Geekbench ML Score

23432
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date April 22 2024 08:47 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model ASUS System Product Name
Motherboard ASUSTeK COMPUTER INC. TUF GAMING B650-PLUS WIFI
Power PlanBalanced
CPU Information
Name AMD Ryzen 7 7800X3D
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 25 Model 97 Stepping 2
Base Frequency 4.20 GHz
Cluster 18 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache32.0 KB x 8
L2 Cache1.00 MB x 8
L3 Cache96.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon RX 7900 XT

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 13877
2.60 KIPS
 
Image Classification (F16)
100% 13941
2.61 KIPS
 
Image Classification (I8)
100% 11865
2.22 KIPS
 
Image Segmentation (F32)
100% 15038
251.2 IPS
 
Image Segmentation (F16)
100% 15109
252.3 IPS
 
Image Segmentation (I8)
98% 13993
233.7 IPS
 
Pose Estimation (F32)
100% 268201
324.8 IPS
 
Pose Estimation (F16)
100% 267758
324.2 IPS
 
Pose Estimation (I8)
100% 230469
279.1 IPS
 
Object Detection (F32)
100% 5257
392.5 IPS
 
Object Detection (F16)
100% 5184
387.0 IPS
 
Object Detection (I8)
56% 6313
471.3 IPS
 
Face Detection (F32)
100% 42240
502.2 IPS
 
Face Detection (F16)
100% 41883
498.0 IPS
 
Face Detection (I8)
89% 36164
430.0 IPS
 
Depth Estimation (F32)
100% 73371
569.0 IPS
 
Depth Estimation (F16)
100% 75353
584.4 IPS
 
Depth Estimation (I8)
95% 61476
476.7 IPS
 
Style Transfer (F32)
100% 223363
293.8 IPS
 
Style Transfer (F16)
100% 215463
283.4 IPS
 
Style Transfer (I8)
98% 203893
268.2 IPS
 
Image Super-Resolution (F32)
100% 23237
829.9 IPS
 
Image Super-Resolution (F16)
100% 23216
829.1 IPS
 
Image Super-Resolution (I8)
99% 18750
669.6 IPS
 
Text Classification (F32)
100% 3743
5.38 KIPS
 
Text Classification (F16)
100% 3783
5.44 KIPS
 
Text Classification (I8)
98% 2554
3.67 KIPS
 
Machine Translation (F32)
100% 4858
89.4 IPS
 
Machine Translation (F16)
100% 4880
89.8 IPS
 
Machine Translation (I8)
70% 3233
59.5 IPS
 

Compare

Set Baseline Geekbench 6 now available