Mobile computing device technology and systems and methods utilizing the same

Storage sled and techniques for a data center

Examples may include a sled for a rack of a data center including physical storage resources. The sled comprises an array of storage devices and an array of memory. The storage devices and memory are directly coupled to storage resource processing circuits which are themselves, directly coupled to dual-mode optical network interface circuitry. The circuitry can store data on the storage devices and metadata associated with the data on non-volatile memory in the memory array.

Technologies for switching network traffic in a data center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

Technologies for switching network traffic in a data center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

RACK LEVEL PRE-INSTALLED INTERCONNECT FOR ENABLING CABLELESS SERVER/STORAGE/NETWORKING DEPLOYMENT

Apparatus and methods for rack level pre-installed interconnect for enabling cableless server, storage, and networking deployment. Plastic cable waveguides are configured to couple millimeter-wave radio frequency (RF) signals between two or more Extremely High Frequency (EHF) transceiver chips, thus supporting millimeter-wave wireless communication links enabling components in the separate chassis to communicate without requiring wire or optical cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. A plurality of plastic cable waveguide may be coupled to applicable support/mounting members, which in turn are mounted to a rack and/or top-of-rack switches. This enables the plastic cable waveguides to be pre-installed at the rack level, and further enables racks to be installed and replaced without requiring further cabling for the supported communication links. The communication links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links. 1. A method , comprising:operatively coupling a first extremely high frequency (EHF) transceiver chip to a first component in a first chassis;operatively coupling a second EHF transceiver chip to a second component in a second chassis;coupling a plastic cable waveguide to at least one of the first chassis, the second chassis, or a rack in which the first and second chassis are installed, the plastic cable waveguide configured to couple millimeter-wave radio frequency (RF) signals output from the first EHF transceiver chip into the plastic cable waveguide and to communicatively couple the millimeter-wave RF signals to the second EHF transceiver chip; andfacilitating communication between the first and second components by transmitting a millimeter-wave RF signal from the first EHF transceiver chip to the second EHF transceiver chip via the plastic cable ...

Network device switch

A switch for transmitting data from a first device to a second device includes a port in communication with the second device, queues which store slices of data received from the first device, and circuitry for selectively outputting a slice of the data from at least one of the queues to the port for transmission to the second device.

Method and apparatus for providing a remotely managed expandable computer system

A remotely managed expandable multi-user computer system is provided. The computer system includes a removable compute cartridge and a removable storage cartridge allowing easy upgrade of the computer system. The computer system self-configures when powered on to allow remote management by another system over a network. Automatic failover support is provided without the need for a separate compute element. A self-configurable removable secure-to-wireless converter to couple to a client computer system allows secure communications between the multi-user system and the client computer system via a wireless network.

Technolgies for millimeter wave rack interconnects

Racks and rack pods to support a plurality of sleds are disclosed herein. Switches for use in the rack pods are also disclosed herein. A rack comprises a plurality of sleds and a plurality of electromagnetic waveguides. The plurality of sleds are vertically spaced from one another. The plurality of electromagnetic waveguides communicate data signals between the plurality of sleds.

TECHNOLOGIES FOR SWITCHING NETWORK TRAFFIC IN A DATA CENTER

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed. 120-. (canceled)21. A system-on-chip (SoC) network switch integrated circuit (IC) for use in forwarding network traffic that is in accordance with multiple different link layer communication protocols , the network traffic to be forwarded via a physical port associated with the SoC network switch IC to an optical communication channel and thence to a destination network device , the SoC network switch IC comprising:network communication circuitry for use, when the SoC network switch IC is in operation, in (1) receiving multiprotocol inbound network communication to the SoC network switch IC and (2) transmitting multiprotocol outbound network communication from the SoC network switch IC;network traffic switching circuitry for use in outbound network communication forwarding address determination; based upon frame data accessed by the SoC network switch IC as a function of one or more of the multiple different link layer communication protocols determined by the SoC network switch IC to correspond to the network traffic, the SoC network switch IC is to identify (1) a forwarding address of the destination network device to which the network traffic is to be forwarded by the SoC network switch ...

Thermally efficient compute resource apparatuses and methods

Examples may include racks for a data center and sleds for the racks, the sleds arranged to house physical resources for the data center. The sleds can house physical resources and heat sinks thermally coupled to the physical resources. The physical resources are arranged on the sleds and the heat sinks are configured so as to limit thermal shadowing between physical resources to reduce interference with airflow provided by fans of the racks.

TECHNOLOGIES FOR OPTICAL COMMUNICATION IN RACK CLUSTERS

Technologies for optical communication in a rack cluster in a data center are disclosed. In the illustrative embodiment, a network switch is connected to each of 1,024 sleds by an optical cable that enables communication at a rate of 200 gigabits per second. The optical cable has low loss, allowing for long cable lengths, which in turn allows for connecting to a large number of sleds. The optical cable also has a very high intrinsic bandwidth limit, allowing for the bandwidth to be upgraded without upgrading the optical infrastructure. 1. A system comprising:a network switch comprising a plurality of optical connectors;a plurality of sleds, each sled of the plurality of sleds comprising a circuit board, an optical connector mounted on the circuit board, and one or more physical resources mounted on the circuit board; at least two optical fibers;', 'a first connector at a first end of the passive optical cable connected to the optical connector of a corresponding sled of the plurality of sleds; and', 'a second connector at a second end of the passive optical cable connected to an optical connector of the plurality of optical connectors of the network switch., 'a plurality of passive optical cables, wherein each passive optical cable of the plurality of passive optical cables comprises2. The system of claim 1 , wherein the plurality of sleds comprises at least 256 sleds.3. The system of claim 1 , wherein each of the plurality of sleds is configured to send and receive optical signals over the corresponding passive optical cables at a rate of at least 50 gigabits per second and wherein the network switch is configured to send and receive optical signals over each of the plurality of passive optical cables at a rate of at least 50 gigabits per second.4. The system of claim 1 , wherein each of the plurality of sleds is configured to send and receive optical signals over the corresponding passive optical cables at a rate of at least 200 gigabits per second and wherein the ...

Battery Charge Termination Voltage Adjustment

In some examples, a control unit is configured to adjust charge termination voltage of a rechargeable energy storage device. The control unit is adapted to charge the rechargeable energy storage device to a charge termination voltage where the rechargeable energy storage device has capacity to support peak load but comes close to a system shutdown voltage after supporting peak load. The control unit is also adapted to increase the charge termination voltage if a voltage of the rechargeable energy storage device is near a system shutdown voltage after supporting peak load.

RACK LEVEL PRE-INSTALLED INTERCONNECT FOR ENABLING CABLELESS SERVER/STORAGE/NETWORKING DEPLOYMENT

Apparatus and methods for rack level pre-installed interconnect for enabling cableless server, storage, and networking deployment. Plastic cable waveguides are configured to couple millimeter-wave radio frequency (RF) signals between two or more Extremely High Frequency (EHF) transceiver chips, thus supporting millimeter-wave wireless communication links enabling components in the separate chassis to communicate without requiring wire or optical cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. A plurality of plastic cable waveguide may be coupled to applicable support/mounting members, which in turn are mounted to a rack and/or top-of-rack switches. This enables the plastic cable waveguides to be pre-installed at the rack level, and further enables racks to be installed and replaced without requiring further cabling for the supported communication links. The communication links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links. 1. A method , comprising:operatively coupling a first extremely high frequency (EHF) transceiver chip to a first component in a first chassis;operatively coupling a second EHF transceiver chip to a second component in a second chassis;coupling a plastic cable waveguide to at least one of the first chassis, the second chassis, or a rack in which the first and second chassis are installed, the plastic cable waveguide configured to couple millimeter-wave radio frequency (RF) signals output from the first EHF transceiver chip into the plastic cable waveguide and to communicatively couple the millimeter-wave RF signals to the second EHF transceiver chip; andfacilitating communication between the first and second components by transmitting a millimeter-wave RF signal from the first EHF transceiver chip to the second EHF transceiver chip via the plastic cable ...

ALL IN ONE MOBILE COMPUTING DEVICE

All in one mobile computing devices and methods performed by the devices. The all in one mobile computing device includes a processor, memory, and software instructions configured to be executed on the processor to enable the mobile computing device to perform various operations. The all in one device may include various wired and wireless interfaces that enable it to communicate with a wide-range of devices, including smartphones, tablets, laptops, personal computers, smart TVs, and others. The all in one device is capable of being remotely accessed when linked in communication with a second device, and is enabled to aggregate data from various user devices and cloud-based services to create unified data resources. Data that is accessed by the device may be synched with a cloud-based storage service to enable a user to access data from across a range of devices via the all in one device. The all in one device has a form factor that is approximately the size of a credit card, yet is capable of running a full-fledged desktop operating system.

Technologies For Switching Network Traffic In A Data Center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuity is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed. 120-. (canceled)21. A system-on-chip (SoC) network switch integrated circuit (IC) for use in forwarding network traffic that is in accordance with multiple different link layer communication protocols , the network traffic to be forwarded via a physical port associated with the SoC network switch IC to an optical communication channel and thence to a destination network device , the SoC network switch IC comprising:network communication circuitry for use, when the SoC network switch IC is in operation, in (1) receiving multiprotocol inbound network communication to the SoC network switch IC and (2) transmitting multiprotocol outbound network communication from the SoC network switch IC;network traffic switching circuitry for use in outbound network communication forwarding address determination; based upon frame data accessed by the SoC network switch IC as a function of one or more of the multiple different link layer communication protocols determined by the SoC network switch IC to correspond to the network traffic, the SoC network switch IC is to identify (1) a forwarding address of the destination network device to which the network traffic is to be forwarded by the SoC network switch ...

