Geekbench ML Score

7977
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 13 2024 10:22 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Z590 PG Velocita
Motherboard ASRock Z590 PG Velocita
Power PlanBalanced
CPU Information
Name Intel Core i5-11600K
Topology 1 Processor, 6 Cores, 12 Threads
Identifier GenuineIntel Family 6 Model 167 Stepping 1
Base Frequency 3.91 GHz
Cluster 16 Cores
L1 Instruction Cache32.0 KB x 6
L1 Data Cache48.0 KB x 6
L2 Cache512 KB x 6
L3 Cache12.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) A580 Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3967
742.4 IPS
 
Image Classification (F16)
100% 4052
758.3 IPS
 
Image Classification (I8)
99% 3168
592.8 IPS
 
Image Segmentation (F32)
100% 5801
96.9 IPS
 
Image Segmentation (F16)
100% 5678
94.8 IPS
 
Image Segmentation (I8)
98% 4700
78.5 IPS
 
Pose Estimation (F32)
100% 60526
73.3 IPS
 
Pose Estimation (F16)
100% 62083
75.2 IPS
 
Pose Estimation (I8)
100% 50154
60.7 IPS
 
Object Detection (F32)
100% 3530
263.5 IPS
 
Object Detection (F16)
100% 3536
264.0 IPS
 
Object Detection (I8)
60% 3249
242.6 IPS
 
Face Detection (F32)
100% 11992
142.6 IPS
 
Face Detection (F16)
100% 12123
144.1 IPS
 
Face Detection (I8)
88% 9556
113.6 IPS
 
Depth Estimation (F32)
100% 24909
193.2 IPS
 
Depth Estimation (F16)
100% 24117
187.0 IPS
 
Depth Estimation (I8)
95% 20588
159.7 IPS
 
Style Transfer (F32)
100% 134562
177.0 IPS
 
Style Transfer (F16)
100% 130589
171.8 IPS
 
Style Transfer (I8)
98% 101632
133.7 IPS
 
Image Super-Resolution (F32)
100% 13317
475.6 IPS
 
Image Super-Resolution (F16)
100% 13925
497.3 IPS
 
Image Super-Resolution (I8)
99% 10616
379.1 IPS
 
Text Classification (F32)
90% 664
953.9 IPS
 
Text Classification (F16)
90% 622
894.3 IPS
 
Text Classification (I8)
90% 528
759.0 IPS
 
Machine Translation (F32)
100% 1266
23.3 IPS
 
Machine Translation (F16)
100% 1292
23.8 IPS
 
Machine Translation (I8)
70% 876
16.1 IPS
 

Compare

Set Baseline Geekbench 6 now available