1. Big Data Analytics and HPC Platforms
Lei Huang
Assistant Professor
Computer Science Department
Prairie View A&M University
NPC 2016
Xi’an, China
Oct 29, 2016
Sponsored by NSF

2. The Cloud Computing Research Lab
Goal: build a scalable cloud platform for data computing and analytics
Built on top of Apache Hadoop and Spark
Big data storage, computing, analytics and visualization
Scalable performance
High-level parallel programming languages to facilitate R&D
User-friendly interface
Target to the geophysics and image processing domains

3. Domain-specific Data analytics platform based on Spark and Hadoop
High level languages: Scala, Java and Python
Keep data in distributed memory, and move computation to data
A common data representation (RDD) for parallel transformations
An open and integrated platform with a variety of tools/packages
Balance of performance and productivity

4. The needs of converging HPC with big data
Problems of Spark
RDD only allows one-time write
Inefficient memory usage
GC takes time
Overheads of JVM
Python performance is even worse

5. What Big data needs from HPC
Performance, performance, performance
Data Distributions
Communication optimizations
Memory and cache optimizations for data locality
Dynamic scheduling
Compiler and runtime optimizations

6. The Big Data Challenge In exploration of Geophysics
Dataset sizes for a seismic survey 50 km square:
2D ~1975
50 lines, spaced 1 km apart, each line 50 km w/ 50 m bins
20-fold stack, 6 4 msec sampling
1 M traces, 6 GB
3D ~2000
25 x 25 m bins, 2000 x 2000 lines, 100-fold stack
400 M traces, 1.2 TB
Advanced 3D ~2015
Double bin resolution, double fold, 8 azimuths
8 sec recording for longer offsets
25,600 M traces, >100 TB
Time-Lapse (4D) exploration through production
1 TB /km2 – Eric Green, BP (Mar 2015)
10,000 M traces (multiple passes), 2,500 TB

7. Volumetric Data Analytics Platform Software Stack
Data Analytics Applications
Visualization
Workflow
Data Server
Volumetric Data Analytics SDK
OpenCV/Breeze
VolumeRDD
MLlib
DL4J / Caffe
Spark Streaming
Spark Batch
Spark Interactive
Hadoop HDFS
YARN
Mesos
Cassandra

8. Volumetric Data Analytics SDK
loadFromFile (HDFS)
aggregate
overlap
transpose
repartition
sample
trace
line
applyMap
(usrFunc)
save (HDFS)
get

9. Parallel Processing Templates

10. Template Code Generator
HDFS CG
User’s Parameter
Template Codes
Spark Application
Spark Jobserver CG
Kernel Codes
Database

11. Seismic Data Analytics Process
1. Training:
Label data
Feature Vectors
Seismic volume
Seismic Attributes
Evaluation Metrics
Machine Learning Algorithms
2. Prediction:
Feature Vectors
Seismic volume
Model
Predicted
Results
Seismic Attributes
Seismic Data Analytics SDK
Spark Distributed Processing Engine

12. Machine Learning COMBINES Multiple Attribute Volumes
Each seismic dataset yields a suite of attributes that are possible faulting indicators
Thinned fault likelihood* from amplitude envelope
Dip-direction curvature from amplitude envelope
* Many thanks to the “fault likelihood” attribute computed by Dave Hale’s IPF package from Colorado School of Mines.

13. Geological Faults Classification
Model
Precision
Recall F
Accuracy
SVM
33.37
82.76
47.57
95.56
CNN
66.93
88.51
76.22
97.48

14. Feature Extraction Performance for 100GB data Python: 2 days
Spark: out of memory
C++: 3 hours
C++, OpenMP, NFS: 45 minutes
Spark, C++, OpenMP, NFS: 23 minutes
Spark, C++, OpenMP, local disks: 1.0 minute

15. Visualization for BIG dATA
Data Distributions for both computation and visualization
Built on Open Inventor

16. New Project
NSF EAGER: A Data Flow Approach to Meet the Challenges of Big Data Analytics
Evaluate machine learning algorithms with Fresh Breeze
Potential direction to bring HPC to Big Data

17. acknowledgement
National Science Foundation