ROBOTICALLY SERVICEABLE COMPUTING RACK AND SLEDS

Examples may include racks for a data center and sleds for the racks, the sleds arranged to house physical resources for the data center. The sleds and racks can be arranged to be autonomously manipulated, such as, by a robot. The sleds and racks can include features to facilitate automated installation, removal, maintenance, and manipulation by a robot. 1. A method comprising:sending a movement control signal to a robot, the movement control including an indication for the robot to move proximate to a sled located in a rack of a data center; andsending a manipulation control signal to the robot, the manipulation control signal including an indication for the robot to physically manipulate the sled.2. The method of claim 1 , wherein sending the manipulation control signal comprises sending a manipulation control signal that includes an indication for the robot to remove the sled from the rack.3. The method of claim 2 , wherein the removed sled includes a physical resource claim 2 , and wherein sending the manipulation control signal comprises sending a manipulation control signal that includes an indication to replace removed sled with another sled having a physical resource of the same type as the physical resource of the removed sled.4. The method of claim 1 , further comprising:receiving, by the robot, the manipulation control signal; andgenerating, by a controller of the robot, a movement control signal to cause the robot to manipulate the sled.5. The method of claim 1 , wherein the rack comprises:a first post and a second post; anda plurality of pairs of sled brackets, a first sled bracket from each of the plurality of pairs of sled brackets coupled to the first post and a second sled bracket from each of the plurality of pairs of sled brackets coupled to the second post, wherein each of the plurality of pairs of sled brackets define a corresponding sled space to receive a corresponding sled.6. The method of claim 5 , wherein the rack further comprises a pair ...

TECHNOLOGIES FOR SWITCHING NETWORK TRAFFIC IN A DATA CENTER

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed. 1. A network switch comprising:one or more processors;communication circuitry coupled to the one or more processors, wherein the communication circuitry is to assist the one or more processors to switch network traffic of multiple link layer protocols; receive, with the communication circuitry through an optical connection, network traffic to be forwarded;', 'determine a link layer protocol of the received network traffic, wherein the received network traffic is formatted according to one of the multiple link layer protocols; and', 'forward the network traffic as a function of the determined link layer protocol to a destination network device., 'one or more memory devices having stored therein a plurality of instructions that, when executed, cause the network switch to2. The network switch of claim 1 , wherein to receive the network traffic comprises to receive network traffic through an optical connection that provides one fourth of a total bandwidth of a link.3. The network switch of claim 1 , wherein to receive the network traffic comprises to receive the network traffic from a sled coupled to the optical connection.4. The network switch of claim 3 , wherein to receive the network ...

Technologies for switching network traffic in a data center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

Network device switch

A switch for transmitting data from a first device to a second device includes a port in communication with the second device, queues which store slices of data received from the first device, and circuitry for selectively outputting a slice of the data from at least one of the queues to the port for transmission to the second device.

CABLELESS CONNECTION APPARATUS AND METHOD FOR COMMUNICATION BETWEEN CHASSIS

Apparatus and methods for cableless connection of components within chassis and between separate chassis. Pairs of Extremely High Frequency (EHF) transceiver chips supporting very short length millimeter-wave wireless communication links are configured to pass radio frequency signals through holes in one or more metal layers in separate chassis and/or frames, enabling components in the separate chassis to communicate without requiring cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. The EHF-based wireless links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links. 1. An apparatus , comprising:a first chassis, configured to be installed in a rack and including a sheet metal base in which a first plurality of holes are formed and having a backplane mounted therein parallel to the sheet metal base and including a first plurality of extremely high frequency (EHF) transceiver chips mounted to its underside, each EHF transceiver chip disposed proximate to a respective hole in the sheet metal base; anda second chassis, configured to be installed in the rack and including at least one of a plurality of blades or modules, wherein at least a portion of the blades or modules includes an EHF transceiver chip that is configured to communicate with a respective EHF transceiver chip in the first plurality of EHF transceiver chips when the first and second chassis are installed in the rack to implement a plurality of millimeter-wave wireless links facilitated by respective pairs of EHF transceiver chips, wherein radio frequency signals for each millimeter-wave wireless link pass through a respective hole in the sheet metal base of the first chassis.2. The apparatus of claim 1 , wherein the backplane comprises a storage array backplane including a plurality of Serial ATA (SATA) connectors.3. The ...

TECHNOLOGIES FOR SLED ARCHITECTURE

A sled for operation in a corresponding rack of a data center includes a chassis-less circuit board substrate having one or more physical resources coupled to a top side of the chassis-less circuit board and one or more memory devices coupled to a bottom side of the chassis-less circuit board. The sled does not include a housing or chassis and is opened to the local environment. In the illustrative embodiments, the sled may be embodied as a compute sled, an accelerator sled, or a storage sled. 1. A sled for operation in a rack of a data center , the sled comprising:a chassis-less circuit board substrate having a top side and a bottom side opposite the top side;one or more physical resources coupled to the top side of the chassis-less circuit board substrate; andone or more memory devices coupled to the bottom side of the chassis-less circuit board substrate, wherein each of the one or more memory devices is electrically coupled to at least one of the one or more physical resources.2. The sled of claim 1 , wherein the chassis-less circuit board substrate is exposed to the local environment.3. The sled of claim 1 , further comprising a plurality of electrical components claim 1 , including the one or more physical resources and the one or more memory devices claim 1 , coupled to the chassis-less circuit board substrate claim 1 , wherein no electrical component of the sled is cooled by an active cooling system of the sled during operation of the sled.4. The sled of claim 3 , further comprising a power connector to mate with a corresponding power connector of the rack to provide power to the electrical components of the sled.5. The sled of claim 1 , further comprising a plurality of electrical components claim 1 , including the one or more physical resources and the one or more memory devices claim 1 , coupled to the chassis-less circuit board substrate claim 1 , wherein no electrical component of the sled receives power from a power supply of the sled during operation ...

Technologies for optical communication in rack clusters

Technologies for optical communication in a rack cluster in a data center are disclosed. In the illustrative embodiment, a network switch is connected to each of 1,024 sleds by an optical cable that enables communication at a rate of 200 gigabits per second. The optical cable has low loss, allowing for long cable lengths, which in turn allows for connecting to a large number of sleds. The optical cable also has a very high intrinsic bandwidth limit, allowing for the bandwidth to be upgraded without upgrading the optical infrastructure.

Technologies for sled architecture

A sled for operation in a corresponding rack of a data center includes a chassis-less circuit board substrate having one or more physical resources coupled to a top side of the chassis-less circuit board and one or more memory devices coupled to a bottom side of the chassis-less circuit board. The sled does not include a housing or chassis and is opened to the local environment. In the illustrative embodiments, the sled may be embodied as a compute sled, an accelerator sled, or a storage sled.

TECHNOLOGIES FOR RACK ARCHITECTURE

A rack for supporting a sleds includes a pair of elongated support posts and pairs of elongated support arms that extend from the elongated support posts. Each pair of the elongated support arms defines a sled slot to receive a corresponding sled. To do so, each elongated support arm includes a circuit board guide to receive a chassis-less circuit board substrate of the corresponding sled. The rack may include a cross-member arm associated with each sled slot and an optical connector mounted to each cross-member arm. Additional elongated support posts may be used to provide additional sled slots. 1. A rack to support a plurality of sleds , the rack comprising:two elongated support posts that extend vertically;a plurality of pairs of elongated support arms, wherein each pair of elongated support arms comprises a first support arm that extends outwardly from a first support post of the two elongated support posts and a second support arm that extends outwardly from a second support post of the two elongated supports posts,wherein each pair of elongated support arms defines a sled slot to receive a sled and each elongated support arm includes a circuit board guide attached to a top side of the corresponding elongated support arm, wherein each circuit board guide includes a circuit board slot to receive a side edge of a chassis-less circuit board substrate of a corresponding sled when the corresponding sled is received in a corresponding sled slot.2. The rack of claim 1 , wherein at least one of the elongated support posts comprises an inner wall that defines an elongated inner chamber claim 1 , andfurther comprising an interconnect positioned in the elongated inner chamber.3. The rack of claim 1 , wherein the plurality of pairs of elongated support arms comprises seven pairs of elongated support arms that define seven different sled slots.4. The rack of claim 1 , wherein each elongated support arm is adjustably attached to the corresponding first or second support post ...

Technologies for optical communication in rack clusters

Technologies for optical communication in a rack cluster in a data center are disclosed. In the illustrative embodiment, a network switch is connected to each of 1,024 sleds by an optical cable that enables communication at a rate of 200 gigabits per second. The optical cable has low loss, allowing for long cable lengths, which in turn allows for connecting to a large number of sleds. The optical cable also has a very high intrinsic bandwidth limit, allowing for the bandwidth to be upgraded without upgrading the optical infrastructure.

TECHNOLOGIES FOR BLIND MATING FOR SLED-RACK CONNECTIONS

Technologies for blind mating of optical connectors in a rack of a data center are disclosed. In the illustrative embodiment, a sled can be slid into a rack and an optical connector on the sled will blindly mate with a corresponding optical connector on the rack. The illustrative optical connector on the sled includes two guide post receivers which mate with corresponding guide posts on the optical connector on the rack such that, when mated, optical fibers of the optical connector on the rack will be aligned and optically coupled with corresponding optical fibers on the optical connector of the sled. 1. A sled for use in a rack in a data center , the sled comprising:a circuit board configured to be supported by a pair of support arms of the rack;a sled-side optical connector configured to blindly mate with a rack-side optical connector of the rack when the sled is slid into the rack to a mounted position,wherein the sled-side connector comprises a plurality of guide posts or a plurality of guide post receivers, andwherein the sled-side connector comprises a ferrule and a plurality of optical fibers, wherein the ferrule comprises a mating surface having a hole for each optical fiber of the plurality of optical fibers, wherein each optical fiber of the plurality of optical fibers is arranged in the corresponding hole of the ferrule such that a polished output surface of the optical fiber is flush with the mating surface of the ferrule.2. The sled of claim 1 , wherein the mating surface is flat.3. The sled of claim 1 , the sled-side connector comprises the plurality of guide posts and wherein each guide post of the plurality of guide posts is at least 5 millimeters long.4. The sled of claim 1 , wherein each optical fiber of the plurality of optical fibers is a 50 micrometer core fiber.5. The sled of claim 1 , wherein the sled-side optical connector does not have a fastener to secure the sled-side optical connector to the rack-side optical connector.6. The sled of ...

TECHNOLOGIES FOR SWITCHING NETWORK TRAFFIC IN A DATA CENTER

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuity is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

Technologies for data center multi-zone cabling

Technologies for connecting data cables in a data center are disclosed. In the illustrative embodiment, racks of the data center are grouped into different zones based on the distance from the racks in a given zone to a network switch. All of the racks in a given zone are connected to the network switch using data cables of the same length. In some embodiments, certain physical resources such as storage may be placed in racks that are in zones closer to the network switch and therefore use shorter data cables with lower latency. An orchestrator server may, in some embodiments, schedule workloads or create virtual servers based on the different zones and corresponding latency of different physical resources.

