Chinese company Moore Threads advances MUSA, a homegrown alternative to Nvidia's CUDA ecosystem, with toolkits enabling code portability.

Moore Threads' GPU programming software stack, dubbed MUSA, has begun to emerge as an alternative to Nvidia's CUDA environment, compatible with the domestic MUSA MTT GPU lineup. Any open-source pedigree of the SDK has not been mentioned, so it is likely proprietary and won't be of much benefit to developers outside China.

The development comes amid escalating U.S. export restrictions on China, which include advanced AI chips, high-bandwidth memory (HBM), manufacturing equipment, and silicon wafers from leading players like Intel, TSMC, and Samsung. In response, China is working to reduce reliance on Western hardware by developing its semiconductor ecosystem with in-house silicon, fab equipment, memory, CPUs, and GPUs. Modern-day machine learning is largely accelerated by parallel computing, something which GPUs excel at, making GPU development critical to China's technological independence.

MUSA provides a built-in compiler (MCC), runtime libraries (MUSA Runtime), a comprehensive list of specialized libraries (MUSA-X), debuggers, and profilers. To ensure compatibility with already written CUDA code, the MUSA SDK also includes Musify, a tool that translates CUDA code for the MUSA environment, likely by translating PTX code at runtime, similar to zLUDA. A strong GPU programming ecosystem offers high-level abstraction, ready-to-use libraries, documentation, and profiling tools—capabilities MUSA aims to provide as Nvidia GPU exports remain restricted.

The MUSA SDK version 4.0.1 is compatible with x86 processors from Intel (on Ubuntu) and Hygon (on Kylin). Moore Threads is demonstrating the prowess of its stack through several demonstrations on its website, including speech synthesis, AI-image generation, image processing, and AI-powered 3D face modeling, some of which are reportedly running on Moore Threads' MTT S3000 datacenter GPUs.

Despite CUDA's clear advantage in terms of advancement, maturity, and support, MUSA could find many indigenous customers in small-scale environments, evolving over time. Chinese GPU maker Cambricon's Q1 revenue hit $423 million as the country's homegrown AI chip market accelerates. While developers envision a heterogeneous future championing hardware-agnostic and open-source platforms, breaking free from CUDA's dominance requires superior alternatives, with ROCm being a key contender—though AMD's hardware support still trails behind Nvidia.