US20190065083A1

US20190065083A1 - Technologies for providing efficient access to pooled accelerator devices

Info

Publication number: US20190065083A1
Application number: US15/858,557
Authority: US
Inventors: Sujoy Sen; Susanne M. Balle; Narayan Ranganathan; Evan Custodio; Paul H. Dormitzer; Francesc Guim Bernat
Original assignee: Intel Corp
Current assignee: Intel Corp
Priority date: 2017-08-30
Filing date: 2017-12-29
Publication date: 2019-02-28
Also published as: WO2019045929A1; US20190069433A1; CN109428843A; US11055149B2; US20190065260A1; US11614979B2; US20190065281A1; CN109428841B; DE112018004798T5; US10888016B2; US20190068693A1; US20190065172A1; US20190065112A1; WO2019046620A1; US20190068521A1; US11392425B2; WO2019046639A1; WO2019045928A1; EP3676708A4; US11416309B2

Abstract

Technologies for providing efficient access to pooled accelerator devices include an accelerator sled. The accelerator sled includes an accelerator device and a controller connected to the accelerator device. The controller is to provide, to a compute sled, accelerator abstraction data. The accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region. The controller is further to receive, from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode. Additionally, the controller is to convert the request from a first format to a second format that is different from the second format and is usable by the accelerator device to perform the operation. Additionally, the controller is to perform, in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode. Other embodiments are also described and claimed.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

The present application claims the benefit of Indian Provisional Patent Application No. 201741030632, filed Aug. 30, 2017, and U.S. Provisional Patent Application No. 62/584,401, filed Nov. 10, 2017.

BACKGROUND

Accelerator devices, such as field programmable gate arrays (FPGA) or other devices capable of accelerating the execution of a function are usually directly attached to a central processing unit (CPU) using a high-speed interconnect (e.g., PCI Express, RLink, etc.). In some data centers, however, accelerator devices may be decoupled from a host (e.g., a compute device executing an application that may periodically request acceleration of a function) such that applications executing on a multitude of hosts can access the accelerator devices as needed. There are myriad application frameworks as well as applications that have custom stacks to access accelerator devices. Further, the use of accelerator devices by an application may range from using a single accelerator device to using multiple accelerator devices concurrently. The wide gamut of application programming models, frameworks, and protocols used to access accelerator devices typically results in a significant amount of the available capacity (e.g., logic gates, processing cycles, etc.) of each accelerator device being devoted to managing communications with the hosts (e.g., parsing requests submitted in various protocols), when that capacity could otherwise be allocated to accelerating functions on behalf of the hosts in the data center.

BRIEF DESCRIPTION OF THE DRAWINGS

The concepts described herein are illustrated by way of example and not by way of limitation in the accompanying figures. For simplicity and clarity of illustration, elements illustrated in the figures are not necessarily drawn to scale. Where considered appropriate, reference labels have been repeated among the figures to indicate corresponding or analogous elements.

FIG. 1 is a simplified diagram of at least one embodiment of a data center for executing workloads with disaggregated resources;

FIG. 2 is a simplified diagram of at least one embodiment of a pod of the data center of FIG. 1;

FIG. 3 is a perspective view of at least one embodiment of a rack that may be included in the pod of FIG. 2;

FIG. 4 is a side plan elevation view of the rack of FIG. 3;

FIG. 5 is a perspective view of the rack of FIG. 3 having a sled mounted therein;

FIG. 6 is a is a simplified block diagram of at least one embodiment of a top side of the sled of FIG. 5;

FIG. 7 is a simplified block diagram of at least one embodiment of a bottom side of the sled of FIG. 6;

FIG. 8 is a simplified block diagram of at least one embodiment of a compute sled usable in the data center of FIG. 1;

FIG. 9 is a top perspective view of at least one embodiment of the compute sled of FIG. 8;

FIG. 10 is a simplified block diagram of at least one embodiment of an accelerator sled usable in the data center of FIG. 1;

FIG. 11 is a top perspective view of at least one embodiment of the accelerator sled of FIG. 10;

FIG. 12 is a simplified block diagram of at least one embodiment of a storage sled usable in the data center of FIG. 1;

FIG. 13 is a top perspective view of at least one embodiment of the storage sled of FIG. 12;

FIG. 14 is a simplified block diagram of at least one embodiment of a memory sled usable in the data center of FIG. 1; and

FIG. 15 is a simplified block diagram of a system that may be established within the data center of FIG. 1 to execute workloads with managed nodes composed of disaggregated resources.

FIG. 16 is a simplified block diagram of at least one embodiment of a system for providing efficient pooling of accelerator devices;

FIG. 17 is a simplified block diagram of at least one embodiment of an accelerator sled of the system of FIG. 16;

FIG. 18 is a simplified block diagram of at least one embodiment of an environment that may be established by the accelerator sled of FIGS. 16 and 17; and

FIGS. 19-22 are a simplified flow diagram of at least one embodiment of a method for providing efficient pooling of accelerator devices that may be performed by the accelerator sled of FIGS. 16 and 17.

