End-to-End on the GPU: How to Parallelize SQL, Visualization and Machine Learning

Companies are harnessing data in ways we once associated with science fiction. Analysts have access to a plethora of visualization and reporting tools, but considering the vast amount of data businesses collect and limitations of CPUs, end users are forced to design their structures and systems with limitations.

Until now. As the cloud toolkit to analyze data has evolved, GPUs have stepped in to massively parallel SQL, visualization and machine learning. From design to interactivity to user experience, Aaron Williams will cover the end-to-end use cases of GPUs and how this technology is producing measurable, significant outcomes for cloud computing.

Transcript

1. End-to-End on the GPU: How to Vastly Parallel SQL, Visualization and Machine Learning Aaron Williams @_arw_ November 1, 2017
2. “Every business will become a software business, build applications, use advanced analytics and provide Saas services.” - Smart CEO Guy has
3. The Evolution of Data as a Weapon 3 Collect It Make It Actionable Make it Predictive
4. MapD: Extreme Analytics 4 100x Faster Queries MapD Core The world’s fastest columnar database, powered by GPUs + Visualization at the Speed of Thought MapD Immerse A visualization front end that leverages the speed & rendering superiority of GPUs
5. MapD System Architecture Accelerating the existing data infrastructure 5
6. 6 MAPD DEMO
7. MapD Benchmarks Blogger Mark Litwintschik benchmarked MapD on a billion-row taxi data set and found it to be orders-of-magnitude faster than the fastest CPU databases 7 MapD Core: Comparative Query Acceleration* System Q 1 Q 2 Q 3 Q 4 BrytlytDB & 2-node p2.16xlarge cluster 36x 47x 25x 12x ClickHouse, Intel Core i5 4670K 49x 58x 32x 25x Redshift, 6-node ds2.8xlarge cluster 74x 24x 14x 6x BigQuery 95x 38x 6x 6x Presto, 50-node n1-standard-4 cluster 190x 75x 61x 41x Amazon Athena 305x 117x 37x 13x Elasticsearch (heavily tuned) 386x 343x n/a n/a Spark 2.1, 11 x m3.xlarge cluster w/ HDFS 485x 153x 119x 169x Presto, 10-node n1-standard-4 cluster 524x 189x 127x 61x Vertica, Intel Core i5 4670K 685x 607x 203x 132x Elasticsearch (lightly tuned) 1,642x 1,194x n/a n/a Presto, 5-node m3.xlarge cluster w/ HDFS 1,667x 735x 388x 159x Presto, 50-node m3.xlarge cluster w/ S3 2,048x 849x 164x 86x PostgreSQL 9.5 & cstore_fdw 7,238x 3,302x 1,424x 722x Spark 1.6, 5-node m3.xlarge cluster w/ S3 12,571x 5,906x 3,758x 1,884x *All speed comparisons are to the “MapD & 1 Nvidia Pascal DGX-1” benchmark Source: http://tech.marksblogg.com/benchmarks.html
8. Query Compilation with LLVM 8 Traditional DBs can be highly inefficient • each operator in SQL treated as a separate function • incurs tremendous overhead and prevents vectorization MapD compiles queries w/LLVM to create one custom function • Queries run at speeds approaching hand-written functions • LLVM enables generic targeting of different architectures (GPUs, X86, ARM, etc). • Code can be generated to run query on CPU and GPU simultaneously 10111010101001010110101101010101 00110101101101010101010101011101 LLVM
9. Keeping Data Close to Compute MapD maximizes performance by optimizing memory use 9 SSD or NVRAM STORAGE (L3) 250GB to 20TB 1-2 GB/sec CPU RAM (L2) 32GB to 3TB 70-120 GB/sec GPU RAM (L1) 24GB to 256GB 1000-6000 GB/sec Hot Data Speedup = 1500x to 5000x Over Cold Data Warm Data Speedup = 35x to 120x Over Cold Data Cold Data COMPUTE LAYER STORAGE LAYER Data Lake/Data Warehouse/System Of Record Speed Increases Space Increases
10. The Status Quo: Memory Bottlenecks 10 PCIe 4-16GB/s
11. The GPU Open Analytics Initiative Model Standard in-memory format; zero-copy interchange 11 GPU
12. The GPU Open Analytics Initiative Model Standard in-memory format; zero-copy interchange 12
13. Interactive Machine Learning Empowering the People in the Pipeline 13 Personas in Analytics Lifecycle (Illustrative) Business Analyst Data Scientist Data Engineer IT Systems Admin Data Scientist / Business Analyst Data Preparation Data Discovery & Feature Engineering Model & Validate Predict Operationalize Monitoring & Refinement Evaluate & Decide GPUs MapD H20.ai MapD
14. Try MapD It’s free and it’s easy 14 Play with the live demos: https://www.mapd.com/demos/ Download the Community Edition: https://www.mapd.com/platform/download-community/ Join our forums: https://community.mapd.com/ Review these slides: https://speakerdeck.com/mapd
15. AWS Credits Available 15 Free GPU Compute! We’re looking for interesting use cases. Email Aaron Williams (aaron@mapd.com) with your ideas!
16. Aaron Williams VP of Global Community @_arw_ aaron@mapd.com /in/aaronwilliams/ /williamsaaron