Battery charge termination voltage adjustment

In some examples, a control unit is configured to adjust charge termination voltage of a rechargeable energy storage device. The control unit is adapted to charge the rechargeable energy storage device to a charge termination voltage where the rechargeable energy storage device has capacity to support peak load but comes close to a system shutdown voltage after supporting peak load. The control unit is also adapted to increase the charge termination voltage if a voltage of the rechargeable energy storage device is near a system shutdown voltage after supporting peak load.

TECHNOLOGIES FOR PROVIDING A SPLIT MEMORY POOL FOR FULL RACK CONNECTIVITY

Technologies for utilizing a split memory pool include a compute sled. The compute sled includes multiple processors communicatively coupled together through a processor communication link. Each processor is to communicate with a different memory sled through a respective memory network dedicated to the corresponding processor and memory sled. The compute sled includes a compute engine to generate a memory access request to access a memory address in far memory. The far memory includes memory located on one of the memory sleds. The compute engine is also to determine, as a function of the memory address and a map of memory address ranges to the memory sleds, the memory sled on which to access the far memory, and send the memory access request to the determined memory sled to access the far memory associated with the memory address. 1. A compute sled comprising:multiple processors communicatively coupled together through a processor communication link, wherein each processor is to communicate with a different memory sled through a respective memory network dedicated to the corresponding processor and memory sled; and generate a memory access request to access a memory address in far memory, wherein the far memory comprises memory located on one of the memory sleds;', 'determine, as a function of the memory address and a map of memory address ranges to the memory sleds, the memory sled on which to access the far memory; and', 'send the memory access request to the determined memory sled to access the far memory associated with the memory address., 'a compute engine to2. The compute sled of claim 1 , wherein to send the memory access request comprises to send a request to read data from the memory address.3. The compute sled of claim 1 , wherein to send the memory access request comprises to send a request to write data to the memory address claim 1 , wherein the memory access request includes the data to be written.4. The compute sled of claim 1 , wherein the multiple ...

Technologies For Switching Network Traffic In A Data Center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed. 120-. (canceled)21. A system-on-chip (SoC) network switch integrated circuit (IC) for use in forwarding network traffic that is in accordance with multiple different link layer communication protocols , the network traffic to be forwarded via a physical port associated with the SoC network switch IC to an optical communication channel and thence to a destination network device , the SoC network switch IC comprising:network communication circuitry for use, when the SoC network switch IC is in operation, in (1) receiving multiprotocol inbound network communication to the SoC network switch IC and (2) transmitting multiprotocol outbound network communication from the SoC network switch IC;network traffic switching circuitry for use in outbound network communication forwarding address determination; based upon frame data accessed by the SoC network switch IC as a function of one or more of the multiple different link layer communication protocols determined by the SoC network switch IC to correspond to the network traffic, the SoC network switch IC is to identify (1) a forwarding address of the destination network device to which the network traffic is to be forwarded by the SoC network switch ...

TECHNOLOGIES FOR OPTICAL COMMUNICATION IN RACK CLUSTERS

Technologies for optical communication in a rack cluster in a data center are disclosed. In the illustrative embodiment, a network switch is connected to each of 1,024 sleds by an optical cable that enables communication at a rate of 200 gigabits per second. The optical cable has low loss, allowing for long cable lengths, which in turn allows for connecting to a large number of sleds. The optical cable also has a very high intrinsic bandwidth limit, allowing for the bandwidth to be upgraded without upgrading the optical infrastructure. 1a plurality of network switches, each network switch of the plurality of network switches comprising a plurality of optical connectors;a plurality of sleds, each sled of the plurality of sleds comprising a circuit board, an optical connecter mounted on the circuit board, and one or more physical resources mounted on the circuit board; at least two optical fibers;', 'a first connector at a first end of the passive optical cable connected to an optical connector of a sled of a plurality of sleds; and', 'a second connector at a second end of the passive optical cable connected to an optical connector of the plurality of optical connectors of a corresponding network switch of the plurality of the network switches,, 'a plurality of passive optical cables, wherein each passive optical cable of the plurality of passive optical cables compriseswherein each of the plurality of sleds is connected to each of the plurality of network switches by at least one of the plurality of passive optical cables.. A system comprising: The present application is a continuation application of U.S. application Ser. No. 15/396,035, entitled “TECHNOLOGIES FOR OPTICAL COMMUNICATION IN RACK CLUSTERS,” which was filed on Dec. 30, 2016, is scheduled to issue as U.S. Pat. No. 10,070,207 on Sep. 4, 2018, and claims the benefit of U.S. Provisional Patent Application No. 62/365,969, filed Jul. 22, 2016, U.S. Provisional Patent Application No. 62/376,859, filed Aug. 18, ...

Technologies for switching network traffic in a data center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuity is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

Techniques to process packets in a dual-mode switching environment

Various embodiments are generally directed to an apparatus, method and other techniques to receive a packet via an optical fabric, the packet comprising a switch mode indicator, determine a switch mode for the packet based on the switch mode indicator, and process the packet in accordance with a first protocol or a second protocol based on the switch mode.

Accelerator resource allocation and pooling

Examples may include techniques to allocate physical accelerator resources from pools of accelerator resources. In particular, virtual computing devices can be composed from physical resources and physical accelerator resources dynamically allocated to the virtual computing devices. The present disclosure provides that physical accelerator resources can be dynamically allocated, or composed, to a virtual computing device despite not being physically coupled to other components in the virtual device.

TECHNOLOGIES FOR DATA CENTER MULTI-ZONE CABLING

Technologies for connecting data cables in a data center are disclosed. In the illustrative embodiment, racks of the data center are grouped into different zones based on the distance from the racks in a given zone to a network switch. All of the racks in a given zone are connected to the network switch using data cables of the same length. In some embodiments, certain physical resources such as storage may be placed in racks that are in zones closer to the network switch and therefore use shorter data cables with lower latency. An orchestrator server may, in some embodiments, schedule workloads or create virtual servers based on the different zones and corresponding latency of different physical resources. 1. A data center comprising:a network switch; wherein each zone of the plurality of zones is associated with a minimum threshold distance and a maximum threshold distance that define a distance range, wherein no two distance ranges of the plurality of zones overlap with each other, and', 'wherein each rack of the plurality of racks is defined as located in a zone of the plurality of zones if the distance from the network switch to the corresponding rack is above the minimum threshold distance associated with the corresponding zone and below a maximum threshold distance associated with the corresponding zone; and, 'a plurality of racks, wherein each rack of the plurality of racks is located in a corresponding zone of a plurality of zones,'}a plurality of data cables, wherein each rack of the plurality of racks is connected to the network switch with one of the data cables of the plurality of data cables and wherein each data cable of the plurality of data cables that is connected to a corresponding rack located in the same zone has approximately the same length.2. The data center of claim 1 , wherein each rack of the plurality of racks comprises a plurality of sleds claim 1 , wherein each data cable of the plurality of data cables is connected directly to a sled ...

Mobile computing device technology and systems and methods utilizing the same

Mobile computing device technology and systems and methods using the same are described herein. In particular, mobile computing devices that may serve as a processing component of a disaggregated computing system described, non-integral screens that may be paired with the mobile computing devices, and systems and methods using such devices and screens are described. In some embodiments, the mobile computing device technology includes a mobile computing device that lacks an integral screen, but which is capable of throwing at least video information to a non-integral target screen, e.g., via a paired connection established over a wired or wireless communication interface.

Battery charge termination voltage adjustment

In some examples, an apparatus is to adjust charge termination voltage. The apparatus includes a controller to adjust a charge termination voltage of a charger of a rechargeable energy storage device based on a comparison of a first threshold level with the voltage of the rechargeable energy storage device during peak load. The charge termination voltage is a voltage at which the rechargeable energy storage device has capacity to support peak load of a system. The controller is to adjust the charge termination voltage based on a comparison of a second threshold level with an end voltage of the rechargeable energy storage device after peak load.

Technologies for switching network traffic in a data center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

Technologies for providing power to a rack

A rack for supporting sleds includes a pair of elongated support posts and pairs of elongated support arms that extend from the elongated support posts. Each pair of the elongated support arms defines a sled slot to receive a corresponding sled. A power supply is attached to an elongated support arm of each pair of elongated support arms to provide power to a corresponding sled. The power supply may include a chassis-less circuit board substrate that is removable from a power supply housing coupled to the corresponding elongated support arm.

Cableless connection apparatus and method for communication between chassis

Apparatus and methods for cableless connection of components within chassis and between separate chassis. Pairs of Extremely High Frequency (EHF) transceiver chips supporting very short length millimeter-wave wireless communication links are configured to pass radio frequency signals through holes in one or more metal layers in separate chassis and/or frames, enabling components in the separate chassis to communicate without requiring cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. The EHF-based wireless links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links.

Memory and power mezzanine connectors

Sleds for operation in racks of data centers are disclosed herein. A sled includes a circuit board substrate, one or more physical resources, and one or more memory devices. The circuit board substrate has a top side and a bottom side arranged opposite the top side. The one or more physical resources are coupled to the top side of the circuit board substrate. The one or more memory devices are coupled to the bottom side of the circuit board substrate. Additionally, the sled includes a connector to electrically couple the one or more physical resources to the one or more memory devices.

Method and apparatus for providing a remotely managed expandable computer system

A remotely managed expandable multi-user computer system is provided. The computer system includes a removable compute cartridge and a removable storage cartridge allowing easy upgrade of the computer system. The computer system self-configures when powered on to allow remote management by another system over a network. Automatic failover support is provided without the need for a separate compute element. A self-configurable removable secure-to-wireless converter to couple to a client computer system allows secure communications between the multi-user system and the client computer system via a wireless network.

Storage sled for data center

Examples may include a sled for a rack of a data center including physical storage resources. The sled comprises an array of storage devices and an array of memory. The storage devices and memory are directly coupled to storage resource processing circuits which are themselves, directly coupled to dual-mode optical network interface circuitry. The dual-mode optical network interface circuitry can have a bandwidth equal to or greater than the storage devices.

Technologies for blind mating for sled-rack connections

Technologies for blind mating of optical connectors in a rack of a data center are disclosed. In the illustrative embodiment, a sled can be slid into a rack and an optical connector on the sled will blindly mate with a corresponding optical connector on the rack. The illustrative optical connector on the sled includes two guide post receivers which mate with corresponding guide posts on the optical connector on the rack such that, when mated, optical fibers of the optical connector on the rack will be aligned and optically coupled with corresponding optical fibers on the optical connector of the sled.

