Repository navigation
Conversation
Use Cargo target names for standalone emit-ltoir artifacts. Bind the compiler and reader to the same intermediate directory when invoked from a Cargo workspace member. Signed-off-by: Trent Nelson <trent@trent.me>
Accept ordered external LTO files when materializing embedded cubins. Include their content in the codegen fingerprint and verify owned bytes before linking through the existing finalizer. Preserve inputs that overlap generated output paths and diagnose unresolved device symbols. Add a standalone CUDA FFI example and a native regression script. Signed-off-by: Trent Nelson <trent@trent.me>
Reuse existing example dependency pins and classify external LTO as an FFI fixture. Run its linking regression in native sweeps and verify relocatable debug output in the existing full-debug route. Signed-off-by: Trent Nelson <trent@trent.me>
Preserve exact geometry and fixed dynamic shared-memory requirements through artifact loading so preparation can select and validate the compiled allocation. Keep artifact writers and readers on one in-tree implementation while preserving legacy bundles without launch facts. Signed-off-by: Trent Nelson <trent@trent.me>
Combine the reviewed compiler prerequisites for native library calls. Keep the external LTO fixture on the shared in-tree artifact implementation. Signed-off-by: Trent Nelson <trent@trent.me>
Use the reviewed Cargo target and output-directory correction in the combined compiler prerequisite tree. Signed-off-by: Trent Nelson <trent@trent.me>
Resolve concrete registration functions and scalar argument types during device compilation, then invoke the native provider and link its owned LTO output through the ordinary artifact finalizer. Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Carry the convergence marker through private dependency metadata and emit it on each marked LLVM declaration before native optimization. Deduplicate repeated extern symbols while rejecting incompatible signatures and convergence requirements. Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
Signed-off-by: Trent Nelson <trent@trent.me>
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
This was referenced Oct 20, 2026
This branch has not been deployed
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.
Generic kernels previously required PTX bundle merging, so a materialized native library call could not use the ordinary generated module loader. This lets generic modules load a single embedded CUBIN while preserving exact entry identity and compiled launch facts.
The loader selects the host image containing the module code, keeps all functions and statics in one loaded device module, and rejects multiple native images or mixed payloads that cannot be linked safely. All-PTX programs keep their existing merge path. The guide states the defining/instantiating host-image requirement, Linux procfs access, and missing-entry behavior.
Validation covers actual generic CUBIN execution, compiled geometry/scratch checks, PTX controls and a retained two-native-image rejection. The coordinated native-provider fixture passes 480 cases and memcheck after input-tracking integration. Separate retention probes cover ordinary, thin/fat host LTO, concurrent builds and a single cdylib; marked-helper LTO requires existing #1496, which was tested separately and is not duplicated here. Strict host/backend checks and the book pass.
Depends on #1566 and its coordinated foundations. This draft is cumulative against main; review the generic-loader delta. Checked collective safety and generic host-body retention remain separate owning changes.