proomt

Search

Search posts, papers, and topics

All posts

LLVM Project BlogMaria Fernanda Guimarães8 min readintermediate

GSoC 2026: Improving HLSL Support in clangd

Read on llvm.org

Summary

The GSoC 2026 project identified and closed numerous gaps in clangd’s HLSL support. By performing a systematic gap analysis, the author authored an RFC, opened 11 GitHub issues, and landed multiple PRs that improve hover (semantic annotations, out/inout parameters, swizzles, RootSignature, register ranges) and code‑completion (attributes, register, semantic annotations, swizzle). The work also ex…

  • Systematic gap analysis (test cases + AST inspection) is essential to decide whether to extend clangd or Clang.
  • Many HLSL features are already present in the AST; exposing them via clangd often requires only thin infrastructure changes.
  • Hover and completion for HLSL can be implemented as independent PRs per feature, easing review and upstreaming.
  • Multiple entry points in a single HLSL file need a compilation‑context switching mechanism; a library‑mode fallback works for modern HLSL.

Improving clangd’s HLSL support directly enhances the developer experience for GPU shader programmers, reducing friction when writing and debugging shaders in IDEs. The project also demonstrates a repeatable process for extending language‑server features for domain‑specific languages, which can be…

6/10
toolingcclangdhlslllvmlanguage server

Related reading

  2. Article: Your Next DSL Author Is a Language Model

    Typed Domain Grounding (TDG) embeds a DSL inside a mainstream language the LLM already knows (e.g., Kotlin) and uses the host compiler as an oracle. The author describes five building blocks—embedding, choosing a host language with high training‑data frequency, compiler‑driven type safety, a generate‑compile‑repair loop, and an on‑demand teaching tool—and shows measured results from kUML, a Kotli…

    InfoQinfoq.com18 min

  3. Constraint Decay: The Fragility of LLM Agents in Backend Code Generation

    A systematic evaluation of LLM agents generating multi‑file backend code shows a sharp drop in correctness when structural constraints (framework conventions, ORM usage, API contracts) are added. Across 100 tasks in 8 Python web frameworks, assertion pass rates fall ~27 points, with data‑layer bugs (bad queries, ORM violations) driving most failures. Mid‑size models cope with minimal frameworks (…

    arXiv cs.SE (Software Engineering)arxiv.org1 minpaperHN287197

  4. Bend 2 and the Vibe-Coding Trap

    The author argues that “vibe‑coding” with LLMs can cause engineers to reinvent existing solutions, using Bend 2—a language that asks LLMs to write long formal proofs—as a case study. By re‑implementing the same demo in SPARK/Ada, the author shows that established formal‑verification tools achieve the same guarantees with a tiny proof, highlighting the need for domain research before prompting LLM…

    Hacker News front pageliampwll.com5 minHN326235

  5. CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

    CodeMidas builds RL environments directly from open‑source code: agents explore a repo, infer a spec, generate tests from the original implementation, and filter tasks via execution checks. The pipeline yields 5,545 high‑quality coding tasks across 23 languages and 15 domains. Training the MiMo‑V2.5 agent with GRPO on this dataset improves benchmark scores by 8‑18% (e.g., DeepSWE +11.7%, ProgramB…

    Hugging Face Daily Papersarxiv.org1 minpaper

  6. Eliminating AI Code Hallucinations with TypeScript Compiler Diagnostics and TDD Loops

    The article shows how to replace raw TypeScript compiler output with a programmatic JSON feedback loop that merges diagnostics and Vitest test failures, feeding the structured data back to an LLM coding agent for self‑correction. It provides concrete code for extracting, enriching, validating, and de‑duplicating errors, and demonstrates token savings and deterministic iteration until compilation…

    SitePointsitepoint.com15 min