BATTERY CHARGING WITH LITHIUM PLATING DETECTION AND BATTERY DEGRADATION DETECTION AND SEPARATION

In some examples, an apparatus includes a controller to monitor voltage of a battery during constant current charging of the battery, and to detect lithium plating of the battery based on a rate of change of the monitored voltage of the battery during constant current charging of the battery. In some examples, a battery module includes a plurality of battery cells connected in parallel, and a controller to determine an impedance of each of the plurality of battery cells, and to disconnect one of the plurality of battery cells from the plurality of battery cells based on a relation of the impedance of the one of the plurality of battery cells with a threshold impedance.

BATTERY CHARGE TERMINATION VOLTAGE ADJUSTMENT

In some examples, a control unit is configured to adjust charge termination voltage of a rechargeable energy storage device. The control unit is adapted to charge the rechargeable energy storage device to a charge termination voltage where the rechargeable energy storage device has capacity to support peak load but comes close to a system shutdown voltage after supporting peak load. The control unit is also adapted to increase the charge termination voltage if a voltage of the rechargeable energy storage device is near a system shutdown voltage after supporting peak load.

TECHNOLOGIES FOR PROVIDING POWER TO A RACK

A rack for supporting sleds includes a pair of elongated support posts and pairs of elongated support arms that extend from the elongated support posts. Each pair of the elongated support arms defines a sled slot to receive a corresponding sled. A power supply is attached to an elongated support arm of each pair of elongated support arms to provide power to a corresponding sled. The power supply may include a chassis-less circuit board substrate that is removable from a power supply housing coupled to the corresponding elongated support arm. 1. A rack to support a plurality of sleds , the rack comprising:two elongated support posts that extend vertically;a plurality of pairs of elongated support arms, wherein each pair of elongated support arms comprises a first support arm that extends outwardly from a first support post of the two elongated support posts and a second support arm that extends outwardly from a second support post of the two elongated supports posts, wherein each pair of elongated support arms defines a sled slot to receive a corresponding sled; anda power supply coupled to each first elongated support arm, wherein each power supply is associated with a corresponding sled slot and includes a sled-side power connector to mate with a corresponding power connector of the corresponding sled when the corresponding sled is received in corresponding sled slot to supply power to electrical components of the corresponding sled.2. The rack of claim 1 , wherein each power supply includes a power supply housing secured to the corresponding first elongated support arm.3. The rack of claim 1 , wherein the sled-side power connector of each power supply is located toward a distal end of the corresponding first support arm relative to the first support post.4. The rack of claim 1 , further comprising a power supply housing secured to each first elongated support arm claim 1 , andwherein each power supply comprises a chassis-less circuit board substrate received in a ...

Cableless connection apparatus and method for communication between chassis

Apparatus and methods for cableless connection of components within chassis and between separate chassis. Pairs of Extremely High Frequency (EHF) transceiver chips supporting very short length millimeter-wave wireless communication links are configured to pass radio frequency signals through holes in one or more metal layers in separate chassis and/or frames, enabling components in the separate chassis to communicate without requiring cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. The EHF-based wireless links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links.

Technologies for switching network traffic in a data center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

Apparatus and method for battery charging with lithium plating detection and battery degradation detection and separation

In some examples, an apparatus includes a controller to monitor voltage of a battery during constant current charging of the battery, and to detect lithium plating of the battery based on a rate of change of the monitored voltage of the battery during constant current charging of the battery. In some examples, a battery module includes a plurality of battery cells connected in parallel, and a controller to determine an impedance of each of the plurality of battery cells, and to disconnect one of the plurality of battery cells from the plurality of battery cells based on a relation of the impedance of the one of the plurality of battery cells with a threshold impedance.

TECHNOLOGIES FOR A CONFIGURABLE PROCESSOR MODULE

A configurable processor module includes a central processing unit (CPU) package mounted to a CPU substrate, which may be mounted to a circuit board substrate. The CPU substrate may include physical resources usable by the CPU package, which may not be included or duplicated on the circuit board substrate. As such, features of the CPU package that are unavailable on the circuit board substrate may be available on the CPU substrate. Additionally, the CPU substrate and physical resources may be selected and designed so as to provide varying levels of functionality across different compute devices that use the same type of CPU package. 1. A configurable processor module comprising:a central processing unit (CPU) package mounted to a CPU substrate, wherein the CPU package comprises at least one processor core;one or more CPU physical resources mounted to the CPU substrate, wherein each of the CPU physical resources is communicatively coupled to the CPU package via an interconnect of the CPU substrate and usable by the CPU package to facilitate operations of the CPU package,wherein the CPU substrate is configured to be received in a CPU substrate connector of a circuit board substrate.2. The configurable processor module of claim 1 , wherein the CPU package is mounted to the CPU substrate by a ball grid array.3. The configurable processor module of claim 1 , wherein the CPU package is mounted to the CPU substrate by a reflow grid array.4. The configurable processor module of claim 1 , wherein the one or more CPU physical resources comprise a physical resource usable by the CPU package to facilitate operation of the CPU package and not duplicated on the circuit board substrate.5. The configurable processor module of claim 4 , wherein the one or more CPU physical resources comprise a channel of memory not accessible on the circuit board substrate.6. The configurable processor module of claim 1 , wherein the one or more CPU physical resources comprise a memory device7. The ...

All in one mobile computing device

All in one mobile computing devices and methods performed by the devices. The all in one mobile computing device includes a processor, memory, and software instructions configured to be executed on the processor to enable the mobile computing device to perform various operations. The all in one device may include various wired and wireless interfaces that enable it to communicate with a wide-range of devices, including smartphones, tablets, laptops, personal computers, smart TVs, and others. The all in one device is capable of being remotely accessed when linked in communication with a second device, and is enabled to aggregate data from various user devices and cloud-based services to create unified data resources. Data that is accessed by the device may be synched with a cloud-based storage service to enable a user to access data from across a range of devices via the all in one device. The all in one device has a form factor that is approximately the size of a credit card, yet is capable ...

Battery charge termination voltage adjustment

In some examples, a control unit is configured to adjust charge termination voltage of a rechargeable energy storage device. The control unit is adapted to charge the rechargeable energy storage device to a charge termination voltage where the rechargeable energy storage device has capacity to support peak load but comes close to a system shutdown voltage after supporting peak load. The control unit is also adapted to increase the charge termination voltage if a voltage of the rechargeable energy storage device is near a system shutdown voltage after supporting peak load.

RACK LEVEL PRE-INSTALLED INTERCONNECT FOR ENABLING CABLELESS SERVER/STORAGE/NETWORKING DEPLOYMENT

Apparatus and methods for rack level pre-installed interconnect for enabling cableless server, storage, and networking deployment. Plastic cable waveguides are configured to couple millimeter-wave radio frequency (RF) signals between two or more Extremely High Frequency (EHF) transceiver chips, thus supporting millimeter-wave wireless communication links enabling components in the separate chassis to communicate without requiring wire or optical cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. A plurality of plastic cable waveguide may be coupled to applicable support/mounting members, which in turn are mounted to a rack and/or top-of-rack switches. This enables the plastic cable waveguides to be pre-installed at the rack level, and further enables racks to be installed and replaced without requiring further cabling for the supported communication links. The communication links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links. 1. A method , comprising:operatively coupling a first extremely high frequency (EHF) transceiver chip to a first component in a first chassis;operatively coupling a second EHF transceiver chip to a second component in a second chassis;coupling a plastic cable waveguide to at least one of the first chassis, the second chassis, or a rack in which the first and second chassis are installed, the plastic cable waveguide configured to couple millimeter-wave radio frequency (RF) signals output from the first EHF transceiver chip into the plastic cable waveguide and to communicatively couple the millimeter-wave RF signals to the second EHF transceiver chip; andfacilitating communication between the first and second components by transmitting a millimeter-wave RF signal from the first EHF transceiver chip to the second EHF transceiver chip via the plastic cable ...

Technologies for providing a split memory pool for full rack connectivity

Technologies for utilizing a split memory pool include a compute sled. The compute sled includes multiple processors communicatively coupled together through a processor communication link. Each processor is to communicate with a different memory sled through a respective memory network dedicated to the corresponding processor and memory sled. The compute sled includes a compute engine to generate a memory access request to access a memory address in far memory. The far memory includes memory located on one of the memory sleds. The compute engine is also to determine, as a function of the memory address and a map of memory address ranges to the memory sleds, the memory sled on which to access the far memory, and send the memory access request to the determined memory sled to access the far memory associated with the memory address.

TECHNOLOGIES FOR RACK COOLING

Technologies for rack cooling includes monitoring a temperature of a sled mounted in a rack and controlling a cooling system of the rack based on the temperature of the sled. The cooling system includes a cooling fan array, which may be controlled to cool the sled. Additionally, if needed, one or more adjacent cooling fan arrays that are located adjacent to the controlled cooling fan array may be adjusted to provide additional cooling to the sled. 1. A cooling controller of a data center , the cooling controller comprising:one or more processors; monitor sensor data indicative of a temperature of a first sled mounted in a first sled slot of a rack; and', 'control a cooling system of the rack based on the temperature of the sled to control the temperature of the sled., 'one or more memory devices having stored therein a plurality of instructions that, when executed by the one or more processors, cause the cooling controller to2. The cooling controller of claim 1 , wherein to control the cooling system of the rack comprises to control a fan speed of a fan array of the first sled slot of the rack to cool the sled.3. The cooling controller of claim 2 , wherein the plurality of instructions claim 2 , when executed by the one or more processors claim 2 , further cause the cooling controller to determine whether the cooling of the first sled provided by the fan array of the first sled slot requires augmenting based on the temperature of the first sled.4. The cooling controller of claim 3 , wherein to determine whether the cooling of the first sled requires augmenting comprises to compare the temperature of the first sled to a reference threshold temperature.5. The cooling controller of claim 4 , wherein to determine whether the cooling of the first sled requires augmenting comprises to compare the temperature of the first sled to a temperature of a second sled mounted in a second sled slot of the rack adjacent to the first sled slot.6. The cooling controller of claim 4 , ...

