[Mlir-commits] [mlir] [mlir][AMDGPU] Fix raw buffer ptr ops lowering (PR #122293)

[Jakub Kuderski]

================
@@ -42,6 +55,28 @@ static Value createI1Constant(ConversionPatternRewriter &rewriter, Location loc,
   return rewriter.create<LLVM::ConstantOp>(loc, llvmI1, value);
 }
 
+/// Returns the linear index used to access an element in the memref.
+static Value getLinearIndexI32(ConversionPatternRewriter &rewriter,
+                               Location loc, MemRefDescriptor &memRefDescriptor,
+                               ValueRange indices, ArrayRef<int64_t> strides) {
+  IntegerType i32 = rewriter.getI32Type();
+  Value index;
+  for (int i = 0, e = indices.size(); i < e; ++i) {
----------------
kuhar wrote:

nit: use `llvm::enumerate(indices, strides)`?

https://github.com/llvm/llvm-project/pull/122293