yum-mirror/slang

Making it easier to work with shaders

git clone https://git.yummers.dev/yum-mirror/slang

Harsh Aggarwal (NVIDIA)Fix#7676 - Add Claude Code Assistant for using LLMs (#7673)df398fab6

master
branchesmasterall refs →
1.6 KiB48 linesraw

Slang Repository Structure

For the repoName: shader-slang/slang repository, the deepwiki mcp server structure includes:

Main Topics:

  • 1 Overview
  • 2 Compiler Architecture
    • 2.1 Front-End: Parsing & AST
    • 2.2 Semantic Analysis
    • 2.3 Intermediate Representation
    • 2.4 IR Lowering & Optimization
    • 2.5 Code Generation
  • 3 Session Management & API
    • 3.1 Session & Linkage System
    • 3.2 ComponentType Hierarchy
  • 4 Language Features
    • 4.1 Automatic Differentiation
    • 4.2 Module System
    • 4.3 Interfaces & Generics
    • 4.4 Capabilities System
  • 5 Target Platforms
    • 5.1 HLSL & DirectX Targets
    • 5.2 GLSL & Vulkan Targets
    • 5.3 C++, CUDA & CPU Targets
    • 5.4 Other Targets & Extensions
  • 6 Rendering System
    • 6.1 GFX API Architecture
    • 6.2 Shader Objects & Resource Binding
    • 6.3 Device & Pipeline Management
  • 7 Testing & Build Infrastructure
    • 7.1 Test Framework
    • 7.2 Build System
    • 7.3 CI/CD Pipeline
  • 8 Development Tools
    • 8.1 Language Server
    • 8.2 Utilities & Core Libraries

MCP Tools

1. mcp__deepwiki__ask_question

  • Purpose: Ask specific questions about a GitHub repository
  • Parameters:
    • repoName (required): GitHub repository in format "shader-slang/slang"
    • question (required): The question to ask about the repository
  • Usage: Returns AI-generated answers based on repository analysis

Build Instructions

  • Build using: cmake --build --preset debug
  • Test using: ./build/Debug/bin/slangc -target path/to/file.slang
    • Add -dump-ir for IR stages / optimization logs and understanding
1# Slang Repository Structure
2
3For the repoName: `shader-slang/slang` repository, the deepwiki mcp server structure includes:
4
5## Main Topics:
6 - 1 Overview
7 - 2 Compiler Architecture
8   - 2.1 Front-End: Parsing & AST
9   - 2.2 Semantic Analysis
10   - 2.3 Intermediate Representation
11   - 2.4 IR Lowering & Optimization
12   - 2.5 Code Generation
13 - 3 Session Management & API
14   - 3.1 Session & Linkage System
15   - 3.2 ComponentType Hierarchy
16 - 4 Language Features
17   - 4.1 Automatic Differentiation
18   - 4.2 Module System
19   - 4.3 Interfaces & Generics
20   - 4.4 Capabilities System
21 - 5 Target Platforms
22   - 5.1 HLSL & DirectX Targets
23   - 5.2 GLSL & Vulkan Targets
24   - 5.3 C++, CUDA & CPU Targets
25   - 5.4 Other Targets & Extensions
26 - 6 Rendering System
27   - 6.1 GFX API Architecture
28   - 6.2 Shader Objects & Resource Binding
29   - 6.3 Device & Pipeline Management
30 - 7 Testing & Build Infrastructure
31   - 7.1 Test Framework
32   - 7.2 Build System
33   - 7.3 CI/CD Pipeline
34 - 8 Development Tools
35   - 8.1 Language Server
36   - 8.2 Utilities & Core Libraries
37### MCP Tools
38#### 1. `mcp__deepwiki__ask_question`
39- **Purpose**: Ask specific questions about a GitHub repository
40- **Parameters**:
41  - `repoName` (required): GitHub repository in format "shader-slang/slang"
42  - `question` (required): The question to ask about the repository
43- **Usage**: Returns AI-generated answers based on repository analysis
44
45## Build Instructions
46- Build using: `cmake --build --preset debug`
47- Test using: `./build/Debug/bin/slangc -target path/to/file.slang`
48    - Add `-dump-ir` for IR stages / optimization logs and understanding