PACKAGE ARCHITECTURE WITH VERTICAL STACKING OF INTEGRATED CIRCUIT DIES HAVING PLANARIZED EDGES

Embodiments of an integrated circuit (IC) die comprise: a first region having a first surface and a second surface, the first surface being orthogonal to the second surface; and a second region attached to the first region along a planar interface that is orthogonal to the first surface and parallel to the second surface, the second region having a third surface coplanar with the first surface. The first region comprises: a dielectric material; layers of conductive traces in the dielectric material, each layer of the conductive traces being parallel to the second surface such that the conductive traces are orthogonal to the first surface; conductive vias through the dielectric material; and bond-pads on the first surface, the bond-pads comprising portions of the conductive traces exposed on the first surface, and the second region comprises a material different from the dielectric material.

Battery Charge Termination Voltage Adjustment

In some examples, an apparatus is to adjust charge termination voltage. The apparatus includes a controller to adjust a charge termination voltage of a charger of a rechargeable energy storage device based on a comparison of a first threshold level with the voltage of the rechargeable energy storage device during peak load. The charge termination voltage is a voltage at which the rechargeable energy storage device has capacity to support peak load of a system. The controller is to adjust the charge termination voltage based on a comparison of a second threshold level with an end voltage of the rechargeable energy storage device after peak load. 1. An apparatus to adjust charge termination voltage , comprising: adjust a charge termination voltage of a charger of a rechargeable energy storage device based on a comparison of a first threshold level with the voltage of the rechargeable energy storage device during peak load, wherein the charge termination voltage is a voltage at which the rechargeable energy storage device has capacity to support peak load of a system; and', 'adjust the charge termination voltage based on a comparison of a second threshold level with an end voltage of the rechargeable energy storage device after peak load., 'a controller to2. The apparatus of claim 1 , the controller to adjust the charge termination voltage based on a temperature of the rechargeable energy storage device.3. The apparatus of claim 1 , the controller to adjust the charge termination voltage based on an impedance of the rechargeable energy storage device.4. The apparatus of claim 3 , wherein the impedance includes an ohmic portion and a polarization portion.5. The apparatus of claim 1 , the controller to adjust the first threshold or the second threshold claim 1 , or both the first threshold and the second threshold claim 1 , based on one or more temperatures of the rechargeable energy storage device.6. The apparatus of claim 1 , the controller to adjust the first ...

SYSTEMS AND METHODS FOR GUARDBAND RECOVERY USING IN SITU CHARACTERIZATION

Methods and apparatuses related to guardband recovery using in situ characterization are disclosed. In one example, a system includes a target circuit, a voltage regulator to provide a variable voltage to, a phase-locked loop (PLL) to provide a variable clock to, and a temperature sensor to sense a temperature of the target circuit, and a control circuit, wherein the control circuit is to set up a characterization environment by setting a temperature, voltage, clock frequency, and workload of the target circuit, execute a plurality of tests on the target circuit, when the target circuit passes the plurality of tests, adjust the variable voltage to increase a likelihood of the target circuit failing the plurality of tests and repeat the plurality of tests, and when the target circuit fails the plurality of tests, adjust the variable voltage to decrease a likelihood of the target circuit failing the plurality of tests.

CABLELESS CONNECTION APPARATUS AND METHOD FOR COMMUNICATION BETWEEN CHASSIS

Apparatus and methods for cableless connection of components within chassis and between separate chassis. Pairs of Extremely High Frequency (EHF) transceiver chips supporting very short length millimeter-wave wireless communication links are configured to pass radio frequency signals through holes in one or more metal layers in separate chassis and/or frames, enabling components in the separate chassis to communicate without requiring cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. The EHF-based wireless links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links. 1. An apparatus , comprising:a first chassis, configured to be installed in a first slot in a data center rack and including a sheet metal base in which a first plurality of holes are formed and having a backplane mounted therein parallel to the sheet metal base, the backplane including a first plurality of extremely high frequency (EHF) transceiver chips mounted to its underside, each EHF transceiver chip disposed proximate to a respective hole in the sheet metal base; anda second chassis, configured to be installed in a second slot in the data center rack beneath the first slot and including a plurality of blades or modules, wherein at least a portion of the blades or modules includes an EHF transceiver chip that is configured to communicate with a respective EHF transceiver chip in the first plurality of EHF transceiver chips when the first and second chassis are installed in the rack to implement a plurality of millimeter-wave wireless links facilitated by respective pairs of EHF transceiver chips, wherein radio frequency signals for each millimeter-wave wireless link pass through a respective hole in the sheet metal base of the first chassis.2. The apparatus of claim 1 , wherein the backplane comprises a storage array ...

Robotically serviceable computing rack and sleds

Examples may include racks for a data center and sleds for the racks, the sleds arranged to house physical resources for the data center. The sleds and racks can be arranged to be autonomously manipulated, such as, by a robot. The sleds and racks can include features to facilitate automated installation, removal, maintenance, and manipulation by a robot.

Storage sled for a data center

Examples may include a sled for a rack of a data center including physical storage resources. The sled comprises mounting flanges to enable robotic insertion and removal from a rack and storage device mounting slots to enable robotic insertion and removal of storage devices into the sled. The storage devices are coupled to an optical fabric through storage resource controllers and a dual-mode optical network interface.

Systems and methods for guardband recovery using in situ characterization

Methods and apparatuses related to guardband recovery using in situ characterization are disclosed. In one example, a system includes a target circuit, a voltage regulator to provide a variable voltage to, a phase-locked loop (PLL) to provide a variable clock to, and a temperature sensor to sense a temperature of the target circuit, and a control circuit, wherein the control circuit is to set up a characterization environment by setting a temperature, voltage, clock frequency, and workload of the target circuit, execute a plurality of tests on the target circuit, when the target circuit passes the plurality of tests, adjust the variable voltage to increase a likelihood of the target circuit failing the plurality of tests and repeat the plurality of tests, and when the target circuit fails the plurality of tests, adjust the variable voltage to decrease a likelihood of the target circuit failing the plurality of tests.

Cableless connection apparatus and method for communication between chassis

Apparatus and methods for cableless connection of components within chassis and between separate chassis. Pairs of Extremely High Frequency (EHF) transceiver chips supporting very short length millimeter-wave wireless communication links are configured to pass radio frequency signals through holes in one or more metal layers in separate chassis and/or frames, enabling components in the separate chassis to communicate without requiring cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. The EHF-based wireless links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links.

TECHNOLOGIES FOR SWITCHING NETWORK TRAFFIC IN A DATA CENTER

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuity is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed. 1. A network switch comprising:one or more processors;communication circuitry coupled to the one or more processors, wherein the communication circuitry is to assist the one or more processors to switch network traffic of multiple link layer protocols; receive, with the communication circuitry through an optical connection, network traffic to be forwarded;', 'determine a link layer protocol of the received network traffic, wherein the received network traffic is formatted according to one of the multiple link layer protocols; and', 'forward the network traffic as a function of the determined link layer protocol to a destination network device., 'one or more memory devices having stored therein a plurality of instructions that, when executed, cause the network switch to2. The network switch of claim 1 , wherein to receive the network traffic comprises to receive network traffic through an optical connection that provides one fourth of a total bandwidth of a link.3. The network switch of claim 1 , wherein to receive the network traffic comprises to receive the network traffic from a sled coupled to the optical connection.4. The network switch of claim 3 , wherein to receive the network ...

MOBILE COMPUTING DEVICE TECHNOLOGY AND SYSTEMS AND METHODS UTILIZING THE SAME

Mobile computing device technology and systems and methods using the same are described herein. In particular, mobile computing devices that may serve as a processing component of a disaggregated computing system described, non-integral screens that may be paired with the mobile computing devices, and systems and methods using such devices and screens are described. In some embodiments, the mobile computing device technology includes a mobile computing device that lacks an integral screen, but which is capable of throwing at least video information to a non-integral target screen, e.g., via a paired connection established over a wired or wireless communication interface. 1. (canceled)2. A system comprising:a touch screen to display visual information within an automobile;at least a wireless communication interface;one or more processors; and establish a connection between the system and a mobile computing device via the wireless communication interface to convey information related to at least one application in the mobile computing device,', 'access, with the system via the at least one application in the mobile computing device, media content from the mobile computing device, wherein the at least one application is available for access by the system in accordance with authorization data in the mobile computing device,', 'process the media content from the mobile computing device, the media content comprising video information, audio information, or both video information and audio information, and', 'display, on the touch screen in response to one or more touches by a user of the touch screen, information related to the video information, audio information, or both video information and audio information., 'memory to store computer readable instructions that, when executed by the one or more processors, cause the system to'}3. The system of claim 2 , wherein the establish a connection between the system and a mobile computing device via the wireless communication ...

Rack level pre-installed interconnect for enabling cableless server/storage/networking deployment

Apparatus and methods for rack level pre-installed interconnect for enabling cableless server, storage, and networking deployment. Plastic cable waveguides are configured to couple millimeter-wave radio frequency (RF) signals between two or more Extremely High Frequency (EHF) transceiver chips, thus supporting millimeter-wave wireless communication links enabling components in the separate chassis to communicate without requiring wire or optical cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. A plurality of plastic cable waveguide may be coupled to applicable support/mounting members, which in turn are mounted to a rack and/or top-of-rack switches. This enables the plastic cable waveguides to be pre-installed at the rack level, and further enables racks to be installed and replaced without requiring further cabling for the supported communication links. The communication links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links.

CABLELESS CONNECTION APPARATUS AND METHOD FOR COMMUNICATION BETWEEN CHASSIS

Apparatus and methods for cableless connection of components within chassis and between separate chassis. Pairs of Extremely High Frequency (EHF) transceiver chips supporting very short length millimeter-wave wireless communication links are configured to pass radio frequency signals through holes in one or more metal layers in separate chassis and/or frames, enabling components in the separate chassis to communicate without requiring cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. The EHF-based wireless links support link bandwidths of up to 6 gigabits per second, and may be aggregated to facilitate multi-lane links. 1. An apparatus , comprising:a first chassis, configured to be installed in a rack and including a sheet metal base in which a first plurality of holes are formed and having a backplane mounted therein parallel to the sheet metal base and including a first plurality of extremely high frequency (EHF) transceiver chips mounted to its underside, each EHF transceiver chip disposed proximate to a respective hole in the sheet metal base; anda second chassis, configured to be installed in the rack and including at least one of a plurality of blades or modules, wherein at least a portion of the blades or modules includes an EHF transceiver chip that is configured to communicate with a respective EHF transceiver chip in the first plurality of EHF transceiver chips when the first and second chassis are installed in the rack to implement a plurality of millimeter-wave wireless links facilitated by respective pairs of EHF transceiver chips, wherein radio frequency signals for each millimeter-wave wireless link pass through a respective hole in the sheet metal base of the first chassis.2. The apparatus of claim 1 , wherein the first backplane comprises a storage array backplane including a plurality of Serial ATA (SATA) connectors.3. The ...

