[Mlir-commits] [mlir] [mlir][ArmSME] Add custom vector.print lowering for SME tiles (PR #66691)

[Cullen Rhodes]

================
@@ -557,9 +558,22 @@ class LLVM_aarch64_sme_write<string direction>
                      Arg<SVEPredicate, "Vector predicate">:$pg,
                      Arg<SVEVector, "Vector operand">:$vector)>;
 
+// Tile slice to vector
+class LLVM_aarch64_sme_read<string direction>
+    : ArmSME_IntrOp<"read." # direction, /*overloadedOperands=*/[],
+                    [AllShapesMatch<["pg", "res"]>],
+                    /*numResults*/1, /*overloadedResults*/[0]>,
+      Arguments<(ins Arg<SVEVector, "Vector operand">:$vector,
+                     Arg<SVEPredicate, "Vector predicate">:$pg,
+                     Arg<I32, "Virtual tile ID">,
+                     Arg<I32, "Tile slice">)>;
+
 def LLVM_aarch64_sme_write_horiz : LLVM_aarch64_sme_write<"horiz">;
 def LLVM_aarch64_sme_write_vert : LLVM_aarch64_sme_write<"vert">;
 
+def LLVM_aarch64_sme_read_horiz : LLVM_aarch64_sme_read<"horiz">;
+def LLVM_aarch64_sme_read_vert : LLVM_aarch64_sme_read<"vert">;
----------------
c-rhodes wrote:

Please could you add roundtrip tests to `mlir/test/Target/LLVMIR/arm-sme.mlir` for these intrinsics

https://github.com/llvm/llvm-project/pull/66691