Merge branch 'main' into llvm14config

.gitignore

@@ -3,7 +3,6 @@ build/
 __pycache__/
 .vscode
 experiments/*/output
-
 seed_embeddings/triplets.txt
 seed_embeddings/triplets14.txt
 seed_embeddings/preprocessed/*

Manylinux2014_Compliant_Source/pkg/tests/test_ir2vec.py

@@ -101,7 +101,6 @@ def assert_valid_functionVector(functionVectorMap):
 
     return True
 
-
 def test_fa_p():
     p_vectors = []
     for file in ll_files:
@@ -194,14 +193,13 @@ def test_fa_f():
             assert(
                 funcObj["vector"] == pytest.approx(functionOutput1[fun]["vector"], abs=ABS_ACCURACY)
             )
-            
+
     print(TEST_SUITE_DIR)
     f_vecs_oracle = read_f_file(
         TEST_SUITE_DIR / "oracle" / f"FA_{SEED_VERSION}_f" / "ir2vec.txt"
     )
     for pname, funs in f_vecs_oracle.items():
         for fname, vec in funs.items():
-
             assert vec == pytest.approx(
                 f_vecs[pname][fname], abs=ABS_ACCURACY
             ), f"Checking {pname}: {fname}"
@@ -256,7 +254,6 @@ def test_sym_f():
     )
     for pname, funs in f_vecs_oracle.items():
         for fname, vec in funs.items():
-
             assert vec == pytest.approx(
                 f_vecs[pname][fname], abs=ABS_ACCURACY
             ), f"Checking {pname}: {fname}"

README.md

@@ -28,6 +28,7 @@ Please see [here](https://compilers.cse.iith.ac.in/projects/ir2vec/) for more de
     - [LLVM Version Archive](#llvm-version-archive)
     - [Table Of Contents](#table-of-contents)
     - [Installation](#installation)
+
     - [Requirements](#requirements)
     - [Binaries and Libraries - Artifacts](#binaries-and-libraries---artifacts)
     - [Building from source](#building-from-source)
@@ -55,7 +56,6 @@ pip install -U IR2Vec
 ```
 However, building from source is also supported for which the requirements and steps are listed down below.
 
-
 ## Requirements
 * cmake (>= 3.13.4)
 * GNU Make (4.2.1)
@@ -70,8 +70,6 @@ However, building from source is also supported for which the requirements and s
 
 (Experiments are done on an Ubuntu 20.04 machine)
 
-## Binaries and Libraries - Artifacts
-Binaries and Libraries (.a and .so) are autogenerated for every relevant checkin using GitHub Actions. Such generated artifacts are tagged along with the successful runs of `Publish` workflow and can be found [here](https://github.com/IITH-Compilers/IR2Vec/actions?query=workflow%3APublish).
 
 ## Building from source
 1. `mkdir build && cd build`
@@ -89,8 +87,10 @@ This process would generate `ir2vec` binary under `build/bin` directory, `libIR2
 
 To ensure the correctness, run `make verify-all`
 
+
+
 ## Generating program representations
-`IR2Vec` can be used either as a stand alone tool using binary, or can be integrated with any third party tools using libraries. Please see below for the usage
+`IR2Vec` can be used either as a stand-alone tool using binary or can be integrated with any third-party tools using libraries. Please see below for the usage
 instructions.
 
 ### Using Binary
@@ -122,16 +122,17 @@ Please use `--help` for further details.
 >     <function-name> = <Embeddings>
 
 #### Flow-Aware Embeddings
-* `` ir2vec -fa -vocab vocabulary/seedEmbeddingVocab-300-llvm12.txt -o <output_file> -level <p|f>  -class <class-number> <input_ll_file>``
+For all functions
+* `` ir2vec -fa -vocab vocabulary/seedEmbeddingVocab-llvm14.txt -o <output_file> -level <p|f>  -class <class-number> <input_ll_file>``
 
-#### Symbolic Embeddings
- * `` ir2vec -sym -vocab vocabulary/seedEmbeddingVocab-300-llvm12.txt -o <output_file> -level <p|f> -class <class-number> <input_ll_file>``
-
-#### On-demand Flow-Aware Embeddings
-* `` ir2vec -fa -vocab vocabulary/seedEmbeddingVocab-300-llvm12.txt -o <output_file> -level f  -class <class-number> -funcName=\<function-name\><input_ll_file>``
+For a specific function
+* `` ir2vec -fa -vocab vocabulary/seedEmbeddingVocab-llvm14.txt -o <output_file> -level f  -class <class-number> -funcName=\<function-name\><input_ll_file>``
 
-#### On-demand Symbolic Embeddings
- * `` ir2vec -sym -vocab vocabulary/seedEmbeddingVocab-300-llvm12.txt -o <output_file> -level f -class <class-number> -funcName=\<function-name\> <input_ll_file>``
+#### Symbolic Embeddings
+For all functions
+ * `` ir2vec -sym -vocab vocabulary/seedEmbeddingVocab-llvm14.txt -o <output_file> -level <p|f> -class <class-number> <input_ll_file>``
+For a specific function
+ * `` ir2vec -sym -vocab vocabulary/seedEmbeddingVocab-llvm14.txt -o <output_file> -level f -class <class-number> -funcName=\<function-name\> <input_ll_file>``
 
 ## Using Libraries
 The libraries can be installed by passing the installation location to the `CMAKE_INSTALL_PREFIX` flag during `cmake` followed by `make install`.
@@ -190,7 +191,6 @@ for (auto val : pgmVec)
     outs() << val << "\t";
 ```
 
-
 ## Using Python package (IR2Vec-Wheels)
 - Input:
   - .ll/.bc file for which embeddings are needed