ADAPTIVE BURST POWER AND FAST BATTERY CHARGING APPARATUS AND METHOD

A microcontroller, processor, and/or software (SW) monitors a battery degradation indicator such as battery State-Of-Health (SOH), impedance or other attributes, and calculates battery degradation rate and regulates burst power, battery charging speed and/or battery charging limit to meet users' expectation of battery service life. The microcontroller, processor, and/or SW increases the burst power, battery charging speed and/or battery charging limit when 1/SOH or impedance change rate (or related parameter) is smaller than expected and there is more longevity budget than expected. In another example, the microcontroller, processor, and/or SW decreases the burst power, battery charging speed and/or battery charging limit when 1/SOH or impedance change rate (or related parameter) is greater than expected and there is less longevity budget than expected. 1. A machine-readable storage media having machine-executable instructions that when executed , cause one or more processors to perform a method comprising:determining a degradation indicator change of a battery of a device;comparing the degradation indicator change of the battery, relative to a baseline; andincreasing burst power, battery charging speed and/or battery charging limit for the device if the degradation indicator change is less than the baseline.2. The machine-readable storage media of having further machine-executable instructions that when executed claim 1 , cause the one or more processors to perform a further method comprising:decreasing the burst power, the battery charging speed and/or the battery charging limit for the device if the degradation indicator change is greater than the baseline.3. The machine-readable storage media of having further machine-executable instructions that when executed claim 1 , cause the one or more processors to perform a further method comprising:receiving a target service life of the battery.4. The machine-readable storage media of having further machine-executable ...

Rack level pre-installed interconnect for enabling cableless server/storage/networking deployment

Apparatus and methods for rack level pre-installed interconnect for enabling cableless server, storage, and networking deployment. Plastic cable waveguides are configured to couple millimeter-wave radio frequency (RF) signals between two or more Extremely High Frequency (EHF) transceiver chips, thus supporting millimeter-wave wireless communication links enabling components in the separate chassis to communicate without requiring wire or optical cables between the chassis. Various configurations are disclosed, including multiple configurations for server chassis, storage chassis and arrays, and network/switch chassis. A plurality of plastic cable waveguide may be coupled to applicable support/mounting members, which in turn are mounted to a rack and/or top-of-rack switches. This enables the plastic cable waveguides to be pre-installed at the rack level, and further enables racks to be installed and replaced without requiring further cabling for the supported communication links. The communication ...

MEMORY AND POWER MEZZANINE CONNECTORS

Sleds for operation in racks of data centers are disclosed herein. A sled includes a circuit board substrate, one or more physical resources, and one or more memory devices. The circuit board substrate has a top side and a bottom side arranged opposite the top side. The one or more physical resources are coupled to the top side of the circuit board substrate. The one or more memory devices are coupled to the bottom side of the circuit board substrate. Additionally, the sled includes a connector to electrically couple the one or more physical resources to the one or more memory devices.

Technologies for cooling rack mounted sleds

Technologies for rack cooling includes monitoring a temperature of a sled mounted in a rack and controlling a cooling system of the rack based on the temperature of the sled. The cooling system includes a cooling fan array, which may be controlled to cool the sled. Additionally, if needed, one or more adjacent cooling fan arrays that are located adjacent to the controlled cooling fan array may be adjusted to provide additional cooling to the sled.

Technologies for rack architecture

A rack for supporting a sleds includes a pair of elongated support posts and pairs of elongated support arms that extend from the elongated support posts. Each pair of the elongated support arms defines a sled slot to receive a corresponding sled. To do so, each elongated support arm includes a circuit board guide to receive a chassis-less circuit board substrate of the corresponding sled. The rack may include a cross-member arm associated with each sled slot and an optical connector mounted to each cross-member arm. Additional elongated support posts may be used to provide additional sled slots.

Robotically serviceable computing rack and sleds

Examples may include racks for a data center and sleds for the racks, the sleds arranged to house physical resources for the data center. The sleds and racks can be arranged to be autonomously manipulated, such as, by a robot. The sleds and racks can include features to facilitate automated installation, removal, maintenance, and manipulation by a robot.

Integrated android and windows device

Techniques for implementing assess to Android applications and native Window application on Android devices and systems. A processor board includes a processor that is configured to run a full version of a Windows operating system and Windows applications. The processor board is configured to be communicatively coupled to the processor board in an Android device, such as a Smartphone or tablet. Upon operations and when the processor board is communicatively coupled to the Android device, a user of the Android device is enabled to selectively run Android applications and Windows applications, with the Windows applications being executed natively on the processor board. The processor board may be implemented in a computing card that is approximately the size of a credit card or smaller, which in turn may be coupled to the Android device via a backpack or similar means. The processor board may also be disposed within the same housing as the Android device.

TECHNOLOGIES FOR SWITCHING NETWORK TRAFFIC IN A DATA CENTER

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuity is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

INTEGRATED ANDROID AND WINDOWS DEVICE

Techniques for implementing assess to Android applications and native Window application on Android devices and systems. A processor board includes a processor that is configured to run a full version of a Windows operating system and Windows applications. The processor board is configured to be communicatively coupled to the processor board in an Android device, such as a Smartphone or tablet. Upon operations and when the processor board is communicatively coupled to the Android device, a user of the Android device is enabled to selectively run Android applications and Windows applications, with the Windows applications being executed natively on the processor board. The processor board may be implemented in a computing card that is approximately the size of a credit card or smaller, which in turn may be coupled to the Android device via a backpack or similar means. The processor board may also be disposed within the same housing as the Android device. 125.- (canceled)26. An apparatus , comprising:a first processor board, including,a first processor;a graphics processor unit (GPU), either built into the first processor or operatively coupled to the first processor;first memory, operably coupled to the first processor;display output circuitry, either built into one of the first processor GPU or operatively coupled to at least one of the first processor and GPU;a touchscreen display, communicatively coupled to the display output circuitry; andnon-volatile storage in which first instructions are stored comprising an Android operating system and a plurality of Android applications;a second processor board, communicatively coupled to the first processor board, including;a second processor;second memory, operatively coupled to the second processor; andnon-volatile storage in which second instructions are stored comprising a Windows operating system and a plurality of Windows applications,wherein, upon operation the apparatus enables a user to selectively run the ...

Accelerator Resource Allocation and Pooling

Examples may include techniques to allocate physical accelerator resources from pools of accelerator resources. In particular, virtual computing devices can be composed from physical resources and physical accelerator resources dynamically allocated to the virtual computing devices. The present disclosure provides that physical accelerator resources can be dynamically allocated, or composed, to a virtual computing device despite not being physically coupled to other components in the virtual device. 1. A system comprising:a plurality of physical compute resources;a plurality of physical accelerator resources;a fabric to communicatively couple the plurality of physical compute resources and the plurality of physical accelerator resources; and compose a plurality of virtual computing resources from the plurality of physical compute resources and the plurality of physical accelerator resources; and', 'dynamically allocate at least one of the plurality of physical accelerator resources to a one of the plurality of virtual computing resources., 'a virtual infrastructure management framework to2. The system of claim 1 , comprising a plurality of physical storage resources claim 1 , the virtual infrastructure management framework to compose the plurality of virtual computing resources from the plurality of physical compute resources claim 1 , the plurality of physical accelerator resources and the plurality of physical storage resources.3. The system of claim 1 , comprising a plurality of physical memory resources claim 1 , the virtual infrastructure management framework to compose the plurality of virtual computing resources from the plurality of physical compute resources claim 1 , the plurality of physical accelerator resources and the plurality of physical memory resources.4. The system claim 1 , a first one of the plurality of virtual computing resources to comprise a first one of the physical compute resources and a first one of the physical accelerator resources; ...

Storage Sled and Techniques for a Data Center

Examples may include a sled for a rack of a data center including physical storage resources. The sled comprises an array of storage devices and an array of memory. The storage devices and memory are directly coupled to storage resource processing circuits which are themselves, directly coupled to dual-mode optical network interface circuitry. The circuitry can store data on the storage devices and metadata associated with the data on non-volatile memory in the memory array. 1. An apparatus for a sled of a data center , comprising:a frame to couple to a rack of a data center, the frame arranged to receive a plurality of storage devices;a group of memory sockets to receive a plurality of memory modules comprising a combination of non-volatile memory modules and volatile memory modules; andat least one storage resource processing circuit to couple to the plurality of storage devices and the plurality of memory modules, the at least one storage resource processing circuit configured to store data on the plurality of storage device and to store metadata associated with the data on the non-volatile memory modules of the plurality of memory modules.2. The apparatus of claim 1 , the at least one storage resource processing circuit comprising a processor component to compress the metadata and store the compressed metadata on the non-volatile memory modules.3. The apparatus of claim 2 , the processor component to decompress the compressed metadata to retrieve the metadata from the non-volatile memory modules.4. The apparatus of claim 1 , the at least one storage resource processing circuit to receive a packet comprising indications of data to be stored on the plurality of storage devices claim 1 , to determine whether the packet corresponds to a triggered operation claim 1 , and to initiate the triggered operation.5. The apparatus of claim 4 , wherein the triggered operation comprises processing the data prior to writing the data to the plurality of storage devices.6. The ...

Memory Module for a Data Center Compute Sled

Examples may include a sled for a rack of a data center including physical compute resources. The sled comprises a processor component and a unitary memory module comprising a memory controller and a quantity of memory based on the processor component. The unitary memory module can comprise a quantity of memory based on a number of cores of processor component to which the unitary memory module is communicably coupled. 1. An apparatus for a sled to house physical compute resources of a data center , the apparatus comprising:a substrate;a first socket to receive a processor component, the first socket disposed on a first surface of the substrate; anda first memory socket to receive a memory module, the first memory socket disposed on a second surface of the substrate different than the first surface of the substrate, the first memory socket to couple the memory module to the processor component.2. The apparatus of claim 1 , wherein the first memory socket is configured to receive a unitary memory module.3. The apparatus of claim 2 , comprising the processor component and the unitary memory module.4. The apparatus of claim 3 , the unitary memory module comprising a quantity of memory based in part on a number of cores of the processor component.5. The apparatus of claim 3 , comprising:a processor component heat sink mechanically coupled to the substrate and thermally coupled to the processor component; anda unitary memory module heat sink mechanically coupled to the substrate and thermally coupled to the near memory unitary module.6. The apparatus of claim 5 , comprising the unitary memory module heat sink removably mechanically coupled to the substrate.7. The apparatus of claim 6 , comprising a hinge coupled to the substrate and a frame coupled to the hinge claim 6 , the frame and hinge to removably mechanically couple the unitary memory module to the substrate.8. The apparatus of claim 7 , the frame and hinge to removably mechanically couple the unitary memory ...

