Merge pull request #128 from IITH-Compilers/main

Pulling latest changes from main

.github/workflows/doxygen.yml

@@ -33,7 +33,7 @@ jobs:
     - name: Deploy
       uses: peaceiris/actions-gh-pages@v3
       with:
-        github_token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+        github_token: ${{ secrets.GITHUB_TOKEN }}
         # Default Doxyfile build documentation to html directory.
         # Change the directory if changes in Doxyfile
         publish_dir: ./html

Manylinux2014_Compliant_Source/pkg/build.sh

@@ -18,7 +18,7 @@ cd ..
 cmake -DCMAKE_BUILD_TYPE=Release .. && make -j"$(nproc)" && make install
 
 cd ..
-cp build/vocabulary.h Manylinux2014_Compliant_Source/pkg/ir2vec/
+cp build/include/Vocabulary*.h Manylinux2014_Compliant_Source/pkg/ir2vec/
 cp src/include/utils.h Manylinux2014_Compliant_Source/pkg/ir2vec/
 cp src/include/IR2Vec.h Manylinux2014_Compliant_Source/pkg/ir2vec/
 cp build/src/version.h Manylinux2014_Compliant_Source/pkg/ir2vec/

Manylinux2014_Compliant_Source/pkg/ir2vec/core.cpp

@@ -20,7 +20,6 @@
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/SmallSet.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/IR/CFG.h"
@@ -75,19 +74,21 @@ class IR2VecHandler {
   std::string outputFile;
   std::string mode;
   std::string level;
+  unsigned dim;
 
 public:
   IR2VecHandler(std::string fileName, std::string outputFile, std::string mode,
-                std::string level)
-      : fileName(fileName), outputFile(outputFile), mode(mode), level(level) {}
+                std::string level, unsigned dim)
+      : fileName(fileName), outputFile(outputFile), mode(mode), level(level),
+        dim(dim) {}
 
   std::string getFile() { return fileName; }
   std::string getOutputFile() { return outputFile; }
   std::string getMode() { return mode; }
   std::string getLevel() { return level; }
 
   // Function to get Program Vector List
-  PyObject *createProgramVectorList(llvm::SmallVector<double, DIM> llvmPgmVec) {
+  PyObject *createProgramVectorList(IR2Vec::Vector llvmPgmVec) {
     // for PgmVector
     PyObject *PgmList = PyList_New(0);
     for (auto &Pgm_it : llvmPgmVec)
@@ -138,7 +139,6 @@ class IR2VecHandler {
     PyObject *instructionVectorList = PyList_New(0);
     for (auto &Inst_it : llvmInstVecMap) {
       PyObject *instructionVector = PyList_New(0);
-      // copy this SmallVector into c++ Vector
       for (auto &Vec_it : Inst_it.second) {
         PyList_Append(instructionVector, PyFloat_FromDouble(Vec_it));
       }
@@ -166,10 +166,10 @@ class IR2VecHandler {
       ofstream output;
       output.open(outFile, ios_base::app);
       emb = std::move(new IR2Vec::Embeddings(
-          *Module, ir2vecMode, (this->level)[0], &output, funcName));
+          *Module, ir2vecMode, (this->level)[0], &output, this->dim, funcName));
     } else {
       emb = std::move(new IR2Vec::Embeddings(
-          *Module, ir2vecMode, (this->level)[0], nullptr, funcName));
+          *Module, ir2vecMode, (this->level)[0], nullptr, this->dim, funcName));
     }
 
     if (!emb) {
@@ -178,7 +178,7 @@ class IR2VecHandler {
     }
 
     if (type == OpType::Program) {
-      llvm::SmallVector<double, DIM> progVector = emb->getProgramVector();
+      IR2Vec::Vector progVector = emb->getProgramVector();
       return this->createProgramVectorList(progVector);
     } else if (type == OpType::Function) {
       llvm::SmallMapVector<const llvm::Function *, IR2Vec::Vector, 16>
@@ -293,9 +293,10 @@ PyObject *getFunctionVectors(PyObject *self, PyObject *args) {
 
 IR2VecHandlerObject *createIR2VECObject(const char *filename,
                                         const char *output_file,
-                                        const char *mode, const char *level) {
+                                        const char *mode, const char *level,
+                                        unsigned dim) {
   IR2VecHandler *ir2vecObj =
-      new IR2VecHandler(filename, output_file, mode, level);
+      new IR2VecHandler(filename, output_file, mode, level, dim);
   if (!ir2vecObj) {
     return nullptr;
   }
@@ -314,8 +315,9 @@ PyObject *initEmbedding(PyObject *self, PyObject *args) {
   const char *mode = "\0";
   const char *level = "\0";
   const char *output_file = "\0";
+  unsigned dim = 300;
 
