finally fast googlenet with correct latency artifacts for fair comparison

test/PIM/CMakeLists.txt

@@ -29,3 +29,10 @@ add_pim_unittest(PimMemoryLivenessPlannerTest
   LINK_LIBS PRIVATE
   OMPimCompilerUtils
 )
+
+add_pim_unittest(SpatialSchedulingTargetTest
+  SpatialSchedulingTargetTest.cpp
+
+  LINK_LIBS PRIVATE
+  OMPimCompilerUtils
+)

test/PIM/SpatialSchedulingTargetTest.cpp

@@ -0,0 +1,58 @@
+#include <cassert>
+#include <cstdlib>
+#include <vector>
+
+#include "src/Accelerators/PIM/Dialect/Spatial/Transforms/MergeComputeNodes/Scheduling/PeftScheduler.hpp"
+
+using namespace onnx_mlir::spatial;
+
+int main() {
+  TransferCost transfer {.fixed = 50, .networkFlits = 4};
+
+  SchedulingTarget fast;
+  fast.processorCount = 2;
+  fast.interProcessorLatencyNs = {0, 3, 3, 0};
+  fast.averageInterProcessorLatencyNs = 3;
+
+  SchedulingTarget slow = fast;
+  slow.interProcessorLatencyNs = {0, 10, 10, 0};
+  slow.averageInterProcessorLatencyNs = 10;
+
+  assert(getPeftTransferTime(transfer, 0, 0, fast) == 0);
+  assert(getPeftTransferTime(transfer, 0, 1, fast) == 62);
+  assert(getPeftTransferTime(transfer, 0, 1, slow) == 90);
+  assert(fast.getInterProcessorLatencyNs(0, 1) == 3);
+  assert(slow.getInterProcessorLatencyNs(0, 1) == 10);
+
+  SchedulingTarget line;
+  line.processorCount = 3;
+  line.interProcessorLatencyNs = {
+    0,
+    1,
+    10,
+    1,
+    0,
+    1,
+    10,
+    1,
+    0,
+  };
+  std::vector<Cost> logicalTrafficFlits(9, 0);
+  logicalTrafficFlits[2] = 100;
+  assert(mapLogicalProcessorsToPhysicalCores(logicalTrafficFlits, line) == std::vector<size_t>({1, 0, 2}));
+
+  SchedulingTarget alreadyPlaced = line;
+  alreadyPlaced.interProcessorLatencyNs = {
+    0,
+    10,
+    1,
+    10,
+    0,
+    1,
+    1,
+    1,
+    0,
+  };
+  assert(mapLogicalProcessorsToPhysicalCores(logicalTrafficFlits, alreadyPlaced) == std::vector<size_t>({0, 1, 2}));
+  return EXIT_SUCCESS;
+}