[Lang] MatrixNdarray refactor part12: Add scalarization for AtomicOpStmt

[jim19930609]

Related issue = #5873, #5819

This PR is working "Part ④" in #5873.

Before scalarization:

TensorType<4 x i32> val = AtomicStmt(TensorType<4 x i32>* dest,
                                      TensorType<4 x i32>  val)

After scalarization:

i32* dest_ptr_0 = MatrixPtrStmt(dest, 0)
i32* dest_ptr_1 = MatrixPtrStmt(dest, 1)
i32* dest_ptr_2 = MatrixPtrStmt(dest, 2)
i32* dest_ptr_3 = MatrixPtrStmt(dest, 3)

i32 dest_val0 = AtomicStmt(dest_ptr_0,
                            val->cast<MatrixInitStmt>()->val[0])
i32 dest_val1 = AtomicStmt(dest_ptr_1,
                            val->cast<MatrixInitStmt>()->val[1])
i32 dest_val2 = AtomicStmt(dest_ptr_2,
                            val->cast<MatrixInitStmt>()->val[2])
i32 dest_val3 = AtomicStmt(dest_ptr_3,
                            val->cast<MatrixInitStmt>()->val[3])

tmp = MatrixInitStmt(dest_val0, dest_val1,
                      dest_val2, dest_val3)

stmt->replace_all_usages_with(tmp)

[netlify]

✅ Deploy Preview for docsite-preview ready!

Name	Link
🔨 Latest commit	6076c74
🔍 Latest deploy log	https://app.netlify.com/sites/docsite-preview/deploys/634cb4ab557a4500086668d8
😎 Deploy Preview	https://deploy-preview-6312--docsite-preview.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site settings.