Conversation
Query graph-dependent heap, runtime image, Definition and scheduler sizes without binding or allocating device memory. Aggregate compatible graphs by region and recompute aligned offsets for one execution slot. Align common resource validation with TMR while retaining the current K1 wire ABI and program byte semantics. Validate three distinct stream roles and reject unsupported configuration-only HBG sizing queries. Cover size overflow, Definition framing, concurrent queries, stream aliases and loader admission; document Host tensor-data capability rules.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Kernel resource preparation needs sizes derived from the built graph. Add read-only queries for heap, runtime image, Definition and scheduler requirements, then aggregate compatible graphs by region and recompute aligned offsets for a serialized execution slot.
Align common contract validation with the TMR resource vocabulary while preserving the 64-byte K1 invocation ABI and program-mode byte semantics. Require three distinct streams: borrowed caller, dedicated non-hidden AICPU and hidden AICore. Reject configuration-only HBG sizing because it lacks the built graph.
Validation
This commit declares resources; it does not allocate the kernel execution slot. The referenced TMR branch's 40-byte invocation envelope still needs alignment with the 64-byte K1 ABI before combining consumers.
Dependency and review scope
Draft stack entry 2/5: 2B. Depends on H1.
codex/hbg-pr-h1at58387071a5291645e78e47957796891f207a3019.641500ce.These draft PRs are stacked in the personal fork, with each PR based on the preceding milestone branch. The stack is pinned to the tested K1 snapshot
21fb15c00ddc82bb716fb80eee07d307e81d5bad; upstream hw-native-sys#2064 is still open and has since advanced. Updating to its final version is separate integration work.Validation above was completed on this implementation before PR creation. Existing simulation golden checks cover program-mode regression. No idle onboard devices were available; mixed ACLGraph capture/replay, DSV4 CSA device accuracy and comparative performance remain unvalidated.