Geekbench ML Score

5305
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 08 2024 04:25 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model LENOVO 83HM
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Intel(R) Core(TM) Ultra 7 256V
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 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) 140V GPU (8GB)

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3643
681.8 IPS
 
Image Classification (F16)
100% 3676
687.9 IPS
 
Image Classification (I8)
100% 2681
501.7 IPS
 
Image Segmentation (F32)
100% 5862
97.9 IPS
 
Image Segmentation (F16)
100% 5839
97.5 IPS
 
Image Segmentation (I8)
98% 4487
74.9 IPS
 
Pose Estimation (F32)
100% 19962
24.2 IPS
 
Pose Estimation (F16)
100% 20277
24.6 IPS
 
Pose Estimation (I8)
100% 16652
20.2 IPS
 
Object Detection (F32)
100% 2792
208.5 IPS
 
Object Detection (F16)
100% 2766
206.5 IPS
 
Object Detection (I8)
61% 2459
183.6 IPS
 
Face Detection (F32)
100% 7488
89.0 IPS
 
Face Detection (F16)
100% 7652
91.0 IPS
 
Face Detection (I8)
89% 5055
60.1 IPS
 
Depth Estimation (F32)
100% 18195
141.1 IPS
 
Depth Estimation (F16)
100% 17382
134.8 IPS
 
Depth Estimation (I8)
94% 14341
111.2 IPS
 
Style Transfer (F32)
100% 45836
60.3 IPS
 
Style Transfer (F16)
100% 47281
62.2 IPS
 
Style Transfer (I8)
98% 37547
49.4 IPS
 
Image Super-Resolution (F32)
100% 7384
263.7 IPS
 
Image Super-Resolution (F16)
100% 8108
289.6 IPS
 
Image Super-Resolution (I8)
99% 4836
172.7 IPS
 
Text Classification (F32)
100% 536
769.9 IPS
 
Text Classification (F16)
100% 727
1.04 KIPS
 
Text Classification (I8)
98% 387
556.1 IPS
 
Machine Translation (F32)
100% 1482
27.3 IPS
 
Machine Translation (F16)
100% 1433
26.4 IPS
 
Machine Translation (I8)
70% 787
14.5 IPS
 

Compare

Set Baseline Geekbench 6 now available