Geekbench ML Score

10082
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 17 2024 06:16 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model Acidanthera iMacPro1,1
Motherboard Acidanthera Mac-7BA5B2D9E42DDD94
Power PlanHchstleistung
CPU Information
Name Intel Core i5-12600K
Topology 1 Processor, 10 Cores, 16 Threads
Identifier GenuineIntel Family 6 Model 151 Stepping 2
Base Frequency 2.00 GHz
Cluster 16 Cores
Cluster 24 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache48.0 KB x 8
L2 Cache1.25 MB x 2
L3 Cache20.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon RX 5700 XT

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5607
1.05 KIPS
 
Image Classification (F16)
100% 5494
1.03 KIPS
 
Image Classification (I8)
99% 4841
905.9 IPS
 
Image Segmentation (F32)
100% 5805
96.9 IPS
 
Image Segmentation (F16)
100% 5760
96.2 IPS
 
Image Segmentation (I8)
98% 5198
86.8 IPS
 
Pose Estimation (F32)
100% 92517
112.0 IPS
 
Pose Estimation (F16)
100% 89214
108.0 IPS
 
Pose Estimation (I8)
100% 76657
92.8 IPS
 
Object Detection (F32)
100% 2914
217.5 IPS
 
Object Detection (F16)
100% 3125
233.3 IPS
 
Object Detection (I8)
67% 3338
249.2 IPS
 
Face Detection (F32)
100% 16543
196.7 IPS
 
Face Detection (F16)
100% 16805
199.8 IPS
 
Face Detection (I8)
89% 13472
160.2 IPS
 
Depth Estimation (F32)
100% 33383
258.9 IPS
 
Depth Estimation (F16)
100% 35430
274.8 IPS
 
Depth Estimation (I8)
95% 22106
171.4 IPS
 
Style Transfer (F32)
100% 94418
124.2 IPS
 
Style Transfer (F16)
100% 94835
124.7 IPS
 
Style Transfer (I8)
98% 82351
108.3 IPS
 
Image Super-Resolution (F32)
100% 10955
391.2 IPS
 
Image Super-Resolution (F16)
100% 11068
395.3 IPS
 
Image Super-Resolution (I8)
99% 8321
297.2 IPS
 
Text Classification (F32)
100% 1544
2.22 KIPS
 
Text Classification (F16)
100% 1513
2.18 KIPS
 
Text Classification (I8)
98% 1019
1.47 KIPS
 
Machine Translation (F32)
100% 2620
48.2 IPS
 
Machine Translation (F16)
100% 2581
47.5 IPS
 
Machine Translation (I8)
69% 2189
40.3 IPS
 

Compare

Set Baseline Geekbench 6 now available