even faster on pimcomp models

2026-07-31 21:15:28 +02:00
parent 9ca1a0ed9f
commit f4a3b012cc
49 changed files with 1923 additions and 583 deletions
@@ -6,34 +6,19 @@
 #include "llvm/ADT/SmallVector.h"

 #include <memory>
-#include <optional>
-
 #include "src/Accelerators/PIM/Common/IR/AddressAnalysis.hpp"

 namespace onnx_mlir {

-struct CompiledTransposePlan {
-  mlir::Value source;
-  mlir::Value destination;
-  size_t elementBytes = 0;
-  size_t totalElements = 0;
-  size_t totalBytes = 0;
-  llvm::SmallVector<size_t> sourceShape;
-  llvm::SmallVector<size_t> destinationStrides;
-  llvm::SmallVector<unsigned> destinationDimensionForSource;
-  llvm::SmallVector<size_t> destinationRewinds;
-  bool storagePreserving = false;
-};
-
 enum class CompiledCoreOpKind : uint8_t {
  Load,
  Store,
  Lmv,
+  VMV,
  Receive,
  Send,
  Concat,
  Vmm,
-  Transpose,
  VVAdd,
  VVSub,
  VVMul,
@@ -62,7 +47,6 @@ struct CompiledCoreNode {
  llvm::SmallVector<int64_t> caseValues;
  llvm::SmallVector<std::unique_ptr<llvm::SmallVector<CompiledCoreNode, 8>>> caseBodies;
  std::unique_ptr<llvm::SmallVector<CompiledCoreNode, 8>> defaultBody;
-  std::optional<CompiledTransposePlan> transposePlan;
 };

 struct CompiledCoreProgram {