Move MD5 below the MurmurHash3 family so that it will go next to SHA …

…in the future.
rapidsai · Mar 16, 2022 · 0a430be · 0a430be
1 parent cb80e44
commit 0a430be
Show file tree

Hide file tree

Showing 6 changed files with 13 additions and 13 deletions.
diff --git a/cpp/benchmarks/hashing/hash.cpp b/cpp/benchmarks/hashing/hash.cpp
@@ -54,11 +54,11 @@ static void BM_hash(benchmark::State& state, cudf::hash_id hid, contains_nulls h
 #define HASH_BENCHMARK_DEFINE(hid, n) H_BENCHMARK_DEFINE(concat(hid, _, n), hid, n)
 
 HASH_BENCHMARK_DEFINE(HASH_MURMUR3, nulls)
-HASH_BENCHMARK_DEFINE(HASH_MD5, nulls)
 HASH_BENCHMARK_DEFINE(HASH_SERIAL_MURMUR3, nulls)
 HASH_BENCHMARK_DEFINE(HASH_SPARK_MURMUR3, nulls)
+HASH_BENCHMARK_DEFINE(HASH_MD5, nulls)
 
 HASH_BENCHMARK_DEFINE(HASH_MURMUR3, no_nulls)
-HASH_BENCHMARK_DEFINE(HASH_MD5, no_nulls)
 HASH_BENCHMARK_DEFINE(HASH_SERIAL_MURMUR3, no_nulls)
 HASH_BENCHMARK_DEFINE(HASH_SPARK_MURMUR3, no_nulls)
+HASH_BENCHMARK_DEFINE(HASH_MD5, no_nulls)
diff --git a/cpp/include/cudf/detail/hashing.hpp b/cpp/include/cudf/detail/hashing.hpp
@@ -42,15 +42,15 @@ std::unique_ptr<column> murmur_hash3_32(
   rmm::cuda_stream_view stream        = rmm::cuda_stream_default,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-std::unique_ptr<column> md5_hash(
+template <template <typename> class hash_function>
+std::unique_ptr<column> serial_murmur_hash3_32(
   table_view const& input,
+  uint32_t seed                       = 0,
   rmm::cuda_stream_view stream        = rmm::cuda_stream_default,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
-template <template <typename> class hash_function>
-std::unique_ptr<column> serial_murmur_hash3_32(
+std::unique_ptr<column> md5_hash(
   table_view const& input,
-  uint32_t seed                       = 0,
   rmm::cuda_stream_view stream        = rmm::cuda_stream_default,
   rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 

diff --git a/cpp/include/cudf/hashing.hpp b/cpp/include/cudf/hashing.hpp
@@ -31,9 +31,9 @@ namespace cudf {
 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
   HASH_SERIAL_MURMUR3,  ///< Serial Murmur3 hash function
-  HASH_SPARK_MURMUR3    ///< Spark Murmur3 hash function
+  HASH_SPARK_MURMUR3,   ///< Spark Murmur3 hash function
+  HASH_MD5              ///< MD5 hash function
 };
 
 /**

diff --git a/cpp/src/hash/hashing.cu b/cpp/src/hash/hashing.cu
@@ -94,11 +94,11 @@ std::unique_ptr<column> hash(table_view const& input,
 {
   switch (hash_function) {
     case (hash_id::HASH_MURMUR3): return murmur_hash3_32(input, stream, mr);
-    case (hash_id::HASH_MD5): return md5_hash(input, stream, mr);
     case (hash_id::HASH_SERIAL_MURMUR3):
       return serial_murmur_hash3_32<MurmurHash3_32>(input, seed, stream, mr);
     case (hash_id::HASH_SPARK_MURMUR3):
       return serial_murmur_hash3_32<SparkMurmurHash3_32>(input, seed, stream, mr);
+    case (hash_id::HASH_MD5): return md5_hash(input, stream, mr);
     default: CUDF_FAIL("Unsupported hash function.");
   }
 }

diff --git a/java/src/main/java/ai/rapids/cudf/HashType.java b/java/src/main/java/ai/rapids/cudf/HashType.java
@@ -24,9 +24,9 @@
 public enum HashType {
   IDENTITY(0),
   MURMUR3(1),
-  HASH_MD5(2),
-  HASH_SERIAL_MURMUR3(3),
-  HASH_SPARK_MURMUR3(4);
+  HASH_SERIAL_MURMUR3(2),
+  HASH_SPARK_MURMUR3(3),
+  HASH_MD5(4);
 
   private static final HashType[] HASH_TYPES = HashType.values();
   final int nativeId;

diff --git a/python/cudf/cudf/_lib/cpp/hash.pxd b/python/cudf/cudf/_lib/cpp/hash.pxd
@@ -14,9 +14,9 @@ cdef extern from "cudf/hashing.hpp" namespace "cudf" nogil:
     ctypedef enum hash_id "cudf::hash_id":
         HASH_IDENTITY "cudf::hash_id::HASH_IDENTITY"
         HASH_MURMUR3 "cudf::hash_id::HASH_MURMUR3"
-        HASH_MD5 "cudf::hash_id::HASH_MD5"
         HASH_SERIAL_MURMUR3 "cudf::hash_id::HASH_SERIAL_MURMUR3"
         HASH_SPARK_MURMUR3 "cudf::hash_id::HASH_SPARK_MURMUR3"
+        HASH_MD5 "cudf::hash_id::HASH_MD5"
 
     cdef unique_ptr[column] hash "cudf::hash" (
         const table_view& input,