Advanced Micro Devices Corporation

Tesla, Inc.

Patryk Kaminski

Keith Lowery

Mauricio Breternitz, Jr

Anton Chernoff

David Brian Glasco

Thaddeus Fortenberry

Thomas R Woller

Daniel William Bailey

Erich Boleyn

Samuel Douglas Crowder

Benjamin Charles Serebrin

Dz-Ching Ju

Leonardo Piga

Gary Frost

Christophe Harle

An autonomous driving controller includes a plurality of parallel processors operating on common input data. Each of the plurality of parallel processors includes a general processor, a security processor subsystem (SCS), and a safety subsystem (SMS). The general processors, the SCSs, and the SMSs of the plurality of parallel processors are configured to first, boot the plurality of SCSs from ROM second, boot the plurality of SMSs of the plurality of parallel processors from RAM or ROM, and, third, boot the plurality of general processors of the plurality of parallel processors from RAM. Between booting of the SCSs and the SMSs, at least one of the plurality of SCSs may load SMS boot code into the RAM that is dedicated to the plurality of SMSs.

Autonomous driving controller parallel processor boot order

An autonomous driving controller includes a plurality of parallel processors operating on common input data received from the plurality of autonomous driving sensors. Each of the plurality of parallel processors includes communication circuitry, a general processor, a security processor subsystem (SCS), and a safety subsystem (SMS). The communication circuitry supports communications between the plurality of parallel processors, including inter-processor communications between the general processors of the plurality of parallel processors, communications between the SCSs of the plurality of parallel processors using SCS cryptography, and communications between the SMSs of the plurality of parallel processors using SMS cryptography, the SMS cryptography differing from the SCS cryptography. The SCS and/or the SMS may each include dedicated hardware and/or memory to support the communications.

Autonomous driving controller encrypted communications

A System on a Chip (SoC) includes a plurality of general purpose processors, a plurality of application specific processors, a plurality of SoC support processing components, a security processing subsystem (SCS), a general access Network on a Chip (NoC) coupled to and servicing communications between the plurality of general purpose processors and the plurality of SoC support components, and a proprietary access NoC coupled to and servicing communications for the plurality of application specific processors and the SCS. The SoC may further include a safety processor subsystem (SMS) coupled to the proprietary access NoC, wherein the proprietary access NoC further services communications for the SMS and isolates communications of the SMS from communications of the plurality of general purpose processors. The general access NoC and the proprietary access NoC isolate communications of the SCS and the SMS from communications of the plurality of general purpose processors.

Isolation of subsystems on a system on a chip

Securely provisioning a System on a Chip (SoC) includes generating a public/private key pair having a public key and a private key, securely storing the private key external to the SoC, embedding the public key in Resistor Transistor Logic (RTL) of the SoC during manufacture of the SoC, encrypting provisioning data using the private key to create encrypted provisioning data, and programming the SoC using the encrypted provisioning data. The secure provisioning may further include generating a secret shared key, embedding the secret shared key in the RTL of the SoC during manufacture of the SoC, and encrypting the provisioning data using the secret shared key. The RTL may be the boot Read Only Memory (ROM) of the SoC. The secure provisioning technique may also be used for subsequent provisioning after the SoC is deployed.

Secure initial provisioning of a system on a chip

The present disclosure relates to a method and system for configuring a computing system, such as a cloud computing system. A method includes providing a user interface comprising selectable boot-time configuration data and selecting, based on at least one user selection of the boot-time configuration data, a boot-time configuration for at least one node of a cluster of nodes of the computing system. The method further includes configuring the at least one node of the cluster of nodes with the selected boot-time configuration to modify at least one boot-time parameter of the at least one node.

System and method for configuring boot-time parameters of nodes of a cloud computing system

Various datacenter or other computing center control apparatus and methods are disclosed. In one aspect, a method of computing is provided that includes defining plural processor performance bins where each processor performance bin has a processor performance state. At least one processor is assigned to each of the plural processor performance bins. Processor performance metrics of at least one of the processors are monitored while the at least one of the processors executes an incoming task. Processor power is modeled based on the monitored performance metrics. Future incoming tasks are assigned to one of the processor performance bins based on the modeled processor power.