DETAILED DESCRIPTION OF THE DRAWINGS

While the concepts of the present disclosure are susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawings and will be described herein in detail. It should be understood, however, that there is no intent to limit the concepts of the present disclosure to the particular forms disclosed, but on the contrary, the intention is to cover all modifications, equivalents, and alternatives consistent with the present disclosure and the appended claims.
References in the specification to “one embodiment,” “an embodiment,” “an illustrative embodiment,” etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may or may not necessarily include that particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described. Additionally, it should be appreciated that items included in a list in the form of “at least one A, B, and C” can mean (A); (B); (C); (A and B); (A and C); (B and C); or (A, B, and C). Similarly, items listed in the form of “at least one of A, B, or C” can mean (A); (B); (C); (A and B); (A and C); (B and C); or (A, B, and C).
The disclosed embodiments may be implemented, in some cases, in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried by or stored on a transitory or non-transitory machine-readable (e.g., computer-readable) storage medium, which may be read and executed by one or more processors. A machine-readable storage medium may be embodied as any storage device, mechanism, or other physical structure for storing or transmitting information in a form readable by a machine (e.g., a volatile or non-volatile memory, a media disc, or other media device).
In the drawings, some structural or method features may be shown in specific arrangements and/or orderings. However, it should be appreciated that such specific arrangements and/or orderings may not be required. Rather, in some embodiments, such features may be arranged in a different manner and/or order than shown in the illustrative figures. Additionally, the inclusion of a structural or method feature in a particular figure is not meant to imply that such feature is required in all embodiments and, in some embodiments, may not be included or may be combined with other features.
Referring now to FIG. 1, a data center 100 in which disaggregated resources may cooperatively execute one or more workloads (e.g., applications on behalf of customers) includes multiple pods 110, 120, 130, 140, each of which includes one or more rows of racks. As described in more detail herein, each rack houses multiple sleds, which each may be embodied as a compute device, such as a server, that is primarily equipped with a particular type of resource (e.g., memory devices, data storage devices, accelerator devices, general purpose processors). In the illustrative embodiment, the sleds in each pod 110, 120, 130, 140 are connected to multiple pod switches (e.g., switches that route data communications to and from sleds within the pod). The pod switches, in turn, connect with spine switches 150 that switch communications among pods (e.g., the pods 110, 120, 130, 140) in the data center 100. In some embodiments, the sleds may be connected with a fabric using Intel Omni-Path technology. As described in more detail herein, resources within sleds in the data center 100 may be allocated to a group (referred to herein as a “managed node”) containing resources from one or more other sleds to be collectively utilized in the execution of a workload. The workload can execute as if the resources belonging to the managed node were located on the same sled. The resources in a managed node may even belong to sleds belonging to different racks, and even to different pods 110, 120, 130, 140. Some resources of a single sled may be allocated to one managed node while other resources of the same sled are allocated to a different managed node (e.g., one processor assigned to one managed node and another processor of the same sled assigned to a different managed node). By disaggregating resources to sleds comprised predominantly of a single type of resource (e.g., compute sleds comprising primarily compute resources, memory sleds containing primarily memory resources), and selectively allocating and deallocating the disaggregated resources to form a managed node assigned to execute a workload, the data center 100 provides more efficient resource usage over typical data centers comprised of hyperconverged servers containing compute, memory, storage and perhaps additional resources). As such, the data center 100 may provide greater performance (e.g., throughput, operations per second, latency, etc.) than a typical data center that has the same number of resources.
Referring now to FIG. 2, the pod 110, in the illustrative embodiment, includes a set of rows 200, 210, 220, 230 of racks 240. Each rack 240 may house multiple sleds (e.g., sixteen sleds) and provide power and data connections to the housed sleds, as described in more detail herein. In the illustrative embodiment, the racks in each row 200, 210, 220, 230 are connected to multiple pod switches 250, 260. The pod switch 250 includes a set of ports 252 to which the sleds of the racks of the pod 110 are connected and another set of ports 254 that connect the pod 110 to the spine switches 150 to provide connectivity to other pods in the data center 100. Similarly, the pod switch 260 includes a set of ports 262 to which the sleds of the racks of the pod 110 are connected and a set of ports 264 that connect the pod 110 to the spine switches 150. As such, the use of the pair of switches 250, 260 provides an amount of redundancy to the pod 110. For example, if either of the switches 250, 260 fails, the sleds in the pod 110 may still maintain data communication with the remainder of the data center 100 (e.g., sleds of other pods) through the other switch 250, 260. Furthermore, in the illustrative embodiment, the switches 150, 250, 260 may be embodied as dual-mode optical switches, capable of routing both Ethernet protocol communications carrying Internet Protocol (IP) packets and communications according to a second, high-performance link-layer protocol (e.g., Intel's Omni-Path Architecture's, Infiniband) via optical signaling media of an optical fabric.
It should be appreciated that each of the other pods 120, 130, 140 (as well as any additional pods of the data center 100) may be similarly structured as, and have components similar to, the pod 110 shown in and described in regard to FIG. 2 (e.g., each pod may have rows of racks housing multiple sleds as described above). Additionally, while two pod switches 250, 260 are shown, it should be understood that in other embodiments, each pod 110, 120, 130, 140 may be connected to different number of pod switches (e.g., providing even more failover capacity).
Referring now to FIGS. 3-5, each illustrative rack 240 of the data center 100 includes two elongated support posts 302, 304, which are arranged vertically. For example, the elongated support posts 302, 304 may extend upwardly from a floor of the data center 100 when deployed. The rack 240 also includes one or more horizontal pairs 310 of elongated support arms 312 (identified in FIG. 3 via a dashed ellipse) configured to support a sled of the data center 100 as discussed below. One elongated support arm 312 of the pair of elongated support arms 312 extends outwardly from the elongated support post 302 and the other elongated support arm 312 extends outwardly from the elongated support post 304.
In the illustrative embodiments, each sled of the data center 100 is embodied as a chassis-less sled. That is, each sled has a chassis-less circuit board substrate on which physical resources (e.g., processors, memory, accelerators, storage, etc.) are mounted as discussed in more detail below. As such, the rack 240 is configured to receive the chassis-less sleds. For example, each pair 310 of elongated support arms 312 defines a sled slot 320 of the rack 240, which is configured to receive a corresponding chassis-less sled. To do so, each illustrative elongated support arm 312 includes a circuit board guide 330 configured to receive the chassis-less circuit board substrate of the sled. Each circuit board guide 330 is secured to, or otherwise mounted to, a top side 332 of the corresponding elongated support arm 312. For example, in the illustrative embodiment, each circuit board guide 330 is mounted at a distal end of the corresponding elongated support arm 312 relative to the corresponding elongated support post 302, 304. For clarity of the Figures, not every circuit board guide 330 may be referenced in each Figure.
Each circuit board guide 330 includes an inner wall that defines a circuit board slot 380 configured to receive the chassis-less circuit board substrate of a sled 400 when the sled 400 is received in the corresponding sled slot 320 of the rack 240. To do so, as shown in FIG. 4, a user (or robot) aligns the chassis-less circuit board substrate of an illustrative chassis-less sled 400 to a sled slot 320. The user, or robot, may then slide the chassis-less circuit board substrate forward into the sled slot 320 such that each side edge 414 of the chassis-less circuit board substrate is received in a corresponding circuit board slot 380 of the circuit board guides 330 of the pair 310 of elongated support arms 312 that define the corresponding sled slot 320 as shown in FIG. 4. By having robotically accessible and robotically manipulable sleds comprising disaggregated resources, each type of resource can be upgraded independently of each other and at their own optimized refresh rate. Furthermore, the sleds are configured to blindly mate with power and data communication cables in each rack 240, enhancing their ability to be quickly removed, upgraded, reinstalled, and/or replaced. As such, in some embodiments, the data center 100 may operate (e.g., execute workloads, undergo maintenance and/or upgrades, etc.) without human involvement on the data center floor. In other embodiments, a human may facilitate one or more maintenance or upgrade operations in the data center 100.
It should be appreciated that each circuit board guide 330 is dual sided. That is, each circuit board guide 330 includes an inner wall that defines a circuit board slot 380 on each side of the circuit board guide 330. In this way, each circuit board guide 330 can support a chassis-less circuit board substrate on either side. As such, a single additional elongated support post may be added to the rack 240 to turn the rack 240 into a two-rack solution that can hold twice as many sled slots 320 as shown in FIG. 3. The illustrative rack 240 includes seven pairs 310 of elongated support arms 312 that define a corresponding seven sled slots 320, each configured to receive and support a corresponding sled 400 as discussed above. Of course, in other embodiments, the rack 240 may include additional or fewer pairs 310 of elongated support arms 312 (i.e., additional or fewer sled slots 320). It should be appreciated that because the sled 400 is chassis-less, the sled 400 may have an overall height that is different than typical servers. As such, in some embodiments, the height of each sled slot 320 may be shorter than the height of a typical server (e.g., shorter than a single rank unit, “1U”). That is, the vertical distance between each pair 310 of elongated support arms 312 may be less than a standard rack unit “1U.” Additionally, due to the relative decrease in height of the sled slots 320, the overall height of the rack 240 in some embodiments may be shorter than the height of traditional rack enclosures. For example, in some embodiments, each of the elongated support posts 302, 304 may have a length of six feet or less. Again, in other embodiments, the rack 240 may have different dimensions. Further, it should be appreciated that the rack 240 does not include any walls, enclosures, or the like. Rather, the rack 240 is an enclosure-less rack that is opened to the local environment. Of course, in some cases, an end plate may be attached to one of the elongated support posts 302, 304 in those situations in which the rack 240 forms an end-of-row rack in the data center 100.
In some embodiments, various interconnects may be routed upwardly or downwardly through the elongated support posts 302, 304. To facilitate such routing, each elongated support post 302, 304 includes an inner wall that defines an inner chamber in which the interconnect may be located. The interconnects routed through the elongated support posts 302, 304 may be embodied as any type of interconnects including, but not limited to, data or communication interconnects to provide communication connections to each sled slot 320, power interconnects to provide power to each sled slot 320, and/or other types of interconnects.
The rack 240, in the illustrative embodiment, includes a support platform on which a corresponding optical data connector (not shown) is mounted. Each optical data connector is associated with a corresponding sled slot 320 and is configured to mate with an optical data connector of a corresponding sled 400 when the sled 400 is received in the corresponding sled slot 320. In some embodiments, optical connections between components (e.g., sleds, racks, and switches) in the data center 100 are made with a blind mate optical connection. For example, a door on each cable may prevent dust from contaminating the fiber inside the cable. In the process of connecting to a blind mate optical connector mechanism, the door is pushed open when the end of the cable enters the connector mechanism. Subsequently, the optical fiber inside the cable enters a gel within the connector mechanism and the optical fiber of one cable comes into contact with the optical fiber of another cable within the gel inside the connector mechanism.
The illustrative rack 240 also includes a fan array 370 coupled to the cross-support arms of the rack 240. The fan array 370 includes one or more rows of cooling fans 372, which are aligned in a horizontal line between the elongated support posts 302, 304. In the illustrative embodiment, the fan array 370 includes a row of cooling fans 372 for each sled slot 320 of the rack 240. As discussed above, each sled 400 does not include any on-board cooling system in the illustrative embodiment and, as such, the fan array 370 provides cooling for each sled 400 received in the rack 240. Each rack 240, in the illustrative embodiment, also includes a power supply associated with each sled slot 320. Each power supply is secured to one of the elongated support arms 312 of the pair 310 of elongated support arms 312 that define the corresponding sled slot 320. For example, the rack 240 may include a power supply coupled or secured to each elongated support arm 312 extending from the elongated support post 302. Each power supply includes a power connector configured to mate with a power connector of the sled 400 when the sled 400 is received in the corresponding sled slot 320. In the illustrative embodiment, the sled 400 does not include any on-board power supply and, as such, the power supplies provided in the rack 240 supply power to corresponding sleds 400 when mounted to the rack 240.
