Download presentation
Presentation is loading. Please wait.
Published byElissa Hyatt Modified over 10 years ago
1
Tesla 101
2
2 CUDA GPU Accelerates Computing The Right Processor for the Right Task
3
3 How CPUs and GPUs Work void serial_function(… ) {... } void parallel_function(float... ) {... } void main( ) {... parallel_function >(..); serial_function(..);... } CUDA Application Code Heavy parallel workload on the GPU Other serial routines on the CPU
4
GPU Performance Far Outstrips CPUs Double Precision: NVIDIA GPU Double Precision: x86 CPU
5
5 Much More Power Efficient Tesla GPUs CPU Only
6
6 Transformational for Customers 4 Months 2 Years $1M Budget ~120 Compute Nodes~45 CPU + GPU Nodes Time to Discovery
7
7 #1 Numerical Computation MATLAB #1 Molecular Dynamics AMBER #1 Engineering Simulation ANSYS #1 3D DCC 3ds Max
8
Science Category GPU Port Complete GPU Port Started & Results Published Early GPU Port Molecular Dynamics NAMD AMBER DL_POLY CHARMM GROMACS Chemistry LAMMPS MOLPRO GAMESS CPMD DESMOND GAUSSIAN Fluid Dynamics OpenFOAM S3D FEFLO ANSYS CFD Structural Mechanics ANSYS Mechanical Simulia Abaqus/Std (beta) CTH LS-DYNA Implicit MSC Marc PAM-CRASH IMPLICIT MSC Nastran Earth Science WRF HOMME, HYCOM COSMO-2, PFLOTRAN ASUCA CCSM/CESM Material Science PARATEC LAMMPS PWscf CPMD VASP GAUSSIAN Oil & Gas Schlumberger PetrelVoxelGeo Paradigm Analytics Matlab Mathworks Others GADGET2 GTC MILC DENOVO Leading HPC Applications Ramping
9
9 CUDA Taking HPC by Storm 100,000 Active GPU Developers 400 Universities Teaching CUDA 1000+ Clusters Worldwide 35+ CUDA Research Centers 200,000,000 CUDA GPUs Deployed 100% OEMs offer CUDA GPUs
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.