add peft scheduling

better deadlock report by pim simulator

src/PIM/Compiler/PimCompilerOptions.cpp

@@ -1,5 +1,7 @@
 #include "src/Accelerators/PIM/Compiler/PimCompilerOptions.hpp"
 
+#include "llvm/Support/ErrorHandling.h"
+
 #define DEBUG_TYPE "PimCompilerOptions"
 
 namespace onnx_mlir {
@@ -13,6 +15,14 @@ llvm::cl::opt<PimEmissionTargetType> pimEmissionTarget(
   llvm::cl::init(EmitPimCodegen),
   llvm::cl::cat(OnnxMlirOptions));
 
+llvm::cl::opt<PimMergeSchedulerType> pimMergeScheduler(
+  "pim-merge-scheduler",
+  llvm::cl::desc("Scheduler used by the Spatial merge-compute-nodes pass"),
+  llvm::cl::values(clEnumValN(MergeSchedulerPeft, "peft", "Use PEFT scheduling")),
+  llvm::cl::values(clEnumValN(MergeSchedulerDcp, "dcp", "Use the legacy DCP-inspired scheduler")),
+  llvm::cl::init(MergeSchedulerPeft),
+  llvm::cl::cat(OnnxMlirOptions));
+
 llvm::cl::opt<bool>
   pimOnlyCodegen("pim-only-codegen",
                  llvm::cl::desc("Only generate code for PIM (assume input is already in bufferized PIM IR)"),
@@ -30,19 +40,19 @@ llvm::cl::opt<bool> pimEmitJson("pim-emit-json",
                                 llvm::cl::cat(OnnxMlirOptions));
 
 llvm::cl::opt<size_t>
-  crossbarSize("crossbar-size", llvm::cl::desc("Width and heigth of a single crossbar"), llvm::cl::init(2));
+  crossbarSize("crossbar-size", llvm::cl::desc("Width and height of a single crossbar"), llvm::cl::init(2));
 
 llvm::cl::opt<size_t>
   crossbarCountInCore("crossbar-count", llvm::cl::desc("Number of crossbars in each core"), llvm::cl::init(256));
 
 llvm::cl::opt<long> coresCount("core-count",
-                               llvm::cl::desc("Number of cores in the chip. `-1` to use the minimum amount of cores."),
+                               llvm::cl::desc("Number of cores in the chip. Required for PIM compilation."),
                                llvm::cl::init(-1));
 
 llvm::cl::opt<size_t> dcpCriticalWindowSize(
   "dcp-critical-window-size",
   llvm::cl::desc("Number of lowest-slack virtual nodes considered by each DCP coarsening iteration. "
-                 "Use 0 to run the legacy full-graph DCP analysis."),
+                 "Use 0 to run the legacy full-graph DCP analysis. Only used by the DCP scheduler."),
   llvm::cl::init(4000));
 
 llvm::cl::opt<bool>
@@ -50,4 +60,13 @@ llvm::cl::opt<bool>
                     llvm::cl::desc("Ignore ConcatOp corner case: do not assert and do a simplification"),
                     llvm::cl::init(false));
 
+bool hasExplicitPimCoreCount() { return coresCount.getNumOccurrences() != 0; }
+
+void verifyExplicitPimCoreCount() {
+  if (!hasExplicitPimCoreCount())
+    llvm::report_fatal_error("PIM compilation requires an explicit --core-count=<positive integer>");
+  if (coresCount.getValue() <= 0)
+    llvm::report_fatal_error("PIM compilation requires --core-count to be a positive integer");
+}
+
 } // namespace onnx_mlir

src/PIM/Compiler/PimCompilerOptions.hpp

@@ -20,8 +20,14 @@ typedef enum {
   EmitPimCodegen = 3
 } PimEmissionTargetType;
 
+typedef enum {
+  MergeSchedulerPeft = 0,
+  MergeSchedulerDcp = 1,
+} PimMergeSchedulerType;
+
 extern llvm::cl::OptionCategory OnnxMlirOptions;
 extern llvm::cl::opt<PimEmissionTargetType> pimEmissionTarget;
+extern llvm::cl::opt<PimMergeSchedulerType> pimMergeScheduler;
 
 extern llvm::cl::opt<bool> pimOnlyCodegen;
 extern llvm::cl::opt<bool> useExperimentalConvImpl;
@@ -32,6 +38,9 @@ extern llvm::cl::opt<size_t> crossbarCountInCore;
 extern llvm::cl::opt<long> coresCount;
 extern llvm::cl::opt<size_t> dcpCriticalWindowSize;
 
+bool hasExplicitPimCoreCount();
+void verifyExplicitPimCoreCount();
+
 // This option, by default set to false, will ignore an error when resolving a
 // specific tiles of the operands of a concat. This specific case is when the
 // wanted tile is generated by two separate operands of the concat. If this is

src/PIM/Compiler/PimCompilerUtils.cpp

@@ -17,6 +17,7 @@ void addPassesPim(OwningOpRef<ModuleOp>& module,
                   PassManager& pm,
                   EmissionTargetType& emissionTarget,
                   std::string outputNameNoExt) {
+  verifyExplicitPimCoreCount();
 
   if (pimOnlyCodegen) {
     // Skip all the lowering passes and directly generate code for PIM.