Geekbench ML Score

2986
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 28 2024 08:22 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO 21KV001CUS
Motherboard LENOVO 21KV001CUS
Power PlanBalanced
CPU Information
Name Intel Core Ultra 9 185H
Topology 1 Processor, 16 Cores, 22 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 2.30 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% 1431
267.9 IPS
 
Image Classification (F16)
100% 1439
269.2 IPS
 
Image Classification (I8)
100% 1246
233.2 IPS
 
Image Segmentation (F32)
100% 1528
25.5 IPS
 
Image Segmentation (F16)
100% 1504
25.1 IPS
 
Image Segmentation (I8)
98% 1308
21.8 IPS
 
Pose Estimation (F32)
100% 13669
16.6 IPS
 
Pose Estimation (F16)
100% 13758
16.7 IPS
 
Pose Estimation (I8)
100% 12015
14.5 IPS
 
Object Detection (F32)
100% 1229
91.7 IPS
 
Object Detection (F16)
100% 1256
93.8 IPS
 
Object Detection (I8)
54% 1007
75.2 IPS
 
Face Detection (F32)
100% 1209
14.4 IPS
 
Face Detection (F16)
100% 1220
14.5 IPS
 
Face Detection (I8)
89% 1097
13.0 IPS
 
Depth Estimation (F32)
100% 8043
62.4 IPS
 
Depth Estimation (F16)
100% 7958
61.7 IPS
 
Depth Estimation (I8)
95% 6431
49.9 IPS
 
Style Transfer (F32)
100% 41285
54.3 IPS
 
Style Transfer (F16)
100% 40991
53.9 IPS
 
Style Transfer (I8)
98% 31789
41.8 IPS
 
Image Super-Resolution (F32)
100% 7183
256.5 IPS
 
Image Super-Resolution (F16)
100% 6922
247.2 IPS
 
Image Super-Resolution (I8)
99% 5172
184.7 IPS
 
Text Classification (F32)
90% 734
1.06 KIPS
 
Text Classification (F16)
90% 751
1.08 KIPS
 
Text Classification (I8)
90% 574
825.1 IPS
 
Machine Translation (F32)
100% 1611
29.6 IPS
 
Machine Translation (F16)
100% 1588
29.2 IPS
 
Machine Translation (I8)
70% 890
16.4 IPS
 

Compare

Set Baseline Geekbench 6 now available