AMD is taking another step forward in its commitment to empowering the AI community with the launch of ROCm 6.0. In addition to the previously supported AMD Radeon RX 7900 XT, XTX, and Radeon PRO W7900 GPUs, AI researchers and ML engineers can now develop on the Radeon PRO W7800 and Radeon RX 7900 GRE desktop GPUs.
With this expansion, AMD is making it easier for the AI community to access powerful GPUs at various price points and performance levels. By broadening the range of hardware offerings, AMD is ensuring that AI workloads can be accelerated efficiently, regardless of budget constraints.
One of the notable additions to ROCm 6.0 is the support for ONNX Runtime, which enables users to perform inference on a wider range of source data on local AMD hardware. This means that AI researchers and ML engineers can leverage the full potential of their AMD GPUs to process and analyze data more effectively.
Furthermore, ROCm 6.0 introduces INT8 via MIGraphX, AMD’s own graph inference engine, expanding the available data types for developers and researchers. The inclusion of INT8 alongside FP32 and FP16 further enhances the flexibility and precision of AI workloads.
AMD’s commitment to democratizing AI development and research continues through its ongoing efforts to make AI more accessible. The company promises to announce additional hardware support and capabilities in the future, ensuring that the AI community can stay up-to-date with the latest advancements in GPU technology.
To delve deeper into the capabilities and features of AMD ROCm 6.0, visit AMD’s blog and unlock new possibilities for ML development.
FAQ section:
1. What is ROCm 6.0?
ROCm 6.0 is a software platform developed by AMD that empowers the AI community by providing support for a wider range of GPUs and enhancing the capabilities of AI workloads.
2. Which GPUs are now supported in ROCm 6.0?
In addition to the previously supported AMD Radeon RX 7900 XT, XTX, and Radeon PRO W7900 GPUs, ROCm 6.0 now supports Radeon PRO W7800 and Radeon RX 7900 GRE desktop GPUs.
3. How does ROCm 6.0 benefit the AI community?
By expanding the range of hardware offerings, ROCm 6.0 makes it easier for AI researchers and ML engineers to access powerful GPUs at various price points and performance levels. This ensures that AI workloads can be accelerated efficiently, regardless of budget constraints.
4. What is ONNX Runtime and how does it relate to ROCm 6.0?
ONNX Runtime is a framework that enables users to perform inference on a wider range of source data. ROCm 6.0 now supports ONNX Runtime, allowing AI researchers and ML engineers to leverage the full potential of their AMD GPUs to process and analyze data more effectively.
5. What is INT8 and how does it enhance the flexibility and precision of AI workloads?
INT8 is a data type that has been included in ROCm 6.0 via MIGraphX, AMD’s graph inference engine. In addition to FP32 and FP16, the inclusion of INT8 expands the available data types for developers and researchers, providing more flexibility and precision in AI workloads.
Definitions:
1. GPUs: Graphics Processing Units are specialized electronic circuits designed to rapidly manipulate and alter memory to accelerate the creation of images and video output.
2. AI: Artificial Intelligence refers to the development of computer systems that can perform tasks that would typically require human intelligence, such as visual perception, speech recognition, and decision-making.
3. ML: Machine Learning is a subset of AI that involves the development of algorithms and models that allow computer systems to learn from data and make predictions or decisions without explicit programming.
4. Inference: In the context of AI, inference refers to the process of using a trained model to make predictions or draw conclusions based on new input data.
Suggested related links:
To learn more about AMD ROCm 6.0 and its capabilities, visit AMD’s ROCm website.
For additional information on machine learning development, consider exploring Towards Data Science, a popular platform for AI and ML articles and tutorials.
The source of the article is from the blog newyorkpostgazette.com