Geekbench ML Score

2565
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date May 18 2024 09:49 AM
Views 6

System Information

System Information
Operating System Microsoft Windows 10 Enterprise (64-bit)
Model HP HP ZBook 15 G5
Motherboard HP 842A
Power PlanBalanced
CPU Information
Name Intel Core i7-8850H
Topology 1 Processor, 6 Cores, 12 Threads
Identifier GenuineIntel Family 6 Model 158 Stepping 10
Base Frequency 2.59 GHz
Cluster 16 Cores
L1 Instruction Cache32.0 KB x 6
L1 Data Cache32.0 KB x 6
L2 Cache256 KB x 6
L3 Cache9.00 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA Quadro P2000

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1056
197.7 IPS
 
Image Classification (F16)
100% 1083
202.6 IPS
 
Image Classification (I8)
100% 907
169.7 IPS
 
Image Segmentation (F32)
100% 1554
26.0 IPS
 
Image Segmentation (F16)
100% 1587
26.5 IPS
 
Image Segmentation (I8)
98% 1370
22.9 IPS
 
Pose Estimation (F32)
100% 10921
13.2 IPS
 
Pose Estimation (F16)
100% 10967
13.3 IPS
 
Pose Estimation (I8)
100% 9584
11.6 IPS
 
Object Detection (F32)
100% 1000
74.7 IPS
 
Object Detection (F16)
100% 804
60.0 IPS
 
Object Detection (I8)
58% 876
65.4 IPS
 
Face Detection (F32)
100% 2429
28.9 IPS
 
Face Detection (F16)
100% 2474
29.4 IPS
 
Face Detection (I8)
89% 2061
24.5 IPS
 
Depth Estimation (F32)
100% 5776
44.8 IPS
 
Depth Estimation (F16)
100% 5891
45.7 IPS
 
Depth Estimation (I8)
95% 4994
38.7 IPS
 
Style Transfer (F32)
100% 26247
34.5 IPS
 
Style Transfer (F16)
100% 25604
33.7 IPS
 
Style Transfer (I8)
98% 20763
27.3 IPS
 
Image Super-Resolution (F32)
100% 4587
163.8 IPS
 
Image Super-Resolution (F16)
100% 4721
168.6 IPS
 
Image Super-Resolution (I8)
99% 3436
122.7 IPS
 
Text Classification (F32)
100% 655
941.9 IPS
 
Text Classification (F16)
100% 798
1.15 KIPS
 
Text Classification (I8)
98% 533
765.7 IPS
 
Machine Translation (F32)
100% 1285
23.6 IPS
 
Machine Translation (F16)
100% 1305
24.0 IPS
 
Machine Translation (I8)
70% 651
12.0 IPS
 

Compare

Set Baseline Geekbench 6 now available