I'm also a little surprised at the speedup using SIMD. If it's RAM constrained, and it clearly is because it scales with the number of memory channels, then I completely fail to understand how instructions - which are bloody fast to execute (SIMD or not) compared to slow RAM access - could benefit you. Both SIMD or not should be waiting on memory AFAICS. Except you clearly do get a big speedup, could anyone enlighten me on this?
1) How does this compare to BlazingDB/MapD/etc, especially in queries on <some benchmark> per $ per hour on AWS?
2) I don't see a way to give you money. What ensures that QuestDB will be around in the future if I architect my data pipelines around this product?
1) We didn't compare directly, but our aim is to squeeze as much performance out of hardware as possible to minimize cloud cost. If we are not the best at this right now - we are going to be the best.
2) We are VC funded with 24 months runway. The product is Open Source Apache 2.0 and will remain as such forever. Any future commercial offering will use open source product as a library.
Amazing work either way. The space of databases can never have too much competition.
JITs are really good at doing speculative optimization then deoptimizing if the optimization failed. Couldn't DBs speculatively offload to the gpu (with coherent memory (HSA, etc) access) at least under some constraints/patterns?
On the contrary, it will hopefully help us gain some popularity by allowing any developer to access latency levels only seen in trading. We hope that QuestDB will allow them to stop worrying about database performance bottlenecks.
High performance databases have a reputation of being inaccessible. They are expensive, closed-source, and require complex proprietary languages.
We have made our code available under Apache 2.0. Under this new release, QuestDB leverages SIMD instructions, vectorizations and parallel execution to achieve performance figures at the top of the high-performance databases. Results are shown in our blog post.
I sincerely hope that you will find this helpful, and that this will unlock new possibilities! In the meantime, we will carry on working on QuestDB, adding more features, and taking this speed to more query types. Feel free to join us on slack or Github if you want to participate.