Geekbench ML Score

2458
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User Atheris
Upload Date September 03 2024 05:49 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home Single Language (64-bit)
Model SAMSUNG ELECTRONICS CO., LTD. 940XGK
Motherboard SAMSUNG ELECTRONICS CO., LTD. NP940XGK-LG3IN
Power PlanSAMSUNG MODE
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 3.80 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 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1045
195.5 IPS
 
Image Classification (F16)
100% 1070
200.2 IPS
 
Image Classification (I8)
100% 929
173.9 IPS
 
Image Segmentation (F32)
100% 1350
22.5 IPS
 
Image Segmentation (F16)
100% 1340
22.4 IPS
 
Image Segmentation (I8)
98% 1205
20.1 IPS
 
Pose Estimation (F32)
100% 11453
13.9 IPS
 
Pose Estimation (F16)
100% 11980
14.5 IPS
 
Pose Estimation (I8)
100% 11240
13.6 IPS
 
Object Detection (F32)
100% 847
63.2 IPS
 
Object Detection (F16)
100% 979
73.1 IPS
 
Object Detection (I8)
54% 681
50.8 IPS
 
Face Detection (F32)
100% 1253
14.9 IPS
 
Face Detection (F16)
100% 1252
14.9 IPS
 
Face Detection (I8)
89% 1143
13.6 IPS
 
Depth Estimation (F32)
100% 6322
49.0 IPS
 
Depth Estimation (F16)
100% 6207
48.1 IPS
 
Depth Estimation (I8)
95% 5304
41.1 IPS
 
Style Transfer (F32)
100% 33578
44.2 IPS
 
Style Transfer (F16)
100% 34824
45.8 IPS
 
Style Transfer (I8)
98% 27394
36.0 IPS
 
Image Super-Resolution (F32)
100% 5666
202.3 IPS
 
Image Super-Resolution (F16)
100% 5990
213.9 IPS
 
Image Super-Resolution (I8)
99% 4003
143.0 IPS
 
Text Classification (F32)
90% 553
794.8 IPS
 
Text Classification (F16)
90% 585
840.5 IPS
 
Text Classification (I8)
90% 456
655.9 IPS
 
Machine Translation (F32)
100% 1240
22.8 IPS
 
Machine Translation (F16)
100% 1224
22.5 IPS
 
Machine Translation (I8)
70% 734
13.5 IPS
 

Compare

Set Baseline Geekbench 6 now available