Combined dynamic and static power and performance optimization on data centers

The present disclosure relates to a method and system for configuring a computing system, such as a cloud computing system. A method includes determining, based on a shared execution of a workload by a cluster of nodes of the computing system, that at least one node of the cluster of nodes operated at less than a threshold operating capacity during the shared execution of the workload. The method further includes selecting a modified hardware configuration of the cluster of nodes based on the determining such that the cluster of nodes with the modified hardware configuration has at least one of a reduced computing capacity and a reduced storage capacity.

System and method for modifying a hardware configuration of a cloud computing system

An interface includes a first hardware register field to store respective chunks of a command directed to a device and respective chunks of a response to the command from the device. The interface also includes a second hardware register field to store a size of the command and a size of the response. The first and second hardware register fields are accessible by the device and by a processor external to the device that generates the command, in response to memory not being available to buffer the command and the response.

Variable-sized buffers mapped to hardware registers

An approach and a method for efficient execution of nested map-reduce framework workloads to take advantage of the combined execution of central processing units (CPUs) and graphics processing units (GPUs) and lower latency of data access in accelerated processing units (APUs) is described. In embodiments, metrics are generated to determine whether a map or reduce function is more efficiently processed on a CPU or a GPU. A first metric is based on ratio of a number of branch instructions to a number of non-branch instructions, and a second metric is based on the comparison of execution times on each of the CPU and the GPU. Selecting execution of map and reduce functions based on the first and second metrics result in accelerated computations. Some embodiments include scheduling pipelined executions of functions on the CPU and functions on the GPU concurrently to achieve power-efficient nested map reduce framework execution.

Power-efficient nested map-reduce execution on a cloud of heterogeneous accelerated processing units

The present disclosure relates to a method and system for configuring a computing system, such as a cloud computing system. A method includes selecting, based on a user selection received via a user interface, a workload for execution on a cluster of nodes of the computing system. The workload is selected from a plurality of available workloads including an actual workload and a synthetic test workload. The method further includes configuring the cluster of nodes of the computing system to execute the selected workload such that processing of the selected workload is distributed across the cluster of nodes. The synthetic test workload may be generated by a code synthesizer based on a set of user-defined workload parameters provided via a user interface that identify execution characteristics of the synthetic test workload.

System and method for configuring a cloud computing system with a synthetic test workload

Techniques for utilizing processor cores include sequestering processor cores for use independently from an operating system. In at least one embodiment of the invention, a method includes executing an operating system on a first subset of cores including one or more cores of a plurality of cores of a computer system. The operating system executes as a guest under control of a virtual machine monitor. The method includes executing work for an application on a second subset of cores including one or more cores of the plurality of cores. The first and second subsets of cores are mutually exclusive and the second subset of cores is not visible to the operating system. In at least one embodiment, the method includes sequestering the second subset of cores from the operating system.

Hypervisor isolation of processor cores to enable computing accelerator cores

The present disclosure relates to a method, system, and apparatus for configuring a computing system, such as a cloud computing system. A method includes, based on user selections received via a user interface, configuring a cluster of nodes by selecting the cluster of nodes from a plurality of available nodes, selecting a workload container module from a plurality of available workload container modules for operation on each node of the selected cluster of nodes, and selecting a workload for execution with the workload container on the cluster of nodes. Each node of the cluster of nodes includes at least one processing device and memory, and the cluster of nodes is operative to share processing of a workload.

System and method for configuring cloud computing systems

A system and method for efficient automatic scheduling of the execution of work units between multiple heterogeneous processor cores. A processing node includes a first processor core with a general-purpose micro-architecture and a second processor core with a single instruction multiple data micro-architecture. A computer program comprises one or more compute kernels, or function calls. A compiler computes pre-runtime information of the given function call. A runtime scheduler produces one or more work units by matching each of the one or more kernels with an associated record of data. The scheduler assigns work units either to the first or to the second processor core based at least in part on the computed pre-runtime information. In addition, the scheduler is able to change an original assignment for a waiting work unit based on dynamic runtime behavior of other work units corresponding to a same kernel as the waiting work unit.

Growing community of inventors

Austin, TX, United States of America

Patryk Kaminski