refactor that details proposed code

rapidsai · Jul 7, 2020 · b626432 · b626432
1 parent 0b7ad98
commit b626432
Show file tree

Hide file tree

Showing 4 changed files with 46 additions and 1 deletion.
diff --git a/cpp/include/cudf/detail/hashing.hpp b/cpp/include/cudf/detail/hashing.hpp
@@ -37,9 +37,24 @@ std::pair<std::unique_ptr<table>, std::vector<size_type>> hash_partition(
  * @param stream CUDA stream used for device memory operations and kernel launches.
  */
 std::unique_ptr<column> hash(table_view const& input,
+                             hash_id hash_function = hash_id::HASH_MURMUR3,
                              std::vector<uint32_t> const& initial_hash = {},
                              rmm::mr::device_memory_resource* mr = rmm::mr::get_default_resource(),
                              cudaStream_t stream                 = 0);
 
+std::unique_ptr<column> identity_hash(table_view const& input,
+                                      rmm::mr::device_memory_resource* mr = rmm::mr::get_default_resource(),
+                                      cudaStream_t stream                 = 0);
+
+std::unique_ptr<column> murmur_hash3_32(table_view const& input,
+                                        std::vector<uint32_t> const& initial_hash = {},
+                                        rmm::mr::device_memory_resource* mr = rmm::mr::get_default_resource(),
+                                        cudaStream_t stream                 = 0);
+
+std::unique_ptr<column> md5_hash(table_view const& input,
+                                 rmm::mr::device_memory_resource* mr = rmm::mr::get_default_resource(),
+                                 cudaStream_t stream                 = 0);
+
+
 }  // namespace detail
 }  // namespace cudf
diff --git a/cpp/include/cudf/hashing.hpp b/cpp/include/cudf/hashing.hpp
@@ -35,6 +35,7 @@ namespace cudf {
  * @returns A column where each row is the hash of a column from the input
  */
 std::unique_ptr<column> hash(table_view const& input,
+                             hash_id hash_function = hash_id::HASH_MURMUR3,
                              std::vector<uint32_t> const& initial_hash = {},
                              rmm::mr::device_memory_resource* mr = rmm::mr::get_default_resource());
 

diff --git a/cpp/include/cudf/types.hpp b/cpp/include/cudf/types.hpp
@@ -269,5 +269,14 @@ inline bool operator==(data_type const& lhs, data_type const& rhs) { return lhs.
  */
 std::size_t size_of(data_type t);
 
+/**
+ *  @brief Identifies the hash function to be used
+ */
+enum class hash_id {
+  HASH_IDENTITY = 0,    ///< Identity hash function that simply returns the key to be hashed
+  HASH_MURMUR3,  ///< Murmur3 hash function
+  HASH_MD5 ///< MD5 hash function
+};
+
 /** @} */
 }  // namespace cudf
diff --git a/cpp/src/hash/hashing.cu b/cpp/src/hash/hashing.cu
@@ -24,6 +24,7 @@
 #include <cudf/partitioning.hpp>
 #include <cudf/table/row_operators.cuh>
 #include <cudf/table/table_device_view.cuh>
+#include <cudf/types.hpp>
 
 #include <thrust/tabulate.h>
 
@@ -634,9 +635,27 @@ std::pair<std::unique_ptr<table>, std::vector<size_type>> hash_partition(
 }
 
 std::unique_ptr<column> hash(table_view const& input,
+                             hash_id hash_function,
                              std::vector<uint32_t> const& initial_hash,
                              rmm::mr::device_memory_resource* mr,
                              cudaStream_t stream)
+{
+  switch(hash_function) {
+    // case(hash_id::HASH_IDENTITY) :
+    //   return identity_hash(input);
+    case(hash_id::HASH_MURMUR3) :
+      return murmur_hash3_32(input, initial_hash, mr, stream);
+    // case(hash_id::HASH_MD5) :
+    //   return md5_hash(input, mr, stream);
+    default :
+      return NULL; 
+  }
+}
+
+std::unique_ptr<column> murmur_hash3_32(table_view const& input,
+  std::vector<uint32_t> const& initial_hash,
+  rmm::mr::device_memory_resource* mr,
+  cudaStream_t stream)
 {
   // TODO this should be UINT32
   auto output = make_numeric_column(
@@ -688,11 +707,12 @@ std::unique_ptr<column> hash(table_view const& input,
 }  // namespace detail
 
 std::unique_ptr<column> hash(table_view const& input,
+                             hash_id hash_function,
                              std::vector<uint32_t> const& initial_hash,
                              rmm::mr::device_memory_resource* mr)
 {
   CUDF_FUNC_RANGE();
-  return detail::hash(input, initial_hash, mr);
+  return detail::hash(input, hash_function, initial_hash, mr);
 }
 
 }  // namespace cudf