[Mlir-commits] [mlir] [mlir][LLVM] Refactor how range() annotations are handled for ROCDL intrinsics (PR #107658)

[Mehdi Amini]

================
@@ -1034,6 +1034,37 @@ def LLVM_TBAATagArrayAttr
   let constBuilderCall = ?;
 }
 
+//===----------------------------------------------------------------------===//
+// ConstantRangeAttr
+//===----------------------------------------------------------------------===//
+def LLVM_ConstantRangeAttr : LLVM_Attr<"ConstantRange", "constant_range"> {
+  let parameters = (ins
+    "IntegerAttr":$lower,
+    "IntegerAttr":$upper
+  );
+  let summary = "A range of two integers, corresponding to LLVM's ConstantRange";
+  let description = [{
+    A pair of two integers, mapping to the ConstantRange structure in LLVM IR,
+    which is allowed to wrap or be empty.
+
+    The range represented is [Lower, Upper), and is either signed or unsigned
+    depending on context.
+
+    `lower` and `upper` must have the same width.
+  }];
+
+  let builders = [
+    AttrBuilder<(ins "uint32_t":$bitWidth, "int64_t":$lower, "int64_t":$upper)>
----------------
joker-eph wrote:

OK, but then this builder is incorrect. It is also leading to inneficiency by hiding costly operations from the user.
 
(I'm also not sure when a i64 would ever be too small for any range in the compiler?)

https://github.com/llvm/llvm-project/pull/107658