Referring now to FIG. 6, the sled 400, in the illustrative embodiment, is configured to be mounted in a corresponding rack 240 of the data center 100 as discussed above. In some embodiments, each sled 400 may be optimized or otherwise configured for performing particular tasks, such as compute tasks, acceleration tasks, data storage tasks, etc. For example, the sled 400 may be embodied as a compute sled 800 as discussed below in regard to FIGS. 8-9, an accelerator sled 1000 as discussed below in regard to FIGS. 10-11, a storage sled 1200 as discussed below in regard to FIGS. 12-13, or as a sled optimized or otherwise configured to perform other specialized tasks, such as a memory sled 1400, discussed below in regard to FIG. 14.
As discussed above, the illustrative sled 400 includes a chassis-less circuit board substrate 602, which supports various physical resources (e.g., electrical components) mounted thereon. It should be appreciated that the circuit board substrate 602 is “chassis-less” in that the sled 400 does not include a housing or enclosure. Rather, the chassis-less circuit board substrate 602 is open to the local environment. The chassis-less circuit board substrate 602 may be formed from any material capable of supporting the various electrical components mounted thereon. For example, in an illustrative embodiment, the chassis-less circuit board substrate 602 is formed from an FR-4 glass-reinforced epoxy laminate material. Of course, other materials may be used to form the chassis-less circuit board substrate 602 in other embodiments.
As discussed in more detail below, the chassis-less circuit board substrate 602 includes multiple features that improve the thermal cooling characteristics of the various electrical components mounted on the chassis-less circuit board substrate 602. As discussed, the chassis-less circuit board substrate 602 does not include a housing or enclosure, which may improve the airflow over the electrical components of the sled 400 by reducing those structures that may inhibit air flow. For example, because the chassis-less circuit board substrate 602 is not positioned in an individual housing or enclosure, there is no backplane (e.g., a backplate of the chassis) to the chassis-less circuit board substrate 602, which could inhibit air flow across the electrical components. Additionally, the chassis-less circuit board substrate 602 has a geometric shape configured to reduce the length of the airflow path across the electrical components mounted to the chassis-less circuit board substrate 602. For example, the illustrative chassis-less circuit board substrate 602 has a width 604 that is greater than a depth 606 of the chassis-less circuit board substrate 602. In one particular embodiment, for example, the chassis-less circuit board substrate 602 has a width of about 21 inches and a depth of about 9 inches, compared to a typical server that has a width of about 17 inches and a depth of about 39 inches. As such, an airflow path 608 that extends from a front edge 610 of the chassis-less circuit board substrate 602 toward a rear edge 612 has a shorter distance relative to typical servers, which may improve the thermal cooling characteristics of the sled 400. Furthermore, although not illustrated in FIG. 6, the various physical resources mounted to the chassis-less circuit board substrate 602 are mounted in corresponding locations such that no two substantively heat-producing electrical components shadow each other as discussed in more detail below. That is, no two electrical components, which produce appreciable heat during operation (i.e., greater than a nominal heat sufficient enough to adversely impact the cooling of another electrical component), are mounted to the chassis-less circuit board substrate 602 linearly in-line with each other along the direction of the airflow path 608 (i.e., along a direction extending from the front edge 610 toward the rear edge 612 of the chassis-less circuit board substrate 602).
As discussed above, the illustrative sled 400 includes one or more physical resources 620 mounted to a top side 650 of the chassis-less circuit board substrate 602. Although two physical resources 620 are shown in FIG. 6, it should be appreciated that the sled 400 may include one, two, or more physical resources 620 in other embodiments. The physical resources 620 may be embodied as any type of processor, controller, or other compute circuit capable of performing various tasks such as compute functions and/or controlling the functions of the sled 400 depending on, for example, the type or intended functionality of the sled 400. For example, as discussed in more detail below, the physical resources 620 may be embodied as high-performance processors in embodiments in which the sled 400 is embodied as a compute sled, as accelerator co-processors or circuits in embodiments in which the sled 400 is embodied as an accelerator sled, storage controllers in embodiments in which the sled 400 is embodied as a storage sled, or a set of memory devices in embodiments in which the sled 400 is embodied as a memory sled.
The sled 400 also includes one or more additional physical resources 630 mounted to the top side 650 of the chassis-less circuit board substrate 602. In the illustrative embodiment, the additional physical resources include a network interface controller (NIC) as discussed in more detail below. Of course, depending on the type and functionality of the sled 400, the physical resources 630 may include additional or other electrical components, circuits, and/or devices in other embodiments.
The physical resources 620 are communicatively coupled to the physical resources 630 via an input/output (I/O) subsystem 622. The I/O subsystem 622 may be embodied as circuitry and/or components to facilitate input/output operations with the physical resources 620, the physical resources 630, and/or other components of the sled 400. For example, the I/O subsystem 622 may be embodied as, or otherwise include, memory controller hubs, input/output control hubs, integrated sensor hubs, firmware devices, communication links (e.g., point-to-point links, bus links, wires, cables, light guides, printed circuit board traces, etc.), and/or other components and subsystems to facilitate the input/output operations. In the illustrative embodiment, the I/O subsystem 622 is embodied as, or otherwise includes, a double data rate 4 (DDR4) data bus or a DDR5 data bus.
In some embodiments, the sled 400 may also include a resource-to-resource interconnect 624. The resource-to-resource interconnect 624 may be embodied as any type of communication interconnect capable of facilitating resource-to-resource communications. In the illustrative embodiment, the resource-to-resource interconnect 624 is embodied as a high-speed point-to-point interconnect (e.g., faster than the I/O subsystem 622). For example, the resource-to-resource interconnect 624 may be embodied as a QuickPath Interconnect (QPI), an UltraPath Interconnect (UPI), or other high-speed point-to-point interconnect dedicated to resource-to-resource communications.
The sled 400 also includes a power connector 640 configured to mate with a corresponding power connector of the rack 240 when the sled 400 is mounted in the corresponding rack 240. The sled 400 receives power from a power supply of the rack 240 via the power connector 640 to supply power to the various electrical components of the sled 400. That is, the sled 400 does not include any local power supply (i.e., an on-board power supply) to provide power to the electrical components of the sled 400. The exclusion of a local or on-board power supply facilitates the reduction in the overall footprint of the chassis-less circuit board substrate 602, which may increase the thermal cooling characteristics of the various electrical components mounted on the chassis-less circuit board substrate 602 as discussed above. In some embodiments, power is provided to the processors 820 through vias directly under the processors 820 (e.g., through the bottom side 750 of the chassis-less circuit board substrate 602), providing an increased thermal budget, additional current and/or voltage, and better voltage control over typical boards.
In some embodiments, the sled 400 may also include mounting features 642 configured to mate with a mounting arm, or other structure, of a robot to facilitate the placement of the sled 600 in a rack 240 by the robot. The mounting features 642 may be embodied as any type of physical structures that allow the robot to grasp the sled 400 without damaging the chassis-less circuit board substrate 602 or the electrical components mounted thereto. For example, in some embodiments, the mounting features 642 may be embodied as non-conductive pads attached to the chassis-less circuit board substrate 602. In other embodiments, the mounting features may be embodied as brackets, braces, or other similar structures attached to the chassis-less circuit board substrate 602. The particular number, shape, size, and/or make-up of the mounting feature 642 may depend on the design of the robot configured to manage the sled 400.
Referring now to FIG. 7, in addition to the physical resources 630 mounted on the top side 650 of the chassis-less circuit board substrate 602, the sled 400 also includes one or more memory devices 720 mounted to a bottom side 750 of the chassis-less circuit board substrate 602. That is, the chassis-less circuit board substrate 602 is embodied as a double-sided circuit board. The physical resources 620 are communicatively coupled to the memory devices 720 via the I/O subsystem 622. For example, the physical resources 620 and the memory devices 720 may be communicatively coupled by one or more vias extending through the chassis-less circuit board substrate 602. Each physical resource 620 may be communicatively coupled to a different set of one or more memory devices 720 in some embodiments. Alternatively, in other embodiments, each physical resource 620 may be communicatively coupled to each memory devices 720.
The memory devices 720 may be embodied as any type of memory device capable of storing data for the physical resources 620 during operation of the sled 400, such as any type of volatile (e.g., dynamic random access memory (DRAM), etc.) or non-volatile memory. Volatile memory may be a storage medium that requires power to maintain the state of data stored by the medium. Non-limiting examples of volatile memory may include various types of random access memory (RAM), such as dynamic random access memory (DRAM) or static random access memory (SRAM). One particular type of DRAM that may be used in a memory module is synchronous dynamic random access memory (SDRAM). In particular embodiments, DRAM of a memory component may comply with a standard promulgated by JEDEC, such as JESD79F for DDR SDRAM, JESD79-2F for DDR2 SDRAM, JESD79-3F for DDR3 SDRAM, JESD79-4A for DDR4 SDRAM, JESD209 for Low Power DDR (LPDDR), JESD209-2 for LPDDR2, JESD209-3 for LPDDR3, and JESD209-4 for LPDDR4 (these standards are available at www.jedec.org). Such standards (and similar standards) may be referred to as DDR-based standards and communication interfaces of the storage devices that implement such standards may be referred to as DDR-based interfaces.
In one embodiment, the memory device is a block addressable memory device, such as those based on NAND or NOR technologies. A memory device may also include next-generation nonvolatile devices, such as Intel 3D XPoint™ memory or other byte addressable write-in-place nonvolatile memory devices. In one embodiment, the memory device may be or may include memory devices that use chalcogenide glass, multi-threshold level NAND flash memory, NOR flash memory, single or multi-level Phase Change Memory (PCM), a resistive memory, nanowire memory, ferroelectric transistor random access memory (FeTRAM), anti-ferroelectric memory, magnetoresistive random access memory (MRAM) memory that incorporates memristor technology, resistive memory including the metal oxide base, the oxygen vacancy base and the conductive bridge Random Access Memory (CB-RAM), or spin transfer torque (STT)-MRAM, a spintronic magnetic junction memory based device, a magnetic tunneling junction (MTJ) based device, a DW (Domain Wall) and SOT (Spin Orbit Transfer) based device, a thyristor based memory device, or a combination of any of the above, or other memory. The memory device may refer to the die itself and/or to a packaged memory product. In some embodiments, the memory device may comprise a transistor-less stackable cross point architecture in which memory cells sit at the intersection of word lines and bit lines and are individually addressable and in which bit storage is based on a change in bulk resistance.
Referring now to FIG. 8, in some embodiments, the sled 400 may be embodied as a compute sled 800. The compute sled 800 is optimized, or otherwise configured, to perform compute tasks. Of course, as discussed above, the compute sled 800 may rely on other sleds, such as acceleration sleds and/or storage sleds, to perform such compute tasks. The compute sled 800 includes various physical resources (e.g., electrical components) similar to the physical resources of the sled 400, which have been identified in FIG. 8 using the same reference numbers. The description of such components provided above in regard to FIGS. 6 and 7 applies to the corresponding components of the compute sled 800 and is not repeated herein for clarity of the description of the compute sled 800.
In the illustrative compute sled 800, the physical resources 620 are embodied as processors 820. Although only two processors 820 are shown in FIG. 8, it should be appreciated that the compute sled 800 may include additional processors 820 in other embodiments. Illustratively, the processors 820 are embodied as high-performance processors 820 and may be configured to operate at a relatively high power rating. Although the processors 820 generate additional heat operating at power ratings greater than typical processors (which operate at around 155-230 W), the enhanced thermal cooling characteristics of the chassis-less circuit board substrate 602 discussed above facilitate the higher power operation. For example, in the illustrative embodiment, the processors 820 are configured to operate at a power rating of at least 250 W. In some embodiments, the processors 820 may be configured to operate at a power rating of at least 350 W.
In some embodiments, the compute sled 800 may also include a processor-to-processor interconnect 842. Similar to the resource-to-resource interconnect 624 of the sled 400 discussed above, the processor-to-processor interconnect 842 may be embodied as any type of communication interconnect capable of facilitating processor-to-processor interconnect 842 communications. In the illustrative embodiment, the processor-to-processor interconnect 842 is embodied as a high-speed point-to-point interconnect (e.g., faster than the I/O subsystem 622). For example, the processor-to-processor interconnect 842 may be embodied as a QuickPath Interconnect (QPI), an UltraPath Interconnect (UPI), or other high-speed point-to-point interconnect dedicated to processor-to-processor communications.
