Geekbench ML Score

2760
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 27 2024 03:31 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home Single Language (64-bit)
Model LENOVO 83DJ
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Intel Core Ultra 7 155H
Topology 1 Processor, 16 Cores, 22 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 1.40 GHz
Cluster 16 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 11
L1 Data Cache48.0 KB x 11
L2 Cache2.00 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1282
239.9 IPS
 
Image Classification (F16)
100% 1296
242.5 IPS
 
Image Classification (I8)
100% 1168
218.5 IPS
 
Image Segmentation (F32)
100% 1517
25.3 IPS
 
Image Segmentation (F16)
100% 1481
24.7 IPS
 
Image Segmentation (I8)
98% 1333
22.3 IPS
 
Pose Estimation (F32)
100% 13495
16.3 IPS
 
Pose Estimation (F16)
100% 13677
16.6 IPS
 
Pose Estimation (I8)
100% 11856
14.4 IPS
 
Object Detection (F32)
100% 1162
86.8 IPS
 
Object Detection (F16)
100% 1170
87.4 IPS
 
Object Detection (I8)
54% 989
73.8 IPS
 
Face Detection (F32)
100% 1278
15.2 IPS
 
Face Detection (F16)
100% 1273
15.1 IPS
 
Face Detection (I8)
89% 1155
13.7 IPS
 
Depth Estimation (F32)
100% 7162
55.5 IPS
 
Depth Estimation (F16)
100% 6699
52.0 IPS
 
Depth Estimation (I8)
95% 6165
47.8 IPS
 
Style Transfer (F32)
100% 35462
46.6 IPS
 
Style Transfer (F16)
100% 21655
28.5 IPS
 
Style Transfer (I8)
98% 30036
39.5 IPS
 
Image Super-Resolution (F32)
100% 6898
246.3 IPS
 
Image Super-Resolution (F16)
100% 7213
257.6 IPS
 
Image Super-Resolution (I8)
99% 4799
171.4 IPS
 
Text Classification (F32)
90% 646
928.5 IPS
 
Text Classification (F16)
90% 697
1.00 KIPS
 
Text Classification (I8)
90% 544
782.0 IPS
 
Machine Translation (F32)
100% 1095
20.2 IPS
 
Machine Translation (F16)
100% 1444
26.6 IPS
 
Machine Translation (I8)
70% 840
15.5 IPS
 

Compare

Set Baseline Geekbench 6 now available