Nvidia patents method to reduce wait times in multi-threaded processors
Nvidia describes a technique for managing data requests in processors that run multiple tasks at once. The system uses a shared counter to track how long data takes to arrive, pausing a task only when necessary to prevent errors.
In the filing’s own words
A process to ameliorate scoreboard aliasing in multi-threaded data processors whereby, in response to executing at least one long-latency instruction in a first thread, a shared hardware scoreboard is incremented. A shared software register is incremented and the shared software register is spilled to a first per-thread register, and execution is switched to a second thread. After execution switches back to the first thread, execution of the first thread is suspended until the shared hardware scoreboard reaches a value at or below a difference between a value in the shared software register and the value spilled into the first per-thread register.
What exactly they claim (claim 1)
1. A process to ameliorate scoreboard aliasing in multi-threaded data processors, the process comprising: in response to executing at least one LOAD instruction in a first thread: incrementing a shared hardware scoreboard; in the first thread, incrementing a shared software register; subsequent to executing the at least one LOAD instruction in the first thread: spilling the shared software register to a first per-thread register; switching to execution of a second thread; switching back to execution of the first thread; and suspending execution of the first thread until the shared hardware scoreboard reaches a value at or below a difference between a value in the shared software register and the value spilled into the first per-thread register.
Facts
- Company
- Nvidia (NVIDIA Corp.)
- Official title
- Anti-aliasing scoreboard mechanism to mitigate execution delays of long-latency instruction executions
- Patent number
- US12801392B2
- Application number
- 18488867
- Filed
- Oct 17, 2023
- Granted
- Nov 17, 2026
- Inventors
- 2
- Claims
- 23
Classified under
G06F 9/3838 Physics & computingG06F 9/52 Physics & computingG06T 1/20 Physics & computingG06T 1/60 Physics & computingMore from Nvidia in Chips & hardware
- Nvidia stacks memory directly on chips to boost data speed Nov 10, 2026
- Nvidia patents method to skip zero data in neural network math Oct 13, 2026
- Nvidia patents hardware to speed up motion blur in ray tracing Oct 13, 2026
- Nvidia patents method to sync data across split processor chips Sep 17, 2026
- Nvidia patents chip math trick to speed up AI calculations Oct 8, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.
