Geekbench ML Score

5544
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 15 2024 08:33 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model Acer Swift SF14-51T
Motherboard LNL Icefish_LNV
Power PlanAcer
CPU Information
Name Intel(R) Core(TM) Ultra 7 258V
Topology 1 Processor, 8 Cores
Identifier GenuineIntel Family 6 Model 189 Stepping 1
Base Frequency 2.20 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache64.0 KB x 4
L1 Data Cache48.0 KB x 4
L2 Cache2.50 MB x 1
L3 Cache12.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) 140V GPU (16GB)

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3750
701.8 IPS
 
Image Classification (F16)
100% 3762
703.9 IPS
 
Image Classification (I8)
100% 2179
407.8 IPS
 
Image Segmentation (F32)
100% 6094
101.8 IPS
 
Image Segmentation (F16)
100% 5997
100.2 IPS
 
Image Segmentation (I8)
98% 4567
76.3 IPS
 
Pose Estimation (F32)
100% 19669
23.8 IPS
 
Pose Estimation (F16)
100% 19812
24.0 IPS
 
Pose Estimation (I8)
100% 16436
19.9 IPS
 
Object Detection (F32)
100% 2746
205.0 IPS
 
Object Detection (F16)
100% 2693
201.1 IPS
 
Object Detection (I8)
61% 2347
175.2 IPS
 
Face Detection (F32)
100% 7826
93.1 IPS
 
Face Detection (F16)
100% 8187
97.3 IPS
 
Face Detection (I8)
89% 5456
64.9 IPS
 
Depth Estimation (F32)
100% 17820
138.2 IPS
 
Depth Estimation (F16)
100% 18950
147.0 IPS
 
Depth Estimation (I8)
94% 14056
109.0 IPS
 
Style Transfer (F32)
100% 46993
61.8 IPS
 
Style Transfer (F16)
100% 47145
62.0 IPS
 
Style Transfer (I8)
98% 38406
50.5 IPS
 
Image Super-Resolution (F32)
100% 7584
270.8 IPS
 
Image Super-Resolution (F16)
100% 7455
266.3 IPS
 
Image Super-Resolution (I8)
99% 5166
184.5 IPS
 
Text Classification (F32)
100% 763
1.10 KIPS
 
Text Classification (F16)
100% 1021
1.47 KIPS
 
Text Classification (I8)
98% 540
776.5 IPS
 
Machine Translation (F32)
100% 1483
27.3 IPS
 
Machine Translation (F16)
100% 1710
31.5 IPS
 
Machine Translation (I8)
70% 824
15.2 IPS
 

Compare

Set Baseline Geekbench 6 now available