The compute sled 800 also includes a communication circuit 830. The illustrative communication circuit 830 includes a network interface controller (NIC) 832, which may also be referred to as a host fabric interface (HFI). The NIC 832 may be embodied as, or otherwise include, any type of integrated circuit, discrete circuits, controller chips, chipsets, add-in-boards, daughtercards, network interface cards, other devices that may be used by the compute sled 800 to connect with another compute device (e.g., with other sleds 400). In some embodiments, the NIC 832 may be embodied as part of a system-on-a-chip (SoC) that includes one or more processors, or included on a multichip package that also contains one or more processors. In some embodiments, the NIC 832 may include a local processor (not shown) and/or a local memory (not shown) that are both local to the NIC 832. In such embodiments, the local processor of the NIC 832 may be capable of performing one or more of the functions of the processors 820. Additionally or alternatively, in such embodiments, the local memory of the NIC 832 may be integrated into one or more components of the compute sled at the board level, socket level, chip level, and/or other levels.
The communication circuit 830 is communicatively coupled to an optical data connector 834. The optical data connector 834 is configured to mate with a corresponding optical data connector of the rack 240 when the compute sled 800 is mounted in the rack 240. Illustratively, the optical data connector 834 includes a plurality of optical fibers which lead from a mating surface of the optical data connector 834 to an optical transceiver 836. The optical transceiver 836 is configured to convert incoming optical signals from the rack-side optical data connector to electrical signals and to convert electrical signals to outgoing optical signals to the rack-side optical data connector. Although shown as forming part of the optical data connector 834 in the illustrative embodiment, the optical transceiver 836 may form a portion of the communication circuit 830 in other embodiments.
In some embodiments, the compute sled 800 may also include an expansion connector 840. In such embodiments, the expansion connector 840 is configured to mate with a corresponding connector of an expansion chassis-less circuit board substrate to provide additional physical resources to the compute sled 800. The additional physical resources may be used, for example, by the processors 820 during operation of the compute sled 800. The expansion chassis-less circuit board substrate may be substantially similar to the chassis-less circuit board substrate 602 discussed above and may include various electrical components mounted thereto. The particular electrical components mounted to the expansion chassis-less circuit board substrate may depend on the intended functionality of the expansion chassis-less circuit board substrate. For example, the expansion chassis-less circuit board substrate may provide additional compute resources, memory resources, and/or storage resources. As such, the additional physical resources of the expansion chassis-less circuit board substrate may include, but is not limited to, processors, memory devices, storage devices, and/or accelerator circuits including, for example, field programmable gate arrays (FPGA), application-specific integrated circuits (ASICs), security co-processors, graphics processing units (GPUs), machine learning circuits, or other specialized processors, controllers, devices, and/or circuits.
Referring now to FIG. 9, an illustrative embodiment of the compute sled 800 is shown. As shown, the processors 820, communication circuit 830, and optical data connector 834 are mounted to the top side 650 of the chassis-less circuit board substrate 602. Any suitable attachment or mounting technology may be used to mount the physical resources of the compute sled 800 to the chassis-less circuit board substrate 602. For example, the various physical resources may be mounted in corresponding sockets (e.g., a processor socket), holders, or brackets. In some cases, some of the electrical components may be directly mounted to the chassis-less circuit board substrate 602 via soldering or similar techniques.
As discussed above, the individual processors 820 and communication circuit 830 are mounted to the top side 650 of the chassis-less circuit board substrate 602 such that no two heat-producing, electrical components shadow each other. In the illustrative embodiment, the processors 820 and communication circuit 830 are mounted in corresponding locations on the top side 650 of the chassis-less circuit board substrate 602 such that no two of those physical resources are linearly in-line with others along the direction of the airflow path 608. It should be appreciated that, although the optical data connector 834 is in-line with the communication circuit 830, the optical data connector 834 produces no or nominal heat during operation.
The memory devices 720 of the compute sled 800 are mounted to the bottom side 750 of the of the chassis-less circuit board substrate 602 as discussed above in regard to the sled 400. Although mounted to the bottom side 750, the memory devices 720 are communicatively coupled to the processors 820 located on the top side 650 via the I/O subsystem 622. Because the chassis-less circuit board substrate 602 is embodied as a double-sided circuit board, the memory devices 720 and the processors 820 may be communicatively coupled by one or more vias, connectors, or other mechanisms extending through the chassis-less circuit board substrate 602. Of course, each processor 820 may be communicatively coupled to a different set of one or more memory devices 720 in some embodiments. Alternatively, in other embodiments, each processor 820 may be communicatively coupled to each memory device 720. In some embodiments, the memory devices 720 may be mounted to one or more memory mezzanines on the bottom side of the chassis-less circuit board substrate 602 and may interconnect with a corresponding processor 820 through a ball-grid array.
Each of the processors 820 includes a heatsink 850 secured thereto. Due to the mounting of the memory devices 720 to the bottom side 750 of the chassis-less circuit board substrate 602 (as well as the vertical spacing of the sleds 400 in the corresponding rack 240), the top side 650 of the chassis-less circuit board substrate 602 includes additional “free” area or space that facilitates the use of heatsinks 850 having a larger size relative to traditional heatsinks used in typical servers. Additionally, due to the improved thermal cooling characteristics of the chassis-less circuit board substrate 602, none of the processor heatsinks 850 include cooling fans attached thereto. That is, each of the heatsinks 850 is embodied as a fan-less heatsinks.
Referring now to FIG. 10, in some embodiments, the sled 400 may be embodied as an accelerator sled 1000. The accelerator sled 1000 is optimized, or otherwise configured, to perform specialized compute tasks, such as machine learning, encryption, hashing, or other computational-intensive task. In some embodiments, for example, a compute sled 800 may offload tasks to the accelerator sled 1000 during operation. The accelerator sled 1000 includes various components similar to components of the sled 400 and/or compute sled 800, which have been identified in FIG. 10 using the same reference numbers. The description of such components provided above in regard to FIGS. 6, 7, and 8 apply to the corresponding components of the accelerator sled 1000 and is not repeated herein for clarity of the description of the accelerator sled 1000.
In the illustrative accelerator sled 1000, the physical resources 620 are embodied as accelerator circuits 1020. Although only two accelerator circuits 1020 are shown in FIG. 10, it should be appreciated that the accelerator sled 1000 may include additional accelerator circuits 1020 in other embodiments. For example, as shown in FIG. 11, the accelerator sled 1000 may include four accelerator circuits 1020 in some embodiments. The accelerator circuits 1020 may be embodied as any type of processor, co-processor, compute circuit, or other device capable of performing compute or processing operations. For example, the accelerator circuits 1020 may be embodied as, for example, field programmable gate arrays (FPGA), application-specific integrated circuits (ASICs), security co-processors, graphics processing units (GPUs), machine learning circuits, or other specialized processors, controllers, devices, and/or circuits.
In some embodiments, the accelerator sled 1000 may also include an accelerator-to-accelerator interconnect 1042. Similar to the resource-to-resource interconnect 624 of the sled 600 discussed above, the accelerator-to-accelerator interconnect 1042 may be embodied as any type of communication interconnect capable of facilitating accelerator-to-accelerator communications. In the illustrative embodiment, the accelerator-to-accelerator interconnect 1042 is embodied as a high-speed point-to-point interconnect (e.g., faster than the I/O subsystem 622). For example, the accelerator-to-accelerator interconnect 1042 may be embodied as a QuickPath Interconnect (QPI), an UltraPath Interconnect (UPI), or other high-speed point-to-point interconnect dedicated to processor-to-processor communications. In some embodiments, the accelerator circuits 1020 may be daisy-chained with a primary accelerator circuit 1020 connected to the NIC 832 and memory 720 through the I/O subsystem 622 and a secondary accelerator circuit 1020 connected to the NIC 832 and memory 720 through a primary accelerator circuit 1020.
Referring now to FIG. 11, an illustrative embodiment of the accelerator sled 1000 is shown. As discussed above, the accelerator circuits 1020, communication circuit 830, and optical data connector 834 are mounted to the top side 650 of the chassis-less circuit board substrate 602. Again, the individual accelerator circuits 1020 and communication circuit 830 are mounted to the top side 650 of the chassis-less circuit board substrate 602 such that no two heat-producing, electrical components shadow each other as discussed above. The memory devices 720 of the accelerator sled 1000 are mounted to the bottom side 750 of the of the chassis-less circuit board substrate 602 as discussed above in regard to the sled 600. Although mounted to the bottom side 750, the memory devices 720 are communicatively coupled to the accelerator circuits 1020 located on the top side 650 via the I/O subsystem 622 (e.g., through vias). Further, each of the accelerator circuits 1020 may include a heatsink 1070 that is larger than a traditional heatsink used in a server. As discussed above with reference to the heatsinks 870, the heatsinks 1070 may be larger than tradition heatsinks because of the “free” area provided by the memory devices 750 being located on the bottom side 750 of the chassis-less circuit board substrate 602 rather than on the top side 650.
Referring now to FIG. 12, in some embodiments, the sled 400 may be embodied as a storage sled 1200. The storage sled 1200 is optimized, or otherwise configured, to store data in a data storage 1250 local to the storage sled 1200. For example, during operation, a compute sled 800 or an accelerator sled 1000 may store and retrieve data from the data storage 1250 of the storage sled 1200. The storage sled 1200 includes various components similar to components of the sled 400 and/or the compute sled 800, which have been identified in FIG. 12 using the same reference numbers. The description of such components provided above in regard to FIGS. 6, 7, and 8 apply to the corresponding components of the storage sled 1200 and is not repeated herein for clarity of the description of the storage sled 1200.
In the illustrative storage sled 1200, the physical resources 620 are embodied as storage controllers 1220. Although only two storage controllers 1220 are shown in FIG. 12, it should be appreciated that the storage sled 1200 may include additional storage controllers 1220 in other embodiments. The storage controllers 1220 may be embodied as any type of processor, controller, or control circuit capable of controlling the storage and retrieval of data into the data storage 1250 based on requests received via the communication circuit 830. In the illustrative embodiment, the storage controllers 1220 are embodied as relatively low-power processors or controllers. For example, in some embodiments, the storage controllers 1220 may be configured to operate at a power rating of about 75 watts.
In some embodiments, the storage sled 1200 may also include a controller-to-controller interconnect 1242. Similar to the resource-to-resource interconnect 624 of the sled 400 discussed above, the controller-to-controller interconnect 1242 may be embodied as any type of communication interconnect capable of facilitating controller-to-controller communications. In the illustrative embodiment, the controller-to-controller interconnect 1242 is embodied as a high-speed point-to-point interconnect (e.g., faster than the I/O subsystem 622). For example, the controller-to-controller interconnect 1242 may be embodied as a QuickPath Interconnect (QPI), an UltraPath Interconnect (UPI), or other high-speed point-to-point interconnect dedicated to processor-to-processor communications.
Referring now to FIG. 13, an illustrative embodiment of the storage sled 1200 is shown. In the illustrative embodiment, the data storage 1250 is embodied as, or otherwise includes, a storage cage 1252 configured to house one or more solid state drives (SSDs) 1254. To do so, the storage cage 1252 includes a number of mounting slots 1256, each of which is configured to receive a corresponding solid state drive 1254. Each of the mounting slots 1256 includes a number of drive guides 1258 that cooperate to define an access opening 1260 of the corresponding mounting slot 1256. The storage cage 1252 is secured to the chassis-less circuit board substrate 602 such that the access openings face away from (i.e., toward the front of) the chassis-less circuit board substrate 602. As such, solid state drives 1254 are accessible while the storage sled 1200 is mounted in a corresponding rack 204. For example, a solid state drive 1254 may be swapped out of a rack 240 (e.g., via a robot) while the storage sled 1200 remains mounted in the corresponding rack 240.
The storage cage 1252 illustratively includes sixteen mounting slots 1256 and is capable of mounting and storing sixteen solid state drives 1254. Of course, the storage cage 1252 may be configured to store additional or fewer solid state drives 1254 in other embodiments. Additionally, in the illustrative embodiment, the solid state drivers are mounted vertically in the storage cage 1252, but may be mounted in the storage cage 1252 in a different orientation in other embodiments. Each solid state drive 1254 may be embodied as any type of data storage device capable of storing long term data. To do so, the solid state drives 1254 may include volatile and non-volatile memory devices discussed above.
