add pipeline stages synchronization

full ops throughput validation now passes

src/PIM/Dialect/Spatial/Spatial.td

@@ -592,13 +592,15 @@ def SpatHostStoreSyncOp : SpatOp<"host_store_sync", []> {
 }
 
 def SpatHostWaitLoadOp : SpatOp<"host_wait_load", []> {
-  let summary = "Wait for a producer and load its tensor from host memory";
+  let summary = "Wait for producers, load from host memory, and acknowledge consumption";
 
   let arguments = (ins
     Index:$sourceCoreId,
     Index:$targetCoreId,
     Index:$hostOffset,
-    Index:$eventRegister
+    Index:$eventRegister,
+    Index:$waitValue,
+    Index:$acknowledgementEventRegister
   );
 
   let results = (outs
@@ -607,7 +609,34 @@ def SpatHostWaitLoadOp : SpatOp<"host_wait_load", []> {
 
   let assemblyFormat = [{
     `from` $sourceCoreId `to` $targetCoreId
-      `host_offset` $hostOffset `event` $eventRegister attr-dict `:` type($output)
+      `host_offset` $hostOffset `event` $eventRegister `count` $waitValue
+      `ack` $acknowledgementEventRegister attr-dict `:` type($output)
+  }];
+}
+
+def SpatSyncOp : SpatOp<"sync", []> {
+  let summary = "Signal a synchronization register on another processor";
+
+  let arguments = (ins
+    Index:$targetCoreId,
+    Index:$eventRegister
+  );
+
+  let assemblyFormat = [{
+    $targetCoreId `event` $eventRegister attr-dict
+  }];
+}
+
+def SpatWaitOp : SpatOp<"wait", []> {
+  let summary = "Wait for a synchronization register value";
+
+  let arguments = (ins
+    Index:$eventRegister,
+    Index:$waitValue
+  );
+
+  let assemblyFormat = [{
+    $eventRegister `value` $waitValue attr-dict
   }];
 }