Amazon Technologies, Inc.

Ian M Bone

Ethan Zane Evans

Richard David Krog

Kerry Chang

Xiaochuan Qin

Eden Ashley Jn Baptiste

Alexandre P Moura

Eden Jn Baptiste

Jun Zhou

Mario Vargas Adoc

Mario Vargas Adoc, Jr

Eden Ashley Baptiste

Disclosed are various embodiments of a server application that facilitates selecting a computing device in which to host execution of an application. The selected application host provides application output to a client, and the client provides application input to the application host. In some embodiments, the application server may be a communications proxy between the client and a remote application host.

Remote execution of applications over a dispersed network

Disclosed are various embodiments for facilitating anticipatory distribution of applications to a network of remote hosts. A demand for each of the applications is calculated. Based on criteria within the demand and computing resources available, remote hosts are selected to receive the applications. Transmissions of the applications to the selected remote hosts are scheduled and monitored for completion according to the schedule.

Distribution of applications over a dispersed network

Disclosed are various embodiments for facilitating load balancing between a first processor and a second processor in at least one computing device. A request is obtained to execute a first application in the at least one computing device. In one embodiment, a second application associated with the first application is assigned to be executed in the second processor instead of the first processor when a resource usage profile associated with the first application indicates that the first application imposes a greater load on the first processor than the second processor. Conversely, the second application is assigned to be executed in the first processor instead of the second processor when the resource usage profile indicates that the first application imposes a greater load on the second processor than the first processor.

Load balancing between processors

Techniques are described for automatically testing network-accessible functionality, such as in at least some situations based on automated operations of a distributed automated functionality testing system. In at least some such situations, the network-accessible functionality may be provided by an online service, such as if the provider of the online service is a client of the distributed automated functionality testing system. In addition, in at least some situations, the testing performed by the distributed automated functionality testing system uses numerous member computing devices that are owned or otherwise controlled by various users who are not part of the distributed automated functionality testing system or otherwise affiliated with each other, but who register the member computing devices with the distributed automated functionality testing system as being available for later use in performing testing actions, such as in return for monetary fees or other compensation.

Automated testing of online functionality providers

Disclosed are various embodiments for facilitating load balancing between central processing units (CPUs) and graphics processing units (GPUs). A request is obtained to execute a first application in one or more computing devices. In one embodiment, a second application associated with the first application is assigned to be executed in GPUs of the one or more computing devices instead of CPUs of the one or more computing devices when a resource usage profile associated with the first application indicates that the first application imposes a greater CPU load than GPU load. Conversely, the second application is assigned to be executed in the CPUs instead of the GPUs when the resource usage profile indicates that the first application imposes a greater GPU load than CPU load.

Load balancing between general purpose processors and graphics processors

Disclosed are various embodiments for facilitating load balancing between central processing units (CPUs) and graphics processing units (GPUs). A request is obtained to execute a first application in one or more computing devices. In one embodiment, a second application associated with the first application is assigned to be executed in GPUs of the one or more computing devices instead of CPUs of the one or more computing devices when a resource usage profile associated with the first application indicates that the first application is relatively more CPU intensive than GPU intensive. Conversely, the second application is assigned to be executed in the CPUs instead of the GPUs when the resource usage profile indicates that the first application is relatively more GPU intensive than CPU intensive.

Growing community of inventors

Seattle, WA, United States of America

Ian M Bone