Adam Gartenberg's Blog

Business Analytics and Optimization, IBM and Social Marketing

DB2 10.5 with BLU Acceleration: Now Available

"We were very impressed with the performance and simplicity of BLU.  We found that some queries achieved an almost 100x speed up with literally no tuning!"- Lennart Henäng, IT Architect, Handelsbanken

It's been over two months since we first shared the details on the new  DB2 10.5 with BLU Acceleration, and a week since the general availability of the release, and so I thought this would be a good time to check in again with some more details on what makes BLU Acceleration such a big deal.

BLU Acceleration
is based on seven "big ideas" - innovations that have been added to DB2 to lower operation costs, optimize hardware, and deliver extreme performance.  Each of these big ideas is a technology capability that provides business value and together make up what we refer to as BLU Acceleration.  
1.        Column Store – By storing table data in column organized format we not only save significantly on storage costs but we also improve I/O and memory efficiency.  This can both lower operating costs as well as increase performance of queries substantially.
2.        Simple to Implement and Use – With BLU Acceleration you just create the column organized table and then load and go. That’s it – no tuning, no indexes, etc. This lowers administration and development costs significantly.
3.        Actionable Compression – by using compression and sophisticated encoding algorithms, DB2 can enable you to save significantly on storage costs, including power, cooling, and management of that storage. In addition to the lower costs, the compression algorithms used exploit processor characteristics to improve performance. The compression we use works with a register friendly encoding technique to improve processor efficiency.
4.        Deep Hardware Instruction Exploitation – Single Instruction Multiple Data (SIMD) capabilities mean that DB2 with BLU Acceleration can apply a single instruction to many data elements simultaneously, effectively multiplying the performance of the processor.
5.        Core Friendly Parallelism – With DB2 with BLU Acceleration we pay very close attention to multi-core parallelism. DB2 with BLU Acceleration is designed from the ground up to take advantage of the cores you have and to always drive multi-core parallelism for the queries you have. This is all done in shared memory – this is not DPF parallelism.
6.        Optimal Memory Caching – With row organized tables, a full table scan ends up putting data into the bufferpool that is often not required. For column organized tables, if there are columns that are involved in joins or other predicates in many queries then we can pack the bufferpool full of those columns while keeping other columns out of memory if they are not regularly used. This improves performance and optimized the memory available
7.        Data Skipping – By keeping track of which pages of data contain which column values, we can avoid a lot of I/O and query processing by simply skipping data we already know would not qualify for the query

But don't just take my word for it.  Here is how some people much closer to DB2 BLU are describing the benefits and reasons to upgrade:

There are also a number of recorded webcasts with technical tours and deep dives on DB2 10.5 with BLU Acceleration over on the IDUG website that I would highly encourage you to check out, including the following:
  • DB2 Tech Talk: "Introduction and Technical Tour: DB2 10.5 with BLU Acceleration" with IBM Distinguished Engineer Berni Schiefer
  • DB2 Tech Talk: "Deep Dive on BLU Acceleration in DB2 10.5, Super Analytics Super Easy”  with IBM Distinguished Engineer Sam Lightstone