Geekbench ML Score

2235
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date September 18 2024 09:07 AM
Views 5

System Information

System Information
Operating System Microsoft Windows 11 Pro (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 32.00 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% 1453
271.8 IPS
 
Image Classification (F16)
100% 1373
256.9 IPS
 
Image Classification (I8)
100% 983
184.0 IPS
 
Image Segmentation (F32)
100% 1539
25.7 IPS
 
Image Segmentation (F16)
100% 1626
27.2 IPS
 
Image Segmentation (I8)
98% 1488
24.9 IPS
 
Pose Estimation (F32)
100% 9448
11.4 IPS
 
Pose Estimation (F16)
100% 9410
11.4 IPS
 
Pose Estimation (I8)
100% 8578
10.4 IPS
 
Object Detection (F32)
100% 1173
87.6 IPS
 
Object Detection (F16)
100% 1185
88.5 IPS
 
Object Detection (I8)
71% 1056
78.8 IPS
 
Face Detection (F32)
100% 2742
32.6 IPS
 
Face Detection (F16)
100% 2745
32.6 IPS
 
Face Detection (I8)
93% 2287
27.2 IPS
 
Depth Estimation (F32)
100% 5404
41.9 IPS
 
Depth Estimation (F16)
100% 5294
41.1 IPS
 
Depth Estimation (I8)
94% 4579
35.5 IPS
 
Style Transfer (F32)
100% 12885
16.9 IPS
 
Style Transfer (F16)
100% 13052
17.2 IPS
 
Style Transfer (I8)
98% 11768
15.5 IPS
 
Image Super-Resolution (F32)
100% 4456
159.1 IPS
 
Image Super-Resolution (F16)
100% 4932
176.1 IPS
 
Image Super-Resolution (I8)
99% 3501
125.0 IPS
 
Text Classification (F32)
100% 284
408.4 IPS
 
Text Classification (F16)
100% 287
411.9 IPS
 
Text Classification (I8)
98% 221
318.0 IPS
 
Machine Translation (F32)
100% 899
16.5 IPS
 
Machine Translation (F16)
100% 974
17.9 IPS
 
Machine Translation (I8)
65% 682
12.6 IPS
 

Compare

Set Baseline Geekbench 6 now available