AMD's RX 9070 series GPUs will feature support for Team Red's ROCm software stack, as confirmed by a company's official through a post on X.
AMD's RDNA 4 GPUs Will Support ROCm Software Stack However, Support Is Expected To Arrive After Initial Launch Period
Well, AMD did finally unveil its RDNA 4 GPU lineup yesterday, and while the announced SKUs did bring a lot to the gaming market, however, it was presumed that the RX 9070 series wouldn't feature support for AMD's ROCm on day one, disappointing many consumers who were looking to run AI-oriented to workloads on the newer GPUs. However, it is now confirmed by AMD's Vice President - AI Software, Anush Elangovan, that the upcoming GPUs will debut with support for ROCm, and a running sample has already been shown as well.
ROCm'ing on just fine https://t.co/KSquDUq34W pic.twitter.com/xhootvpzuE
— Anush Elangovan (@AnushElangovan) February 28, 2025
The official quoted the post by Phoronix, which initially ignited the rumor, by saying that during a Q&A session, AMD felt hesitant about disclosing RDNA 4 support for ROCm. However, this isn't the case at all for now, since Team Red's VP has shown a running sample of ROCm on the RX 9070 series, putting an end to the debate. The bigger question is whether ROCm will be available for use on the exact launch date, since things aren't confirmed for now.
Team Red has been heavily focused on improving its ROCm software stack in an attempt to come on par with NVIDIA's CUDA, which has been a catalyst in the revenue figures Team Green has managed to obtain. Moreover, with edge AI applications seeing a rise, several users are utilizing AMD's high-end consumer GPUs to run such workloads locally, showing that ROCm is witnessing growing adoption, which is why Team Red is committed more than ever.
AMD's RX 9070 series GPUs are expected to bring a lot to the markets in terms of their gaming performance and the value they offer. For AI workloads, considering the VRAM onboard, they might not be the best option, but they are definitely enough for an average consumer.
About the author: Muhammad Zuhair is a hardware and technology reporter for Wccftech, specializing in the semiconductor industry and the complex interplay between technology, manufacturing, and geopolitics. His coverage focuses on the corporate strategies and technological roadmaps of industry giants like TSMC, NVIDIA, Samsung, and Intel. Zuhair's expertise lies in deconstructing complex topics such as fabrication nodes (e.g., 2nm process), the economic impact of policies like the CHIPS Act, and the strategic development of AI infrastructure from NVIDIA, AMD and Intel.
Follow Wccftech on Google to get more of our news coverage in your feeds.
