Geekbench ML Score

1196
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 15 2024 01:36 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 10 Enterprise LTSC (64-bit)
Model Supermicro Super Server
Motherboard Supermicro X13SAV-LVDS
Power PlanUltimate Performance
CPU Information
Name Intel Core i7-13700E
Topology 1 Processor, 16 Cores, 24 Threads
Identifier GenuineIntel Family 6 Model 183 Stepping 1
Base Frequency 1.88 GHz
Cluster 18 Cores
Cluster 28 Cores
L1 Instruction Cache64.0 KB x 12
L1 Data Cache32.0 KB x 12
L2 Cache4.00 MB x 3
L3 Cache30.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) UHD Graphics 770

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 532
99.6 IPS
 
Image Classification (F16)
100% 536
100.3 IPS
 
Image Classification (I8)
100% 449
84.1 IPS
 
Image Segmentation (F32)
100% 992
16.6 IPS
 
Image Segmentation (F16)
100% 991
16.6 IPS
 
Image Segmentation (I8)
98% 757
12.6 IPS
 
Pose Estimation (F32)
100% 3165
3.83 IPS
 
Pose Estimation (F16)
100% 3174
3.84 IPS
 
Pose Estimation (I8)
100% 2891
3.50 IPS
 
Object Detection (F32)
100% 527
39.3 IPS
 
Object Detection (F16)
100% 525
39.2 IPS
 
Object Detection (I8)
54% 463
34.5 IPS
 
Face Detection (F32)
100% 1361
16.2 IPS
 
Face Detection (F16)
100% 1358
16.1 IPS
 
Face Detection (I8)
89% 984
11.7 IPS
 
Depth Estimation (F32)
100% 2062
16.0 IPS
 
Depth Estimation (F16)
100% 2065
16.0 IPS
 
Depth Estimation (I8)
94% 1811
14.0 IPS
 
Style Transfer (F32)
100% 9082
11.9 IPS
 
Style Transfer (F16)
100% 9083
11.9 IPS
 
Style Transfer (I8)
98% 7875
10.4 IPS
 
Image Super-Resolution (F32)
100% 1612
57.6 IPS
 
Image Super-Resolution (F16)
100% 1621
57.9 IPS
 
Image Super-Resolution (I8)
99% 1288
46.0 IPS
 
Text Classification (F32)
100% 819
1.18 KIPS
 
Text Classification (F16)
100% 833
1.20 KIPS
 
Text Classification (I8)
98% 399
573.0 IPS
 
Machine Translation (F32)
100% 479
8.81 IPS
 
Machine Translation (F16)
100% 480
8.83 IPS
 
Machine Translation (I8)
70% 323
5.94 IPS
 

Compare

Set Baseline Geekbench 6 now available