llvm-project

e6c20ada - [mlir][gpu][math] Fix assertion in OpToFuncCallLowering on vector results (#215317)

[mlir][gpu][math] Fix assertion in OpToFuncCallLowering on vector results (#215317) `OpToFuncCallLowering` asserts that operand and result types match, with an escape hatch for scalar `i1` results. Math vector FP classification ops return `vector<...xi1>`, which the escape hatch does not cover, so they trigger the assertion. Reject non-scalar results before the assertion, allowing `ScalarizeVectorOpLowering` to lower them element-wise. This preserves the existing behavior in non-assert builds, where `OpToFuncCallLowering` already failed to match vector types. Add regression coverage for vector and scalar FP classification ops. Fixes #210855 Assisted-by: Claude (Anthropic)