fixes

slightly faster codegen

src/PIM/Compiler/PimArtifactWriter.hpp

@@ -2,16 +2,45 @@
 
 #include "mlir/Dialect/Func/IR/FuncOps.h"
 #include "mlir/IR/BuiltinOps.h"
+#include "mlir/Support/LogicalResult.h"
 
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Support/JSON.h"
+#include "llvm/Support/raw_ostream.h"
+
+#include <cstddef>
+#include <cstdint>
+#include <vector>
 
 #include "onnx-mlir/Compiler/OMCompilerTypes.h"
+#include "src/Accelerators/PIM/Compiler/PimBinaryFormat.hpp"
 
 namespace onnx_mlir {
 
 class PimAcceleratorMemory;
 
+class PimInstructionWriter {
+public:
+  explicit PimInstructionWriter(llvm::raw_pwrite_stream& stream);
+  explicit PimInstructionWriter(llvm::raw_fd_ostream& stream);
+
+  mlir::LogicalResult append(const pim_binary::InstructionRecord& record);
+  mlir::LogicalResult finalize();
+
+private:
+  static constexpr size_t kBufferSize = 256 * 1024;
+  mlir::LogicalResult flushBuffer();
+  bool consumeStreamError();
+
+  llvm::raw_pwrite_stream& stream;
+  llvm::raw_fd_ostream* fileStream = nullptr;
+  std::vector<char> buffer;
+  size_t bufferedBytes = 0;
+  uint32_t count = 0;
+  bool finalized = false;
+  bool hasFailure = false;
+};
+
 OnnxMlirCompilerErrorCodes writeMemoryBinary(mlir::ModuleOp moduleOp,
                                              mlir::func::FuncOp funcOp,
                                              PimAcceleratorMemory& memory,