floor_examples

floor_examples copied to clipboard

= floor examples =

== dnn ==

• demonstrates inference on a VGG16 deep neural network (implements convolution, max-pooling, fully-connected and softmax layers)
• build with ./build.sh inside the folder
• cd data/nets/vgg16 && ./get_vgg16.sh to download the necessary VGG16 layers/net
• desktop/cli: run with --image <path/to/image.png> (image must be 224*224px 32-bit RGBA for now)
• iOS: press cheese and take a photo image:https://raw.githubusercontent.com/a2flo/floor_examples/master/dnn/ios_cli_example.png["iOS: Lake in the Alps; cli: Tiger, licensed under CC BY 2.0 by Tony Hisgett"]

== warp ==

• image-based warping, implemented using a scatter-based approach and a gather-based approach (based on "Image-Based Bidirectional Scene Reprojection")
• also demonstrates use of: tessellation/displacement, argument buffers and indirect command pipelines
• build with ./build.sh inside the folder
• gather-based warping ref: link:https://www.cse.ust.hk/~psander/docs/bireproj.pdf[Image-Based Bidirectional Scene Reprojection] (link:https://web.archive.org/web/20170611112307/http://www.cs.virginia.edu:80/~gfx/pmwiki/index.php?n=Pubs.Yang2011IBB[original])
• NOTE: in addition to floor + dependencies, this requires SDL2_image with libpng, as well as link:https://github.com/a2flo/libwarp[libwarp]
• video: + image:http://img.youtube.com/vi/PmfJ2kzC49A/0.jpg[link=https://www.youtube.com/watch?v=PmfJ2kzC49A]

== nbody ==

• N-body simulation to demonstrate local/shared memory buffers, local memory barriers, OpenGL and Metal buffer sharing, loop unrolling and that high performance computing is indeed possible with this toolchain
• build with ./build.sh inside the folder
• ref: http://http.developer.nvidia.com/GPUGems3/gpugems3_ch31.html
• video: + image:http://img.youtube.com/vi/DoLe1c-eokI/0.jpg[link=https://www.youtube.com/watch?v=DoLe1c-eokI]

== hlbvh ==

• triangle/triangle collision detection of animated meshes using HLBVH (constructed per-step/frame)
• build with ./build.sh inside the folder
• ref: https://research.nvidia.com/sites/default/files/publications/karras2012hpg_paper.pdf image:https://raw.githubusercontent.com/a2flo/floor_examples/master/hlbvh/hlbvh.gif["sinbad tries slicing golems back, but faceplants into golems back instead, 'cause golem don't giv' no f's"]

== path_tracer ==

• a simple path tracer to demonstrate compute code compilation and execution, as well as some mildly complex modern C++ code
• build with ./build.sh inside the folder
• default output: + image:https://raw.githubusercontent.com/a2flo/floor_examples/master/data/path_tracer_default.png["noise and streaks courtesy of the horrible random function that I'm using"]
• output with --with-textures: + image:https://raw.githubusercontent.com/a2flo/floor_examples/master/data/path_tracer_with_textures.png["with simple textures",width=67%]

== reduction ==

• simple (WIP) reduction example that showcases 3 different reduce implementations: local/shared memory reduce, shuffle reduce and CUDA coop kernel + shuffle reduce
• inclusive/exclusive scan test
• build with ./build.sh inside the folder

== img ==

• small program to demonstrate image functionality by doing a gaussian blur, implemented as both a single-stage blur with manual local memory caching, as well as a separable horizontal/vertical "dumb" blur w/o manual caching (also: a GLSL/OpenGL implementation that does the same)
• build with ./build.sh inside the folder
• example output: + image:https://raw.githubusercontent.com/a2flo/floor_examples/master/data/img_example.png["image blur example",width=67%]

== occ ==

• offline-compute-compiler, compiles compute/graphics C++ code to CUDA/PTX, Metal/AIR, OpenCL/SPIR/SPIR-V, Vulkan/SPIR-V code/binaries (see link:https://github.com/a2flo/floor_examples/blob/master/offline_compiler/src/main.cpp#L109[--help] for all options)
• build with ./build.sh inside the folder

== libfloor and toolchain ==

• https://github.com/a2flo/floor