Abstract: There is provided an alternating current supply noise reducer for a 3D chip stack having two or more strata. Each of the strata has a respective one of a plurality of power distribution circuits and a respective one of a plurality of clock distribution circuits arranged thereon. The alternating current supply noise reducer includes a plurality of voltage droop sensors and a plurality of skew adjustors. The plurality of voltage droop sensors is for detecting alternating current supply noise in the plurality of power distribution circuits. One or more voltage droop sensors are respectively arranged on at least some of the strata. The plurality of skew adjusters are for delaying one or more clock signals provided by the plurality of clock distribution circuits responsive to an amount of the alternating current supply noise. Each skew adjuster is respectively arranged on the at least some of the strata.

Abstract: There is provided a synchronization circuit for a 3D chip stack having multiple circuits and multiple strata interconnected using a first and a second stack-wide broadcast connection chain. The synchronization circuit includes the following, on each stratum. A synchronizer connected to the first connection chain receives an asynchronous signal therefrom and performs a synchronization to provide a synchronous signal. A driver is connected to the second chain for driving the synchronous signal. A latch connected to the second chain receives the synchronous signal driven by the driver on a same or different stratum within a next clock cycle from the synchronization to provide the stack-wide synchronous signal to a circuit on a same stratum. An output of a single driver on one stratum is selected at any given time for use by the latch on all strata.

Abstract: There is provided a clock distribution network for synchronizing global clock signals within a 3D chip stack having two or more strata. The clock distribution network includes a plurality of clock distribution circuits, each being arranged on a respective one of the two or more strata for providing the global clock signals to various chip locations. Each of the plurality of clock distribution circuits includes a resonant circuit for providing stratum-to-stratum coupling for the clock distribution network. The resonant circuit includes at least one capacitor and at least one inductor.

Abstract: There is provided a strata manager within a 3D chip stack having two or more strata. The strata manager includes a plurality of scannable configuration registers, each being arranged on a respective one of the two or more strata for storing a set of bits. The set of bits is configured to program an operation of a corresponding one of the two or more strata on which the set of bits is stored or a device thereon. Additionally, a stratum identifier within a 3D stack and stack-wide scan circuit within a 3D stack are provided.

Abstract: There is provided a connection configuration for a multiple layer chip stack having two or more strata. Each of the two or more strata has multiple circuit components, a front-side and a back-side. The connection configuration includes a connection pair having as members a front-side connection and a backside connection unconnected to the front-side connection. The front-side connection and the backside connection are co-located with respect to each other on a given stratum from among the two or more strata, and are respectively connected to different ones of the multiple circuit components on the given stratum. At least one of the front-side connection and the backside connection is also connected to a particular one of the multiple circuit components on an adjacent stratum to the given stratum from among the two or more strata.

Abstract: There is provided a strata manager within a 3D chip stack having two or more strata. The strata manager includes a plurality of scannable configuration registers, each being arranged on a respective one of the two or more strata for storing a set of bits. The set of bits is configured to program an operation of a corresponding one of the two or more strata on which the set of bits is stored or a device thereon. Additionally, a stratum identifier within a 3D stack and stack-wide scan circuit within a 3D stack are provided.

Abstract: There is provided a clock distribution network for synchronizing global clock signals within a 3D chip stack having two or more strata. The clock distribution network includes a plurality of clock distribution circuits, each being arranged on a respective one of the two or more strata for providing the global clock signals to various chip locations. Each of the plurality of clock distribution circuits includes a resonant circuit for providing stratum-to-stratum coupling for the clock distribution network. The resonant circuit includes at least one capacitor and at least one inductor.

Abstract: A processor having a dependency matrix comprises a first array comprising a plurality of first cells. A second array couples to the first array and comprises a plurality of second cells. A first write port couples to the first array and the second array and writes to the first array and the second array. A first read port couples to the first array and the second array and reads from the first array and the second array. A second read port couples to the first array and reads from the first array. A second write port couples to the second read port, reads from the second read port and writes to the second array.

Abstract: A processor having a dependency matrix comprises a first array comprising a plurality of first cells. A second array couples to the first array and comprises a plurality of second cells. A first write port couples to the first array and the second array and writes to the first array and the second array. A first read port couples to the first array and the second array and reads from the first array and the second array. A second read port couples to the first array and reads from the first array. A second write port couples to the second read port, reads from the second read port and writes to the second array.

Abstract: A scannable latch is disclosed. The scannable latch includes a dynamic circuit, two cross-coupled NAND gates coupled to the dynamic circuit, and a pair of stacked transistors coupled to the dynamic circuit. One of the stacked transistors is for receiving data signals, and the other stacked transistors is for receiving scan in signals.

