Geekbench ML Score

1372
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date April 26 2024 05:30 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model Dell Inc. Inspiron 3505
Motherboard Dell Inc. 05HPX6
Power PlanAMD Ryzen Balanced
CPU Information
Name AMD Ryzen 5 3450U with Radeon Vega Mobile Gfx
Topology 1 Processor, 4 Cores, 8 Threads
Identifier AuthenticAMD Family 23 Model 24 Stepping 1
Base Frequency 2.10 GHz
Cluster 14 Cores
L1 Instruction Cache64.0 KB x 4
L1 Data Cache32.0 KB x 4
L2 Cache512 KB x 4
L3 Cache4.00 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon(TM) Vega 8 Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 721
134.9 IPS
 
Image Classification (F16)
100% 711
133.1 IPS
 
Image Classification (I8)
99% 596
111.6 IPS
 
Image Segmentation (F32)
100% 660
11.0 IPS
 
Image Segmentation (F16)
100% 662
11.1 IPS
 
Image Segmentation (I8)
98% 582
9.71 IPS
 
Pose Estimation (F32)
100% 6542
7.92 IPS
 
Pose Estimation (F16)
100% 6515
7.89 IPS
 
Pose Estimation (I8)
100% 5770
6.99 IPS
 
Object Detection (F32)
100% 626
46.8 IPS
 
Object Detection (F16)
100% 622
46.4 IPS
 
Object Detection (I8)
67% 551
41.1 IPS
 
Face Detection (F32)
100% 1664
19.8 IPS
 
Face Detection (F16)
100% 1667
19.8 IPS
 
Face Detection (I8)
89% 1324
15.7 IPS
 
Depth Estimation (F32)
100% 3866
30.0 IPS
 
Depth Estimation (F16)
100% 3894
30.2 IPS
 
Depth Estimation (I8)
94% 3167
24.6 IPS
 
Style Transfer (F32)
100% 9015
11.9 IPS
 
Style Transfer (F16)
100% 8919
11.7 IPS
 
Style Transfer (I8)
98% 7572
9.96 IPS
 
Image Super-Resolution (F32)
100% 1162
41.5 IPS
 
Image Super-Resolution (F16)
100% 1148
41.0 IPS
 
Image Super-Resolution (I8)
99% 942
33.6 IPS
 
Text Classification (F32)
100% 494
710.5 IPS
 
Text Classification (F16)
100% 528
758.6 IPS
 
Text Classification (I8)
98% 336
483.6 IPS
 
Machine Translation (F32)
100% 805
14.8 IPS
 
Machine Translation (F16)
100% 798
14.7 IPS
 
Machine Translation (I8)
69% 433
7.96 IPS
 

Compare

Set Baseline Geekbench 6 now available