Geekbench ML Score

5646
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 15 2024 05:14 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% 3337
624.4 IPS
 
Image Classification (F16)
100% 3777
706.8 IPS
 
Image Classification (I8)
100% 2462
460.6 IPS
 
Image Segmentation (F32)
100% 6264
104.6 IPS
 
Image Segmentation (F16)
100% 6160
102.9 IPS
 
Image Segmentation (I8)
98% 4598
76.8 IPS
 
Pose Estimation (F32)
100% 20132
24.4 IPS
 
Pose Estimation (F16)
100% 20646
25.0 IPS
 
Pose Estimation (I8)
100% 16843
20.4 IPS
 
Object Detection (F32)
100% 3082
230.1 IPS
 
Object Detection (F16)
100% 3067
229.0 IPS
 
Object Detection (I8)
61% 2577
192.4 IPS
 
Face Detection (F32)
100% 8241
98.0 IPS
 
Face Detection (F16)
100% 8264
98.3 IPS
 
Face Detection (I8)
89% 6023
71.6 IPS
 
Depth Estimation (F32)
100% 18981
147.2 IPS
 
Depth Estimation (F16)
100% 18671
144.8 IPS
 
Depth Estimation (I8)
94% 14444
112.0 IPS
 
Style Transfer (F32)
100% 48989
64.4 IPS
 
Style Transfer (F16)
100% 48417
63.7 IPS
 
Style Transfer (I8)
98% 41367
54.4 IPS
 
Image Super-Resolution (F32)
100% 8073
288.3 IPS
 
Image Super-Resolution (F16)
100% 7419
265.0 IPS
 
Image Super-Resolution (I8)
99% 5011
179.0 IPS
 
Text Classification (F32)
100% 762
1.10 KIPS
 
Text Classification (F16)
100% 709
1.02 KIPS
 
Text Classification (I8)
98% 449
645.9 IPS
 
Machine Translation (F32)
100% 1543
28.4 IPS
 
Machine Translation (F16)
100% 1770
32.6 IPS
 
Machine Translation (I8)
70% 932
17.2 IPS
 

Compare

Set Baseline Geekbench 6 now available