Merge branch 'fix-hashing' into 'main'

fix: use Murmur hashing for DHT lookup

See merge request naaice/poet!2

include/poet/DHT.h

@@ -100,7 +100,7 @@ typedef struct {
   /** Size of the MPI communicator respectively all participating processes. */
   int comm_size;
   /** Pointer to a hashfunction. */
-  uint64_t (*hash_func)(int, void*);
+  uint64_t (*hash_func)(int, const void*);
   /** Pre-allocated memory where a bucket can be received. */
   void* recv_entry;
   /** Pre-allocated memory where a bucket to send can be stored. */
@@ -143,7 +143,7 @@ typedef struct {
  */
 extern DHT* DHT_create(MPI_Comm comm, uint64_t size_per_process,
                        unsigned int data_size, unsigned int key_size,
-                       uint64_t (*hash_func)(int, void*));
+                       uint64_t (*hash_func)(int, const void*));
 
 /**
  * @brief Write data into DHT.

include/poet/HashFunctions.hpp

@@ -1,3 +1,5 @@
+// //  Time-stamp: "Last modified 2023-03-27 14:51:05 mluebke"
+
 /*
 ** Copyright (C) 2018-2021 Alexander Lindemann, Max Luebke (University of
 ** Potsdam)
@@ -26,13 +28,15 @@
 
 namespace poet {
 
+// Sum of POET interpreted as ASCII
+constexpr uint32_t HASH_SEED = 80 + 79 + 69 + 84;
+
 void initHashCtx(const EVP_MD *md);
 void freeHashCtx();
 
-uint64_t hashDHT(int key_size, void *key);
+uint64_t hashDHT(int key_size, const void *key);
+uint64_t Murmur2_64A(int len, const void *key);
 
-
+} // namespace poet
-
-}
 
 #endif // HASHFUNCTIONS_H_

src/ChemistryModule/DHT.c

@@ -52,7 +52,7 @@ static int read_flag(char flag_byte) {
 }
 
 DHT *DHT_create(MPI_Comm comm, uint64_t size, unsigned int data_size,
-                unsigned int key_size, uint64_t (*hash_func)(int, void *)) {
+                unsigned int key_size, uint64_t (*hash_func)(int, const void *)) {
   DHT *object;
   MPI_Win window;
   void *mem_alloc;

src/ChemistryModule/DHT_Wrapper.cpp

@@ -76,8 +76,8 @@ DHT_Wrapper::DHT_Wrapper(MPI_Comm dht_comm, uint32_t dht_size,
   uint32_t key_size = key_count * sizeof(DHT_Keyelement);
   uint32_t data_size = data_count * sizeof(double);
   uint32_t buckets_per_process = dht_size / (1 + data_size + key_size);
-  dht_object = DHT_create(dht_comm, buckets_per_process, data_size, key_size,
+  dht_object = DHT_create(dht_comm, buckets_per_process, data_size, key_size + 1,
-                          &poet::hashDHT);
+                          &poet::Murmur2_64A);
 
   // extract needed values from sim_param struct
   // t_simparams tmp = params.getNumParams();

src/ChemistryModule/HashFunctions.cpp

@@ -1,4 +1,10 @@
+//  Time-stamp: "Last modified 2023-03-27 14:50:53 mluebke"
 /*
+**-----------------------------------------------------------------------------
+** MurmurHash2 was written by Austin Appleby, and is placed in the public
+** domain. The author hereby disclaims copyright to this source code.
+**-----------------------------------------------------------------------------
+**
 ** Copyright (C) 2018-2021 Alexander Lindemann, Max Luebke (University of
 ** Potsdam)
 **
@@ -25,6 +31,18 @@
 #include <openssl/md5.h>
 #include <stdexcept>
 
+#if defined(_MSC_VER)
+
+#define BIG_CONSTANT(x) (x)
+
+// Other compilers
+
+#else // defined(_MSC_VER)
+
+#define BIG_CONSTANT(x) (x##LLU)
+
+#endif // !defined(_MSC_VER)
+
 // HACK: I know this is not a good practice, but this will do it for now!
 EVP_MD_CTX *ctx = NULL;
 
@@ -40,7 +58,7 @@ void poet::freeHashCtx() {
   ctx = NULL;
 }
 
-uint64_t poet::hashDHT(int key_size, void *key) {
+uint64_t poet::hashDHT(int key_size, const void *key) {
   unsigned char sum[MD5_DIGEST_LENGTH];
   uint32_t md_len;
   uint64_t retval, *v1, *v2;
@@ -60,3 +78,59 @@ uint64_t poet::hashDHT(int key_size, void *key) {
 
   return retval;
 }
+
+//-----------------------------------------------------------------------------
+// MurmurHash2, 64-bit versions, by Austin Appleby
+
+// The same caveats as 32-bit MurmurHash2 apply here - beware of alignment
+// and endian-ness issues if used across multiple platforms.
+
+// 64-bit hash for 64-bit platforms
+// objsize: 0x170-0x321: 433
+
+uint64_t poet::Murmur2_64A(int len, const void *key) {
+  const uint64_t m = BIG_CONSTANT(0xc6a4a7935bd1e995);
+  const int r = 47;
+
+  uint64_t h = HASH_SEED ^ (len * m);
+
+  const uint64_t *data = (const uint64_t *)key;
+  const uint64_t *end = data + (len / 8);
+
+  while (data != end) {
+    uint64_t k = *data++;
+
+    k *= m;
+    k ^= k >> r;
+    k *= m;
+
+    h ^= k;
+    h *= m;
+  }
+
+  const unsigned char *data2 = (const unsigned char *)data;
+
+  switch (len & 7) {
+  case 7:
+    h ^= uint64_t(data2[6]) << 48;
+  case 6:
+    h ^= uint64_t(data2[5]) << 40;
+  case 5:
+    h ^= uint64_t(data2[4]) << 32;
+  case 4:
+    h ^= uint64_t(data2[3]) << 24;
+  case 3:
+    h ^= uint64_t(data2[2]) << 16;
+  case 2:
+    h ^= uint64_t(data2[1]) << 8;
+  case 1:
+    h ^= uint64_t(data2[0]);
+    h *= m;
+  };
+
+  h ^= h >> r;
+  h *= m;
+  h ^= h >> r;
+
+  return h;
+}