[Mlir-commits] [mlir] [mlir][ArithToAMDGPU] limit scaling truncf/extf support to gfx950 (PR #155431)

[Krzysztof Drewniak]

krzysz00 wrote:

Landing over objections that have been resolved (test added) because this is blocking basic end-to-end testing of these operations and because there has been no response from @arsenm for over two weeks, and because this is a bug fix more than a feature.

Any remaining issues with the testing and so on should be fixed forward.

https://github.com/llvm/llvm-project/pull/155431