Rust threads on the GPU

Summary

At VectorWare, we are building the first GPU-native software company. Today, we are excited to announce that we can successfully use Rust's std::thread on the GPU. This milestone marks a significant step towards our vision of enabling developers to write complex, high-performance applications that leverage the full power of GPU hardware using familiar Rust abstractions. Execution models CPUs and GPUs execute programs in fundamentally different ways. A CPU program begins on a single thread and spawns additional threads as needed. Each thread runs independently and the programmer controls when and how concurrency is introduced. main()main threadthread::spawn()main threadnew threadthread::join()main threadexit() GPU programs work differently. A GPU program consists of one or more kernels. Each kernel is launched with many instances that run in parallel. Concurrency is not something the programmer introduces explicitly. It is inherent in the way GPU programs are run by the hardware. launch_by_cpu()kernel()Warp 0kernel()Warp 1kernel()Warp 2kernel()Warp 3kernel()Warp N⋯exit() This model works well for uniform workloads like matrix multiplication, image processing, and graphics rendering where every warp does the same thing to different data. As GPU programs grow more sophisticated, developers use warp specialization to activate different parts of the same program on different warps concurrently. launch_by_cpu()kernel()a()Warp 0kernel()b()Warp 1kernel()c()Warp 2kernel()d()Warp 3kernel()n()Warp N⋯exit() Functions as programs Most CPU programming models begin with a main function as the program's entry point. Because execution begins with exactly one thread, representing the program as a function makes sense: the function body describes the work performed by that single thread. fn main() { // Single threaded CPU code } Surprisingly, most GPU programming models use a function as their entry point as well. The programmer writes the function as if it executes once but the hardw...