Geekbench ML Score

14572
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User navtiidia
Upload Date August 01 2024 08:27 PM
Views 7

System Information

System Information
Operating System Microsoft Windows 11 Pro for Workstations Insider Preview (64-bit)
Model X570 PG Velocita
Motherboard ASRock X570 PG Velocita
Power PlanHigh performance
CPU Information
Name AMD Ryzen 9 5900X
Topology 1 Processor, 12 Cores, 24 Threads
Identifier AuthenticAMD Family 25 Model 33 Stepping 0
Base Frequency 3.70 GHz
Cluster 112 Cores
L1 Instruction Cache32.0 KB x 12
L1 Data Cache32.0 KB x 12
L2 Cache512 KB x 12
L3 Cache32.0 MB x 2
Memory Information
Size 128.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 2080 Ti

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7262
1.36 KIPS
 
Image Classification (F16)
100% 7271
1.36 KIPS
 
Image Classification (I8)
100% 4867
910.7 IPS
 
Image Segmentation (F32)
100% 11399
190.4 IPS
 
Image Segmentation (F16)
100% 11519
192.4 IPS
 
Image Segmentation (I8)
98% 8887
148.4 IPS
 
Pose Estimation (F32)
100% 102159
123.7 IPS
 
Pose Estimation (F16)
100% 102406
124.0 IPS
 
Pose Estimation (I8)
100% 81757
99.0 IPS
 
Object Detection (F32)
100% 5322
397.3 IPS
 
Object Detection (F16)
100% 5208
388.8 IPS
 
Object Detection (I8)
63% 4263
318.2 IPS
 
Face Detection (F32)
100% 21059
250.4 IPS
 
Face Detection (F16)
100% 21175
251.8 IPS
 
Face Detection (I8)
89% 15184
180.5 IPS
 
Depth Estimation (F32)
100% 47020
364.6 IPS
 
Depth Estimation (F16)
100% 47046
364.8 IPS
 
Depth Estimation (I8)
94% 30510
236.6 IPS
 
Style Transfer (F32)
100% 198150
260.6 IPS
 
Style Transfer (F16)
100% 195056
256.6 IPS
 
Style Transfer (I8)
98% 148270
195.0 IPS
 
Image Super-Resolution (F32)
100% 29405
1.05 KIPS
 
Image Super-Resolution (F16)
100% 30602
1.09 KIPS
 
Image Super-Resolution (I8)
99% 17234
615.5 IPS
 
Text Classification (F32)
100% 1841
2.65 KIPS
 
Text Classification (F16)
100% 1840
2.64 KIPS
 
Text Classification (I8)
98% 1079
1.55 KIPS
 
Machine Translation (F32)
100% 3401
62.6 IPS
 
Machine Translation (F16)
100% 3406
62.7 IPS
 
Machine Translation (I8)
70% 1544
28.4 IPS
 

Compare

Set Baseline Geekbench 6 now available