Abstract: A method of restoring register mapper states for an out-of-order microprocessor. A processor maps a logical register to a physical register in a map table in response to a first instruction. Instruction sequencing logic records a second speculatively executed instruction as a most recently dispatched instruction in the map table when the second instruction maps the same logical register of the first instruction. The instruction sequencing logic sets an evictor instruction tag (ITAG) of the first instruction in the map table when the second instruction maps a same logical register of the first instruction. The instruction sequencing logic detects mispredicted speculative instructions, determines which instructions in the map table were dispatched prior to the mispredicted speculative instructions, and restores the map table to a state prior to the mispredicted speculative instructions by utilizing the evictor ITAG to restore one or more A bits in the map table data structure.

Abstract: A computer implemented method, apparatus, and computer usable program code are provided for implementing a set of architected register files as a set of temporary rename buffers. An instruction dispatch unit receives an instruction that includes instruction data. The instruction dispatch unit determines a thread mode under which a processor is operating. Responsive to determining the thread mode, the instruction dispatch unit determines an ability to use the set of architected register files as the set of temporary rename buffers. Responsive to the ability to use the set of architected register files as the set of temporary rename buffers, the instruction dispatch unit analyzes the instruction to determine an address of an architected register file in the set of architected register files where the instruction data is to be stored. The architected register file operating as a temporary rename buffer stores the instruction data as finished data.

Abstract: A method of restoring register mapper states for an out-of-order microprocessor. A processor maps a logical register to a physical register in a map table in response to a first instruction. Instruction sequencing logic records a second speculatively executed instruction as a most recently dispatched instruction in the map table when the second instruction maps the same logical register of the first instruction. The instruction sequencing logic sets an evictor instruction tag (ITAG) of the first instruction in the map table when the second instruction maps a same logical register of the first instruction. The instruction sequencing logic detects mispredicted speculative instructions, determines which instructions in the map table were dispatched prior to the mispredicted speculative instructions, and restores the map table to a state prior to the mispredicted speculative instructions by utilizing the evictor ITAG to restore one or more A bits in the map table data structure.

Abstract: An apparatus, a method and a computer program are provided to reduce leakage current in a processor. Traditionally, extra logic is employed to reduce leakage currents. However, reducing leakage current without sacrificing fine grain operations and speed can be difficult. Achieving such a goal can be accomplished by incorporating a multiplexer (mux) into the scan-in path of scan registers so that units or sub-units of the processor can be powered down individually. Additionally, the muxes are not incorporated into time paths, so speed can be preserved.

Abstract: A scannable latch is disclosed. The scannable latch includes a dynamic circuit, two cross-coupled NAND gates coupled to the dynamic circuit, and a pair of stacked transistors coupled to the dynamic circuit. One of the stacked transistors is for receiving data signals, and the other stacked transistors is for receiving scan in signals.

Abstract: An apparatus, a method and a computer program product are provided for conserving energy during functional mode of a processor by disabling the scan chain. By inserting logic gating into the scan chain it is possible to disable the scan chain during the processor's functional mode. During functional mode the scan out port of the latch bit in a scan chain toggles, which leads to unnecessary energy consumption. By gating scan control signals and the scan out port of a latch bit, the scan chain segment between latch bits can be disconnected. Therefore, the scan control signals can disable the scan chain during functional mode.

Abstract: An apparatus, a method, and a computer program are provided to efficiently use a microprocessor array. Typically, microprocessor arrays can be divided into multiple subarrays. Also, in the conventional arrays, each of the subarrays were engaged when the microprocessor array is used. To alleviate the power consumed by the microprocessor arrays, row selection logic is employed to engage only specific rows of subarrays. Therefore, power consumed by unused subarrys is saved.

Abstract: A programmable logic array (PLA) latch is disclosed. The PLA latch includes a first logic array, a second logic array and only one output latch. The second logic array is coupled to the first logic array. The output latch is coupled to the second logic array.

Abstract: A scannable latch is disclosed. The scannable latch includes a dynamic circuit, two cross-coupled NAND gates coupled to the dynamic circuit, and a pair of stacked transistors coupled to the dynamic circuit. One of the stacked transistors is for receiving data signals, and the other stacked transistors is for receiving scan in signals.

Abstract: This invention reduces power consumed during CAM search operations in a CAM/RAM structure utilizing a segmented match line structure. This device is useful when it is known that a portion or portions of the compare data inputs vary infrequently. The apparatus sometimes may be referred to as local match line hold latch, and is a device that stores the value of a local match line comparison result the first time that a search operation occurs, and will stay at that value until the value of the compare data in of the local match line changes.