Geekbench ML Score

4099
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date September 23 2024 09:28 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Home Single Language (64-bit)
Model LENOVO 83D4
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Intel Core Ultra 9 185H
Topology 1 Processor, 16 Cores, 22 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 2.30 GHz
Cluster 16 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 11
L1 Data Cache48.0 KB x 11
L2 Cache2.00 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2259
422.8 IPS
 
Image Classification (F16)
100% 2271
425.0 IPS
 
Image Classification (I8)
100% 2013
376.7 IPS
 
Image Segmentation (F32)
100% 3082
51.5 IPS
 
Image Segmentation (F16)
100% 2832
47.3 IPS
 
Image Segmentation (I8)
98% 2467
41.2 IPS
 
Pose Estimation (F32)
100% 17893
21.7 IPS
 
Pose Estimation (F16)
100% 17584
21.3 IPS
 
Pose Estimation (I8)
100% 13782
16.7 IPS
 
Object Detection (F32)
100% 2192
163.6 IPS
 
Object Detection (F16)
100% 1662
124.1 IPS
 
Object Detection (I8)
54% 1337
99.8 IPS
 
Face Detection (F32)
100% 4555
54.2 IPS
 
Face Detection (F16)
100% 4584
54.5 IPS
 
Face Detection (I8)
89% 3324
39.5 IPS
 
Depth Estimation (F32)
100% 10394
80.6 IPS
 
Depth Estimation (F16)
100% 10142
78.7 IPS
 
Depth Estimation (I8)
95% 8231
63.8 IPS
 
Style Transfer (F32)
100% 46524
61.2 IPS
 
Style Transfer (F16)
100% 46727
61.5 IPS
 
Style Transfer (I8)
98% 34424
45.3 IPS
 
Image Super-Resolution (F32)
100% 7092
253.3 IPS
 
Image Super-Resolution (F16)
100% 7453
266.2 IPS
 
Image Super-Resolution (I8)
99% 4079
145.7 IPS
 
Text Classification (F32)
90% 752
1.08 KIPS
 
Text Classification (F16)
90% 719
1.03 KIPS
 
Text Classification (I8)
90% 544
781.5 IPS
 
Machine Translation (F32)
100% 1410
25.9 IPS
 
Machine Translation (F16)
100% 1482
27.3 IPS
 
Machine Translation (I8)
70% 857
15.8 IPS
 

Compare

Set Baseline Geekbench 6 now available