As shown in FIG. 13, the storage controllers 1220, the communication circuit 830, and the optical data connector 834 are illustratively mounted to the top side 650 of the chassis-less circuit board substrate 602. Again, as discussed above, any suitable attachment or mounting technology may be used to mount the electrical components of the storage sled 1200 to the chassis-less circuit board substrate 602 including, for example, sockets (e.g., a processor socket), holders, brackets, soldered connections, and/or other mounting or securing techniques.
As discussed above, the individual storage controllers 1220 and the communication circuit 830 are mounted to the top side 650 of the chassis-less circuit board substrate 602 such that no two heat-producing, electrical components shadow each other. For example, the storage controllers 1220 and the communication circuit 830 are mounted in corresponding locations on the top side 650 of the chassis-less circuit board substrate 602 such that no two of those electrical components are linearly in-line with other along the direction of the airflow path 608.
The memory devices 720 of the storage sled 1200 are mounted to the bottom side 750 of the of the chassis-less circuit board substrate 602 as discussed above in regard to the sled 400. Although mounted to the bottom side 750, the memory devices 720 are communicatively coupled to the storage controllers 1220 located on the top side 650 via the I/O subsystem 622. Again, because the chassis-less circuit board substrate 602 is embodied as a double-sided circuit board, the memory devices 720 and the storage controllers 1220 may be communicatively coupled by one or more vias, connectors, or other mechanisms extending through the chassis-less circuit board substrate 602. Each of the storage controllers 1220 includes a heatsink 1270 secured thereto. As discussed above, due to the improved thermal cooling characteristics of the chassis-less circuit board substrate 602 of the storage sled 1200, none of the heatsinks 1270 include cooling fans attached thereto. That is, each of the heatsinks 1270 is embodied as a fan-less heatsink.
Referring now to FIG. 14, in some embodiments, the sled 400 may be embodied as a memory sled 1400. The storage sled 1400 is optimized, or otherwise configured, to provide other sleds 400 (e.g., compute sleds 800, accelerator sleds 1000, etc.) with access to a pool of memory (e.g., in two or more sets 1430, 1432 of memory devices 720) local to the memory sled 1200. For example, during operation, a compute sled 800 or an accelerator sled 1000 may remotely write to and/or read from one or more of the memory sets 1430, 1432 of the memory sled 1200 using a logical address space that maps to physical addresses in the memory sets 1430, 1432. The memory sled 1400 includes various components similar to components of the sled 400 and/or the compute sled 800, which have been identified in FIG. 14 using the same reference numbers. The description of such components provided above in regard to FIGS. 6, 7, and 8 apply to the corresponding components of the memory sled 1400 and is not repeated herein for clarity of the description of the memory sled 1400.
In the illustrative memory sled 1400, the physical resources 620 are embodied as memory controllers 1420. Although only two memory controllers 1420 are shown in FIG. 14, it should be appreciated that the memory sled 1400 may include additional memory controllers 1420 in other embodiments. The memory controllers 1420 may be embodied as any type of processor, controller, or control circuit capable of controlling the writing and reading of data into the memory sets 1430, 1432 based on requests received via the communication circuit 830. In the illustrative embodiment, each storage controller 1220 is connected to a corresponding memory set 1430, 1432 to write to and read from memory devices 720 within the corresponding memory set 1430, 1432 and enforce any permissions (e.g., read, write, etc.) associated with sled 400 that has sent a request to the memory sled 1400 to perform a memory access operation (e.g., read or write).
In some embodiments, the memory sled 1400 may also include a controller-to-controller interconnect 1442. Similar to the resource-to-resource interconnect 624 of the sled 400 discussed above, the controller-to-controller interconnect 1442 may be embodied as any type of communication interconnect capable of facilitating controller-to-controller communications. In the illustrative embodiment, the controller-to-controller interconnect 1442 is embodied as a high-speed point-to-point interconnect (e.g., faster than the I/O subsystem 622). For example, the controller-to-controller interconnect 1442 may be embodied as a QuickPath Interconnect (QPI), an UltraPath Interconnect (UPI), or other high-speed point-to-point interconnect dedicated to processor-to-processor communications. As such, in some embodiments, a memory controller 1420 may access, through the controller-to-controller interconnect 1442, memory that is within the memory set 1432 associated with another memory controller 1420. In some embodiments, a scalable memory controller is made of multiple smaller memory controllers, referred to herein as “chiplets”, on a memory sled (e.g., the memory sled 1400). The chiplets may be interconnected (e.g., using EMIB (Embedded Multi-Die Interconnect Bridge)). The combined chiplet memory controller may scale up to a relatively large number of memory controllers and I/O ports, (e.g., up to 16 memory channels). In some embodiments, the memory controllers 1420 may implement a memory interleave (e.g., one memory address is mapped to the memory set 1430, the next memory address is mapped to the memory set 1432, and the third address is mapped to the memory set 1430, etc.). The interleaving may be managed within the memory controllers 1420, or from CPU sockets (e.g., of the compute sled 800) across network links to the memory sets 1430, 1432, and may improve the latency associated with performing memory access operations as compared to accessing contiguous memory addresses from the same memory device.
Further, in some embodiments, the memory sled 1400 may be connected to one or more other sleds 400 (e.g., in the same rack 240 or an adjacent rack 240) through a waveguide, using the waveguide connector 1480. In the illustrative embodiment, the waveguides are 64 millimeter waveguides that provide 16 Rx (i.e., receive) lanes and 16 Rt (i.e., transmit) lanes. Each lane, in the illustrative embodiment, is either 16 Ghz or 32 Ghz. In other embodiments, the frequencies may be different. Using a waveguide may provide high throughput access to the memory pool (e.g., the memory sets 1430, 1432) to another sled (e.g., a sled 400 in the same rack 240 or an adjacent rack 240 as the memory sled 1400) without adding to the load on the optical data connector 834.
Referring now to FIG. 15, a system for executing one or more workloads (e.g., applications) may be implemented in accordance with the data center 100. In the illustrative embodiment, the system 1510 includes an orchestrator server 1520, which may be embodied as a managed node comprising a compute device (e.g., a compute sled 800) executing management software (e.g., a cloud operating environment, such as OpenStack) that is communicatively coupled to multiple sleds 400 including a large number of compute sleds 1530 (e.g., each similar to the compute sled 800), memory sleds 1540 (e.g., each similar to the memory sled 1400), accelerator sleds 1550 (e.g., each similar to the memory sled 1000), and storage sleds 1560 (e.g., each similar to the storage sled 1200). One or more of the sleds 1530, 1540, 1550, 1560 may be grouped into a managed node 1570, such as by the orchestrator server 1520, to collectively perform a workload (e.g., an application 1232 executed in a virtual machine or in a container). The managed node 1570 may be embodied as an assembly of physical resources 620, such as processors 820, memory resources 720, accelerator circuits 1020, or data storage 1250, from the same or different sleds 400. Further, the managed node may be established, defined, or “spun up” by the orchestrator server 1520 at the time a workload is to be assigned to the managed node or at any other time, and may exist regardless of whether any workloads are presently assigned to the managed node. In the illustrative embodiment, the orchestrator server 1520 may selectively allocate and/or deallocate physical resources 620 from the sleds 400 and/or add or remove one or more sleds 400 from the managed node 1570 as a function of quality of service (QoS) targets (e.g., performance targets associated with a throughput, latency, instructions per second, etc.) associated with a service level agreement for the workload (e.g., the application 1532). In doing so, the orchestrator server 1520 may receive telemetry data indicative of performance conditions (e.g., throughput, latency, instructions per second, etc.) in each sled 400 of the managed node 1570 and compare the telemetry data to the quality of service targets to determine whether the quality of service targets are being satisfied. If the so, the orchestrator server 1520 may additionally determine whether one or more physical resources may be deallocated from the managed node 1570 while still satisfying the QoS targets, thereby freeing up those physical resources for use in another managed node (e.g., to execute a different workload). Alternatively, if the QoS targets are not presently satisfied, the orchestrator server 1520 may determine to dynamically allocate additional physical resources to assist in the execution of the workload (e.g., the application 1532) while the workload is executing.
Additionally, in some embodiments, the orchestrator server 1520 may identify trends in the resource utilization of the workload (e.g., the application 1532), such as by identifying phases of execution (e.g., time periods in which different operations, each having different resource utilizations characteristics, are performed) of the workload (e.g., the application 1532) and pre-emptively identifying available resources in the data center 100 and allocating them to the managed node 1570 (e.g., within a predefined time period of the associated phase beginning). In some embodiments, the orchestrator server 1520 may model performance based on various latencies and a distribution scheme to place workloads among compute sleds and other resources (e.g., accelerator sleds, memory sleds, storage sleds) in the data center 100. For example, the orchestrator server 1520 may utilize a model that accounts for the performance of resources on the sleds 400 (e.g., FPGA performance, memory access latency, etc.) and the performance (e.g., congestion, latency, bandwidth) of the path through the network to the resource (e.g., FPGA). As such, the orchestrator server 1520 may determine which resource(s) should be used with which workloads based on the total latency associated with each potential resource available in the data center 100 (e.g., the latency associated with the performance of the resource itself in addition to the latency associated with the path through the network between the compute sled executing the workload and the sled 400 on which the resource is located).
In some embodiments, the orchestrator server 1520 may generate a map of heat generation in the data center 100 using telemetry data (e.g., temperatures, fan speeds, etc.) reported from the sleds 400 and allocate resources to managed nodes as a function of the map of heat generation and predicted heat generation associated with different workloads, to maintain a target temperature and heat distribution in the data center 100. Additionally or alternatively, in some embodiments, the orchestrator server 1520 may organize received telemetry data into a hierarchical model that is indicative of a relationship between the managed nodes (e.g., a spatial relationship such as the physical locations of the resources of the managed nodes within the data center 100 and/or a functional relationship, such as groupings of the managed nodes by the customers the managed nodes provide services for, the types of functions typically performed by the managed nodes, managed nodes that typically share or exchange workloads among each other, etc.). Based on differences in the physical locations and resources in the managed nodes, a given workload may exhibit different resource utilizations (e.g., cause a different internal temperature, use a different percentage of processor or memory capacity) across the resources of different managed nodes. The orchestrator server 1520 may determine the differences based on the telemetry data stored in the hierarchical model and factor the differences into a prediction of future resource utilization of a workload if the workload is reassigned from one managed node to another managed node, to accurately balance resource utilization in the data center 100.
To reduce the computational load on the orchestrator server 1520 and the data transfer load on the network, in some embodiments, the orchestrator server 1520 may send self-test information to the sleds 400 to enable each sled 400 to locally (e.g., on the sled 400) determine whether telemetry data generated by the sled 400 satisfies one or more conditions (e.g., an available capacity that satisfies a predefined threshold, a temperature that satisfies a predefined threshold, etc.). Each sled 400 may then report back a simplified result (e.g., yes or no) to the orchestrator server 1520, which the orchestrator server 1520 may utilize in determining the allocation of resources to managed nodes.
Referring now to FIG. 16, a system 1610 for allocating resources across data centers may be implemented in accordance with the data center 100 as described above with reference to FIG. 1. In the illustrative embodiment, the system 1610 includes an orchestrator server 1620 communicatively coupled to multiple sleds including a compute sled 1630 and an accelerator sled 1640. One or more of the sleds 1630, 1640 may be grouped into a managed node, such as by the orchestrator server 1620, to collectively perform a workload (e.g., the application 1638). A managed node may be embodied as an assembly of resources, such as compute resources, memory resources, storage resources, or other resources, from the same or different sleds or racks. Further, a managed node may be established, defined, or “spun up” by the orchestrator server 1620 at the time a workload is to be assigned to the managed node or at any other time, and may exist regardless of whether any workloads are presently assigned to the managed node. The system 1610 may be located in a data center and provide storage and compute services (e.g., cloud services) to a client device 1614 that is in communication with the system 1610 through a network 1612. The orchestrator server 1620 may support a cloud operating environment, such as OpenStack, and managed nodes established by the orchestrator server 1620 may execute one or more applications or processes (i.e., workloads), such as in virtual machines or containers, on behalf of a user of a client device (not shown).
