[Mlir-commits] [mlir] [MLIR] Fix rewrite of ops with vector operands to LLVM on GPU (PR #127844)

[Krzysztof Drewniak]

================
@@ -513,3 +513,44 @@ module {
     "test.possible_terminator"() : () -> ()
   }) : () -> ()
 }
+
+// -----
+
+module @test_module {
+  // CHECK-LABEL: func @math_sin_vector_1d
+  func.func @math_sin_vector_1d(%arg : vector<4xf16>) -> vector<4xf16> {
+    // CHECK: llvm.extractelement {{.*}} : vector<4xf16>
----------------
krzysz00 wrote:

Do we want to check to see these actually getting passed in to a `sin` call?

https://github.com/llvm/llvm-project/pull/127844