MOBILE COMPUTING DEVICE TECHNOLOGY AND SYSTEMS AND METHODS UTILIZING THE SAME

Mobile computing device technology and systems and methods using the same are described herein. In particular, mobile computing devices that may serve as a processing component of a disaggregated computing system described, non-integral screens that may be paired with the mobile computing devices, and systems and methods using such devices and screens are described. In some embodiments, the mobile computing device technology includes a mobile computing device that lacks an integral screen, but which is capable of throwing at least video information to a non-integral target screen, e.g., via a paired connection established over a wired or wireless communication interface. 154.-. (canceled)55. A mobile computing device comprising a processor and a memory , the memory comprising at least one module comprising computer readable instructions which when executed by said processor causes said mobile computing device to perform the following operations comprising:establish a paired connection with at least one target screen via at least one of a wired and wireless communication interface, wherein the target screen is a screen that is not integral to said mobile computing device;transmit at least video information generated by at least one of an application executing on said mobile computing device and an operating system (OS) executing on said mobile computing device to said target screen over at least said paired connection;wherein said mobile computing device lacks an integral display.56. The mobile computing device of claim 55 , comprising a wireless communication interface wherein said at least one module comprises an input device module comprising computer readable instructions which when executed by said processor cause said mobile computing device to wirelessly pair with said at least one input device via said wireless communication interface.57. The mobile computing device of claim 55 , wherein said at least one module further comprises a device pairing module ...

Automated data center maintenance

Techniques for automated data center maintenance are described. In an example embodiment, an automated maintenance device may comprise processing circuitry and non-transitory computer-readable storage media comprising instructions for execution by the processing circuitry to cause the automated maintenance device to receive an automation command from an automation coordinator for a data center, identify an automated maintenance procedure based on the received automation command, and perform the identified automated maintenance procedure. Other embodiments are described and claimed.

TECHNIQUES TO PROCESS PACKETS IN A DUAL-MODE SWITCHING ENVIRONMENT

Various embodiments are generally directed to an apparatus, method and other techniques to receive a packet via an optical fabric, the packet comprising a switch mode indicator, determine a switch mode for the packet based on the switch mode indicator, and process the packet in accordance with a first protocol or a second protocol based on the switch mode. 1. An apparatus , comprising:a controller; receive a packet via an optical fabric, the packet comprising a switch mode indicator;', 'determine a switch mode for the packet based on the switch mode indicator; and', 'process the packet in accordance with a first protocol or a second protocol based on the switch mode., 'memory storing instructions operable on the controller, the instructions, when executed, cause the controller to2. The apparatus of claim 1 , the switch mode comprising an Ethernet switch mode and the controller to process the packet in accordance with the first protocol comprising an Ethernet protocol.3. The apparatus of claim 1 , the switch mode comprising a low latency switch mode and the controller to process the packet in accordance with the second protocol comprising a low latency protocol.4. The apparatus of claim 1 , the controller to send the packet to a sled via a first data path comprising one or more Ethernet links when the packet is processed in accordance with the first protocol.5. The apparatus of claim 1 , the controller to send the packet to a sled via a second data path comprising one or more low latency links when the packet is processed in accordance with the second protocol.6. The apparatus of claim 1 , the packet comprising the switch mode indicator in a switch mode indicator field claim 1 , the switch mode indicator including one or more bits to indicate the switch mode for the packet claim 1 , the controller to determine the switch mode is an Ethernet switch mode or a low latency switch mode based on the one or more bits.7. The apparatus of claim 1 , comprising a dual-mode ...

Mobile computing device technology and systems and methods utilizing the same

Mobile computing device technology and systems and methods using the same are described herein. In particular, mobile computing devices that may serve as a processing component of a disaggregated computing system described, non-integral screens that may be paired with the mobile computing devices, and systems and methods using such devices and screens are described. In some embodiments, the mobile computing device technology includes a mobile computing device that lacks an integral screen, but which is capable of throwing at least video information to a non-integral target screen, e.g., via a paired connection established over a wired or wireless communication interface.

Thermally Efficient Compute Resource Apparatuses and Methods

Examples may include racks for a data center and sleds for the racks, the sleds arranged to house physical resources for the data center. The sleds can house physical resources and heat sinks thermally coupled to the physical resources. The physical resources are arranged on the sleds and the heat sinks are configured so as to limit thermal shadowing between physical resources to reduce interference with airflow provided by fans of the racks. 1. A data center sled , comprising:a substrate having a top surface and a bottom surface;a first plurality of physical resources disposed on the top surface of the substrate; andat least one heat sink coupled to the top surface of the substrate and thermally coupled to the first plurality of physical resources, the first plurality of physical resources arranged on the top surface laterally across the top surface of the substrate to reduce thermal shadowing between ones of the first plurality of physical resources.2. The data center sled of claim 1 , wherein the substrate is a printed circuit board and the at least one heat sink is greater than 1U height.3. The data center sled of claim 1 , comprising a second plurality of physical resources disposed on the bottom surface of the substrate claim 1 , the second plurality of physical resources arranged on the bottom surface laterally across the bottom surface to reduce thermal shadowing between ones of the second plurality of physical resources.4. The data center sled of claim 3 , the second plurality of physical resources comprising a plurality of memory modules claim 3 , the plurality of memory modules comprising dual in-line memory modules (DIMMs) claim 3 , each of the plurality DIMMs arranged on the bottom surface of the substrate such that ends of each of the DIMMs are positioned perpendicular to a front edge of the top surface of the substrate.5. The data center sled of claim 4 , the second plurality of physical resources comprising a voltage regulator resource claim 4 , the ...

Storage Sled for Data Center

Examples may include a sled for a rack of a data center including physical storage resources. The sled comprises an array of storage devices and an array of memory. The storage devices and memory are directly coupled to storage resource processing circuits which are themselves, directly coupled to dual-mode optical network interface circuitry. The dual-mode optical network interface circuitry can have a bandwidth equal to or greater than the storage devices. 1. An apparatus for a sled of a data center , comprising:a frame to couple to a rack of a data center, the frame arranged to receive a plurality of storage devices;a group of memory sockets to receive a plurality of memory modules comprising a combination of three-dimensional (3D) cross-point memory and another type of computer-readable memory, different than the 3D cross-point memory;at least one storage resource processing circuit to couple to the plurality of storage devices and the plurality of memory modules; anda dual-mode optical network interface operably coupled to the at least one storage resource processing circuit to couple the plurality of storage devices to a network fabric.2. The apparatus of claim 1 , the at least one storage resource processing circuit including a plurality of storage resource processing circuits claim 1 , comprising:a first storage resource processing circuit coupled to a first subset of the plurality of storage devices and a first subset of the plurality of memory modules; anda second storage resource processing circuit coupled to a second subset of the plurality of storage devices and a second subset of the plurality of memory modules.3. The apparatus of claim 2 , comprising: the first storage resource processing circuit claim 2 , the first subset of the plurality of storage devices claim 2 , and the first subset of the plurality of memory modules corresponding to a first fault domain claim 2 , and the second storage resource processing circuit claim 2 , the second subset of ...

Storage Sled for a Data Center

Examples may include a sled for a rack of a data center including physical storage resources. The sled comprises mounting flanges to enable robotic insertion and removal from a rack and storage device mounting slots to enable robotic insertion and removal of storage devices into the sled. The storage devices are coupled to an optical fabric through storage resource controllers and a dual-mode optical network interface. 1. A data center sled , comprising:a frame to couple to a rack of a data center, the frame comprising a plurality of removable storage device mounting slots arranged to receive a plurality of storage devices;a substrate coupled to the frame;a multi-purpose connector module (MPCM) disposed on the substrate, the MPCM arranged to couple to a corresponding connector module of the rack; anda plurality of storage device MPCMs disposed on the substrate, each of the plurality of storage device MPCMs coupled to the MPCM arranged to couple to a corresponding one of the plurality of storage devices.2. The data center sled of claim 1 , comprising a dual-mode optical network interface disposed on the substrate claim 1 , the dual-mode optical network interface operably coupled to the MPCM and the storage device MPCMs.3. The data center sled of claim 2 , comprising at least one storage resource processing circuit claim 2 , the dual-mode optical network interface operably coupled to the storage device MPCMs via the at least one storage resource processing circuit.4. The data center sled of claim 3 , the at least one storage resource processing circuit comprising a first storage resource processing circuit and a second storage resource processing circuit claim 3 , the dual-mode optical network interface operably coupled to a first subset of the storage device MPCMs via the first storage resource processing circuit and operably coupled to a second subset of the storage device MPCMs via the second storage resource processing circuit.5. The data center sled of claim 4 , ...

Robotically Serviceable Computing Rack and Sleds

Examples may include racks for a data center and sleds for the racks, the sleds arranged to house physical resources for the data center. The sleds and racks can be arranged to be autonomously manipulated, such as, by a robot. The sleds and racks can include features to facilitate automated installation, removal, maintenance, and manipulation by a robot. 1. A data center rack , comprising:a first post and a second post; anda plurality of pairs of sled brackets, a first sled bracket from each of the plurality of pairs of sled brackets coupled to the first post and a second sled bracket from each of the plurality of pairs of sled brackets coupled to the second post, each of the plurality of pairs of sled brackets to receive a sled.2. The data center rack of claim 1 , each of the plurality of pairs of sled brackets to define a sled space and comprising claim 1 , a plurality of pairs of sled retainers claim 1 , a first sled retainer from each of the plurality of pairs of sled retainers coupled to the first sled bracket of a respective one of the plurality of pairs of sled brackets and a second sled retainer from each of the plurality of pairs of sled retainers coupled to the second sled bracket of the respective one of the plurality of pairs of sled brackets claim 1 , each of the plurality of pairs of sled retainers arranged to couple to a sled inserted into the sled space defined by a one of the plurality of pairs of sled brackets to which the pair of sled retainers is coupled.3. The data center rack of claim 2 , each of the plurality of pairs of sled retainers arranged to couple to a sled autonomously inserted into the sled space defined by the one of the plurality of pairs of sled brackets to which the pair of sled retainers is coupled.4. The data center rack of claim 1 , comprising a plurality of multi-purpose connector modules (MPCMs) claim 1 , each of the plurality of MPCMs disposed in a respective one of the plurality of sled spaces.5. The data center rack of ...

