LSHSearch Parallelization

CMakeLists.txt

@@ -27,7 +27,6 @@ option(BUILD_TESTS "Build tests." ON)
 option(BUILD_CLI_EXECUTABLES "Build command-line executables." ON)
 option(BUILD_SHARED_LIBS
     "Compile shared libraries (if OFF, static libraries are compiled)." ON)
-#option(HAS_OPENMP "Use OpenMP for parallel execution, if available." ON)
 
 enable_testing()
 
@@ -237,7 +236,7 @@ add_definitions(-DBOOST_TEST_DYN_LINK)
 # This way we can skip calls to functions defined in omp.h with code like:
 # if (HAS_OPENMP == 1) { openMP code here }
 # If OpenMP is found, define HAS_OPENMP to be 1. Otherwise define it to be 0.
-find_package(OpenMP 3)
+find_package(OpenMP 3.0.0 )
 if (OPENMP_FOUND)
   add_definitions(-DHAS_OPENMP)
   set(HAS_OPENMP "1")

src/mlpack/methods/lsh/lsh_search.hpp

@@ -268,12 +268,6 @@ class LSHSearch
   //! removed in mlpack 2.1.0!
   const arma::mat& Projection(size_t i) { return projections.slice(i); }
 
-  //! Set the maximum number of threads the object is allowed to use
-  void MaxThreads(size_t numThreads) { maxThreads = numThreads;}
-
-  //! Return the current maxumum threads the object is allowed to use
-  size_t MaxThreads(void) const { return maxThreads; }
-
  private:
   /**
    * This function takes a query and hashes it into each of the hash tables to
@@ -451,9 +445,6 @@ class LSHSearch
   //! The number of distance evaluations.
   size_t distanceEvaluations;
 
-  //! The maximum number of threads allowed.
-  size_t maxThreads;
-
 }; // class LSHSearch
 
 } // namespace neighbor

src/mlpack/methods/lsh/lsh_search_impl.hpp

@@ -12,22 +12,6 @@
 namespace mlpack {
 namespace neighbor {
 
-// If OpenMP was found by the compiler and was used in compiling mlpack,
-// then we can get more than one thread.
-inline size_t CalculateMaxThreads()
-{
-  // HAS_OPENMP should be defined by CMakeLists after the check for OpenMP has
-  // been performed.
-  #ifdef HAS_OPENMP
-    if (HAS_OPENMP) // If compiler has OpenMP support, use all available threads.
-      return omp_get_max_threads();
-    return 1; // Compiler doesn't support OpenMP. Hard-wire maxThreads to 1.
-  #endif
-
-  // In case HAS_OPENMP wasn't properly defined by CMakeLists, use 1 thread.
-  return 1;
-}
-
 // Construct the object with random tables
 template<typename SortPolicy>
 LSHSearch<SortPolicy>::
@@ -46,7 +30,6 @@ LSHSearch(const arma::mat& referenceSet,
   bucketSize(bucketSize),
   distanceEvaluations(0)
 {
-  maxThreads = CalculateMaxThreads();
   // Pass work to training function.
   Train(referenceSet, numProj, numTables, hashWidthIn, secondHashSize,
       bucketSize);
@@ -69,7 +52,6 @@ LSHSearch(const arma::mat& referenceSet,
   bucketSize(bucketSize),
   distanceEvaluations(0)
 {
-  maxThreads = CalculateMaxThreads();
   // Pass work to training function
   Train(referenceSet, numProj, numTables, hashWidthIn, secondHashSize,
       bucketSize, projections);
@@ -87,8 +69,6 @@ LSHSearch<SortPolicy>::LSHSearch() :
     bucketSize(500),
     distanceEvaluations(0)
 {
-  // Only define maxThreads. Nothing else to do.
-  maxThreads = CalculateMaxThreads();
 }
 
 // Destructor.
@@ -763,7 +743,7 @@ void LSHSearch<SortPolicy>::ReturnIndicesFromTable(
     // Retrieve candidates.
     size_t start = 0;
 
-    for (long long int i = 0; i < numTablesToSearch; ++i) // For all tables
+    for (size_t i = 0; i < numTablesToSearch; ++i) // For all tables
     {
       for (size_t p = 0; p < T + 1; ++p)
       {
@@ -842,14 +822,10 @@ void LSHSearch<SortPolicy>::Search(const arma::mat& querySet,
   Timer::Start("computing_neighbors");
 
   // Parallelization to process more than one query at a time.
-  // use as many threads possible but not more than allowed number
-  size_t numThreadsUsed = maxThreads;
   #pragma omp parallel for \
-    num_threads ( numThreadsUsed )\
     shared(avgIndicesReturned, resultingNeighbors, distances) \
     schedule(dynamic)
-  // Go through every query point. Use long int because some compilers complain
-  // for openMP unsigned index variables.
+  // Go through every query point.
   for (size_t i = 0; i < querySet.n_cols; i++)
   {
 
@@ -914,10 +890,7 @@ Search(const size_t k,
   Timer::Start("computing_neighbors");
 
   // Parallelization to process more than one query at a time.
-  // use as many threads possible but not more than allowed number
-  size_t numThreadsUsed = maxThreads;
   #pragma omp parallel for \
-    num_threads ( numThreadsUsed )\
     shared(avgIndicesReturned, resultingNeighbors, distances) \
     schedule(dynamic)
   // Go through every query point. Use long int because some compilers complain

src/mlpack/tests/lsh_test.cpp

@@ -784,8 +784,10 @@ BOOST_AUTO_TEST_CASE(ParallelBichromatic)
   lshTest.Search(qdata, k, parallelNeighbors, distances);
 
   // Now perform same search but with 1 thread
-  lshTest.MaxThreads(1);
+  size_t prevNumThreads = omp_get_max_threads(); // Store number of threads used.
+  omp_set_num_threads(1);
   lshTest.Search(qdata, k, sequentialNeighbors, distances);
+  omp_set_num_threads(prevNumThreads);
 
   // Require both have same results
   double recall = LSHSearch<>::ComputeRecall(sequentialNeighbors, parallelNeighbors);
@@ -818,8 +820,10 @@ BOOST_AUTO_TEST_CASE(ParallelMonochromatic)
   lshTest.Search(k, parallelNeighbors, distances);
 
   // Now perform same search but with 1 thread.
-  lshTest.MaxThreads(1);
+  size_t prevNumThreads = omp_get_max_threads(); // Store number of threads used.
+  omp_set_num_threads(1);
   lshTest.Search(k, sequentialNeighbors, distances);
+  omp_set_num_threads(prevNumThreads);
 
   // Require both have same results.
   double recall = LSHSearch<>::ComputeRecall(sequentialNeighbors, parallelNeighbors);