[Mlir-commits] [mlir] [MLIR][ROCDL] Add conversion for gpu.subgroup_id to ROCDL (PR #136405)

[Alan Li]

================
@@ -99,6 +80,26 @@ static constexpr StringLiteral amdgcnDataLayout =
     "64-S32-A5-G1-ni:7:8:9";
 
 namespace {
+
+// Truncate or extend the result depending on the index bitwidth specified
+// by the LLVMTypeConverter options.
+static Value truncOrExtToLLVMType(ConversionPatternRewriter &rewriter,
+                                  Location loc, Value value,
+                                  const LLVMTypeConverter &converter) {
+  int64_t intWidth = cast<IntegerType>(value.getType()).getWidth();
+  int64_t indexBitwidth = converter.getIndexTypeBitwidth();
+  auto indexBitwidthType =
+      IntegerType::get(rewriter.getContext(), converter.getIndexTypeBitwidth());
+  // TODO: use <=> in C++20.
----------------
lialan wrote:

You are right, there aren't a lot it can do at this moment except saving a few brackets.

https://github.com/llvm/llvm-project/pull/136405