While we are eagerly awaiting ROCm support for more RDNA3 GPUs said to be coming later this calendar year, shipping Tuesday night was ROCm 5.6.1 as the newest point release for this open-source GPU compute stack.

ROCm 5.6.1 is a new bug-fix release over ROCm 5.6 that shipped back in June. It's rather light on the fixes side with just a few HIP-focused issues being resolved.

The release notes lay out the ROCm 5.6.1 changes simply as:

HIP 5.6.1 (for ROCm 5.6.1)
Fixed Defects

- hipMemcpy device-to-device (intra device) is now asynchronous with respect to the host
- Enabled xnack+ check in HIP catch2 tests hang when executing tests
- Memory leak when code object files are loaded/unloaded via hipModuleLoad/hipModuleUnload APIs
- Using hipGraphAddMemFreeNode no longer results in a crash

That's it over ROCm 5.6, which was a released focused on providing greater AI/LLM capabilities for this Radeon Open eCosystem stack.

ROCm 5.6.1 source code is available for download from GitHub . Here's to hoping that the broader RDNA3 GPU support for ROCm will be coming sooner rather than later (ROCm 6.0?).