heterogeneous-computing

cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.

LLM speculative inference server for consumer & heterogeneous hardware

A curated list of awesome parallel computing resources

📚 计算机体系结构与C++书籍收集(持续更新)

Compare and test GPU programming frameworks / Comparaison d'outils pour GPU

CHARM: Composing Heterogeneous Accelerators on Heterogeneous SoC Architecture

A mixed-criticality platform built around Cheshire, with a number of safety/security and predictability features. Ready-to-use FPGA flow on multiple boards is available.

Heterogeneous Research Platform (HERO) for exploration of heterogeneous computers consisting of programmable many-core accelerators and an application-class host CPU, including full-stack software and hardware.

Concurrent CPU-GPU Programming using Task Models

GPU integrations for Dagger.jl

Monte Carlo eXtreme for OpenCL (MCXCL)

a unified cross-architecture heterogeneous CFD solver

Data Parallel Extensions for Python*

"Optimizing Performance and Energy Efficiency in Massively Parallel Systems" PhD Dissertation repository.

AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP (Full Paper accepted to ICCAD2023)!

Open-source bring-up + verified matmul on the first-gen AMD XDNA1 (Phoenix/Hawk Point) NPU on Linux — the gen FastFlowLM/Lemonade skip. RyzenAI-npu1, mlir-aie/IRON, XRT.

A Python based programming system for heterogeneous computing

[ICLR 2024] FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler

🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit-for-bit identical to single-machine. No torch.distributed, no datacenter.