Geekbench ML Score

28584
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 15 2024 06:57 PM
Views 3

System Information

System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model EVGA Corp. Z690 CLASSIFIED
Motherboard EVGA Corp. Z690 CLASSIFIED
Power PlanBalanced
CPU Information
Name Intel Core i9-13900K
Topology 1 Processor, 24 Cores, 32 Threads
Identifier GenuineIntel Family 6 Model 183 Stepping 1
Base Frequency 3.00 GHz
Cluster 18 Cores
Cluster 216 Cores
L1 Instruction Cache64.0 KB x 16
L1 Data Cache32.0 KB x 16
L2 Cache4.00 MB x 4
L3 Cache36.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 4090

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 12297
2.30 KIPS
 
Image Classification (F16)
100% 13610
2.55 KIPS
 
Image Classification (I8)
100% 11331
2.12 KIPS
 
Image Segmentation (F32)
100% 19317
322.6 IPS
 
Image Segmentation (F16)
100% 19421
324.4 IPS
 
Image Segmentation (I8)
98% 17300
288.9 IPS
 
Pose Estimation (F32)
100% 284746
344.8 IPS
 
Pose Estimation (F16)
100% 284511
344.5 IPS
 
Pose Estimation (I8)
100% 239346
289.8 IPS
 
Object Detection (F32)
100% 8090
604.0 IPS
 
Object Detection (F16)
100% 8321
621.2 IPS
 
Object Detection (I8)
54% 7659
571.8 IPS
 
Face Detection (F32)
100% 42238
502.2 IPS
 
Face Detection (F16)
100% 41574
494.3 IPS
 
Face Detection (I8)
88% 36651
435.8 IPS
 
Depth Estimation (F32)
100% 80068
620.9 IPS
 
Depth Estimation (F16)
100% 79675
617.9 IPS
 
Depth Estimation (I8)
95% 62970
488.3 IPS
 
Style Transfer (F32)
100% 488247
642.2 IPS
 
Style Transfer (F16)
100% 487537
641.3 IPS
 
Style Transfer (I8)
98% 425201
559.3 IPS
 
Image Super-Resolution (F32)
100% 53517
1.91 KIPS
 
Image Super-Resolution (F16)
100% 53948
1.93 KIPS
 
Image Super-Resolution (I8)
99% 39935
1.43 KIPS
 
Text Classification (F32)
100% 3244
4.66 KIPS
 
Text Classification (F16)
100% 3386
4.87 KIPS
 
Text Classification (I8)
98% 1891
2.72 KIPS
 
Machine Translation (F32)
100% 4836
89.0 IPS
 
Machine Translation (F16)
100% 4833
88.9 IPS
 
Machine Translation (I8)
70% 2680
49.3 IPS
 

Compare

Set Baseline Geekbench 6 now available