Geekbench ML Score

2219
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date August 15 2024 05:30 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro Insider Preview (64-bit)
Model OEMMN OEMMN Product Name DV CVL2
Motherboard OEMMN OEMMN Product Name DV CVL2
Power PlanBalanced
CPU Information
Name Snapdragon(R) X Elite - X1E78100 - Qualcomm(R) Oryon(TM) CPU
Topology 1 Processor, 12 Cores
Identifier ARMv8 (64-bit) Family 8 Model 1 Revision 201
Base Frequency 3.42 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Snapdragon(R) X Elite - X1E78100 - Qualcomm(R) Adreno(TM) GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1447
270.8 IPS
 
Image Classification (F16)
100% 1216
227.5 IPS
 
Image Classification (I8)
100% 1017
190.2 IPS
 
Image Segmentation (F32)
100% 1543
25.8 IPS
 
Image Segmentation (F16)
100% 1543
25.8 IPS
 
Image Segmentation (I8)
98% 1420
23.7 IPS
 
Pose Estimation (F32)
100% 8456
10.2 IPS
 
Pose Estimation (F16)
100% 9398
11.4 IPS
 
Pose Estimation (I8)
100% 8390
10.2 IPS
 
Object Detection (F32)
100% 1195
89.2 IPS
 
Object Detection (F16)
100% 1064
79.4 IPS
 
Object Detection (I8)
71% 1017
75.9 IPS
 
Face Detection (F32)
100% 2507
29.8 IPS
 
Face Detection (F16)
100% 2656
31.6 IPS
 
Face Detection (I8)
93% 2157
25.6 IPS
 
Depth Estimation (F32)
100% 5381
41.7 IPS
 
Depth Estimation (F16)
100% 5524
42.8 IPS
 
Depth Estimation (I8)
94% 4543
35.2 IPS
 
Style Transfer (F32)
100% 12793
16.8 IPS
 
Style Transfer (F16)
100% 12674
16.7 IPS
 
Style Transfer (I8)
98% 11924
15.7 IPS
 
Image Super-Resolution (F32)
100% 4825
172.3 IPS
 
Image Super-Resolution (F16)
100% 4875
174.1 IPS
 
Image Super-Resolution (I8)
99% 3410
121.8 IPS
 
Text Classification (F32)
100% 279
400.5 IPS
 
Text Classification (F16)
100% 292
420.3 IPS
 
Text Classification (I8)
98% 244
350.3 IPS
 
Machine Translation (F32)
100% 1064
19.6 IPS
 
Machine Translation (F16)
100% 1077
19.8 IPS
 
Machine Translation (I8)
65% 685
12.6 IPS
 

Compare

Set Baseline Geekbench 6 now available