Open yhmo opened 2 months ago
Test script:
import random
import time
import numpy as np
from pymilvus import (
connections,
FieldSchema, CollectionSchema, DataType,
Collection,
utility,
)
HOST = 'localhost'
PORT = '19530'
connections.connect(host=HOST, port=PORT)
F16_COLLECTION = "f16_col"
DIM = 768
METRIC_TYPE = "L2"
ID_FIELD = "id"
VECTOR_FIELD = "vector"
def gen_fp16_vectors(num):
raw_vectors = []
fp16_vectors = []
for _ in range(num):
raw_vector = [random.random() for _ in range(DIM)]
raw_vectors.append(raw_vector)
fp16_vector = np.array(raw_vector, dtype=np.float16)
fp16_vectors.append(fp16_vector)
return raw_vectors, fp16_vectors
def create_collection():
if utility.has_collection(F16_COLLECTION):
utility.drop_collection(F16_COLLECTION)
fields = [
FieldSchema(name="id", dtype=DataType.INT64, is_primary=True, auto_id=True),
FieldSchema(name="vector", dtype=DataType.FLOAT16_VECTOR, dim=DIM),
]
schema = CollectionSchema(fields=fields)
collection = Collection(name=F16_COLLECTION, schema=schema)
print(f"Collection '{F16_COLLECTION}' created")
def prepare_data():
collection_16 = Collection(name=F16_COLLECTION)
count = 10000
for i in range(100):
raw_vectors, fp16_vectors = gen_fp16_vectors(count)
collection_16.insert(data=[
fp16_vectors,
])
print(f"insert batch {i}")
print("insert done")
time.sleep(5)
collection_16.flush()
print("flush done")
start = time.time()
index_params = {
'metric_type': METRIC_TYPE,
'index_type': "HNSW",
'params': {"M": 8, "efConstruction": 200},
}
collection_16.create_index(field_name=VECTOR_FIELD, index_params=index_params)
utility.wait_for_index_building_complete(collection_name=F16_COLLECTION)
print("index done")
end = time.time()
print(f"fp16 index time cost: {end-start} seconds")
if __name__ == '__main__':
create_collection()
prepare_data()
/assign @cqy123456 /unassign
/assign @yhmo use latest 2.4 to try, fp16 and bf16 add simd support in latest 2.4.
Is there an existing issue for this?
Environment
Current Behavior
Index process for Float16Vector is so poor. One million vector 768 dim, HNSW{"M": 8, "efConstruction": 200}, it takes 1.5 hours to build index. Much slower than FloatVector.
Expected Behavior
The time cost to build index for Float16Vector should be less or equal to FloatVector.
Steps To Reproduce
Milvus Log
No response
Anything else?
No response