NVIDIA Q2 FY2021 Financial Summary
NVIDIA DGX SUPERPOD SETS ALL 8 AT SCALE AI
RECORDS
Under 18 Minutes To Train Each MLPerf Benchmark
Translation (Non-recurrent) Transformer
Translation (Recurrent) GNMT
XXL XX
0.6 (480 A100)
0.7 (1024 A100)
0.8 (1840 A100)
Image Classification ResNet-50 v.1.5
0.8 (1024 A100)
Object Detection (Light Weight) SSD
XX
0.8 (2048 A100)
NLP BERT
Recommendation DLRM
Object Detection (Heavy Weight) Mask R-CNN
Reinforcement Learning MiniGo
0
XX
XX
XX
3.3 (8 A100)
Time to Train (Lower is Better)
Commercially Available Solutions
10.5 (256 A100)
17.1 (1792 A100)
5
10
15
20
25
Time to Train (Minutes)
28.7 (16 TPUv3)
30
0
NVIDIA A100
NVIDIA V100
■Google TPUv3
Huawei Ascend
35
56.7
(16 TPUv3)
40
X = No result submitted
MLPerf 0.7 Performance comparison at Max Scale. Max scale used for NVIDIA A100, NVIDIA V100, TPUV3 and Huawei Ascend for all applicable benchmarks. | MLPerf ID at Scale: : Transformer: 0.7-30, 0.7-52, GNMT: 0.7-34, 0.7-54, ResNet-50 v1.5: 0.7-37, 0.7-55,
0.7-1, 0.7-3, SSD: 0.7-33, 0.7-53, BERT: 0.7-38, 0.7-56, 0.7-1, DLRM: 0.7-17, 0.7-43, Mask R-CNN: 0.7-28, 0.7-48, MiniGo: 0.7-36, 0.7-51 | MLPerf name and logo are trademarks. See www.mlperf.org for more information.View entire presentation