Geekbench ML Score

784
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date January 21 2024 09:05 PM
Views 1

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Gigabyte Technology Co., Ltd. Z390 AORUS PRO WIFI
Motherboard Gigabyte Technology Co., Ltd. Z390 AORUS PRO WIFI-CF
Power PlanBalanced
CPU Information
Name Intel Core i9-9900K
Topology 1 Processor, 8 Cores, 16 Threads
Identifier GenuineIntel Family 6 Model 158 Stepping 13
Base Frequency 3.60 GHz
Cluster 18 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache32.0 KB x 8
L2 Cache256 KB x 8
L3 Cache16.0 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) UHD Graphics 630

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 397
74.3 IPS
 
Image Classification (F16)
100% 396
74.2 IPS
 
Image Classification (I8)
100% 359
67.3 IPS
 
Image Segmentation (F32)
100% 514
8.59 IPS
 
Image Segmentation (F16)
100% 588
9.81 IPS
 
Image Segmentation (I8)
98% 429
7.17 IPS
 
Pose Estimation (F32)
0% 2244
2.72 IPS
 
Pose Estimation (F16)
0% 2240
2.71 IPS
 
Pose Estimation (I8)
100% 2030
2.46 IPS
 
Object Detection (F32)
100% 445
33.2 IPS
 
Object Detection (F16)
100% 446
33.3 IPS
 
Object Detection (I8)
54% 407
30.4 IPS
 
Face Detection (F32)
18% 787
9.36 IPS
 
Face Detection (F16)
18% 719
8.55 IPS
 
Face Detection (I8)
89% 598
7.12 IPS
 
Depth Estimation (F32)
100% 1642
12.7 IPS
 
Depth Estimation (F16)
100% 1632
12.7 IPS
 
Depth Estimation (I8)
95% 1475
11.4 IPS
 
Style Transfer (F32)
100% 5181
6.82 IPS
 
Style Transfer (F16)
100% 4721
6.21 IPS
 
Style Transfer (I8)
98% 4865
6.40 IPS
 
Image Super-Resolution (F32)
100% 1131
40.4 IPS
 
Image Super-Resolution (F16)
100% 1157
41.3 IPS
 
Image Super-Resolution (I8)
99% 926
33.1 IPS
 
Text Classification (F32)
100% 274
394.0 IPS
 
Text Classification (F16)
100% 275
395.7 IPS
 
Text Classification (I8)
98% 197
283.0 IPS
 
Machine Translation (F32)
100% 390
7.17 IPS
 
Machine Translation (F16)
100% 389
7.16 IPS
 
Machine Translation (I8)
70% 266
4.89 IPS
 

Compare

Set Baseline Geekbench 6 now available