Spiral
@spiraldb.com
Bringing simplicity to your multimodal data.
SPIRAL = Storage Packed In Recursive Arrays and Layers
SPIRAL = Storage Packed In Recursive Arrays and Layers
Reposted by Spiral
Vortex is incredibly exciting, we’ve already made plans months ago to make it the primary format we will be storing our data in on object storage! www.linuxfoundation.org/press/lf-ai-...
LF AI & Data Foundation Hosts Vortex Project to Power High Performance Data Access for AI and Analytics
Contributed by SpiralDB, Vortex is an extensible, next-generation columnar storage format designed for building high-performance, future-proof data systems
www.linuxfoundation.org
August 6, 2025 at 5:32 PM
Vortex is incredibly exciting, we’ve already made plans months ago to make it the primary format we will be storing our data in on object storage! www.linuxfoundation.org/press/lf-ai-...
We managed to accelerate the entire TPC-H (sf=100) suite by 30%, with many of the slowest queries seeing a 2-4x speedup.
Check out the post for the inside scoop 🧊
Check out the post for the inside scoop 🧊
Last month I worked on Apache Iceberg integration for Vortex, the results of which we presented earlier this month at Iceberg Summit.
I wrote a post about my experience bridging our Rust-based system to Iceberg and Spark
spiraldb.com/post/vortex-...
I wrote a post about my experience bridging our Rust-based system to Iceberg and Spark
spiraldb.com/post/vortex-...
Vortex on Ice
Using Vortex to accelerate Apache Iceberg queries up to 4x
spiraldb.com
April 30, 2025 at 2:52 PM
We managed to accelerate the entire TPC-H (sf=100) suite by 30%, with many of the slowest queries seeing a 2-4x speedup.
Check out the post for the inside scoop 🧊
Check out the post for the inside scoop 🧊
If you're at #IcebergSummit, be sure to come see our CEO and Founder @will-manning.bsky.social
present on Turbocharging Apache Iceberg scans with Vortex!
present on Turbocharging Apache Iceberg scans with Vortex!
April 8, 2025 at 3:10 PM
If you're at #IcebergSummit, be sure to come see our CEO and Founder @will-manning.bsky.social
present on Turbocharging Apache Iceberg scans with Vortex!
present on Turbocharging Apache Iceberg scans with Vortex!
Turns out, all researchers should use rust for their reference implementations.
blog.spiraldb.com/alp-rust-is-...
blog.spiraldb.com/alp-rust-is-...
ALP Rust is faster than C++
How well-defined casting semantics in Rust allow for 20-50% faster ALP compression
blog.spiraldb.com
March 18, 2025 at 11:02 AM
Turns out, all researchers should use rust for their reference implementations.
blog.spiraldb.com/alp-rust-is-...
blog.spiraldb.com/alp-rust-is-...
We're starting a London Systems meetup, to give a chance for (software) engineers to share and discuss their work on the underlying systems and that power most of our world - databases, compilers, VMs etc. and we're looking for speakers!
lu.ma/londonsystems
lu.ma/londonsystems
London Systems · Events Calendar
View and subscribe to events from London Systems on Luma. A meetup focus on systems-oriented software engineering topics, from experts to anyone. Focused on systems like compilers, databases, browsers...
lu.ma
January 13, 2025 at 4:53 PM
We're starting a London Systems meetup, to give a chance for (software) engineers to share and discuss their work on the underlying systems and that power most of our world - databases, compilers, VMs etc. and we're looking for speakers!
lu.ma/londonsystems
lu.ma/londonsystems
🌪️📲
*me, embedding @spiraldb.com Vortex files inside the browser and using the most basic tailwinds*
🦋
👐
“Is this full stack development?”
🦋
👐
“Is this full stack development?”
December 20, 2024 at 10:06 PM
🌪️📲
Reposted by Spiral
It's still early days, but initial results suggest DataFusion (Vortex, partitioned) knocks ~15% off the total runtime of DataFusion (Parquet, partitioned) 🚀
This is awesome work! It’s got us curious how much faster we can push ClickBench with DataFusion on Vortex files 🧐
Will report back…
Will report back…
This has been a long time coming. After the concerted efforts many engineers from across companies and across continents, posted some great benchmark results
datafusion.apache.org/blog/2024/11...
datafusion.apache.org/blog/2024/11...
December 6, 2024 at 11:18 PM
It's still early days, but initial results suggest DataFusion (Vortex, partitioned) knocks ~15% off the total runtime of DataFusion (Parquet, partitioned) 🚀
Greetings fellow data folks! 🦋
December 9, 2024 at 4:38 PM
Greetings fellow data folks! 🦋