AMD Developing Next-Gen Fortran Compiler Based on Flang, Optimized for AMD GPUs
AMD is developing an open-source Fortran compiler based on LLVM's Flang, optimized for OpenMP offloading to AMD GPUs, enhancing support for ROCm and HIP frameworks, with a dedicated GitHub repository.
Read original article
AMD has announced the development of a new open-source Fortran compiler, the "AMD Next-Gen Fortran Compiler," which is based on LLVM's Flang. This compiler is specifically designed for OpenMP offloading to AMD GPUs and will interface directly with the ROCm and HIP frameworks. Unlike AMD's existing AOMP compiler, which also focuses on GPU offloading, this new compiler is being developed as a separate codebase. It is intended to enhance support for AMD GPUs and is being tested across various Linux distributions using the ROCm driver. The initiative aims to provide improved performance for Fortran applications on AMD hardware, particularly for those utilizing the ROCm compute stack. AMD has made the GitHub repository for this project available under its InfinityHub CI tree. This development is distinct from AMD's CPU compiler efforts, which have already integrated Flang for Fortran support on AMD Zen processors.
- AMD is developing a new open-source Fortran compiler optimized for AMD GPUs.
- The compiler is based on LLVM's Flang and focuses on OpenMP offloading.
- It will interface directly with ROCm and HIP frameworks.
- The project is separate from AMD's existing AOMP compiler and CPU compiler efforts.
- The GitHub repository for the compiler is available under AMD's InfinityHub CI tree.
Related
AMD ROCm 6.2 Release Appears Imminent for Advancing Open-Source GPU Compute
The upcoming AMD ROCm 6.2 release will enhance the open-source GPU compute stack with new features. AMD aims to expand support for consumer GPUs and package ROCm 6.2 for Fedora 41, including the AOMP compiler for OpenMP device offloading. Expectations include AI improvements, performance optimizations, and broader Radeon GPU support. Community engagement is encouraged.
AMD and FreeBSD Begin Collaborating over OS Improvements
AMD and the FreeBSD Foundation are collaborating to develop an AMD IOMMU driver, enhancing FreeBSD's performance, supporting over 256 CPU cores, and improving audio, wireless, and RISC-V capabilities.
AMD ROCm Looks Like It Will Be Supporting OpenCL 3.0 Soon
AMD's ROCm compute stack is set to support OpenCL 3.0 soon, aligning with competitors like NVIDIA and Intel, following recent GitHub activity indicating progress and a completed upgrade ticket.
Fujitsu, AMD Plan to Pair Monaka CPUs with Instinct GPUs
Fujitsu and AMD are collaborating to create an AI and HPC platform integrating Fujitsu's Monaka CPUs and AMD's Instinct GPUs, aiming for energy efficiency and enhanced computational capabilities by 2027.
AMD Announces OLMo, Its First Open LLM
AMD has launched OLMo, its first fully open large language model, designed for data centers and smaller organizations. It runs on AMD GPUs, offers strong performance, and is free for developers.
0 commentsRelated
AMD ROCm 6.2 Release Appears Imminent for Advancing Open-Source GPU Compute
The upcoming AMD ROCm 6.2 release will enhance the open-source GPU compute stack with new features. AMD aims to expand support for consumer GPUs and package ROCm 6.2 for Fedora 41, including the AOMP compiler for OpenMP device offloading. Expectations include AI improvements, performance optimizations, and broader Radeon GPU support. Community engagement is encouraged.
AMD and FreeBSD Begin Collaborating over OS Improvements
AMD and the FreeBSD Foundation are collaborating to develop an AMD IOMMU driver, enhancing FreeBSD's performance, supporting over 256 CPU cores, and improving audio, wireless, and RISC-V capabilities.
AMD ROCm Looks Like It Will Be Supporting OpenCL 3.0 Soon
AMD's ROCm compute stack is set to support OpenCL 3.0 soon, aligning with competitors like NVIDIA and Intel, following recent GitHub activity indicating progress and a completed upgrade ticket.
Fujitsu, AMD Plan to Pair Monaka CPUs with Instinct GPUs
Fujitsu and AMD are collaborating to create an AI and HPC platform integrating Fujitsu's Monaka CPUs and AMD's Instinct GPUs, aiming for energy efficiency and enhanced computational capabilities by 2027.
AMD Announces OLMo, Its First Open LLM
AMD has launched OLMo, its first fully open large language model, designed for data centers and smaller organizations. It runs on AMD GPUs, offers strong performance, and is free for developers.