETs used in memory cells. When a memory cell is in standby, the voltage applied to Nwells containing PFETs is increased in order to reduce leakage current. When a memory cell is being written, read, or refreshed, the voltage applied to Nwells containing PFETs is reduced in order to allow the memory cell to switch more quickly.

Abstract: A multiple dispatch processor has several instruction fetch units, each for providing a stream of instructions to an instruction decode and dispatch unit. The processor also has an resource allocation unit, and multiple resources such as combined integer and address execution pipelines and floating point execution pipelines. Each instruction decode and dispatch unit requests resources needed to perform an instruction of the resource allocation unit, which arbitrates among the multiple instruction decode and dispatch units.

Abstract: The invention provides a processor architecture that bypasses data hazards. The architecture has an array of pipelines and a register file. Each of the pipelines includes an array of execution units. The register file has a first section of n registers (e.g., 128 registers) and a second section of m registers (e.g., 16 registers). A write mux couples speculative data from the execution units to the second set of m registers and non-speculative data from a write-back stage of the execution units to the first section of n registers. A read mux couples the speculative data from the second set of m registers to the execution units to bypass data hazards within the execution units. The register file preferably includes column decode logic for each of the registers in the second section of m registers to architect speculative data without moving data. The decode logic first decodes, and then selects, an age of the producer of the speculative state; the newest producer enables the decode.

Abstract: A system and method for reducing the power and the size of a cache memory is implemented by creating a large cache which is subdivided into a smaller cache. One tag controls both the large cache and the smaller, subdivided cache. A second tag controls only the smaller cache. In addition to saving power and area, this system and method may be used to reduce the write-through and write-back effort, improve the latency and the coherency of a cache memory, and improve the ability of multiprocessor system to snoop cache memory.

Abstract: A circuit for reducing power in an on-chip cache memory on a microprocessor chip is implemented by dynamically controlling power applied to individual memory sections. Individual sections of memory are isolated from a fixed power supply by inserting one or more switches between GND and a negative connection of an individual memory section or by inserting one or more switches between VDD and a positive connection of an individual memory section. If a memory section is not accessed for a defined time, a PMU (Performance Monitor Unit) detects it and the power to that section is switched off, saving power. In addition, a software application may send information to the PMU to select the amount of cache memory needed for the particular software application.

Abstract: A system and method of compensating for voltage droop in an integrated circuit. The integrated circuit may include a plurality of chip circuits, a clock control system, a clock distribution network including at least one delay element and a voltage droop detector. The clock control system adapts cycle time in the clock distribution network through use of the at least one delay element when a voltage droop is detected. The method may include detecting a voltage droop in an integrated circuit where the integrated circuit is driven by a clock signal, determining an optimum frequency change to compensate for the voltage droop, and adapting cycle time of the clock signal in an incremental manner to achieve the optimum frequency change.

Abstract: A system and method of compensating for voltage droop in an integrated circuit. The integrated circuit may include a plurality of chip circuits, a clock control system, a clock distribution network including at least one delay element and a voltage droop detector. The clock control system adapts cycle time in the clock distribution network through use of the at least one delay element when a voltage droop is detected. The method may include detecting a voltage droop in an integrated circuit where the integrated circuit is driven by a clock signal, determining an optimum frequency change to compensate for the voltage droop, and adapting cycle time of the clock signal in an incremental manner to achieve the optimum frequency change.

Abstract: A circuit for reducing power in SRAMS and DRAMS is implemented by dynamically controlling a voltage applied to Nwells containing PFETs used in memory cells. When a memory cell is in standby, the voltage applied to Nwells containing PFETs is increased in order to reduce leakage current. When a memory cell is being written, read, or refreshed, the voltage applied to Nwells containing PFETs is reduced in order to allow the memory cell to switch more quickly.

Abstract: A circuit for reducing power in SRAMS and DRAMS is implemented by dynamically controlling a voltage applied to individual memory sections of a semiconductor memory array. Individual sections of memory are isolated from a fixed power supply by inserting one or more PFETs between a fixed power supply and a positive connection, VDD, of an individual memory section. The voltage applied to each memory section is controlled by applying a separate variable voltage to each gate of all PFETs connected to a particular memory section. If a memory section is not accessed, the voltage to that section can be lowered, saving power. If a memory section is accessed, the voltage to that section may be raised, providing more power and shortening read and write times.