Samsung Galaxy S23 Ultra
Geekbench ML Score
554
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | May 01 2024 07:39 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Samsung Galaxy S23 Ultra |
| Model ID | samsung SM-S918B |
| Motherboard | kalama |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
| Base Frequency | 2.02 GHz |
| Cluster 1 | 3 Cores @ 2.02 GHz |
| Cluster 2 | 4 Cores @ 2.80 GHz |
| Cluster 3 | 1 Core @ 3.36 GHz |
| Memory Information | |
|---|---|
| Size | 10.77 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
254
47.5 IPS |
|
|
Image Classification (F16)
|
100% |
255
47.7 IPS |
|
|
Image Classification (I8)
|
97% |
607
113.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
320
5.35 IPS |
|
|
Image Segmentation (F16)
|
100% |
320
5.34 IPS |
|
|
Image Segmentation (I8)
|
98% |
620
10.4 IPS |
|
|
Pose Estimation (F32)
|
100% |
454
0.55 IPS |
|
|
Pose Estimation (F16)
|
100% |
454
0.55 IPS |
|
|
Pose Estimation (I8)
|
100% |
1726
2.09 IPS |
|
|
Object Detection (F32)
|
100% |
265
19.8 IPS |
|
|
Object Detection (F16)
|
100% |
266
19.9 IPS |
|
|
Object Detection (I8)
|
61% |
695
51.9 IPS |
|
|
Face Detection (F32)
|
100% |
625
7.43 IPS |
|
|
Face Detection (F16)
|
100% |
628
7.46 IPS |
|
|
Face Detection (I8)
|
86% |
1297
15.4 IPS |
|
|
Depth Estimation (F32)
|
100% |
554
4.29 IPS |
|
|
Depth Estimation (F16)
|
100% |
556
4.31 IPS |
|
|
Depth Estimation (I8)
|
95% |
1486
11.5 IPS |
|
|
Style Transfer (F32)
|
100% |
867
1.14 IPS |
|
|
Style Transfer (F16)
|
100% |
873
1.15 IPS |
|
|
Style Transfer (I8)
|
98% |
2073
2.73 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
306
10.9 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
307
11.0 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1064
38.0 IPS |
|
|
Text Classification (F32)
|
100% |
354
509.2 IPS |
|
|
Text Classification (F16)
|
100% |
355
510.4 IPS |
|
|
Text Classification (I8)
|
92% |
504
724.6 IPS |
|
|
Machine Translation (F32)
|
100% |
588
10.8 IPS |
|
|
Machine Translation (F16)
|
100% |
587
10.8 IPS |
|
|
Machine Translation (I8)
|
64% |
594
10.9 IPS |
