US 12,591,474 B2 · Batch scheduling function calls of a transactional application programming interface (API) protocol

Abstract

Embodiments described herein are generally directed to improving performance of a transactional API protocol by batch scheduling data dependent functions. In an example, a prescribed sequence of function calls associated with a transactional application programming interface (API) is received that is to be carried out by an executer (e.g., a compute service or a second processing resource remote from a first processing resource with which an application is associated) to perform an atomic unit of work on behalf of the application. Transport latency over an interconnect between the application and the executer is reduced by: (i) creating a batch representing the prescribed sequence of function calls in a form of a list of function descriptors in which variable arguments of the prescribed sequence of function calls are replaced with corresponding global memory references; and (ii) transmitting the batch via the interconnect as a single message.

Claims20

Dependent claims

At least one non-transitory machine-readable medium having stored thereon instructions which, when executed, cause a processing resource of a computer system to:

receive a prescribed sequence of function calls that is to be carried out by an executer to perform an atomic unit of work on behalf of an application, wherein the prescribed sequence of function calls is associated with a transactional application programming interface (API);
and
reduce transport latency over an interconnect between the application and the executer by:
creating a batch representing the prescribed sequence of function calls in a form of a list of function descriptors in which variable arguments of the prescribed sequence of function calls are represented with corresponding global memory references;
and
transmitting the batch via the interconnect as a single message.

3 more elements

A method comprising:

receiving a prescribed sequence of function calls that is to be carried out by an executer to perform an atomic unit of work on behalf of an application, wherein the prescribed sequence of function calls is associated with a transactional application programming interface (API);
and
reducing transport latency over an interconnect between the application and the executer by:
creating a batch representing the prescribed sequence of function calls in a form of a list of function descriptors in which variable arguments of the prescribed sequence of function calls are replaced with corresponding global memory references;
and
transmitting the batch via the interconnect as a single message.

3 more elements

A system comprising:

a first processing resource;
and
instructions, which when executed by the first processing resource cause the first processing resource to:
receive a prescribed sequence of function calls that is to be carried out by a compute service or a second processing resource remote from the first processing resource to perform an atomic unit of work on behalf of an application associated with the first processing, wherein the prescribed sequence of function calls is associated with a transactional application programming interface (API);
and
reduce transport latency over an interconnect between the application and the compute service or the second processing resource by:
creating a batch representing the prescribed sequence of function calls in a form of a list of function descriptors in which variable arguments of the prescribed sequence of function calls are represented with corresponding global memory references;
and
transmitting the batch via the interconnect as a single message.

6 more elements

Dependencies are inferred from the claim text.

Batch scheduling function calls of a transactional application programming interface (API) protocol

Life of this patent

Batch scheduling function calls of a transactional application programming interface (API) protocol

Life of this patent

Abstract

Claims20