[Mlir-commits] [mlir] [mlir][amdgpu] Add conversion from arith.scaling_extf to amdgpu (PR #146372)

[Tim Gymnich]

================
@@ -0,0 +1,635 @@
+// RUN: mlir-opt --split-input-file %s -convert-arith-to-amdgpu="chipset=gfx950" | FileCheck %s
+
+// CHECK-LABEL: @conversion_f8_f32_fallback
+// CHECK:         [[CST:%.+]] = arith.constant dense<0.000000e+00> : vector<2x2xf32>
----------------
tgymnich wrote:

fixed

https://github.com/llvm/llvm-project/pull/146372