MULTI-LEVEL MEMORY WITH IMPROVED MEMORY SIDE CACHE IMPLEMENTATION

An apparatus is described. The apparatus includes a semiconductor chip package. The semiconductor chip package includes an SOC. The SOC has a memory controller. The semiconductor chip package includes an interface to an external memory. The semiconductor chip package includes a memory side cache. The memory side cache is composed of eDRAM and is coupled between the memory controller and the interface to the external memory. The eDRAM is to cache more frequently used items of the external memory. The semiconductor chip package has an out-of-order interface between the memory controller and the memory side cache. 1. An apparatus , comprising: a) a system one chip (SOC), the SOC comprising a memory controller;', 'b) an interface to an external memory', 'c) a memory side cache comprising embedded dynamic random access memory (eDRAM) coupled between the memory controller and the interface to the external memory, the eDRAM to cache more frequently used items of the external memory; and,', 'd) an out-of-order interface between the memory controller and the memory side cache., 'a semiconductor chip package comprising2. The apparatus of wherein the memory side cache is implemented on a separate semiconductor chip than the SOC.3. The apparatus of wherein the interface to the external memory is integrated on the same semiconductor chip as the memory side cache.4. The apparatus of wherein the interface to the external memory is integrated on a different semiconductor chip than the memory side cache and the SOC.5. The apparatus of wherein the semiconductor chip package comprises mapping logic circuitry to map a page in the memory side cache to one or more page groups in the external memory.6. An apparatus claim 2 , comprising:mapping logic circuitry to map a page in a memory side cache to a page group in a system memory.7. The apparatus of wherein the mapping logic circuitry is further to map a second page in the memory side cache to a second page group in the system memory ...

REMOVABLE AND LOW INSERTION FORCE CONNECTOR SYSTEM

Examples described herein relate to an apparatus that includes a flexible conductor covered in an insulative material and at least one conductor region in contact with the flexible conductor. In some examples, melting of the at least one conductor region is to cause a conductive coupling of the flexible conductor with a second conductor and wherein the flexible conductor is adapted to conductively couple a first circuit board oriented orthogonal to a second circuit board. In some examples, the at least one conductor region comprises at least one solder ball of a grid array. In some examples, the at least one conductor region is re-solderable. 1. An apparatus comprising:a flexible conductor covered in an insulative material andat least one conductor region in contact with the flexible conductor, wherein melting of the at least one conductor region is to cause a conductive coupling of the flexible conductor with a second conductor and wherein the flexible conductor is adapted to conductively couple a first circuit board oriented orthogonal to a second circuit board.2. The apparatus of claim 1 , wherein the at least one conductor region comprises at least one solder ball of a grid array.3. The apparatus of claim 1 , wherein the at least one conductor region is re-solderable.4. The apparatus of claim 1 , comprising:a circuit board comprising a conductor trace coupled to the at least one conductor region anda current source coupled to the conductor trace to provide a current to the at least one conductor region to heat the at least one conductor region.5. The apparatus of claim 4 , wherein the current source is to provide current to heat the at least one conductor region in connection with forming of a bond between the flexible conductor and the second conductor.6. The apparatus of claim 4 , wherein the current source is to provide current to heat the at least one conductor region in connection with breaking a bond between the flexible conductor and the second conductor. ...

Technolgies for millimeter wave rack interconnects

Racks and rack pods to support a plurality of sleds are disclosed herein. Switches for use in the rack pods are also disclosed herein. A rack comprises a plurality of sleds and a plurality of electromagnetic waveguides. The plurality of sleds are vertically spaced from one another. The plurality of electromagnetic waveguides communicate data signals between the plurality of sleds.

Accelerator resource allocation and pooling

Examples may include techniques to allocate physical accelerator resources from pools of accelerator resources. In particular, virtual computing devices can be composed from physical resources and physical accelerator resources dynamically allocated to the virtual computing devices. The present disclosure provides that physical accelerator resources can be dynamically allocated, or composed, to a virtual computing device despite not being physically coupled to other components in the virtual device.

Rack level pre-installed interconnect for enabling cableless server/storage/networking deployment

Rack level pre-installed interconnect for enabling cableless server/storage/networking deployment

Allocation and pooling of accelerator resources

Beispiele können Techniken zum Zuteilen von physischen Beschleunigerressourcen aus Pools von Beschleunigerressourcen beinhalten. Insbesondere können virtuelle Datenverarbeitungsvorrichtungen aus physischen Ressourcen und physischen Beschleunigerressourcen, die den virtuellen Datenverarbeitungsvorrichtungen dynamisch zugeteilt sind, zusammengestellt werden. Die vorliegende Offenbarung stellt es bereit, dass physische Beschleunigerressourcen einer virtuellen Datenverarbeitungsvorrichtung dynamisch zugeteilt oder zu dieser zusammengestellt werden können, obwohl sie an andere Komponenten in der virtuellen Vorrichtung nicht physisch gekoppelt sind. Examples may include techniques for allocating physical accelerator resources from pools of accelerator resources. In particular, virtual computing devices may be assembled from physical resources and physical accelerator resources dynamically allocated to the virtual computing devices. The present disclosure provides that physical accelerator resources may be dynamically allocated or aggregated to a virtual computing device, although they are not physically coupled to other components in the virtual device.

Technolgies for millimeter wave rack interconnects

Racks and rack pods to support a plurality of sleds are disclosed herein. Switches for use in the rack pods are also disclosed herein. A rack comprises a plurality of sleds and a plurality of electromagnetic waveguides. The plurality of sleds are vertically spaced from one another. The plurality of electromagnetic waveguides communicate data signals between the plurality of sleds.

Technologies for rack cooling

Technologies for rack cooling includes monitoring a temperature of a sled mounted in a rack and controlling a cooling system of the rack based on the temperature of the sled. The cooling system includes a cooling fan array, which may be controlled to cool the sled. Additionally, if needed, one or more adjacent cooling fan arrays that are located adjacent to the controlled cooling fan array may be adjusted to provide additional cooling to the sled.

Memory module for a data center compute sled

Digital signal processor

A monolithic digital signal processor includes a core processor for performing digital signal computations, an I/O processor for controlling external access to and from the digital signal processor through an external port, first and second memory banks for storing instructions and data for the digital signal computations, and first and second buses interconnecting the core processor, the I/O processor and the memory banks. The core processor and the I/O processor access the memory banks on the first bus without interference on different clock phases of a clock cycle. The internal memory and the I/O processor of the digital signal processor are assigned to a region of a global memory space, which facilitates multiprocessing configurations. In a multiprocessor system, each digital signal processor is assigned a processor ID. The digital signal processor includes a bus arbitration circuit for controlling access to an external bus through the external port. The digital signal processor may include one or more serial ports and one or more link ports for point-to-point communication with external devices. A DMA controller controls DMA transfers through the external port, the serial ports and the link ports.

System device aggregation in a liquid cooling environment

The system can include a container that contains fluid to provide two phase immersion liquid cooling (2PILC) for a system within the container. The container can enclose a first circuit board with a first side of the first circuit board is conductively coupled to at least one device. The container can enclose a motherboard conductively coupled to a second side of the first circuit board with a first side of the motherboard is conductively coupled to the second side of the first circuit board. Connectors can conductively connect the motherboard with a second circuit board. The second circuit board can include at least four edges and an edge of the motherboard is oriented approximately 90 degrees to an edge of the second circuit board. At least one device can include one or more of: a processor, memory device, accelerator device, or network interface.

Battery charge termination voltage adjustment

In some examples, an apparatus is to adjust charge termination voltage. The apparatus includes a controller to adjust a charge termination voltage of a charger of a rechargeable energy storage device based on a comparison of a first threshold level with the voltage of the rechargeable energy storage device during peak load. The charge termination voltage is a voltage at which the rechargeable energy storage device has capacity to support peak load of a system. The controller is to adjust the charge termination voltage based on a comparison of a second threshold level with an end voltage of the rechargeable energy storage device after peak load

Battery charge termination voltage adjustment

In some examples, an apparatus is to adjust charge termination voltage. The apparatus includes a controller to adjust a charge termination voltage of a charger of a rechargeable energy storage device based on a comparison of a first threshold level with the voltage of the rechargeable energy storage device during peak load. The charge termination voltage is a voltage at which the rechargeable energy storage device has capacity to support peak load of a system. The controller is to adjust the charge termination voltage based on a comparison of a second threshold level with an end voltage of the rechargeable energy storage device after peak load

Battery charge termination voltage adjustment

System device aggregation in a liquid cooling environment

Technologies for switching network traffic in a data center

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuity is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

Digital signal processor

Wormhole backplane ultrahigh density optical routing system

Apparatus and methods employing wormhole structures supporting ultra-high density optical routing systems. Microstructures comprising wormhole tunnels are formed in optical looms with wormhole openings arranged in patterns, such as a high-density XY grid. Optical fibers are inserted into respective wormhole tunnels, and sleeves are used to precisely align fiber ends. A rack loom comprising a wormhole backplane is fabricated in a similar manner, with wormhole openings arrayed in the same patterns. The sleeves comprise plug-receptacle sleeve pairs, where when an optical loom (or connector bar of the optical loom) face urged toward the front face of the rack loom, the plug and receptacle sleeves are mated, resulting in precise alignment of the optical fiber ends in the pairs of sleeves. Palpebral structures may also be fabricated to provide a self-cleaning function with optional lubrication. The solutions provide more than an order of magnitude improvement over current fiber connector densities, while substantially reducing costs.

System device aggregation in a liquid cooling environment

Examples described herein relate to a system. The system can include a container that contains fluid to provide two phase immersion liquid cooling (2PILC) for a system within the container. The container can enclose a first circuit board with a first side of the first circuit board is conductively coupled to at least one device. The container can enclose a motherboard conductively coupled to a second side of the first circuit board with a first side of the motherboard is conductively coupled to the second side of the first circuit board. The motherboard can include at least four edges. Connectors can conductively connect the motherboard with a second circuit board. The second circuit board can include at least four edges and an edge of the motherboard is oriented approximately 90 degrees to an edge of the second circuit board. At least one device can include one or more of: a processor, memory device, accelerator device, or network interface.