In the illustrative embodiment, the compute sled 1630 executes an application 1638 (e.g., a workload). The accelerator sled 1640 includes multiple accelerator devices 1644, 1646 coupled to a controller 1642, which, in the illustrative embodiment, abstracts away details of the accelerator devices 1644, 1646 and presents the accelerator devices 1644, 1646 as one or more logical devices usable by the compute sled 1630 on an as-requested basis. Further, the controller 1642, in operation, converts between a message format (e.g., a protocol) used between the compute sled 1630 and the accelerator sled 1640 through the network 1612 and a message format used internally for communications between the controller 1642 and the accelerator devices 1644, 1646, such as messages formatted for use with a local bus (e.g., Peripheral Component Interconnect Express (PCIe)).
Referring now to FIG. 17, the accelerator sled 1640 may be embodied as any type of compute device capable of performing the functions described herein, including providing, to a compute sled, accelerator abstraction data, receiving, from the compute sled, a request to perform an operation on an identified memory region of an accelerator device, converting the request from one format to a different format, and performing, in response to the request, the operation on the identified memory region of the accelerator device with a corresponding access mode. As shown in FIG. 17, the illustrative accelerator sled 1640 includes a compute engine 1702, an input/output (I/O) subsystem 1710, communication circuitry 1712, and one or more accelerator devices 1716. Of course, in other embodiments, the accelerator sled 1640 may include other or additional components, such as those commonly found in a computer (e.g., display, peripheral devices, etc.). Additionally, in some embodiments, one or more of the illustrative components may be incorporated in, or otherwise form a portion of, another component.
The compute engine 1702 may be embodied as any type of device or collection of devices capable of performing various compute functions described below. In some embodiments, the compute engine 1702 may be embodied as a single device such as an integrated circuit, an embedded system, a field-programmable gate array (FPGA), a system-on-a-chip (SOC), or other integrated system or device. In the illustrative embodiment, the compute engine 1702 includes or is embodied as a controller 1642 and a memory 1706. The controller 1642 may be embodied as any type of processor capable of performing the functions described herein. For example, the controller 1642 may be embodied as a microcontroller, a single or multi-core processor(s), or other processor or processing/controlling circuit. In some embodiments, the controller 1642 may be embodied as, include, or be coupled to an FPGA, an application specific integrated circuit (ASIC), reconfigurable hardware or hardware circuitry, or other specialized hardware to facilitate performance of the functions described herein. In the illustrative embodiment, the controller 1642 includes an abstraction logic unit 1708 which may be embodied as any device or circuitry (e.g., a co-processor, an ASIC, etc.) capable of representing the accelerator devices 1716 to other compute devices (e.g., the compute sled 1630) as one or more logical devices (e.g., devices accessible using a network communication protocol, such as TCP/IP, rather than a local bus protocol, such as PCIe) and enabling access to regions of the accelerator devices (e.g., memory regions) through a proxy mode (e.g., intermediating between the compute sled 1630 and the target accelerator device 1720, 1722) and/or a direct access mode (e.g., remote direct memory access).
The memory 1706 may be embodied as any type of volatile (e.g., dynamic random access memory (DRAM), etc.) or non-volatile memory or data storage capable of performing the functions described herein. Volatile memory may be a storage medium that requires power to maintain the state of data stored by the medium. Non-limiting examples of volatile memory may include various types of random access memory (RAM), such as dynamic random access memory (DRAM) or static random access memory (SRAM). One particular type of DRAM that may be used in a memory module is synchronous dynamic random access memory (SDRAM). In particular embodiments, DRAM of a memory component may comply with a standard promulgated by JEDEC, such as JESD79F for DDR SDRAM, JESD79-2F for DDR2 SDRAM, JESD79-3F for DDR3 SDRAM, JESD79-4A for DDR4 SDRAM, JESD209 for Low Power DDR (LPDDR), JESD209-2 for LPDDR2, JESD209-3 for LPDDR3, and JESD209-4 for LPDDR4 (these standards are available at www.jedec.org). Such standards (and similar standards) may be referred to as DDR-based standards and communication interfaces of the storage devices that implement such standards may be referred to as DDR-based interfaces.
In one embodiment, the memory device is a block addressable memory device, such as those based on NAND or NOR technologies. A memory device may also include future generation nonvolatile devices, such as a three dimensional crosspoint memory device (e.g., Intel 3D XPoint™ memory), or other byte addressable write-in-place nonvolatile memory devices. In one embodiment, the memory device may be or may include memory devices that use chalcogenide glass, multi-threshold level NAND flash memory, NOR flash memory, single or multi-level Phase Change Memory (PCM), a resistive memory, nanowire memory, ferroelectric transistor random access memory (FeTRAM), anti-ferroelectric memory, magnetoresistive random access memory (MRAM) memory that incorporates memristor technology, resistive memory including the metal oxide base, the oxygen vacancy base and the conductive bridge Random Access Memory (CB-RAM), or spin transfer torque (STT)-MRAM, a spintronic magnetic junction memory based device, a magnetic tunneling junction (MTJ) based device, a DW (Domain Wall) and SOT (Spin Orbit Transfer) based device, a thyristor based memory device, or a combination of any of the above, or other memory. The memory device may refer to the die itself and/or to a packaged memory product.
In some embodiments, 3D crosspoint memory (e.g., Intel 3D XPoint™ memory) may comprise a transistor-less stackable cross point architecture in which memory cells sit at the intersection of word lines and bit lines and are individually addressable and in which bit storage is based on a change in bulk resistance. In some embodiments, all or a portion of the memory 1706 may be integrated into the controller 1642. In operation, the memory 1706 may store various software and data used during operation such as accelerator abstraction data, access policy data, applications, programs, and libraries.
The compute engine 1702 is communicatively coupled to other components of the accelerator sled 1640 via the I/O subsystem 1710, which may be embodied as circuitry and/or components to facilitate input/output operations with the compute engine 1702 (e.g., with the controller 1642 and/or the memory 1706) and other components of the accelerator sled 1640. For example, the I/O subsystem 1710 may be embodied as, or otherwise include, memory controller hubs, input/output control hubs, integrated sensor hubs, firmware devices, communication links (e.g., point-to-point links, bus links, wires, cables, light guides, printed circuit board traces, etc.), and/or other components and subsystems to facilitate the input/output operations. In some embodiments, the I/O subsystem 1710 may form a portion of a system-on-a-chip (SoC) and be incorporated, along with one or more of the controller 1642, the memory 1706, and other components of the accelerator sled 1640, into the compute engine 1702.
The communication circuitry 1712 may be embodied as any communication circuit, device, or collection thereof, capable of enabling communications over the network 1612 between the accelerator sled 1640 and another compute device (e.g., the compute sled 1630, the orchestrator server 1620). The communication circuitry 1712 may be configured to use any one or more communication technology (e.g., wired or wireless communications) and associated protocols (e.g., Ethernet, Bluetooth®, Wi-Fi®, WiMAX, etc.) to effect such communication.
The communication circuitry 1712 may include a network interface controller (NIC) 1714 (e.g., as an add-in device), which may also be referred to as a host fabric interface (HFI). The NIC 1714 may be embodied as one or more add-in-boards, daughter cards, network interface cards, controller chips, chipsets, or other devices that may be used by the accelerator sled 1640 to connect with another compute device (e.g., the compute sled 1630, the orchestrator server 1620, etc.). In some embodiments, the NIC 1714 may be embodied as part of a system-on-a-chip (SoC) that includes one or more processors, or included on a multichip package that also contains one or more processors. In some embodiments, the NIC 1714 may include a local processor (not shown) and/or a local memory (not shown) that are both local to the NIC 1714. In such embodiments, the local processor of the NIC 1714 may be capable of performing one or more of the functions of the compute engine 1702 described herein. Additionally or alternatively, in such embodiments, the local memory of the NIC 1714 may be integrated into one or more components of the accelerator sled 1640 at the board level, socket level, chip level, and/or other levels.
The accelerator devices 1716, similar to the accelerator devices 1644, 1646, of FIG. 16, include multiple FPGAs 1720, 1722. In the illustrative embodiment, each FPGA 1720, 1722 includes multiple slots 1730, 1732, 1740, 1742, each of which may be embodied as a portion of the logic or circuitry (e.g., logic gates) present on the corresponding FPGA 1720, 1722 and which may be programmed with a bit stream to provide a kernel capable of accelerating a particular function. Further, each FPGA 1720, 1722 includes a memory 1734, 1744, similar to the memory 1706 described above. In the illustrative embodiment, each memory 1734, 1744 additionally includes one or more registers associated with administrative commands, such as for resetting or reprogramming an FPGA 1720, 1722, and one or more registers associated with user commands, such as commands to execute an accelerated function pursuant to a set of parameters.
The accelerator sled 1640 may also include one or more data storage devices 1718, which may be embodied as any type of devices configured for short-term or long-term storage of data such as, for example, memory devices and circuits, memory cards, hard disk drives, solid-state drives, or other data storage devices. Each data storage device 1718 may include a system partition that stores data and firmware code for the data storage device 1718. Each data storage device 1718 may also include one or more operating system partitions that store data files and executables for operating systems.
The orchestrator server 1620, the compute sled 1630, and the client device 1614 may have components similar to those described in FIG. 17, with the exception that, in some embodiments, orchestrator server 1620, the compute sled 1630, and/or the client device 1614 may not include the accelerator devices 1716. The description of those components of the accelerator sled 1640 is equally applicable to the description of components of those devices and is not repeated herein for clarity of the description. Further, it should be appreciated that any of the accelerator sled 1640, the compute sled 1630, the orchestrator server 1620, or the client device 1614 may include other components, sub-components, and devices commonly found in a computing device, which are not discussed above in reference to the accelerator sled 1640 and not discussed herein for clarity of the description.
As described above, the orchestrator server 1620, the sleds 1630, 1640, and the client device 1614 are illustratively in communication via the network 1612, which may be embodied as any type of wired or wireless communication network, including global networks (e.g., the Internet), local area networks (LANs) or wide area networks (WANs), cellular networks (e.g., Global System for Mobile Communications (GSM), 3G, Long Term Evolution (LTE), Worldwide Interoperability for Microwave Access (WiMAX), etc.), digital subscriber line (DSL) networks, cable networks (e.g., coaxial networks, fiber networks, etc.), or any combination thereof.
Referring now to FIG. 18, the accelerator sled 1640 may establish an environment 1800 during operation. The illustrative environment 1800 includes a network communicator 1820 and an access manager 1830. Each of the components of the environment 1800 may be embodied as hardware, firmware, software, or a combination thereof. As such, in some embodiments, one or more of the components of the environment 1800 may be embodied as circuitry or a collection of electrical devices (e.g., network communicator circuitry 1820, access manager circuitry 1830, etc.). It should be appreciated that, in such embodiments, one or more of the network communicator circuitry 1820 or access manager circuitry 1830 may form a portion of one or more of the compute engine 1702, accelerator devices 1716, the I/O subsystem 1710, the communication circuitry 1712, and/or other components of the accelerator sled 1640. In the illustrative embodiment, the environment 1800 includes accelerator abstraction data 1802 which may be embodied as any data indicative of representations of the accelerator devices 1716 as one or more logical devices, memory regions of the accelerator devices 1716 accessible to a remote compute device (e.g., the compute sled 1630), and a mode of access (e.g., a proxy mode or a direct access mode) associated with each memory region. Additionally, the environment 1800 includes access policy data 1804, which may be embodied as any data indicative of administrative commands that may be requested and an indication of whether each command is allowed or disallowed. As such, the access policy data 1804 may be provided by an administrator of the system 1610, hard coded, or provided from another source (e.g., a source other than a typical customer of the system 1610).
In the illustrative environment 1800, the network communicator 1820, which may be embodied as hardware, firmware, software, virtualized hardware, emulated architecture, and/or a combination thereof as discussed above, is configured to facilitate inbound and outbound network communications (e.g., network traffic, network packets, network flows, etc.) to and from the accelerator sled 1640, respectively. To do so, the network communicator 1820 is configured to receive and process data packets from one system or computing device (e.g., the compute sled 1630, the orchestrator server 1620, etc.) and to prepare and send data packets to a computing device or system (e.g., the compute sled 1630, the orchestrator server 1620, etc.). Accordingly, in some embodiments, at least a portion of the functionality of the network communicator 1820 may be performed by the communication circuitry 1712, and, in the illustrative embodiment, by the NIC 1714.
