LuisaGroup avatar

LuisaGroup

Official

@luisagroup · China

0Followers
|
47Public Repos
|
24Published Skills

High-performance graphics and beyond

Skills Distribution
DomainDeveloper To...Graphics Kernel En.. (50%)Build System Confi.. (30%)C++ Language Archi.. (20%)

Agent Skills by LuisaGroup

Showing 24 vetted skills indexed across 1 GitHub repositories.

LuisaGroupLuisaGroup
1.0k

lc_vstl

Documents vstd container APIs including HashMap, pools, queues, and smart pointers for LuisaCompute.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

lc_core

Reference LuisaCompute core library APIs for types, math, logging, fibers, and STL containers.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

yyjson

Parse, create, and modify JSON documents in C using the yyjson library.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

lc_ast

Documents AST usage marking and CallOp propagation rules in LuisaCompute.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

cmake

Configure and build LuisaCompute with CMake options, custom functions, and backend patterns.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

spirv_codegen

Lowers XIR kernels to validated SPIR-V 1.5 for the Vulkan backend.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

lsp

Provides clangd-powered C++ syntax checks and symbol navigation over an HTTP bridge.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

lc_dsl

Write LuisaCompute DSL kernels, callables, structs, and GPU dispatch code in C++.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

backend_architecture

Documents LuisaCompute backend plugin architecture, DeviceInterface API, and command encoding patterns.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

glslang

Constructs SPIR-V modules programmatically using the glslang SpvBuilder API.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

xir_passes

Author and test XIR transformation passes for the LuisaCompute compiler IR.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

cpp-style

Enforces C++ naming, formatting, static analysis, and RTTI rules for LuisaCompute.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

lc_optimize

Optimize LuisaCompute DSL kernels using warp collectives, shared memory, and command batching.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

project_structure

Documents LuisaCompute's layered architecture, module layout, compiler pipeline, and design patterns.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

rust_workspace

Documents the LuisaCompute Rust workspace covering IR, compiler transforms, CPU backend, and FFI integration.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

ir_pipeline

Documents the legacy IR and XIR compiler pipeline, AST lowering, and optimization passes.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

llvm-spirv

Compiles LuisaCompute AST kernels to Vulkan SPIR-V through LLVM's SPIR-V target.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

spv-opt

Implements SPIRV-Tools optimizer passes with IR manipulation and PassTest registration.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

lc_runtime

Implements GPU compute workflows using LuisaCompute runtime APIs for devices, streams, buffers, and ray tracing.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

hlsl

Generates HLSL shader code using StringBuilder patterns and embedded builtin headers.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

git

Inspect uncommitted changes and commit history using non-interactive git commands.

Official
Basic
LuisaGroupLuisaGroup
1.0k

debug

Diagnose LuisaCompute crashes and test failures using stack-traces, device logging, and buffer read-back.

Official
Intermediate
LuisaGroupLuisaGroup
1.0k

ast

Construct raw kernel and callable ASTs with FunctionBuilder in C++.

Official
Advanced
LuisaGroupLuisaGroup
1.0k

xmake

Automate cross-platform project configuration and builds with XMake.

Official
Intermediate

Frequently Asked Questions About LuisaGroup

FAQPage Schema
What specific tasks can I perform with LuisaGroup's AST capabilities?

You can construct raw kernels and callable abstract syntax trees directly within C++ environments. This enables fine-grained control over kernel generation and function composition, facilitating the development of high-performance rendering logic and complex computational structures.

Which engineers benefit most from XMake integration?

Graphics engineers and systems developers working on cross-platform projects benefit most from XMake. It simplifies project configuration and build management, allowing developers to maintain a unified build structure across Windows, macOS, and Linux environments without manual project file maintenance.

What are the primary prerequisites for implementing these build configurations?

Implementation requires a C++ development environment and the installation of the XMake build system. Users must be familiar with C++ syntax and project structure definitions to effectively utilize the configuration capabilities provided by the XMake framework.