Fast Software Designed for Fast Hardware: 100x faster SQL, Python Pandas and Geospatial Visualizations Using OmniSci on GPUs

There is a great deal of excitement and hype around GPU computing, and with good reason. The implications of GPU technology for machine and deep learning have already been enormous; they’re capable of performing the high-end computations that are the staple of modern data science. At this meetup, NVIDIA and MapD will demonstrate the use of GPUs and help answer the questions: what's causing the shift to GPUs? How are they are fundamentally changing the analytics space? What are the relevant business applications?

Transcript

1. Fast Software Designed for Fast Hardware: 100x faster SQL, Python Pandas and Geospatial Visualizations Using OmniSci on GPUs Minneapolis | October 4, 2018 slides: https://speakerdeck.com/mapd
2. © OmniSci 2018 © OmniSci 2018
3. © OmniSci 2018 Aaron Williams VP, Global Community at OmniSci @_arw_ aaron@omnisci.com /in/aaronwilliams/ /williamsaaron
4. The Fastest Software Designed for the Fastest Hardware HARNESS GPUs
5. © OmniSci 2018 5
6. D E M O S https://www.omnisci.com/demos/
7. © OmniSci 2018 7 GPU Parallelism Drives Fast Analytics at Scale High Memory Bandwidth Native Rendering Pipeline Supercomputer Processing
8. © OmniSci 2018 8 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 Advanced Memory Management
9. © OmniSci 2018 9 MapD Core: Query Compilation with LLVM 10111010101001010110101101010101 00110101101101010101010101011101 Traditional DBs can be highly inefficient • Each operator in SQL treated as a separate function • Incurs tremendous overhead and prevents vectorization OmniSci 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
10. © OmniSci 2018 10 GPU Data Frames /mapd/pymapd /gpuopenanalytics/pygdf OMNISCI CORE
11. https://www.jowanza.com/blog/2018/9/8/real-time- station-tracking-ford-gobike-and-mapd twitter: @jowanza Another Kafka Example
12. © OmniSci 2018 TOP-TIER VENTURE BACKING USED BY 100+ GLOBAL ORGS $37 MILLION IN FUNDING OPEN-SOURCE COMMUNITY About OmniSci 12
13. © OmniSci 2018 Aaron Williams VP, Global Community at OmniSci @_arw_ aaron@omnisci.com /in/aaronwilliams/ /williamsaaron Thank you! Any Questions?