Pinned Loading

1. Heliora Heliora Public

   GPU-driven Vulkan renderer — compute-shader culling, bindless materials, async-compute SSAO; 1.13M triangles in 38 draw calls at an 11 ms frame budget

   C++ 2

2. Zenith Zenith Public

   C++17 memory allocator toolkit — linear, pool, stack and free-list allocators with benchmarks and a deterministic engine-style frame simulation

   C++ 1

3. Tinyforge Tinyforge Public

   CUDA GEMM optimization lab: 9.2x over a naive baseline, 4289 GFLOPS at N=4096 on an RTX 3050, level with cuBLAS SGEMM in strict FP32

   Cuda 1

4. glslang glslang Public

   Forked from KhronosGroup/glslang

   Khronos-reference front end for GLSL/ESSL, partial front end for HLSL, and a SPIR-V generator.

   C++

5. highway highway Public

   Forked from google/highway

   Performance-portable, length-agnostic SIMD with runtime dispatch

   C++

6. cccl cccl Public

   Forked from NVIDIA/cccl

   CUDA Core Compute Libraries

   C++