feat(bootstrap): host DMA-driven multi-layer inference flow (Wave 41, R-HS-3)#790
Open
gHashTag wants to merge 2 commits into
Open
feat(bootstrap): host DMA-driven multi-layer inference flow (Wave 41, R-HS-3)#790gHashTag wants to merge 2 commits into
gHashTag wants to merge 2 commits into
Conversation
…-HS-2, Closes #786) Wave 40 adds IrqHandler callback registry, IrqDrivenDriver with wait_done_irq, and host-poll-vs-irq CLI that runs both completion paths against MockMmio and compares write/read counts. 32 new tests (11 inline + 21 integration). Zero regressions.
…loses #789) Wave 41 adds InferenceEngine with per-layer DMA prefetch -> inference -> DMA drain cycle, wait_irq_mask generic IRQ wait, and host-inference CLI. 36 new tests (16 inline + 20 integration). Zero regressions.
This was referenced May 23, 2026
This was referenced May 24, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Wave 41 — R-HS-3: DMA-driven multi-layer BitNet inference flow
Closes #789
What changed
New file
bootstrap/src/host/engine.rs:InferenceEnginewith per-layer: DMA prefetch (wait DmaDone) → inference (wait InferenceDone) → DMA drain (wait DmaDone)InferenceReport(total_layers, layers_completed, error_layer, writes, reads)Updated
bootstrap/src/host/irq.rs:wait_irq_mask(mask, max_rounds)— generic IRQ wait for any maskwait_done_irqrefactored to delegate towait_irq_maskUpdated
bootstrap/src/host/mod.rs:pub mod engine+ re-exportsUpdated
bootstrap/src/main.rs:Commands::HostInferencewith--max-roundsflagrun_host_inference()printsOK layers=N completed=M writes=W reads=RNew file
bootstrap/tests/host_engine.rs: 20 integration testsUpdated
docs/NOW.md: wave-41 entryTest results