Geekbench ML Score

1489
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date September 13 2024 09:39 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model HUAWEI MACHC-WAX9
Motherboard HUAWEI MACHC-WAX9-PCB
Power PlanRovnovha
CPU Information
Name Intel Core i7-10510U
Topology 1 Processor, 4 Cores, 8 Threads
Identifier GenuineIntel Family 6 Model 142 Stepping 12
Base Frequency 2.30 GHz
Cluster 14 Cores
L1 Instruction Cache32.0 KB x 4
L1 Data Cache32.0 KB x 4
L2 Cache256 KB x 4
L3 Cache8.00 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce MX250

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 585
109.5 IPS
 
Image Classification (F16)
100% 587
109.8 IPS
 
Image Classification (I8)
100% 507
94.9 IPS
 
Image Segmentation (F32)
100% 815
13.6 IPS
 
Image Segmentation (F16)
100% 802
13.4 IPS
 
Image Segmentation (I8)
98% 680
11.4 IPS
 
Pose Estimation (F32)
100% 4510
5.46 IPS
 
Pose Estimation (F16)
100% 4476
5.42 IPS
 
Pose Estimation (I8)
100% 4053
4.91 IPS
 
Object Detection (F32)
100% 723
54.0 IPS
 
Object Detection (F16)
100% 730
54.5 IPS
 
Object Detection (I8)
58% 644
48.1 IPS
 
Face Detection (F32)
100% 1240
14.7 IPS
 
Face Detection (F16)
100% 1244
14.8 IPS
 
Face Detection (I8)
89% 1021
12.1 IPS
 
Depth Estimation (F32)
100% 2629
20.4 IPS
 
Depth Estimation (F16)
100% 2621
20.3 IPS
 
Depth Estimation (I8)
95% 2268
17.6 IPS
 
Style Transfer (F32)
100% 10368
13.6 IPS
 
Style Transfer (F16)
100% 10388
13.7 IPS
 
Style Transfer (I8)
98% 8884
11.7 IPS
 
Image Super-Resolution (F32)
100% 2646
94.5 IPS
 
Image Super-Resolution (F16)
100% 2996
107.0 IPS
 
Image Super-Resolution (I8)
99% 1950
69.7 IPS
 
Text Classification (F32)
100% 768
1.10 KIPS
 
Text Classification (F16)
100% 856
1.23 KIPS
 
Text Classification (I8)
98% 470
674.9 IPS
 
Machine Translation (F32)
100% 1090
20.1 IPS
 
Machine Translation (F16)
100% 1077
19.8 IPS
 
Machine Translation (I8)
68% 545
10.0 IPS
 

Compare

Set Baseline Geekbench 6 now available