add pipeline stages synchronization

full ops throughput validation now passes

src/PIM/Compiler/PimCodeGen.cpp

@@ -695,13 +695,16 @@ void PimCodeGen::codeGenSendOp(pim::PimSendOp sendOp, const StaticValueKnowledge
 void PimCodeGen::codeGenWaitOp(
     pim::PimWaitOp waitOp, const StaticValueKnowledge& knowledge) const {
   auto eventRegister = indexOf(waitOp.getEventRegister(), knowledge);
-  assert(succeeded(eventRegister)
-         && "pim.wait event register must be statically resolvable during codegen");
+  auto waitValue = indexOf(waitOp.getWaitValue(), knowledge);
+  assert(succeeded(eventRegister) && succeeded(waitValue)
+         && "pim.wait operands must be statically resolvable during codegen");
+  if (*waitValue == 0)
+    return;
   pim_binary::InstructionRecord instruction;
   instruction.opcode = pim_binary::Opcode::wait;
   instruction.generic1 = pim::checkedI32OrCrash(
     *eventRegister, "wait event register");
-  instruction.generic2 = waitOp.getWaitValue();
+  instruction.generic2 = pim::checkedI32OrCrash(*waitValue, "wait value");
   emitInstruction(instruction);
 }
 

src/PIM/Compiler/PimCompilerUtils.cpp

@@ -12,6 +12,7 @@
 #include <limits>
 #include <tuple>
 
+#include "src/Accelerators/PIM/Common/PimCommon.hpp"
 #include "src/Accelerators/PIM/Compiler/PimCompilerOptions.hpp"
 #include "src/Accelerators/PIM/Compiler/PimCompilerUtils.hpp"
 #include "src/Accelerators/PIM/Conversion/ONNXToSpatial/ONNXToSpatialOptions.hpp"
@@ -78,6 +79,7 @@ spatial::SchedulingTarget getDefaultPimSchedulingTarget() {
   target.residentWeightCapacity = crossbarCountInCore.getValue();
   target.matrixRows = crossbarSize.getValue();
   target.matrixColumns = crossbarSize.getValue();
+  target.synchronizationRegisterCount = kPimEventRegisterCount;
 
   setDefaultPimInterProcessorLatencies(target);
   return target;