G06F13/4273

Grouping central processing unit memories based on dynamic clock and voltage scaling timing to improve dynamic/leakage power using array power multiplexers

Systems, methods, and apparatus for operating a central processing unit (CPU) are provided. The CPU includes a plurality of memories including a first group of memories and a second group of memories. The plurality of memories are grouped based on a timing criticality of each memory. The CPU further includes a memory core (MX) voltage supply configured to provide the plurality of memories with an MX voltage, an application processor core (APC) voltage supply configured to provide the plurality of memories with an APC voltage, and a voltage switching circuit. The voltage switching circuit detects an operating mode of the CPU and switches a voltage provided to at least one of the first group of memories or the second group of memories between the MX voltage and the APC voltage based on a type of the operating mode detected.

Integrated circuit for operating on a bus, and method for operating the integrated circuit

An integrated circuit includes a reception port an address port, and a memory with a number of memory sections for storing activation information. The number of memory sections is equal to the number, encodable by the address port, of activatable integrated circuits that are operable over a common bus. A control unit is configured to compare the address encoded by the address port with an address received at the reception port. The control unit writes a defined bit pattern to the memory section associated with the address in the event of a positive comparison, and withholds transmission of a negative acknowledgement signal in the event of a negative comparison. The integrated circuit is configured to be activated by the defined bit pattern in the memory section that corresponds to the address defined at the address port, for communicating with a microprocessor connected to the integrated circuit via the common bus.

High performance interconnect physical layer

Re-initialization of a link can take place without termination of the link, where the link includes, a transmitter and a receiver are to be coupled to each lane in the number of lanes, and re-initialization of the link is to include transmission of a pre-defined sequence on each of the lanes.

ASYMMETRIC POWER STATES ON A COMMUNICATION LINK
20190236043 · 2019-08-01 ·

Asymmetric power states on a communication link are disclosed. In one aspect, the communication link is a Peripheral Component Interconnect (PCI) express (PCIe) link. PCIe is a point-to-point communication link between two termini. Exemplary aspects of the present disclosure allow the two termini to be in different power states. By allowing the two termini to be in the different power states, an individual terminus may be put into a low-power state even though the other terminus is maintained at a higher-power state. The different power states are enabled by providing switches between a reference clock and respective termini such that the reference clock may selectively be provided to only one terminus of the communication link, allowing that terminus to remain in the higher-power state while the other terminus enters a low-power state that does not require the reference clock.

Asymmetric power states on a communication link
10365706 · 2019-07-30 · ·

Asymmetric power states on a communication link are disclosed. In one aspect, the communication link is a Peripheral Component Interconnect (PCI) express (PCIe) link. PCIe is a point-to-point communication link between two termini. Exemplary aspects of the present disclosure allow the two termini to be in different power states. By allowing the two termini to be in the different power states, an individual terminus may be put into a low-power state even though the other terminus is maintained at a higher-power state. The different power states are enabled by providing switches between a reference clock and respective termini such that the reference clock may selectively be provided to only one terminus of the communication link, allowing that terminus to remain in the higher-power state while the other terminus enters a low-power state that does not require the reference clock.

Asymmetric chip-to-chip interconnect
10353668 · 2019-07-16 · ·

Methods and apparatuses to transfer data between a first device and a second device are disclosed. In various embodiments, an apparatus includes a first device and a second device. The first device includes at least one first non-differential transmitter coupled to a first channel, at least one second non-differential transmitter coupled to a second channel, and at least one differential receiver to receive a data bit and its complement on the first and second channels in parallel. The second device includes at least one first non-differential receiver coupled to the first channel, at least one second non-differential receiver coupled to the second channel, and at least one differential transmitter to transmit a data bit and its complement on the first and second channels in parallel. Other methods and apparatuses are disclosed.

STORAGE CONTROLLER, STORAGE DEVICE INCLUDING THE SAME, AND OPERATION METHOD OF STORAGE CONTROLLER
20190187774 · 2019-06-20 ·

A storage controller communicates with an external device including a submission queue and a completion queue. An operation method of the storage controller includes receiving a notification associated with a command from the external device, based on a first clock, fetching the command from the submission queue, based on a second clock, performing an operation corresponding to the fetched command, based on a third clock, writing completion information to the completion queue, based on a fourth clock, and transmitting an interrupt signal to the external device, based on a fifth clock. Each of the first clock to the fifth clock is selectively activated depending on each operation phase.

Semiconductor memory device, memory system, and method using bus-invert encoding

A semiconductor memory device comprises a memory cell array and a data inversion circuit. The data inversion circuit is configured to receive a first unit data and a second unit data stored in the memory cell array through different first data lines, determine, while the first unit data is transmitted to a data input/output (I/O) buffer through a second data line, whether to the invert the second unit data based on a Hamming distance between the first unit data and the second unit data, and transmit the inverted or non-inverted second unit data to the data I/O buffer through the second data line.

Replacement physical layer (PHY) for low-speed peripheral component interconnect (PCI) express (PCIe) systems

A replacement physical layer (PHY) for low-speed Peripheral Component Interconnect (PCI) Express (PCIe) systems is disclosed. In one aspect, an analog PHY of a conventional PCIe system is replaced with a digital PHY. The digital PHY is coupled to a media access control (MAC) logic by a PHY interface for PCIe (PIPE) directly. In further exemplary aspects, the digital PHY may be a complementary metal oxide semiconductor (CMOS) PHY that includes a serializer and a deserializer. Replacing the analog PHY with the digital PHY allows entry and exit from low-power modes to occur much quicker, resulting in substantial power savings and reduced latency. Because the digital PHY is operable with low-speed communication, the digital PHY can maintain sufficient bandwidth that communication is not unnecessarily impacted by digital logic of the digital PHY.

STORAGE CONTROLLER, STORAGE DEVICE INCLUDING THE SAME, AND OPERATION METHOD OF STORAGE CONTROLLER
20240201774 · 2024-06-20 ·

A storage controller communicates with an external device including a submission queue and a completion queue. An operation method of the storage controller includes receiving a notification associated with a command from the external device, based on a first clock, fetching the command from the submission queue, based on a second clock, performing an operation corresponding to the fetched command, based on a third clock, writing completion information to the completion queue, based on a fourth clock, and transmitting an interrupt signal to the external device, based on a fifth clock. Each of the first clock to the fifth clock is selectively activated depending on each operation phase.