Geekbench ML Score

5502
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 15 2024 08:37 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% 3998
748.1 IPS
 
Image Classification (F16)
100% 3594
672.5 IPS
 
Image Classification (I8)
100% 2578
482.5 IPS
 
Image Segmentation (F32)
100% 6187
103.3 IPS
 
Image Segmentation (F16)
100% 6120
102.2 IPS
 
Image Segmentation (I8)
98% 4479
74.8 IPS
 
Pose Estimation (F32)
100% 20297
24.6 IPS
 
Pose Estimation (F16)
100% 19730
23.9 IPS
 
Pose Estimation (I8)
100% 17945
21.7 IPS
 
Object Detection (F32)
100% 2919
217.9 IPS
 
Object Detection (F16)
100% 2896
216.2 IPS
 
Object Detection (I8)
61% 2560
191.2 IPS
 
Face Detection (F32)
100% 7919
94.2 IPS
 
Face Detection (F16)
100% 8009
95.2 IPS
 
Face Detection (I8)
89% 5287
62.9 IPS
 
Depth Estimation (F32)
100% 17196
133.4 IPS
 
Depth Estimation (F16)
100% 18108
140.4 IPS
 
Depth Estimation (I8)
94% 14350
111.3 IPS
 
Style Transfer (F32)
100% 45849
60.3 IPS
 
Style Transfer (F16)
100% 48302
63.5 IPS
 
Style Transfer (I8)
98% 38799
51.0 IPS
 
Image Super-Resolution (F32)
100% 7910
282.5 IPS
 
Image Super-Resolution (F16)
100% 7712
275.4 IPS
 
Image Super-Resolution (I8)
99% 4861
173.6 IPS
 
Text Classification (F32)
100% 697
1.00 KIPS
 
Text Classification (F16)
100% 700
1.01 KIPS
 
Text Classification (I8)
98% 416
598.4 IPS
 
Machine Translation (F32)
100% 1745
32.1 IPS
 
Machine Translation (F16)
100% 1490
27.4 IPS
 
Machine Translation (I8)
70% 836
15.4 IPS
 

Compare

Set Baseline Geekbench 6 now available