Abstract: A system includes a processor, such as a CPU, surrounded by high-density memory with lower profile than a standard DIMM. The low profile, high-density memory provides multiple memory channels for the processor. With the memory configuration, the system can maintain the memory configurability with increased density and increased memory channels for the processor.

Abstract: Four-way pseudo split Dynamic Random Access Memory (DRAM) architectures and techniques are described. In one example, a 4-way pseudo split DRAM device includes four slices. In one example, a memory channel includes four pseudo channels, each of the four pseudo channels includes a corresponding slice of each of the plurality of DRAM devices. In one example, each of the four pseudo channels includes one slice from each of the plurality of DRAM devices.

Abstract: Bandwidth efficiency is improved by reducing time to access a cache line in a DRAM chip. A memory array in the DRAM chip is internally segmented into two equal size portions, each portion having a plurality of banks. Each respective portion is internally segmented into two equal size sub-portions. A cache line in the memory array is accessed by accessing a first half of the cache line in parallel in all of the sub-portions and accessing a second half of the cache line in parallel in all of the sub-portions of the memory array after a gap time.

Abstract: In an example, a system and method for centering in a high-performance interconnect (HPI) are disclosed. When an interconnect is powered up from a dormant state, it may be necessary to “center” the clock signal to ensure that data are read at the correct time. A multi-phase method may be used, in which a first phase comprises a reference voltage sweep to identify an optimal reference voltage. A second phase comprises a phase sweep to identify an optimal phase. A third sweep comprises a two-dimensional “eye” phase, in which a plurality of values within a two-dimensional eye derived from the first two sweeps are tested. In each case, the optimal value is the value that results in the fewest bit error across multiple lanes. In one example, the second and third phases are performed in software, and may include testing a “victim” lane, with adjacent “aggressor” lanes having a complementary bit pattern.

Abstract: In an example, a system and method for centering in a high-performance interconnect (HPI) are disclosed. When an interconnect is powered up from a dormant state, it may be necessary to “center” the clock signal to ensure that data are read at the correct time. A multi-phase method may be used, in which a first phase comprises a reference voltage sweep to identify an optimal reference voltage. A second phase comprises a phase sweep to identify an optimal phase. A third sweep comprises a two-dimensional “eye” phase, in which a plurality of values within a two-dimensional eye derived from the first two sweeps are tested. In each case, the optimal value is the value that results in the fewest bit error across multiple lanes. In one example, the second and third phases are performed in software, and may include testing a “victim” lane, with adjacent “aggressor” lanes having a complementary bit pattern.

Abstract: In an example, a system and method for centering in a high-performance interconnect (HPI) are disclosed. When an interconnect is powered up from a dormant state, it may be necessary to “center” the clock signal to ensure that data are read at the correct time. A multi-phase method may be used, in which a first phase comprises a reference voltage sweep to identify an optimal reference voltage. A second phase comprises a phase sweep to identify an optimal phase. A third sweep comprises a two-dimensional “eye” phase, in which a plurality of values within a two-dimensional eye derived from the first two sweeps are tested. In each case, the optimal value is the value that results in the fewest bit error across multiple lanes. In one example, the second and third phases are performed in software, and may include testing a “victim” lane, with adjacent “aggressor” lanes having a complementary bit pattern.

Abstract: Apparatuses for interconnecting integrated circuit dies. A first set of single-ended transmitter circuits are included on a first die. The transmitter circuits are impedance matched and have no equalization. A first set of single-ended receiver circuits are included on a second die. The receiver circuits have no termination and no equalization. Conductive lines are coupled between the first set of transmitter circuits and the first set of receiver circuits. The lengths of the conductive lines are matched. The first die, the first set of single-ended transmitter circuits, the second die, the first set of single ended receiver circuits and the conductive lines are disposed within a first package. A second set of single-ended transmitter circuits are included on the first die. The transmitter circuits are impedance matched and have no equalization. Data transmitted from the second set of transmitter circuits is transmitted according to a data bus inversion (DBI) scheme.

Abstract: An on-package interface. A first set of single-ended transmitter circuits on a first die. The transmitter circuits are impedance matched and have no equalization. A first set of single-ended receiver circuits on a second die. The receiver circuits have no termination and no equalization. A plurality of conductive lines couple the first set of transmitter circuits and the first set of receiver circuits. The lengths of the plurality of conductive lines are matched.

Abstract: In an example, a system and method for centering in a high-performance interconnect (HPI) are disclosed. When an interconnect is powered up from a dormant state, it may be necessary to “center” the clock signal to ensure that data are read at the correct time. A multi-phase method may be used, in which a first phase comprises a reference voltage sweep to identify an optimal reference voltage. A second phase comprises a phase sweep to identify an optimal phase. A third sweep comprises a two-dimensional “eye” phase, in which a plurality of values within a two-dimensional eye derived from the first two sweeps are tested. In each case, the optimal value is the value that results in the fewest bit error across multiple lanes. In one example, the second and third phases are performed in software, and may include testing a “victim” lane, with adjacent “aggressor” lanes having a complementary bit pattern.

Abstract: An on-package interface. A first set of single-ended transmitter circuits on a first die. The transmitter circuits are impedance matched and have no equalization. A first set of single-ended receiver circuits on a second die. The receiver circuits have no termination and no equalization. A plurality of conductive lines couple the first set of transmitter circuits and the first set of receiver circuits. The lengths of the plurality of conductive lines are matched.

Abstract: Apparatuses for interconnecting integrated circuit dies. A first set of single-ended transmitter circuits are included on a first die. The transmitter circuits are impedance matched and have no equalization. A first set of single-ended receiver circuits are included on a second die. The receiver circuits have no termination and no equalization. Conductive lines are coupled between the first set of transmitter circuits and the first set of receiver circuits. The lengths of the conductive lines are matched. The first die, the first set of single-ended transmitter circuits, the second die, the first set of single ended receiver circuits and the conductive lines are disposed within a first package. A second set of single-ended transmitter circuits are included on the first die. The transmitter circuits are impedance matched and have no equalization. Data transmitted from the second set of transmitter circuits is transmitted according to a data bus inversion (DBI) scheme.

Abstract: A tunable current mode integrator for low-frequency continuous-time filters that requires a reduced amount of area when implemented in an integrated circuit (IC). The integrator includes input and output transistors, and cross-coupled current mirrors, integration capacitors, and operational transconductance amplifiers (OTAs) that form a feedback structure with the input transistors. Input currents are converted to small current swings within the OTAs, and are subsequently integrated by the capacitors. Resulting integrated voltages are converted to output currents by the output transistors.

Abstract: A synchronous interconnect structure is provided for transmitting and receiving source synchronous signals. The receiver of the synchronous interconnect structure continuously monitors the phase relationship between the source clock signal and each transmitted data signal. In this manner, the synchronous interconnect structure can perform signal timing alignment for each transmitted clock and data signal in near real time fashion without impacting data transmission rates across the synchronous interconnect structure.

Abstract: An electronic apparatus for receiving source synchronous signals is provided. The receiver continuously monitors the phase relationship between each data signal and the source synchronous clock signal. In this manner, the electronic apparatus can compensate for phase discrepancies that occur over time without having to interrupt any data operations.