Back to results
US 10,255,109 B2Granted
High bandwidth connection between processor dies
AssigneeIntel Corporation
InventorsAltug Koker, Abhishek R. Appu, Kiran C. Veernapu, Joydeep Ray, Balaji Vembu
Life of this patent
Estimating the term…
Abstract
Methods and apparatus relating to techniques for avoiding cache lookup for cold cache. In an example, an apparatus comprises logic, at least partially comprising hardware logic, to receive a completion acknowledgment from the plurality of graphics processing units and in response to a determination that the workload is finished, to terminate one or more communication connections on the interconnect bridge. Other embodiments are also disclosed and claimed.
Claims7
An apparatus comprising:
- a processor to:
- receive a metadata from an application, wherein the metadata indicates a level of graphics processing activity associated with the application;
- determine, from the metadata, a number of graphics processing resources to be dedicated to the application, the graphics processing resources comprising a plurality of graphics processing units located on a plurality of separate dies communicatively connected by an interconnect bridge on a semiconductor package;
- configure one or more network connections between the graphics processing resources on the semiconductor package to accommodate the number of graphics processing resources to be dedicated to the application;
- receive graphics data for a workload from the application;
- transmit the graphics data to the plurality of graphics processing units via the interconnect bridge;
- receive a completion acknowledgment from the plurality of graphics processing units;
- and
- in response to a determination that the workload is finished, to terminate one or more communication connections on the interconnect bridge.
6 more elements
An electronic device, comprising:
- a processor
- to:
- receive a metadata from an application, wherein the metadata indicates a level of graphics processing activity associated with the application;
- determine, from the metadata, a number of graphics processing resources to be dedicated to the application, the graphics processing resources comprising a plurality of graphics processing units located on a plurality of separate dies communicatively connected by an interconnect bridge on a semiconductor package;
- configure one or more network connections between the graphics processing resources on the semiconductor package to accommodate the number of graphics processing resources to be dedicated to the application;
- receive graphics data for a workload from the application;
- transmit the graphics data to the plurality of graphics processing units via the interconnect bridge;
- receive a completion acknowledgment from the plurality of graphics processing units;
- and
- in response to a determination that the workload is finished, to terminate one or more communication connections on the interconnect bridge;
- and
- a computer readable memory communicatively coupled to the processor.
9 more elements
A method comprising:
- receiving a metadata from an application, wherein the metadata indicates a level of graphics processing activity associated with the application;
- determining, from the metadata, a number of graphics processing resources to be dedicated to the application, the graphics processing resources comprising a plurality of graphics processing units located on a plurality of separate dies communicatively connected by an interconnect bridge on a semiconductor package;
- configuring one or more network connections between the graphics processing resources on the semiconductor package to accommodate the number of graphics processing resources to be dedicated to the application;
- receiving graphics data for a workload from the application;
- transmitting the graphics data to the plurality of graphics processing units via the interconnect bridge;
- receiving a completion acknowledgment from the plurality of graphics processing units;
- and
- in response to a determination that the workload is finished, terminating one or more communication connections on the interconnect bridge.
5 more elements
One or more non-transitory computer-readable medium comprising one or more instructions that when executed on at least one processor configure the at least one processor to perform one or more operations to:
- receive a metadata from an application, wherein the metadata indicates a level of graphics processing activity associated with the application;
- determine, from the metadata, a number of graphics processing resources to be dedicated to the application, the graphics processing resources comprising a plurality of graphics processing units located on a plurality of separate dies communicatively connected by an interconnect bridge on a semiconductor package;
- configure one or more network connections between the graphics processing resources on the semiconductor package to accommodate the number of graphics processing resources to be dedicated to the application;
- receive graphics data for a workload from the application;
- transmit the graphics data to the plurality of graphics processing units via the interconnect bridge;
- receive a completion acknowledgment from the plurality of graphics processing units;
- and
- in response to a determination that the workload is finished, to terminate one or more communication connections on the interconnect bridge.
5 more elements
Dependencies are inferred from the claim text.