[Mlir-commits] [mlir] Allow 16 bit floating point operand for LLVM_AtomicRMWOp (PR #110553)

[Matt Arsenault]

================
@@ -643,6 +643,14 @@ func.func @atomicrmw_expected_float(%i32_ptr : !llvm.ptr, %i32 : i32) {
 
 // -----
 
+func.func @atomicrmw_unexpected_vector_element(%ptr : !llvm.ptr, %f32_vec : vector<3xf32>) {
+  // expected-error at +1 {{unexpected LLVM IR type for vector element}}
----------------
arsenm wrote:

This is not an IR rule, just pass through any FP vector? 

https://github.com/llvm/llvm-project/pull/110553