Cache Coherency Adopted GPU Shared Memory
AssigneeInternational Business Machines Corporation
InventorsZhichao Li, Li Li, Riaz Y. Hussain, Ben Gibbs, Su Liu
Life of this patent
Estimating the term…
Abstract
An approach is provided in which a system includes a GPU cluster. The GPU cluster includes multiple GPU nodes, that each includes a GPU core and a corresponding local cache. The GPU cluster also includes a shared memory and an internal bus that maintains cache coherency between the shared memory and the local caches included in the GPU nodes.
Claims20
A system comprising:
- a graphics processing unit (GPU) cluster comprising:
- a plurality of GPU nodes, each of the plurality of GPU nodes comprising at least one of a plurality of GPU cores and a corresponding at least one of a plurality of local caches;
- a shared memory accessible by each of the plurality of GPU nodes;
- and
- an internal bus that connects the shared memory to the plurality of GPU nodes and maintains cache coherency between the shared memory and each of the plurality of local caches.
The system of 2 wherein the one or more P2P high speed buses maintain cache coherency between the shared memory in the GPU cluster and a different shared memory in a different one of the plurality of GPU clusters.
A method implemented by an information handling system, the method comprising:
- storing a set of data in a first local cache by a first GPU core, wherein the first GPU core and the first local cache are included in a first GPU node, and wherein the first GPU node is included in a GPU cluster that comprises a plurality of GPU nodes and a first shared memory;
- utilizing a cache coherency protocol to copy the set of data over an internal bus from the first local cache to the shared memory;
- utilizing the cache coherency protocol to copy the set of data from the shared memory to a second one of the plurality of GPU nodes, wherein the second GPU node stores the set of data in a second local cache;
- and
- accessing, by a second GPU core included in the second GPU node, the set of data from the second local cache.
An information handling system comprising:
- one or more processors;
- a memory coupled to at least one of the processors;
- a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions of:
- storing a set of data in a first local cache by a first GPU core, wherein the first GPU core and the first local cache are included in a first GPU node, and wherein the first GPU node is included in a GPU cluster that comprises a plurality of GPU nodes and a first shared memory;
- utilizing a cache coherency protocol to copy the set of data over an internal bus from the first local cache to the shared memory;
- utilizing the cache coherency protocol to copy the set of data from the shared memory to a second one of the plurality of GPU nodes, wherein the second GPU node stores the set of data in a second local cache;
- and
- accessing, by a second GPU core included in the second GPU node, the set of data from the second local cache.
Dependencies are inferred from the claim text.