Implementation of GPU stream compaction and other parallel algorithms in CUDA
-
Updated
Sep 22, 2020 - C++
#
stream-compaction
Here are 5 public repositories matching this topic...
High-performance GPU Path Tracer implemented in CUDA & C++. Features PBR, Wavefront architecture, and advanced BVH acceleration.
-
Updated
Jan 8, 2026 - C++
A GPU path tracer in CUDA with physically-based light transport: Lambertian, mirror, and refractive BSDFs. Features stream compaction via Thrust, stochastic anti-aliasing, depth of field, OBJ mesh loading and BVH acceleration.
opengl cpp gpu cuda bsdf ray-tracing thrust path-tracing physically-based-rendering bounding-volume-hierarchy stream-compaction
-
Updated
Feb 10, 2026 - C++
-
Updated
Jun 1, 2018 - C++
A CUDA implementations of work-efficient parallel scan (Blelloch, O(n) work), stream compaction, and LSD radix sort - built from scratch with shared memory, bank conflict avoidance, and recursive scanning for arbitrary array sizes up to 1B elements.
cpp gpu parallel-computing cuda high-performance-computing prefix-sum shared-memory radix-sort parallel-algorithms stream-compaction
-
Updated
Sep 18, 2025 - Python
Improve this page
Add a description, image, and links to the stream-compaction topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the stream-compaction topic, visit your repo's landing page and select "manage topics."