huge refactor for high RewritePatterns usage and less ad-hoc cpp code

remove Spatial many ops in favor of tensor ops like in pim

src/PIM/Dialect/Pim/Pim.td

@@ -113,6 +113,18 @@ def PimSendBatchOp : PimOp<"send_batch", []> {
   let hasCustomAssemblyFormat = 1;
 }
 
+def PimSendTensorBatchOp : PimOp<"send_tensor_batch", []> {
+  let summary = "Send equal contiguous chunks of one per-lane tensor from a batched core";
+
+  let arguments = (ins
+    PimTensor:$input,
+    DenseI32ArrayAttr:$targetCoreIds
+  );
+
+  let hasVerifier = 1;
+  let hasCustomAssemblyFormat = 1;
+}
+
 def PimReceiveOp : PimOp<"receive", [DestinationStyleOpInterface]> {
   let summary = "Receive a tensor from another core";
 
@@ -181,6 +193,28 @@ def PimReceiveBatchOp : PimOp<"receive_batch", [DestinationStyleOpInterface]> {
   let hasCustomAssemblyFormat = 1;
 }
 
+def PimReceiveTensorBatchOp : PimOp<"receive_tensor_batch", [DestinationStyleOpInterface]> {
+  let summary = "Receive equal contiguous chunks into one per-lane tensor inside a batched core";
+
+  let arguments = (ins
+    PimTensor:$outputBuffer,
+    DenseI32ArrayAttr:$sourceCoreIds
+  );
+
+  let results = (outs
+    PimTensor:$output
+  );
+
+  let extraClassDeclaration = [{
+    mlir::MutableOperandRange getDpsInitsMutable() {
+      return getOutputBufferMutable();
+    }
+  }];
+
+  let hasVerifier = 1;
+  let hasCustomAssemblyFormat = 1;
+}
+
 def PimMemCopyHostToDevOp : PimOp<"memcp_hd", [DestinationStyleOpInterface]> {
   let summary = "Copy a memory region from host memory into device memory";