[Mlir-commits] [mlir] 65ed4fa - [mlir] Python: Parse ModuleOp from file path (#126572)

[llvmlistbot at llvm.org]

Author: Nikhil Kalra
Date: 2025-02-12T14:02:41-08:00
New Revision: 65ed4fa57e6293f8e059a368ac52e2a57b1f78e4

URL: https://github.com/llvm/llvm-project/commit/65ed4fa57e6293f8e059a368ac52e2a57b1f78e4
DIFF: https://github.com/llvm/llvm-project/commit/65ed4fa57e6293f8e059a368ac52e2a57b1f78e4.diff

LOG: [mlir] Python: Parse ModuleOp from file path (#126572)

For extremely large models, it may be inefficient to load the model into
memory in Python prior to passing it to the MLIR C APIs for
deserialization. This change adds an API to parse a ModuleOp directly
from a file path.

Re-lands
[4e14b8a](https://github.com/llvm/llvm-project/commit/4e14b8afb44af58ab7073bb8c0b52875599b0ae1).

Added: 
    

Modified: 
    mlir/include/mlir-c/IR.h
    mlir/lib/Bindings/Python/IRCore.cpp
    mlir/lib/CAPI/IR/IR.cpp
    mlir/python/mlir/_mlir_libs/_mlir/ir.pyi
    mlir/test/python/ir/module.py

Removed: 
    


################################################################################
diff  --git a/mlir/include/mlir-c/IR.h b/mlir/include/mlir-c/IR.h
index 7d2fd89e8560f..14ccae650606a 100644
--- a/mlir/include/mlir-c/IR.h
+++ b/mlir/include/mlir-c/IR.h
@@ -309,6 +309,10 @@ MLIR_CAPI_EXPORTED MlirModule mlirModuleCreateEmpty(MlirLocation location);
 MLIR_CAPI_EXPORTED MlirModule mlirModuleCreateParse(MlirContext context,
                                                     MlirStringRef module);
 
+/// Parses a module from file and transfers ownership to the caller.
+MLIR_CAPI_EXPORTED MlirModule
+mlirModuleCreateParseFromFile(MlirContext context, MlirStringRef fileName);
+
 /// Gets the context that a module was created with.
 MLIR_CAPI_EXPORTED MlirContext mlirModuleGetContext(MlirModule module);
 

diff  --git a/mlir/lib/Bindings/Python/IRCore.cpp b/mlir/lib/Bindings/Python/IRCore.cpp
index 47a85c2a486fd..827db5f3eba84 100644
--- a/mlir/lib/Bindings/Python/IRCore.cpp
+++ b/mlir/lib/Bindings/Python/IRCore.cpp
@@ -299,7 +299,7 @@ struct PyAttrBuilderMap {
     return *builder;
   }
   static void dunderSetItemNamed(const std::string &attributeKind,
-                                nb::callable func, bool replace) {
+                                 nb::callable func, bool replace) {
     PyGlobals::get().registerAttributeBuilder(attributeKind, std::move(func),
                                               replace);
   }
@@ -3049,6 +3049,18 @@ void mlir::python::populateIRCore(nb::module_ &m) {
           },
           nb::arg("asm"), nb::arg("context").none() = nb::none(),
           kModuleParseDocstring)
+      .def_static(
+          "parseFile",
+          [](const std::string &path, DefaultingPyMlirContext context) {
+            PyMlirContext::ErrorCapture errors(context->getRef());
+            MlirModule module = mlirModuleCreateParseFromFile(
+                context->get(), toMlirStringRef(path));
+            if (mlirModuleIsNull(module))
+              throw MLIRError("Unable to parse module assembly", errors.take());
+            return PyModule::forModule(module).releaseObject();
+          },
+          nb::arg("path"), nb::arg("context").none() = nb::none(),
+          kModuleParseDocstring)
       .def_static(
           "create",
           [](DefaultingPyLocation loc) {

