Update: replace block core assignment with round-robin in AICPU executors

[ChaoZheng109]

• host_build_graph: remove even-distribution requirement; assign AIC/AIV cores to threads via round-robin (core i → thread i % thread_num_). thread_cores_num_ becomes a per-thread array so each thread knows its exact core count; aic_per_thread_/aiv_per_thread_ store ceil values used as local queue caps.
• tensormap_and_ringbuffer: replace sequential cluster block allocation with round-robin (cluster ci → sched thread ci % divisor). Per-thread core_idx array tracks fill position during assignment; thread_cores_num_ set from ceil(cluster_count/divisor)*3.

Both runtimes previously failed when core counts were not evenly divisible by the thread count. Round-robin handles uneven distributions correctly.

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the robustness of AICPU core assignment by transitioning from a strict block-based distribution to a flexible round-robin approach. This change addresses previous limitations where core counts had to be evenly divisible by the number of threads, preventing failures in uneven distribution scenarios. The update ensures that both host_build_graph and tensormap_and_ringbuffer runtimes can efficiently assign and manage cores, improving overall system stability and resource utilization.

Highlights

• Flexible Core Assignment: Replaced the rigid block-based core assignment with a more robust round-robin strategy for AICPU executors, eliminating the requirement for even core distribution across threads.
• Per-Thread Core Tracking: Updated thread_cores_num_ to be a per-thread array, allowing each thread to accurately track its assigned core count.
• Improved Cluster Allocation: Modified the tensormap_and_ringbuffer runtime to use round-robin allocation for core clusters, ensuring correct handling of uneven distributions.
• Ceiling-based Core Caps: aic_per_thread_ and aiv_per_thread_ now store ceiling values, serving as local queue caps and accommodating uneven core distributions.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request effectively replaces the block-based core assignment with a round-robin strategy in both host_build_graph and tensormap_and_ringbuffer AICPU executors. This change correctly addresses the issue of uneven core distribution among threads. The implementation is sound, with corresponding updates to data structures and logic to support the new assignment method. I have one suggestion to improve code maintainability by reducing duplication in a logging section.