Introduction to Scientific Visualization

1
Introduction toScientific Visualization

• Paul Navrátil
• 26 May 2009

2
Scientific Visualization
The purpose of computing is insight not
numbers. -- R. W. Hamming (1961)
3
(No Transcript)
4
(No Transcript)
5
(No Transcript)
6
Visualization Allows Us to See the Science
Geometric Primitives
Pixels
Raw Data
01001101011001 11001010010101 00101010100110 11101
101011011 00110010111010
Application
Render
7
Schedule

• Scientific Visualization Overview
• Visualization Methods
• Visualization Resources
• Demonstrations
• Lab
• Remote Visualization on Spur
• Visualization using ParaView
• Visualization using VisIt

8
Getting from Data to Insight
Data Representation
Visualization Primitives
Graphics Primitives
Display
Iterationand Refinement
9
I, We, They Development Path
Simulation Data
I Data Exploration
We Collaboration
They Communication
Iterationand Refinement
10
Visualization Process Summary

• The primary goal of visualization is insight
• A picture is worth not just 1000 words,but
  potentially tera- or peta-bytes of data
• Larger datasets demand not just visualization,
  but advanced visualization resources and
  techniques
• Visualization system technology improves with
  advances in GPUs and LCD technology
• Visualization software slower to adapt

11
Types Input Data

• Point / Particle
• N-body simulation
• Regular grid
• Medical scan
• Curvilinear grid
• Engineering model
• Unstructured grid
• Extracted surface

12
Types of Input Data

• Point scattered values with no defined
  structure

13
Types of Input Data

• Grid regular structure, all voxels (cells)
  are the same size and shape

14
Types of Input Data

• Curvilinear regularly grided mesh shaping
  function applied

15
Types of Input Data

• Unstructured grid irregular mesh typically
  composed of tetrahedra, prisms, pyramids, or
  hexahedra.

16
Visualization Operations

• Surface Shading (Pseudocolor)
• Isosufacing (Contours)
• Volume Rendering
• Clipping Planes
• Streamlines

17
Surface Shading (Pseudocolor)

• Given a scalar value at a point on the surface
  and a color map,
• find the corresponding color (and opacity) and
  apply it to the surface point.
• Most common operation, often combined with other
  ops

18
Isosurfaces (Contours)

• Plot the surface for a given scalar value.
• Good for showing known values of interest
• Good for sampling through a data range

19
Volume Rendering

• Expresses how light travels through a volume
• Color and opacity controlled by transfer function
• Smoother transitions than isosurfaces

20
Clipping Planes

• Extract a plane from the volume to show features
• Hide part of dataset to focus on features

21
Particle Traces (Streamlines)

• Given a vector field, extract a trace that
  follows that trajectory defined by the vector.
• Pnew Pcurrent VPDt
• Streamlines trace in space
• Pathlines trace in time

22
Visualization Resources

• Personal machines
• Most accessible, least powerful
• Projection systems
• Seamless image, high purchase and maintenance
  costs
• Tiled-LCD displays
• Lowest per-pixel costs, bezels divide image
• Remote visualization
• Access to high-performance system, latency can
  affect user experience

23
ACES Visualization Lab 2000-2007
5x2 Tiled Display 6400x2048
3x1 Tiled Display 2816x1024

• 2900 Square Feet of Laboratory Space
• Single User Environment
• Costly to Maintain
• Steep Learning Curve for Users

24
Updated Vis lab

• 15x5 30-inch Dell tiled-LCD display 307
  Megapixels
• Sony 4K (4x 1080p) projector and screen
• Collaboration Room
• high end workstations

25
Stallion

• 15x5 tiled display of Dell 30-inch LCDs
• 307M pixel resolution, 4.61 aspect ratio
• 24 nodes,100 processing cores over 36 GB of
  graphics memory 108 GB of system memory
• 6TB shared file system

26
Stallion
27
Bronco

• Dell Precision 690 workstation
• Sony SRX-S105 projector, 5000 lumens
• 20 ft. x 11 ft. screen
• 8.8 Mpixel (4096 x 2160) image resolution

28
Bronco
29
Collaboration Room (Saddle)

• Dell Precision 690 workstation
• Dell 5100 DLP projector, 10 ft. x 7.5 ft. display

30
Colt - Visualization System

• Dell Visualization cluster
• 10 Dell precision 690 workstations
• 40 processor cores (2.66 GHz Xeon), NVIDIA G80
  graphics
• 3x3 30 Dell LCDs
• InfiniBand interconnect
• 36 million pixel display

31
Spur - Visualization System

• 128 cores, 1 TB distributed memory, 32 GPUs
• 1 Sun Fire X4600 server
• 8 AMD Opteron dual-core CPUs
• 256 GB memory
• 4 NVIDIA FX5600 GPUs
• 7 Sun Fire X4440 servers
• 4 AMD Opteron quad-core CPUs per node
• 128 GB memory per node
• 4 NVIDIA FX5600 GPUs per node
• Shares Ranger interconnect and file system

32
Obrigado!pnav_at_tacc.utexas.edu