Geekbench AI Score

31709
Single Precision Score
44413
Half Precision Score
24044
Quantized Score
Geekbench AI 1.1.0 for Windows AVX2

Result Information

Upload Date November 07 2024 07:10 PM
Views 2

System Information

AI Information
Framework ONNX
Backend DirectML
Device NVIDIA L40-48Q
System Information
Operating System Microsoft Windows 11 Enterprise (64-bit)
Model VMware, Inc. VMware20,1
Motherboard Intel Corporation 440BX Desktop Reference Platform
Power PlanBalanced
CPU Information
Name AMD EPYC 9534
Topology 1 Processor, 64 Cores
Identifier AuthenticAMD Family 25 Model 17 Stepping 1
Base Frequency 2.45 GHz
Cluster 164 Cores
Memory Information
Size 128.00 GB
Type DRAM

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 11149
2.07 KIPS
 
Image Classification (HP)
99% 14152
2.64 KIPS
 
Image Classification (Q)
100% 9453
1.76 KIPS
 
Image Segmentation (SP)
100% 21465
348.0 IPS
 
Image Segmentation (HP)
100% 26675
432.4 IPS
 
Image Segmentation (Q)
98% 20470
332.8 IPS
 
Pose Estimation (SP)
100% 253006
295.2 IPS
 
Pose Estimation (HP)
100% 592380
691.2 IPS
 
Pose Estimation (Q)
97% 224529
262.9 IPS
 
Object Detection (SP)
100% 16107
1.28 KIPS
 
Object Detection (HP)
100% 20416
1.62 KIPS
 
Object Detection (Q)
89% 12962
1.04 KIPS
 
Face Detection (SP)
100% 43937
522.1 IPS
 
Face Detection (HP)
100% 54531
648.0 IPS
 
Face Detection (Q)
97% 36964
440.7 IPS
 
Depth Estimation (SP)
100% 80491
620.1 IPS
 
Depth Estimation (HP)
99% 132515
1.02 KIPS
 
Depth Estimation (Q)
76% 58950
473.9 IPS
 
Style Transfer (SP)
100% 487469
626.6 IPS
 
Style Transfer (HP)
100% 960926
1.24 KIPS
 
Style Transfer (Q)
98% 420764
542.6 IPS
 
Image Super-Resolution (SP)
100% 47976
1.77 KIPS
 
Image Super-Resolution (HP)
100% 62914
2.32 KIPS
 
Image Super-Resolution (Q)
99% 36652
1.36 KIPS
 
Text Classification (SP)
100% 2658
3.55 KIPS
 
Text Classification (HP)
99% 3177
4.24 KIPS
 
Text Classification (Q)
97% 1728
2.31 KIPS
 
Machine Translation (SP)
100% 4794
82.6 IPS
 
Machine Translation (HP)
100% 4713
81.2 IPS
 
Machine Translation (Q)
60% 1975
44.1 IPS
 

Compare

Set Baseline Geekbench 6 now available