CPU：2x Intel® Xeon® Platinum 8369B 32Core @2.9GHz，共64核/节点GPU：8x NVIDIA A100 80GB SXM4内存：32x 64GB DDR4 3200MT/s，共2TB内存/节点硬盘：2x 480GB SATA SSD，4x 3.84TB NVMe SSD计算网络：1x 25Gbps DP Ethernet NIC,4x 100Gbps

北京国际大数据交易所260

Accelerated Conformational Entropy Calculations Using Graphic Processing Units

构象熵分析

GPU加速计算

Conformational entropy calculation, usually computed by normal-mode analysis (NMA) or quasi harmonic analysis (QHA), is extremely time-consuming. Here, instead of NMA or QHA, a solvent accessible surf

NIAID Data Ecosystem100

cublas int8 gemm algorithm

低精度矩阵乘法

GPU加速计算

cublas int8 gemm algorithm

NIAID Data Ecosystem80

PyTorch 1.7.0 + Cuda Toolkit 11.0.221

深度学习

GPU加速计算

PyTorch 1.7.0 + other Torch libraries + Cuda Toolkit 11.0.221

kaggle2021-07-18 更新120

Data for: An Effective Parallelization Algorithm for DEM Generalization based on CUDA