Geekbench ML Score

5549
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 15 2024 05:04 PM
Views 3

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% 3294
616.4 IPS
 
Image Classification (F16)
100% 2561
479.2 IPS
 
Image Classification (I8)
100% 2347
439.3 IPS
 
Image Segmentation (F32)
100% 6208
103.7 IPS
 
Image Segmentation (F16)
100% 6102
101.9 IPS
 
Image Segmentation (I8)
98% 4645
77.6 IPS
 
Pose Estimation (F32)
100% 20013
24.2 IPS
 
Pose Estimation (F16)
100% 20202
24.5 IPS
 
Pose Estimation (I8)
100% 16955
20.5 IPS
 
Object Detection (F32)
100% 3002
224.1 IPS
 
Object Detection (F16)
100% 2967
221.5 IPS
 
Object Detection (I8)
61% 2533
189.1 IPS
 
Face Detection (F32)
100% 8238
98.0 IPS
 
Face Detection (F16)
100% 8271
98.3 IPS
 
Face Detection (I8)
89% 6057
72.0 IPS
 
Depth Estimation (F32)
100% 18447
143.1 IPS
 
Depth Estimation (F16)
100% 18891
146.5 IPS
 
Depth Estimation (I8)
94% 14846
115.1 IPS
 
Style Transfer (F32)
100% 48533
63.8 IPS
 
Style Transfer (F16)
100% 52878
69.6 IPS
 
Style Transfer (I8)
98% 40125
52.8 IPS
 
Image Super-Resolution (F32)
100% 8018
286.3 IPS
 
Image Super-Resolution (F16)
100% 7891
281.8 IPS
 
Image Super-Resolution (I8)
99% 4826
172.4 IPS
 
Text Classification (F32)
100% 807
1.16 KIPS
 
Text Classification (F16)
100% 668
960.6 IPS
 
Text Classification (I8)
98% 449
644.7 IPS
 
Machine Translation (F32)
100% 1536
28.3 IPS
 
Machine Translation (F16)
100% 1763
32.4 IPS
 
Machine Translation (I8)
70% 895
16.5 IPS
 

Compare

Set Baseline Geekbench 6 now available