Samsung Galaxy S21+ 5G
Geekbench ML Score
555
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| User | AR_Gaming |
| Upload Date | January 09 2024 10:50 AM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Samsung Galaxy S21+ 5G |
| Model ID | samsung SM-G996B |
| Motherboard | exynos2100 |
| Governor | energy_step |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 2.21 GHz |
| Cluster 1 | 4 Cores @ 2.21 GHz |
| Cluster 2 | 3 Cores @ 2.81 GHz |
| Cluster 3 | 1 Core @ 2.91 GHz |
| Memory Information | |
|---|---|
| Size | 7.03 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
210
39.2 IPS |
|
|
Image Classification (F16)
|
100% |
369
69.0 IPS |
|
|
Image Classification (I8)
|
97% |
354
66.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
281
4.69 IPS |
|
|
Image Segmentation (F16)
|
100% |
448
7.48 IPS |
|
|
Image Segmentation (I8)
|
98% |
437
7.29 IPS |
|
|
Pose Estimation (F32)
|
100% |
128
0.15 IPS |
|
|
Pose Estimation (F16)
|
100% |
339
0.41 IPS |
|
|
Pose Estimation (I8)
|
100% |
338
0.41 IPS |
|
|
Object Detection (F32)
|
100% |
356
26.6 IPS |
|
|
Object Detection (F16)
|
100% |
555
41.4 IPS |
|
|
Object Detection (I8)
|
62% |
553
41.3 IPS |
|
|
Face Detection (F32)
|
100% |
1490
17.7 IPS |
|
|
Face Detection (F16)
|
98% |
2278
27.1 IPS |
|
|
Face Detection (I8)
|
86% |
2100
25.0 IPS |
|
|
Depth Estimation (F32)
|
100% |
575
4.46 IPS |
|
|
Depth Estimation (F16)
|
100% |
755
5.85 IPS |
|
|
Depth Estimation (I8)
|
95% |
769
5.97 IPS |
|
|
Style Transfer (F32)
|
100% |
1212
1.59 IPS |
|
|
Style Transfer (F16)
|
100% |
2099
2.76 IPS |
|
|
Style Transfer (I8)
|
98% |
2096
2.76 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
400
14.3 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
689
24.6 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
676
24.1 IPS |
|
|
Text Classification (F32)
|
100% |
272
390.5 IPS |
|
|
Text Classification (F16)
|
100% |
272
390.4 IPS |
|
|
Text Classification (I8)
|
92% |
489
703.3 IPS |
|
|
Machine Translation (F32)
|
100% |
457
8.41 IPS |
|
|
Machine Translation (F16)
|
100% |
447
8.23 IPS |
|
|
Machine Translation (I8)
|
64% |
519
9.55 IPS |
