Lunch & Learn: Visualizing Billions of Data Points with GPUs

Nearly a decade ago, disk-based data analytics platforms began to be superseded by in-memory systems, which offered orders-of-magnitude more bandwidth than their predecessors. This technological sea change was driven in large part by memory prices falling to the point where it became viable to hold large working sets of data entirely in RAM. Today we are witness to a similar paradigm shift as analytics workloads are increasingly shifted from CPUs to GPUs, which possess much higher compute and memory bandwidth than CPUs. 8 GPUs and 256GB of GPU VRAM can be fit into a single server, and while CPUs have seen relatively minimal memory bandwidth increases over the last several years, GPUs are rapidly moving to stacked DRAM (High-Bandwidth Memory), meaning that by next year a single GPU will possess over a terabyte per second of bandwidth.

Using the MapD data analytics platform as an example, Aaron Williams will explain why data scientists and analysts leveraging GPUs will have an immense advantage over CPU alternatives. He will show how MapD's open source GPU database and Immerse visualization platform leverage the massive parallelism and memory bandwidth of multiple GPUs to execute SQL queries and render complex visualizations with billions of rows in milliseconds, literally orders of magnitude faster than CPU systems. Aaron will also explain and demonstrate the 3 APIs available to developers who want to build their own custom applications that take advantage of the speed of the GPUs.

MapD has collaborated with researchers at the Harvard Center for Geographic Analysis to provide true interactive access to NWM predictions for stream flow and ground saturation across the entire continental US. Aaron will briefly cover MapD’s GPU-based analytics platform and how it has advanced the visualization and analysis of geospatial data, using the NWM as a use case.

Transcript

1. © MapD 2018 Lunch & Learn: Visualizing Billions of Data Points with GPUs DFW Data Visualization & Infographics | June 20, 2018
2. © MapD 2018 Aaron Williams VP of Global Community @_arw_ aaron@mapd.com /in/aaronwilliams/ /williamsaaron slides: https://speakerdeck.com/mapd
3. © MapD 2018 © MapD 2018 3 “Every business will become a software business, build applications, use advanced analytics and provide SaaS services.” - Smart CEO Guy has
4. Core Density Makes a Huge Difference 4 GPU Processing CPU Processing 40,000 Cores 20 Cores *fictitious example Latency Throughput CPU 1 ns per task (1 task/ns) x (20 cores) = 20 tasks/ns GPU 10 ns per task (0.1 task per ns) x (40,000 cores) = 4,000 task per ns Latency: Time to do a task. | Throughput: Number of tasks per unit time.
5. © MapD 2018 MapD is the analytics platform created for GPUs
6. © MapD 2018 © MapD 2018 6 DEMO
7. © MapD 2018 Advanced memory management Three-tier caching to GPU RAM for speed and to SSDs for persistent storage 7 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
8. © MapD 2018 MapD Core: Query Compilation with LLVM
9. © MapD 2018 MapD Immerse: Hybrid Rendering
10. © MapD 2018 And Now … Native Geospatial! 10 First Data Types • POINT • LINE • POLYGON First Functions • DISTANCE • CONTAINS Get Involved • Roadmap Being Discussed MapD (OSS) Working Group geo-wg@mapd.com • Beta Available Now Email Aaron - aaron@mapd.com
11. © MapD 2018 Categories of common MapD use cases 11 Operational Analytics • Thwart Banking Fraud • Scan for Cyber Threats • Fine-tune Advertising • Maintain the Utility Grid Geospatial Analytics • Monitor Networks • Ready Logistics • Forecast Micro-weather Data Science • Model Financial Markets • Predict Maintenance • Predict Staffing Levels
12. © MapD 2018 The GPU Open Analytics Initiative (GOAI) Creating common data frameworks to accelerate data science on GPUs 1 2 /mapd/pymapd /gpuopenanalytics/pygdf
13. © MapD 2018 © MapD 2018 • mapd.com/demos Play with our demos • mapd.cloud Get a MapD instance in less than 60 seconds • mapd.com/platform/download-community/ Download the Community Edition • community.mapd.com Ask questions and share your experiences 13 Next Steps
14. © MapD 2018 Aaron Williams VP of Global Community @_arw_ aaron@mapd.com /in/aaronwilliams/ /williamsaaron slides: https://speakerdeck.com/mapd Thank you! Questions?