Inline data inspection for workload simplification

US12399716B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-12399716-B2
Application numberUS-202418625903-A
CountryUS
Kind codeB2
Filing dateApr 3, 2024
Priority dateAug 31, 2017
Publication dateAug 26, 2025
Grant dateAug 26, 2025

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A method, computer readable medium, and processor are described herein for inline data inspection by using a decoder to decode a load instruction, including a signal to cause a circuit in a processor to indicate whether data loaded by a load instruction exceeds a threshold value. Moreover, an indication of whether data loaded by a load instruction exceeds a threshold value may be stored.

First claim

Opening claim text (preview).

What is claimed is: 1. A processor, comprising: a load/store circuit to load stored data indicated by a load instruction; and an inspection circuit to indicate to the load/store circuit whether the stored data to be loaded by the load instruction equals zero. 2. The processor of claim 1 , wherein the inspection circuit is to transmit the stored data and a predicate value to the load/store circuit, wherein the predicate value is asserted when the stored data equals zero and is negated when the stored data does not equal zero. 3. The processor of claim 1 , wherein the load/store circuit is to store the stored data in a register specified by the load instruction. 4. The processor of claim 1 , wherein the load/store circuit is to discard the stored data based, at least in part, on a predicate signal. 5. The processor of claim 1 , wherein the stored data comprises two or more operands of an arithmetic operation. 6. The processor of claim 1 , wherein a branch instruction follows the load instruction in a sequence of instructions by the processor and a predicate signal controls execution of the branch instruction. 7. The processor of claim 1 , wherein a portion of instructions after the load instruction are not executed when the stored data equals zero. 8. A method, comprising: using a load/store circuit to load stored data indicated by a load instruction; and using an inspection circuit to indicate to the load/store circuit whether the stored data to be loaded by the load instruction equals zero. 9. The method of claim 8 , wherein decoding of the load instruction causes the inspection circuit to compare the stored data with zero. 10. The method of claim 8 , further comprising: using a functional circuit to discard the stored data when the stored data equals zero. 11. The method of claim 8 , further comprising: executing a second instruction that follows the load instruction in a sequence of instructions based at least in part on the indication by the inspection circuit. 12. The method of claim 8 , wherein the indication by the inspection circuit is through a signal used to calculate a predicate value. 13. The method of claim 8 , wherein a predicate value changes execution of one or more instructions after the load instruction, the predicate value is asserted when the stored data equals zero and is negated when the stored data does not equal zero. 14. The method of claim 8 , wherein the stored data is compared with a non-zero threshold value indicated by a second load instruction. 15. A system, comprising: a load/store circuit to load stored data indicated by a load instruction; and an inspection circuit to indicate to the load/store circuit whether the stored data to be loaded by the load instruction equals zero. 16. The system of claim 15 , wherein the inspection circuit is to transmit the stored data and a predicate value to the load/store circuit, wherein the predicate value is asserted when the stored data equals zero and is negated when the stored data does not equal zero. 17. The system of claim 15 , wherein the load/store circuit is to discard the stored data based, at least in part, on a predicate signal. 18. The system of claim 15 , wherein the stored data comprises one or more portions representing one or more values, wherein a predicate value is shared among the one or more values. 19. The system of claim 15 , wherein a branch instruction follows the load instruction in a sequence of instructions by the system and a predicate signal controls execution of the branch instruction. 20. The system of claim 15 , wherein the inspection circuit is to indicate to the load/store circuit whether the stored data to be loaded by the load instruction equals a threshold value determined by one or more neural networks.

Assignees

Inventors

Classifications

  • Compare instructions, e.g. Greater-Than, Equal-To, MINMAX · CPC title

  • Machine learning · CPC title

  • Condition code generation, e.g. Carry, Zero flag · CPC title

  • Register arrangements · CPC title

  • G06F9/3001Primary

    Arithmetic instructions · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US12399716B2 cover?
A method, computer readable medium, and processor are described herein for inline data inspection by using a decoder to decode a load instruction, including a signal to cause a circuit in a processor to indicate whether data loaded by a load instruction exceeds a threshold value. Moreover, an indication of whether data loaded by a load instruction exceeds a threshold value may be stored.
Who is the assignee on this patent?
Nvidia Corp
What technology area does this patent fall under?
Primary CPC classification G06F9/3001. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Aug 26 2025 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 10 related publications on this page (citations in our corpus or others sharing the same primary CPC).