Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
407
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | January 19 2022 09:58 AM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998U |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 9.97 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
378
40.5 IPS |
|
|
Image Classification (F16)
|
100% |
274
29.4 IPS |
|
|
Image Classification (I8)
|
81% |
192
20.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
633
3.91 IPS |
|
|
Image Segmentation (F16)
|
100% |
622
3.84 IPS |
|
|
Image Segmentation (I8)
|
89% |
872
5.38 IPS |
|
|
Pose Estimation (F32)
|
100% |
239
0.97 IPS |
|
|
Pose Estimation (F16)
|
100% |
248
1.00 IPS |
|
|
Pose Estimation (I8)
|
80% |
239
0.97 IPS |
|
|
Object Detection (F32)
|
100% |
383
13.4 IPS |
|
|
Object Detection (F16)
|
100% |
378
13.2 IPS |
|
|
Object Detection (I8)
|
52% |
245
8.58 IPS |
|
|
Face Detection (F32)
|
100% |
579
6.65 IPS |
|
|
Face Detection (F16)
|
100% |
616
7.08 IPS |
|
|
Face Detection (I8)
|
75% |
510
5.86 IPS |
|
|
Text Classification (F32)
|
100% |
340
134.6 IPS |
|
|
Text Classification (F16)
|
100% |
340
134.4 IPS |
|
|
Machine Translation (F32)
|
100% |
741
114.1 IPS |
|
|
Machine Translation (F16)
|
100% |
745
114.9 IPS |
