AMD engineers are experimenting with a proof-of-concept implementation of a [1]Shared Virtual Memory (SVM) implementation atop the DRM_GPUSVM framework.

The AMD Linux graphics driver already supports Shared Virtual Memory while the drm_gpusvm framework is a newer approach to provide a unified implementation for GPU drivers for handling memory allocation / mapping / migration across CPU and GPU address spaces. Shared Virtual Memory at large is about enjoying a unified address space where the CPU and GPUs/accelerators can access the same memory locations and use the same memory pointers. With the unified drm_gpusvm framework it should be easier to maintain across drivers compared to each driver's existing (or not) SVM implementation directly atop the likes of Linux's [2]Heterogeneous Memory Management (HMM). More details on the evolving DRM GPU SVM framework can be found via the [3]kernel.org documentation .

AMD is experimenting with DRM_GPUSVM to validate the framework's design and allow for discussing the framework's evolution. This new code is just a basic SVM implementation for now and lacks features like multi-GPU support and other advanced functionality. Even so this basic implementation was enough to pass all ROCR tests and pass a vast majority of the AMDKFD and HIP tests.

DRM_GPUSVM challenges were uncovered in the multi-GPU code paths, no global migration decision logic, no vRAM to vRAM migration, and other technical items. So there's more work ahead before AMD could potentially adopt using the drm_gpusvm framework for its SVM implementation.

Those curious about the request for comments (RFC) patches can find them on the [4]dri-devel mailing list .



[1] https://www.phoronix.com/search/Shared+Virtual+Memory

[2] https://www.phoronix.com/search/Heterogeneous+Memory+Management

[3] https://docs.kernel.org/gpu/rfc/gpusvm.html

[4] https://lore.kernel.org/dri-devel/20260317112958.2925370-1-honglei1.huang@amd.com/