The access manager 1830, which may be embodied as hardware, firmware, software, virtualized hardware, emulated architecture, and/or a combination thereof, is configured to identify the accelerator devices 1716 present on the accelerator sled 1630, produce the accelerator abstraction data 1802 to represent the accelerator devices 1716 as one or more logical devices to any remote compute devices (e.g., the compute sled 1630), and enable access to memory regions of the accelerator devices 1716 through a proxy mode or a direct access mode. To do so, in the illustrative embodiment, the access manager 1830 includes an accelerator device identifier 1832, a proxy access manager 1834, and a direct access manager 1836.
The accelerator device identifier 1832, in the illustrative embodiment, is configured to identify the accelerator devices 1716, including their attributes (e.g., accelerator device types, number of FPGA slots, memory regions) and available capacity, and produce the accelerator abstraction data 1802 representing the accelerator devices 1716 as one or more logical devices for use by a remote compute device (e.g., the compute sled 1630). In the illustrative embodiment, the accelerator device identifier 1832 provides, in the accelerator abstraction data 1802, an indication of an access mode associated with each identified region of each accelerator device. For example, the accelerator device identifier 1832 may enable only a proxy mode for regions of memory (e.g., administrative command register regions) that could present a security risk to the system 1610, could damage the accelerator sled 1640, or could interrupt operations of the accelerator sled 1640 that are being performed on behalf of other customers (e.g., on behalf of applications being executed on the compute sled 1630 or another sled (not shown)) and may enable direct access for other regions of memory (e.g., user command register regions, memory regions reserved for bit streams, input parameters, output data, etc.). The proxy access manager 1834, in the illustrative embodiment, is configured to receive requests from the remote compute device (e.g., the compute sled 1630), determine whether operations (e.g., commands) associated with the requests are allowed or disallowed (e.g., as a function of the access policy data 1804), and pass allowed requests to the corresponding accelerator devices 1716. The direct access manager 1836, by contrast, is configured to provide direct access (e.g., direct read or write access) to the memory regions of the corresponding accelerator devices 1716.
It should be appreciated that each of the accelerator device identifier 1832, the proxy access manager 1834, and the direct access manager 1836 may be separately embodied as hardware, firmware, software, virtualized hardware, emulated architecture, and/or a combination thereof. For example, the accelerator device identifier 1832 may be embodied as a hardware component, while the proxy access manager 1834 and the direct access manager 1836 are embodied as virtualized hardware components or as some other combination of hardware, firmware, software, virtualized hardware, emulated architecture, and/or a combination thereof.
Referring now to FIG. 19, the accelerator sled 1640, in operation, may execute a method 1900 for providing efficient pooling of accelerator devices. The method 1900 begins with block 1902, in which the accelerator sled 1640 identifies the accelerator devices 1716 present on the accelerator sled 1640 (e.g., in a bus enumeration process such as in a boot up sequence or by otherwise querying the devices connected to one or more local buses, such as a PCIe bus, of the accelerator sled 1640). In the illustrative embodiment, the accelerator sled 1640 identifies attributes of the accelerator devices 1716, as indicated in block 1904. In doing so, the accelerator sled 1640 may identify the types (e.g., FPGA, ASIC, graphics processor, etc.) of the accelerator devices 1716 present on the accelerator sled 1640, as indicated in block 1906. For example, the controller 1642 may query each detected accelerator device 1716 for a code indicative of the type or may read a register containing data indicative of the type of accelerator device. As indicated in block 1908, the accelerator sled 1640 may identify FPGAs (e.g., the FPGAs 1720, 1722) present on the accelerator sled 1640. In doing so, and as indicated in block 1910, the accelerator sled 1640 may also identify any slots (e.g., the slots 1730, 1732, 1740, 1742) in the FPGAs 1720, 1722, such as by querying each FPGA 1720, 1722 for the number of slots. Further, as indicated in block 1912, the accelerator sled 1640 may identify any other types (e.g., ASICs, graphics processors, etc.) of accelerator devices present on the accelerator sled 1640.
In block 1914, the accelerator sled 1640, in the illustrative embodiment, identifies regions of the memory 1734, 1744, that are available for access by a remote compute device (e.g., the compute sled 1630). In doing so, the accelerator sled 1640 identifies random access memory regions, as indicated in block 1916, identifies user command register regions, as indicated in block 1918, and identifies administrative command register regions, as indicated in block 1920, such as by querying each accelerator device 1716 for address ranges associated with the regions. As described in more detail herein, the accelerator sled 1640 may associate each type of memory region with a corresponding access mode (e.g., proxy or direct) to be used by a remote compute device (e.g., the compute sled 1630). In block 1922, the accelerator sled 1640 may further identify the available capacity of each of the accelerator devices 1716 (e.g., a number of slots that have not been allocated to the execution a function on behalf of a remote compute device, a percentage of total processing capacity still available, etc.).
Subsequently, in block 1924, the accelerator sled 1640 determines whether to provide acceleration for a compute device (e.g., the compute sled 1630). For example, the accelerator sled 1640 may receive a request from the compute sled 1630 for data indicative of the available acceleration capacity on the accelerator sled 1640 in preparation to request acceleration of a particular function. In response to a determination that the accelerator sled 1640 has not been requested to provide acceleration for a compute device, the method 1900 loops back to block 1902 to continue to monitor the attributes and available capacity of the accelerator devices 1716 on the accelerator sled 1640. Otherwise, the method 1900 advances to block 1926 of FIG. 20, in which the accelerator sled 1640 provides the accelerator abstraction data 1802, representing the identified accelerator devices 1716 as one or more logical devices to the compute device (e.g., the compute sled 1630). As described herein, the number logical devices may differ from the number of accelerator devices 1716 physically present on the accelerator sled 1640 (e.g., the mapping is not necessary one-to-one).
Referring now to FIG. 20, in providing the accelerator abstraction data 1802, the accelerator sled 1640 may represent multiple accelerator devices 1716 as a single logical device, as indicated in block 1928. Additionally or alternatively, the accelerator sled 1640 may represent a single accelerator device 1716 as multiple logical devices, as indicated in block 1930. In doing so, the accelerator sled 1640 may represent each slot of an FPGA (e.g., slots 1730, 1732) as separate logical devices, as indicated in block 1932. The accelerator sled 1640 may represent the accelerator devices as a number of logical devices that is determined as a function of the available capacity (e.g., the available capacity determined in block 1922) of the accelerator devices 1716, as indicated in block 1934. For example, the accelerator sled 1640 may represent two accelerator devices that have only 50% capacity available as a single logical device and/or may represent an accelerator device having twice the capacity of other accelerator devices on the accelerator sled 1640 (or twice the capacity of a reference amount of capacity) as two logical devices. In block 1936, the accelerator sled 1640, in the illustrative embodiment, indicates the memory regions of the accelerator devices 1716 that are available for access by a remote compute device (e.g., compute sled 1630). In doing so, the accelerator sled 1640 indicates random access memory (e.g., volatile memory) available for access, in block 1938, indicates user command register regions available for access, in block 1940, and indicates administrative command register regions available for access in block 1942. The accelerator sled 1640, in the illustrative embodiment, also indicates the access mode available for each memory region, as indicated in block 1944. In doing so, the accelerator sled 1640 indicates memory regions (e.g., random access memory for temporarily storing bit streams, parameters associated with the execution of functions on the accelerator device(s), output from the execution of one or more functions, etc.) that are available for a direct access mode, as indicated in block 1946. Further, the accelerator sled 1640, in the illustrative embodiment, indicates memory regions that are available for access through the proxy mode (e.g., in which the controller 1642 acts as an intermediary to evaluate commands and selectively reject or issue the commands to the corresponding accelerator device(s)), as indicated in block 1948. Subsequently, in block 1950, the accelerator sled 1640 determines whether a request (e.g., to perform an operation with one or more of the represented logical devices) has been received (e.g., from the compute sled 1630). If not, the method 1900 continues to await such a request. Otherwise, the method 1900 advances to block 1952 of FIG. 21, in which the accelerator sled 1640 determines parameters of the request.
Referring now to FIG. 21, in determining the parameters of the request, the accelerator sled 1640 determines whether the request is a direct access request or a proxy access request, as indicated in block 1954. The accelerator sled 1640 may make the determination by comparing one or more commands (e.g., names of operations) in the request to a predefined set of available commands for each type of mode of access (e.g., read or write may correspond to direct access while reprogram or reset may correspond to proxy access), may identify the requested type of access from a parameter indicating the type of access requested (e.g., a 0 for direct access or a 1 for proxy access), or based on other factors. Regardless, the accelerator sled 1640, in the illustrative embodiment, also determines the memory region to be accessed (e.g., by a parameter indicating a memory address or other identifier that was previously provided to the compute sled 1630 in the accelerator abstraction data 1802 to indicate that memory region), as indicated in block 1956. In the illustrative embodiment, the accelerator sled 1640 also converts the received request from a format used for communications through the network 1612 (e.g., TCP/IP) to a format usable with the accelerator devices 1716 on the accelerator sled (e.g., a PCIe format or other format associated with a local bus), as indicated in block 1958. As such, by reformatting communications between the network 1612 and the accelerator devices 1716 on the accelerator sled 1640, the accelerator sled 1640 may free up a significant amount of processing capacity on each accelerator device 1716 that would otherwise be devoted to managing different communication protocols.
In block 1960, the accelerator sled 1640 compares the parameters of the request to the allowed access mode (e.g., the access mode indicated in block 1944) associated with the memory region to be accessed. Afterwards, in block 1962, the accelerator sled 1640 determines a subsequent course of action based on whether the compute sled 1630 requested an access mode that is allowed for the corresponding memory region. If not, the method 1900 advances to block 1964, in which the accelerator sled 1640 returns an error message indicative of an incorrect access mode for the memory region, and subsequently loops back to block 1950 of FIG. 20 to await another request from the compute sled 1630. Otherwise, the method 1900 advances to block 1966 in which the accelerator sled 1640 determines the subsequent course of action as a function of whether the request is for proxy access. If so, the method 1900 advances to block 1968, in which the accelerator sled 1640 performs, with the controller 1642, a proxy operation on the identified memory region, provided that the operation is allowed. In doing so, the accelerator sled 1640 may reset one or more accelerator devices 1716, as indicated in block 1970. As indicated in block 1972, the accelerator sled 1640 may reprogram one or more accelerator devices 1716. As indicated in block 1974, in some instances, such as where the requested operation is not allowed (e.g., per the access policy data 1804), the accelerator sled 1640 may prevent the operation from being performed. Subsequently, the method 1900 loops back to block 1950 of FIG. 20, in which the accelerator sled 1640 awaits another request from the compute sled 1630. Referring back to block 1966, if proxy access was not requested, the method 1900 advances to block 1976 of FIG. 22, in which the accelerator sled 1640 determines the subsequent course of action as a function of whether the remote compute device (e.g., compute sled 1630) requested direct access.
Referring now to FIG. 22, if the accelerator sled 1640 determines that the remote compute device (e.g., the compute sled 1630) did not request direct access either, the method 1900 loops back to block 1950 of FIG. 20, in which the accelerator sled 1640 awaits another request from the remote compute device. Otherwise (e.g., if the compute sled 1630 did request direct access), the method 1900 advances to block 1978, in which the accelerator sled 1640 performs the requested direct access operation on the identified memory region. In doing so, the accelerator sled 1640 may enable the remote compute device (e.g., the compute sled 1630) to write data directly to the identified memory region, as indicated in block 1980. As indicated in block 1982, the accelerator sled 1640 may enable the remote compute device (e.g., the compute sled 1630) to write parameter data for use by an accelerated function (e.g., input data to operate on). Additionally or alternatively, the accelerator sled 1640 may enable the remote compute device to write a bit stream representative of an accelerated function (e.g., a kernel) to be executed on the accelerator device 1716, as indicated in block 1984. As indicated in block 1986, the accelerator sled 1640 may enable the remote compute device to read data directly from the identified memory region. In doing so, the accelerator sled 1640 may enable the remote compute device to read output data produced from the execution of an accelerated function (e.g., output data written to volatile memory). Further, the accelerator sled 1640 may convert any response (e.g., a response that includes the read data) to be sent back to the remote compute device (e.g., the compute sled 1630) from a format used by the corresponding accelerator device(s) 1716 to a format usable for communications through the network (e.g., TCP/IP). Subsequently, the method 1900 loops back to block 1950 of FIG. 20, in which the accelerator sled 1640 awaits another request from the remote compute device (e.g., compute sled 1630).

