Geekbench ML Score

2962
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 27 2024 07:01 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO 21KYZBZ6US
Motherboard LENOVO 21KYZBZ6US
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 64.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1384
259.0 IPS
 
Image Classification (F16)
100% 1365
255.4 IPS
 
Image Classification (I8)
100% 1253
234.5 IPS
 
Image Segmentation (F32)
100% 1522
25.4 IPS
 
Image Segmentation (F16)
100% 1486
24.8 IPS
 
Image Segmentation (I8)
98% 1291
21.6 IPS
 
Pose Estimation (F32)
100% 13888
16.8 IPS
 
Pose Estimation (F16)
100% 14055
17.0 IPS
 
Pose Estimation (I8)
100% 12037
14.6 IPS
 
Object Detection (F32)
100% 1202
89.7 IPS
 
Object Detection (F16)
100% 1227
91.6 IPS
 
Object Detection (I8)
54% 1105
82.5 IPS
 
Face Detection (F32)
100% 1179
14.0 IPS
 
Face Detection (F16)
100% 1187
14.1 IPS
 
Face Detection (I8)
89% 1053
12.5 IPS
 
Depth Estimation (F32)
100% 7921
61.4 IPS
 
Depth Estimation (F16)
100% 7769
60.2 IPS
 
Depth Estimation (I8)
95% 6433
49.9 IPS
 
Style Transfer (F32)
100% 39711
52.2 IPS
 
Style Transfer (F16)
100% 39826
52.4 IPS
 
Style Transfer (I8)
98% 30386
40.0 IPS
 
Image Super-Resolution (F32)
100% 6746
240.9 IPS
 
Image Super-Resolution (F16)
100% 6787
242.4 IPS
 
Image Super-Resolution (I8)
99% 4824
172.3 IPS
 
Text Classification (F32)
90% 809
1.16 KIPS
 
Text Classification (F16)
90% 791
1.14 KIPS
 
Text Classification (I8)
90% 595
855.3 IPS
 
Machine Translation (F32)
100% 1599
29.4 IPS
 
Machine Translation (F16)
100% 1594
29.3 IPS
 
Machine Translation (I8)
70% 884
16.3 IPS
 

Compare

Set Baseline Geekbench 6 now available