Geekbench ML Score

2304
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date August 23 2024 12:35 PM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model LENOVO 83ED
Motherboard LENOVO LNVNB161216
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% 1382
258.6 IPS
 
Image Classification (F16)
100% 1469
275.0 IPS
 
Image Classification (I8)
100% 1199
224.3 IPS
 
Image Segmentation (F32)
100% 1673
27.9 IPS
 
Image Segmentation (F16)
100% 1692
28.3 IPS
 
Image Segmentation (I8)
98% 1474
24.6 IPS
 
Pose Estimation (F32)
100% 9058
11.0 IPS
 
Pose Estimation (F16)
100% 9295
11.3 IPS
 
Pose Estimation (I8)
100% 8459
10.2 IPS
 
Object Detection (F32)
100% 1212
90.5 IPS
 
Object Detection (F16)
100% 1192
89.0 IPS
 
Object Detection (I8)
71% 1071
79.9 IPS
 
Face Detection (F32)
100% 2756
32.8 IPS
 
Face Detection (F16)
100% 2836
33.7 IPS
 
Face Detection (I8)
93% 2272
27.0 IPS
 
Depth Estimation (F32)
100% 5462
42.4 IPS
 
Depth Estimation (F16)
100% 5430
42.1 IPS
 
Depth Estimation (I8)
94% 4576
35.5 IPS
 
Style Transfer (F32)
100% 12997
17.1 IPS
 
Style Transfer (F16)
100% 12886
16.9 IPS
 
Style Transfer (I8)
98% 11816
15.5 IPS
 
Image Super-Resolution (F32)
100% 4928
176.0 IPS
 
Image Super-Resolution (F16)
100% 4914
175.5 IPS
 
Image Super-Resolution (I8)
99% 3576
127.7 IPS
 
Text Classification (F32)
100% 296
425.4 IPS
 
Text Classification (F16)
100% 300
430.6 IPS
 
Text Classification (I8)
98% 234
336.1 IPS
 
Machine Translation (F32)
100% 1071
19.7 IPS
 
Machine Translation (F16)
100% 1070
19.7 IPS
 
Machine Translation (I8)
65% 689
12.7 IPS
 

Compare

Set Baseline Geekbench 6 now available