EXAMPLES

Illustrative examples of the technologies disclosed herein are provided below. An embodiment of the technologies may include any one or more, and any combination of, the examples described below.
Example 1 includes an accelerator sled comprising an accelerator device; a controller connected to the accelerator device, wherein the controller is to (i) provide, to a compute sled, accelerator abstraction data, wherein the accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region, (ii) receive, from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode, (iii) convert the request from a first format to a second format, wherein the first format is different from the second format and the second format is usable by the accelerator device to perform the operation, and (iv) perform, in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode.
Example 2 includes the subject matter of Example 1, and wherein to perform the operation on the identified memory region comprises to perform the operation in a proxy mode.
Example 3 includes the subject matter of any of Examples 1 and 2, and wherein to perform the operation in a proxy mode comprises to compare the requested operation to policy data indicative of whether one or more operations are allowed or disallowed; and perform, in response to a determination that the requested operation is allowed, the requested operation on the identified memory region of the accelerator device.
Example 4 includes the subject matter of any of Examples 1-3, and wherein to perform the requested operation comprises to perform the requested operation on an administrative command register.
Example 5 includes the subject matter of any of Examples 1-4, and wherein to perform the requested operation comprises to reprogram the accelerator device or reset the accelerator device.
Example 6 includes the subject matter of any of Examples 1-5, and wherein to perform the operation on the identified memory region of the accelerator device comprises to perform a direct access operation.
Example 7 includes the subject matter of any of Examples 1-6, and wherein to perform the direct access operation comprises to enable the compute sled to write data to the identified memory region of the accelerator device.
Example 8 includes the subject matter of any of Examples 1-7, and wherein to perform the direct access operation comprises to enable the compute sled to read data from the identified memory region of the accelerator device.
Example 9 includes the subject matter of any of Examples 1-8, and wherein the accelerator device is one of a plurality of accelerator devices on the accelerator sled; and wherein to provide the accelerator abstraction data comprises to provide accelerator abstraction data that represents the plurality of accelerator devices as a single logical device.
Example 10 includes the subject matter of any of Examples 1-9, and wherein to provide the accelerator abstraction data comprises to provide accelerator abstraction data that represents the accelerator device as multiple logical devices.
Example 11 includes the subject matter of any of Examples 1-10, and wherein the accelerator device is a field programmable gate array with multiple slots and to provide the accelerator abstraction data that represents the accelerator device as multiple logical devices comprises to provide accelerator abstraction data that represents each slot as a different logical device.
Example 12 includes the subject matter of any of Examples 1-11, and wherein the accelerator device is one of a plurality of accelerator devices present on the accelerator sled and the controller is further to identify the accelerator devices present on the sled and the memory regions of each accelerator device that are accessible by the compute sled.
Example 13 includes the subject matter of any of Examples 1-12, and wherein to identify the regions of each accelerator device that are accessible by the compute sled comprises to identify one or more of a random access memory region, a user command register region, or an administrative command register region.
Example 14 includes a method comprising providing, by an accelerator sled that includes an accelerator device connected to a controller, accelerator abstraction data to a compute sled, wherein the accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region; receiving, by the accelerator sled and from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode; converting, with the controller, the request from a first format to a second format, wherein the first format is different from the second format and the second format is usable by the accelerator device to perform the operation; and performing, by the accelerator sled and in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode.
Example 15 includes the subject matter of Example 14, and wherein performing the operation on the identified memory region comprises performing the operation in a proxy mode.
Example 16 includes the subject matter of any of Examples 14 and 15, and wherein performing the operation in a proxy mode comprises comparing the requested operation to policy data indicative of whether one or more operations are allowed or disallowed; and performing, in response to a determination that the requested operation is allowed, the requested operation on the identified memory region of the accelerator device.
Example 17 includes the subject matter of any of Examples 14-16, and wherein performing the requested operation comprises performing the requested operation on an administrative command register.
Example 18 includes the subject matter of any of Examples 14-17, and wherein performing the requested operation comprises reprogramming the accelerator device or resetting the accelerator device.
Example 19 includes the subject matter of any of Examples 14-18, and wherein performing the operation on the identified memory region of the accelerator device comprises performing a direct access operation.
Example 20 includes the subject matter of any of Examples 14-19, and wherein performing the direct access operation comprises enabling the compute sled to write data to the identified memory region of the accelerator device.
Example 21 includes the subject matter of any of Examples 14-20, and wherein performing the direct access operation comprises enabling the compute sled to read data from the identified memory region of the accelerator device.
Example 22 includes the subject matter of any of Examples 14-21, and wherein the accelerator device is one of a plurality of accelerator devices on the accelerator sled; and wherein providing the accelerator abstraction data comprises providing accelerator abstraction data that represents the plurality of accelerator devices as a single logical device.
Example 23 includes the subject matter of any of Examples 14-22, and wherein providing the accelerator abstraction data comprises providing accelerator abstraction data that represents the accelerator device as multiple logical devices.
Example 24 includes the subject matter of any of Examples 14-23, and wherein the accelerator device is a field programmable gate array with multiple slots and wherein providing the accelerator abstraction data that represents the accelerator device as multiple logical devices comprises providing accelerator abstraction data that represents each slot as a different logical device.
Example 25 includes the subject matter of any of Examples 14-24, and wherein the accelerator device is one of a plurality of accelerator devices present on the accelerator sled, the method further comprising identifying, by the accelerator sled, the accelerator devices present on the accelerator sled and the memory regions of each accelerator device that are accessible by the compute sled.
Example 26 includes the subject matter of any of Examples 14-25, and wherein identifying the regions of each accelerator device that are accessible by the compute sled comprises identifying one or more of a random access memory region, a user command register region, or an administrative command register region.
Example 27 includes an accelerator sled comprising means for performing the method of any of Examples 14-26.
Example 28 includes one or more machine-readable storage media comprising a plurality of instructions stored thereon that, in response to being executed, cause an accelerator sled to perform the method of any of Examples 14-26.
Example 29 includes an accelerator sled comprising a compute engine to perform the method of any of Examples 14-26.
Example 30 includes an accelerator sled comprising an accelerator device; access manager circuitry to provide, to a compute sled, accelerator abstraction data, wherein the accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region; and network communicator circuitry to receive, from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode, wherein the access manager circuitry is further to convert the request from a first format to a second format, wherein the first format is different from the second format and the second format is usable by the accelerator device to perform the operation; perform, in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode.
Example 31 includes the subject matter of Example 30, and wherein to perform the operation on the identified memory region comprises to perform the operation in a proxy mode.
Example 32 includes the subject matter of any of Examples 30 and 31, and wherein to perform the operation in a proxy mode comprises to compare the requested operation to policy data indicative of whether one or more operations are allowed or disallowed; and perform, in response to a determination that the requested operation is allowed, the requested operation on the identified memory region of the accelerator device.
Example 33 includes the subject matter of any of Examples 30-32, and wherein to perform the requested operation comprises to perform the requested operation on an administrative command register.
Example 34 includes the subject matter of any of Examples 30-33, and wherein to perform the requested operation comprises to reprogram the accelerator device or reset the accelerator device.
Example 35 includes the subject matter of any of Examples 30-34, and wherein to perform the operation on the identified memory region of the accelerator device comprises to perform a direct access operation.
Example 36 includes the subject matter of any of Examples 30-35, and wherein to perform the direct access operation comprises to enable the compute sled to write data to the identified memory region of the accelerator device.
Example 37 includes the subject matter of any of Examples 30-36, and wherein to perform the direct access operation comprises to enable the compute sled to read data from the identified memory region of the accelerator device.
Example 38 includes the subject matter of any of Examples 30-37, and wherein the accelerator device is one of a plurality of accelerator devices on the accelerator sled; and wherein to provide the accelerator abstraction data comprises to provide accelerator abstraction data that represents the plurality of accelerator devices as a single logical device.
Example 39 includes the subject matter of any of Examples 30-38, and wherein to provide the accelerator abstraction data comprises to provide accelerator abstraction data that represents the accelerator device as multiple logical devices.
Example 40 includes the subject matter of any of Examples 30-39, and wherein the accelerator device is a field programmable gate array with multiple slots and to provide the accelerator abstraction data that represents the accelerator device as multiple logical devices comprises to provide accelerator abstraction data that represents each slot as a different logical device.
Example 41 includes the subject matter of any of Examples 30-40, and wherein the accelerator device is one of a plurality of accelerator devices present on the accelerator sled and the access manager circuitry is further to identify the accelerator devices present on the sled and the memory regions of each accelerator device that are accessible by the compute sled.
Example 42 includes the subject matter of any of Examples 30-41, and wherein to identify the regions of each accelerator device that are accessible by the compute sled comprises to identify one or more of a random access memory region, a user command register region, or an administrative command register region.
Example 43 includes an accelerator sled comprising an accelerator device; means for providing, to a compute sled, accelerator abstraction data, wherein the accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region; circuitry for receiving, from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode; means for converting the request from a first format to a second format, wherein the first format is different from the second format and the second format is usable by the accelerator device to perform the operation; means for performing, in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode.
Example 44 includes the subject matter of Example 43, and wherein the means for performing the operation on the identified memory region comprises means for performing the operation in a proxy mode.
Example 45 includes the subject matter of any of Examples 43 and 44, and wherein the means for performing the operation in a proxy mode comprises means for comparing the requested operation to policy data indicative of whether one or more operations are allowed or disallowed; and means for performing, in response to a determination that the requested operation is allowed, the requested operation on the identified memory region of the accelerator device.
Example 46 includes the subject matter of any of Examples 43-45, and wherein the means for performing the requested operation comprises circuitry for performing the requested operation on an administrative command register.
Example 47 includes the subject matter of any of Examples 43-46, and wherein the means for performing the requested operation comprises circuitry for reprogramming the accelerator device or resetting the accelerator device.
Example 48 includes the subject matter of any of Examples 43-47, and wherein the means for performing the operation on the identified memory region of the accelerator device comprises circuitry for performing a direct access operation.
Example 49 includes the subject matter of any of Examples 43-48, and wherein the means for performing the direct access operation comprises circuitry for enabling the compute sled to write data to the identified memory region of the accelerator device.
Example 50 includes the subject matter of any of Examples 43-49, and wherein the circuitry for performing the direct access operation comprises circuitry for enabling the compute sled to read data from the identified memory region of the accelerator device.
Example 51 includes the subject matter of any of Examples 43-50, and wherein the accelerator device is one of a plurality of accelerator devices on the accelerator sled; and wherein the means for providing the accelerator abstraction data comprises circuitry for providing accelerator abstraction data that represents the plurality of accelerator devices as a single logical device.
Example 52 includes the subject matter of any of Examples 43-51, and wherein the means for providing the accelerator abstraction data comprises circuitry for providing accelerator abstraction data that represents the accelerator device as multiple logical devices.
Example 53 includes the subject matter of any of Examples 43-52, and wherein the accelerator device is a field programmable gate array with multiple slots and the circuitry for providing the accelerator abstraction data that represents the accelerator device as multiple logical devices comprises circuitry for providing accelerator abstraction data that represents each slot as a different logical device.
Example 54 includes the subject matter of any of Examples 43-53, and wherein the accelerator device is one of a plurality of accelerator devices present on the accelerator sled and the compute device further comprises circuitry for identifying the accelerator devices present on the sled and the memory regions of each accelerator device that are accessible by the compute sled.
Example 55 includes the subject matter of any of Examples 43-54, and wherein the circuitry for identifying the regions of each accelerator device that are accessible by the compute sled comprises circuitry for identifying one or more of a random access memory region, a user command register region, and an administrative command register region.

Claims

1. An accelerator sled comprising:

an accelerator device;

a controller connected to the accelerator device, wherein the controller is to (i) provide, to a compute sled, accelerator abstraction data, wherein the accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region, (ii) receive, from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode, (iii) convert the request from a first format to a second format, wherein the first format is different from the second format and the second format is usable by the accelerator device to perform the operation, and (iv) perform, in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode.

2. The accelerator sled of claim 1, wherein to perform the operation on the identified memory region comprises to perform the operation in a proxy mode.

3. The accelerator sled of claim 2, wherein to perform the operation in a proxy mode comprises to:

compare the requested operation to policy data indicative of whether one or more operations are allowed or disallowed; and

perform, in response to a determination that the requested operation is allowed, the requested operation on the identified memory region of the accelerator device.

4. The accelerator sled of claim 3, wherein to perform the requested operation comprises to perform the requested operation on an administrative command register.

5. The accelerator sled of claim 3, wherein to perform the requested operation comprises to reprogram the accelerator device or reset the accelerator device.

6. The accelerator sled of claim 1, wherein to perform the operation on the identified memory region of the accelerator device comprises to perform a direct access operation.

7. The accelerator sled of claim 6, wherein to perform the direct access operation comprises to enable the compute sled to write data to the identified memory region of the accelerator device.

8. The accelerator sled of claim 6, wherein to perform the direct access operation comprises to enable the compute sled to read data from the identified memory region of the accelerator device.

9. The accelerator sled of claim 1, wherein the accelerator device is one of a plurality of accelerator devices on the accelerator sled; and

wherein to provide the accelerator abstraction data comprises to provide accelerator abstraction data that represents the plurality of accelerator devices as a single logical device.

10. The accelerator sled of claim 1, wherein to provide the accelerator abstraction data comprises to provide accelerator abstraction data that represents the accelerator device as multiple logical devices.

11. The accelerator sled of claim 10, wherein the accelerator device is a field programmable gate array with multiple slots and to provide the accelerator abstraction data that represents the accelerator device as multiple logical devices comprises to provide accelerator abstraction data that represents each slot as a different logical device.

12. The accelerator sled of claim 1, wherein the accelerator device is one of a plurality of accelerator devices present on the accelerator sled and the controller is further to identify the accelerator devices present on the sled and the memory regions of each accelerator device that are accessible by the compute sled.

13. One or more machine-readable storage media comprising a plurality of instructions stored thereon that, in response to being executed, cause an accelerator sled to:

provide, to a compute sled, accelerator abstraction data, wherein the accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region;

receive, from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode;

convert the request from a first format to a second format, wherein the first format is different from the second format and the second format is usable by the accelerator device to perform the operation; and

perform, in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode.

14. The one or more machine-readable storage media of claim 13, wherein to perform the operation on the identified memory region comprises to perform the operation in a proxy mode.

15. The one or more machine-readable storage media of claim 14, wherein to perform the operation in a proxy mode comprises to:

16. The one or more machine-readable storage media of claim 15, wherein to perform the requested operation comprises to perform the requested operation on an administrative command register.

17. The one or more machine-readable storage media of claim 15, wherein to perform the requested operation comprises to reprogram the accelerator device or reset the accelerator device.

18. The one or more machine-readable storage media of claim 13, wherein to perform the operation on the identified memory region of the accelerator device comprises to perform a direct access operation.

19. The one or more machine-readable storage media of claim 18, wherein to perform the direct access operation comprises to enable the compute sled to write data to the identified memory region of the accelerator device.

20. The one or more machine-readable storage media of claim 18, wherein to perform the direct access operation comprises to enable the compute sled to read data from the identified memory region of the accelerator device.

21. The one or more machine-readable storage media of claim 13, wherein the accelerator device is one of a plurality of accelerator devices on the accelerator sled; and

22. The one or more machine-readable storage media of claim 13, wherein to provide the accelerator abstraction data comprises to provide accelerator abstraction data that represents the accelerator device as multiple logical devices.

23. The one or more machine-readable storage media of claim 22, wherein the accelerator device is a field programmable gate array with multiple slots and to provide the accelerator abstraction data that represents the accelerator device as multiple logical devices comprises to provide accelerator abstraction data that represents each slot as a different logical device.

24. The one or more machine-readable storage media of claim 13, wherein the accelerator device is one of a plurality of accelerator devices present on the accelerator sled and the plurality of instructions, when executed, further cause the accelerator sled to identify the accelerator devices present on the sled and the memory regions of each accelerator device that are accessible by the compute sled.

25. An accelerator sled comprising:

an accelerator device;

means for providing, to a compute sled, accelerator abstraction data, wherein the accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region;

circuitry for receiving, from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode;

means for converting the request from a first format to a second format, wherein the first format is different from the second format and the second format is usable by the accelerator device to perform the operation;

means for performing, in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode.

26. A method comprising:

providing, by an accelerator sled that includes an accelerator device connected to a controller, accelerator abstraction data to a compute sled, wherein the accelerator abstraction data represents the accelerator device as one or more logical devices, each logical device having one or more memory regions accessible by the compute sled, and defines an access mode usable to access each corresponding memory region;

receiving, by the accelerator sled and from the compute sled, a request to perform an operation on an identified memory region of the accelerator device with a corresponding access mode;

converting, with the controller, the request from a first format to a second format, wherein the first format is different from the second format and the second format is usable by the accelerator device to perform the operation; and

performing, by the accelerator sled and in response to the request, the operation on the identified memory region of the accelerator device with the corresponding access mode.

27. The method of claim 26, wherein performing the operation on the identified memory region comprises performing the operation in a proxy mode.

28. The method of claim 27, wherein performing the operation in a proxy mode comprises:

comparing the requested operation to policy data indicative of whether one or more operations are allowed or disallowed; and

performing, in response to a determination that the requested operation is allowed, the requested operation on the identified memory region of the accelerator device.