Bugfix: fix type of number for offset and size (#229)

* fix type of number for offset and size

* optimization for reading in deep speed framework.

* increase buffer to 16 MB

* revert changes

dlio_benchmark/data_generator/indexed_binary_generator.py

@@ -69,7 +69,7 @@ def generate(self):
                 out_path_spec_off_idx = self.index_file_path_off(out_path_spec)
                 out_path_spec_sz_idx = self.index_file_path_size(out_path_spec)
                 fh = MPI.File.Open(comm, out_path_spec, amode)
-                samples_per_loop = int(MB / sample_size)
+                samples_per_loop = int(MB * 16 / sample_size)
 
                 for sample_index in range(self.my_rank*samples_per_rank, samples_per_rank*(self.my_rank+1), samples_per_loop):
                     #logging.info(f"{utcnow()} rank {self.my_rank} writing {sample_index} * {samples_per_loop} for {samples_per_rank} samples")

dlio_benchmark/reader/indexed_binary_mmap_reader.py

@@ -57,10 +57,10 @@ def load_index_file(self, global_sample_idx, filename, sample_index):
             self.file_map_ibr[filename] = []
             bin_buffer_mmap = np.memmap(offset_file, mode='r', order='C')
             bin_buffer = memoryview(bin_buffer_mmap)
-            self.file_map_ibr[filename].append(np.frombuffer(bin_buffer, dtype=np.uint8))
+            self.file_map_ibr[filename].append(np.frombuffer(bin_buffer, dtype=np.uint64))
             bin_buffer_mmap = np.memmap(sz_file, mode='r', order='C')
             bin_buffer = memoryview(bin_buffer_mmap)
-            self.file_map_ibr[filename].append(np.frombuffer(bin_buffer, dtype=np.uint8))
+            self.file_map_ibr[filename].append(np.frombuffer(bin_buffer, dtype=np.uint64))
 
     @dlp.log
     def load_index(self):
@@ -113,4 +113,4 @@ def is_index_based(self):
         return True
 
     def is_iterator_based(self):
-        return True
+        return True