Placement and scheduling of radio signal processing dataflow operations

Inventors

O'Shea, Timothy James

Assignees

DeepSig Inc

Interested in licensing this patent?

MTEC can help explore whether this patent might be available for licensing for your application.

Publication Number

US-12212975-B2

Patent

Publication Date

2025-01-28

Expiration Date


Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for placement and scheduling of radio signal processing dataflow operations. An example method provides a primitive radio signal processing computational dataflow graph that comprises nodes representing operations and directed edges representing data flow. The nodes and directed edges of the primitive radio signal processing computational dataflow graph are partitioned to produce a set of software kernels that, when executed on processing units of a target hardware platform, achieve a specific optimization objective. Runtime resource scheduling, including data placement for individual software kernels in the set of software kernels to efficiently execute operations on the processing units of the target hardware platform. The resources of the processing units in the target hardware platform are then allocated according to the defined runtime resource scheduling.

Core Innovation

A radio system wirelessly receives an RF signal and performs at least one of interference removal or distortion correction. The radio system accesses runtime resource scheduling stored at the radio system, where the runtime resource scheduling is generated by providing a primitive radio signal processing computational dataflow graph corresponding to at least one of interference removal or distortion correction. The graph includes nodes representing operations and directed edges representing data flow.

The radio system partitions the nodes and directed edges of the primitive radio signal processing computational dataflow graph to produce a set of software kernels. The radio system determines runtime resource scheduling that includes instructions for handling individual software kernels in the set of software kernels using computational resources of the radio system, and based on the runtime resource scheduling allocates computational resources to perform the at least one of interference removal or distortion correction on the RF signal.

In other embodiments, the runtime resource scheduling is determined using hardware configuration information characterizing the radio system. The partitioning of the primitive radio signal processing computational dataflow graph into software kernels uses the hardware configuration information, and the scheduling includes kernel-related handling instructions for allocating computational resources according to the runtime resource scheduling.

The document further characterizes the runtime resource scheduling as including scheduling configuration factors such as data placement, buffer sizes, execution order or work, and memory or bus transfers between processor domains. The scheduling and partitioning workflow may include predicting an initial kernel partition, measuring resource use while executing kernels, and iteratively changing the partitioning to meet an optimization objective based on measured resource use.

Claims Coverage

Two independent claims are identified. Each independent claim centers on generating runtime resource scheduling from a primitive radio signal processing computational dataflow graph partitioned into software kernels, and performing interference removal and/or distortion correction by allocating computational resources according to the runtime scheduling. Across the two independent claims, the core inventive features involve partitioning into software kernels and runtime scheduling instructions for kernel handling, and using hardware configuration information to guide partitioning and determine runtime resource scheduling.

Partitioning a primitive radio signal processing computational dataflow graph into software kernels to generate runtime resource scheduling

Providing a primitive radio signal processing computational dataflow graph corresponding to at least one of interference removal or distortion correction, where the graph comprises nodes representing operations and directed edges representing data flow; partitioning the nodes and directed edges to produce a set of software kernels; determining runtime resource scheduling comprising instructions for handling individual software kernels in the set of software kernels using computational resources of the radio system.

Using hardware configuration information to partition into software kernels and determine runtime resource scheduling

Obtaining hardware configuration information characterizing a radio system; providing a primitive radio signal processing computational dataflow graph corresponding to at least one of interference removal or distortion correction for radio frequency signals, where the graph comprises nodes representing operations and directed edges representing data flow; partitioning, using the hardware configuration information, the nodes and directed edges to produce a set of software kernels; determining runtime resource scheduling comprising instructions for handling individual software kernels in the set of software kernels using computational resources of the radio system.

Both independent claims require runtime resource scheduling determined from a primitive radio signal processing computational dataflow graph partitioned into software kernels, and allocating the radio system computational resources according to that runtime resource scheduling to perform at least one of interference removal or distortion correction on an RF signal. The second independent claim additionally requires using hardware configuration information to guide the partitioning before determining the runtime resource scheduling.

Stated Advantages

Not explicitly described in patent.

Documented Applications

Not explicitly described in patent.

JOIN OUR MAILING LIST

Stay Connected with MTEC

Keep up with active and upcoming solicitations, MTEC news and other valuable information.