-  if (!PyArg_ParseTuple(args, "sss|s", &filename, &mode, &level,
+  if (!PyArg_ParseTuple(args, "sss|Is", &filename, &mode, &level, &dim,
                         &output_file)) {
     // raise error here
     PyErr_SetString(PyExc_TypeError, "Invalid Arguments");
@@ -348,7 +350,7 @@ PyObject *initEmbedding(PyObject *self, PyObject *args) {
   }
 
   IR2VecHandlerObject *ir2vecObj =
-      createIR2VECObject(filename, output_file, mode, level);
+      createIR2VECObject(filename, output_file, mode, level, dim);
 
   if (!ir2vecObj) {
     PyErr_SetString(PyExc_TypeError, "Embedding Object not created");

Manylinux2014_Compliant_Source/pkg/tests/test_ir2vec.py

@@ -160,7 +160,7 @@ def test_fa_f():
         path = (TEST_SUITE_DIR / file).resolve()
         full_path = str(path).strip()
 
-        initObj = ir2vec.initEmbedding(full_path, "fa", "f")
+        initObj = ir2vec.initEmbedding(full_path, "fa", "f", 300)
         assert initObj is not None
 
         functionVectorMap = ir2vec.getFunctionVectors(initObj)

README.md

@@ -113,13 +113,16 @@ To ensure the correctness, run `make check_ir2vec`
 instructions.
 
 ### Using Binary
-> ir2vec -\<mode\> -o \<output-file\> -level \<p|f\> -class \<class-number\> -funcName=\<function-name\> \<input-ll-file\>
+> ir2vec -\<mode\> -dim \<dimensions\> -o \<output-file\> -level \<p|f\> -class \<class-number\> -funcName=\<function-name\> \<input-ll-file\>
 
 #### Command-Line options
 
 - `mode` - can be one of `sym`/`fa`
     - `sym` denotes Symbolic representation
     - `fa` denotes Flow-Aware representation
+- `dim` - Dimensions of embeddings
+    - This is an optional argument. Defaults to `300`.
+    - Other supported dimensions are `75` and `100`
 -  `o` - file in which the embeddings are to be appended;     (Note : If  file doesn’t exist, new file would be created, else embeddings would be appended)
 - `level` - can be one of chars `p`/`f`.
     - `p` denotes `program level` encoding
@@ -141,16 +144,16 @@ Please use `--help` for further details.
 
 #### Flow-Aware Embeddings
 For all functions
-* `` ir2vec -fa -o <output_file> -level <p|f>  -class <class-number> <input_ll_file>``
+* `` ir2vec -fa -dim <dimension> -o <output_file> -level <p|f>  -class <class-number> <input_ll_file>``
 
 For a specific function
-* `` ir2vec -fa -o <output_file> -level f  -class <class-number> -funcName=\<function-name\><input_ll_file>``
+* `` ir2vec -fa -dim <dimension> -o <output_file> -level f  -class <class-number> -funcName=\<function-name\><input_ll_file>``
 
 #### Symbolic Embeddings
 For all functions
- * `` ir2vec -sym -o <output_file> -level <p|f> -class <class-number> <input_ll_file>``
+ * `` ir2vec -sym -dim <dimension> -o <output_file> -level <p|f> -class <class-number> <input_ll_file>``
 For a specific function
- * `` ir2vec -sym -o <output_file> -level f -class <class-number> -funcName=\<function-name\> <input_ll_file>``
+ * `` ir2vec -sym -dim <dimension> -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`.
@@ -178,7 +181,7 @@ The following example snippet shows how to query the exposed vector representati
 
 // Creating object to generate FlowAware representation
 auto ir2vec =
-      IR2Vec::Embeddings(<LLVM Module>, IR2Vec::IR2VecMode::FlowAware);
+      IR2Vec::Embeddings(<LLVM Module>, IR2Vec::IR2VecMode::FlowAware, <DIM>);
 
 // Getting Instruction vectors corresponding to the instructions in <LLVM Module>
 auto instVecMap = ir2vec.getInstVecMap();
@@ -218,6 +221,8 @@ for (auto val : pgmVec)
 * `file_path`: str - Path to the `.ll` or `.bc` file.
 * `encoding_type`: str - Choose `fa` (Flow-Aware) or `sym` (Symbolic).
 * `level`: str - Choose `p` for program-level or `f` for function-level.
+* `dim`: uint - Choose from `[300, 100, 75]`. Default value is `300`
+* `output_file`: str - If provided, embeddings are saved to this file. Default is an empty string.
 
 **Returns:**
 
@@ -228,7 +233,14 @@ for (auto val : pgmVec)
 ```python
 import ir2vec
 
+# Approach 1
 initObj = ir2vec.initEmbedding("/path/to/file.ll", "fa", "p")
+
+# Approach 2
+initObj = ir2vec.initEmbedding("/path/to/file.ll", "fa", "p", 100)
+
+# Approach 3
+initObj = ir2vec.initEmbedding("/path/to/file.ll", "fa", "p", 100, "output.txt")
 ```
 
 ### getProgramVector