株式会社HPCテック | NVIDIA A100
NVIDIA RTX 3090 FE OpenSeq2Seq FP16 Mixed Precision - ServeTheHome
Choose FP16, FP32 or int8 for Deep Learning Models
Apache MXNet リリースに追加された新しい NVIDIA Volta GPU と Sparse Tensor のサポート | Amazon Web Services ブログ
FP16 Throughput on GP104: Good for Compatibility (and Not Much Else) - The NVIDIA GeForce GTX 1080 & GTX 1070 Founders Editions Review: Kicking Off the FinFET Generation
NVIDIA's 80-billion transistor H100 GPU and new Hopper Architecture will drive the world's AI Infrastructure - HardwareZone.com.sg
Testing AMD Radeon VII Double-Precision Scientific And Financial Performance – Techgage
Titan V Deep Learning Benchmarks with TensorFlow
More In-Depth Details of Floating Point Precision - NVIDIA CUDA - PyTorch Dev Discussions
TensorFlow Performance with 1-4 GPUs -- RTX Titan, 2080Ti, 2080, 2070, GTX 1660Ti, 1070, 1080Ti, and Titan V | Puget Systems
Caffe2 adds 16 bit floating point training support on the NVIDIA Volta platform | Caffe2
FP16 Demotion: A Trick Used by ATI to Boost Benchmark Score Says NVIDIA | Geeks3D
NVIDIA Tesla T4 ResNet 50 Training FP16 - ServeTheHome
Hardware for Deep Learning. Part 3: GPU | by Grigory Sapunov | Intento
Introducing native PyTorch automatic mixed precision for faster training on NVIDIA GPUs | PyTorch
TensorFlowでディープラーニング性能をGPU別にベンチマーク比較 | パソコン工房 NEXMAG
Titan V Deep Learning Benchmarks with TensorFlow
NVIDIAが語るVoltaとTuring、最新GPUはこう使おう：GTC Japan 2018（3/4 ページ） - EE Times Japan
後藤弘茂のWeekly海外ニュース】NVIDIAが次世代グラフィックスのために作ったGPU「GeForce RTX」ファミリー - PC Watch
FP16 Throughput on GP104: Good for Compatibility (and Not Much Else) - The NVIDIA GeForce GTX 1080 & GTX 1070 Founders Editions Review: Kicking Off the FinFET Generation
AMD FidelityFX Super Resolution FP32 fallback tested, native FP16 is 7% faster - VideoCardz.com
Dell Precision T7920 Dual Intel Xeon Workstation Review - Page 5 of 9 - ServeTheHome
Hardware Recommendations for Machine Learning / AI | Puget Systems