diff  --git a/mlir/lib/CAPI/IR/IR.cpp b/mlir/lib/CAPI/IR/IR.cpp
index f27af0ca9a2c7..999e8cbda1295 100644
--- a/mlir/lib/CAPI/IR/IR.cpp
+++ b/mlir/lib/CAPI/IR/IR.cpp
@@ -22,6 +22,7 @@
 #include "mlir/IR/Location.h"
 #include "mlir/IR/Operation.h"
 #include "mlir/IR/OperationSupport.h"
+#include "mlir/IR/OwningOpRef.h"
 #include "mlir/IR/Types.h"
 #include "mlir/IR/Value.h"
 #include "mlir/IR/Verifier.h"
@@ -328,6 +329,15 @@ MlirModule mlirModuleCreateParse(MlirContext context, MlirStringRef module) {
   return MlirModule{owning.release().getOperation()};
 }
 
+MlirModule mlirModuleCreateParseFromFile(MlirContext context,
+                                         MlirStringRef fileName) {
+  OwningOpRef<ModuleOp> owning =
+      parseSourceFile<ModuleOp>(unwrap(fileName), unwrap(context));
+  if (!owning)
+    return MlirModule{nullptr};
+  return MlirModule{owning.release().getOperation()};
+}
+
 MlirContext mlirModuleGetContext(MlirModule module) {
   return wrap(unwrap(module).getContext());
 }

diff  --git a/mlir/python/mlir/_mlir_libs/_mlir/ir.pyi b/mlir/python/mlir/_mlir_libs/_mlir/ir.pyi
index fb7efb8cd28a5..ab975a6954044 100644
--- a/mlir/python/mlir/_mlir_libs/_mlir/ir.pyi
+++ b/mlir/python/mlir/_mlir_libs/_mlir/ir.pyi
@@ -46,6 +46,7 @@ import abc
 import collections
 from collections.abc import Callable, Sequence
 import io
+from pathlib import Path
 from typing import Any, ClassVar, TypeVar, overload
 
 __all__ = [
@@ -2129,6 +2130,15 @@ class Module:
 
         Returns a new MlirModule or raises an MLIRError if the parsing fails.
 
+        See also: https://mlir.llvm.org/docs/LangRef/
+        """
+    @staticmethod
+    def parseFile(path: str, context: Context | None = None) -> Module:
+        """
+        Parses a module's assembly format from file.
+
+        Returns a new MlirModule or raises an MLIRError if the parsing fails.
+
         See also: https://mlir.llvm.org/docs/LangRef/
         """
     def _CAPICreate(self) -> Any: ...

diff  --git a/mlir/test/python/ir/module.py b/mlir/test/python/ir/module.py
index ecafcb46af217..6065e59fd6ed9 100644
--- a/mlir/test/python/ir/module.py
+++ b/mlir/test/python/ir/module.py
@@ -1,6 +1,7 @@
 # RUN: %PYTHON %s | FileCheck %s
 
 import gc
+from tempfile import NamedTemporaryFile
 from mlir.ir import *
 
 
@@ -27,6 +28,24 @@ def testParseSuccess():
     print(str(module))
 
 
+# Verify successful parse from file.
+# CHECK-LABEL: TEST: testParseFromFileSuccess
+# CHECK: module @successfulParse
+ at run
+def testParseFromFileSuccess():
+    ctx = Context()
+    with NamedTemporaryFile(mode="w") as tmp_file:
+        tmp_file.write(r"""module @successfulParse {}""")
+        tmp_file.flush()
+        module = Module.parseFile(tmp_file.name, ctx)
+        assert module.context is ctx
+        print("CLEAR CONTEXT")
+        ctx = None  # Ensure that module captures the context.
+        gc.collect()
+        module.operation.verify()
+        print(str(module))
+
+
 # Verify parse error.
 # CHECK-LABEL: TEST: testParseError
 # CHECK: testParseError: <