Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Alenka: GPU database engine

github.com

Post reply on HN
Print view View original

11–20 of 54 posts

Re: Alenka: GPU database engine

#11

Post by krona »

nrjdhsbsid wrote: post #9
MayeulC wrote: post #7

Earlier quoted context omitted.

Apache 2.0, going by the source files. Edit: though the "bison" files are GPLv3+, son It might be a safer bet.

Wot? Somebody threw up this "database" without even checking the licenses? I'm sure it works great

fyi, the Bison GPL exception is in its documentation: https://www.gnu.org/software/bison/manual/html_node/Conditio...

The exception is littered throughout bison generated code: "This special exception was added by the Free Software Foundation..."

Re: Alenka: GPU database engine

#12

Post by nrjdhsbsid »

I keep hearing the promise of GPU databases but they don't seem to be terribly useful for most real world workloads.

It reminds me of the big hoopla for GPU h264 encoders. When they came out everyone realized the quality was worse and not much faster.

Some things don't lend themselves to parallel processing, notably anything linear like transactions.

I mean yeah the GPU can sort a hundred billion items a second but how often do you really need to sort that many items using a database? In 99.9% of uses you have indexing or limits on the number of results.

Just saying, this program looks more like a stream processing platform with a SQL-like frontend than a full database

Re: Alenka: GPU database engine

#13

Post by nrjdhsbsid »

krona wrote: post #11
nrjdhsbsid wrote: post #9

Earlier quoted context omitted.

Wot? Somebody threw up this "database" without even checking the licenses? I'm sure it works great

fyi, the Bison GPL exception is in its documentation: https://www.gnu.org/software/bison/manual/html_node/Conditio... The exception is littered throughout bison generated code: "This special exception was added by the Free Software Foundation..."

Fair point, I'll leave my comment up so yours make sense. The downvotes should be fun :)

Re: Alenka: GPU database engine

#14

Post by dagw »

MayeulC wrote: post #8
gcp wrote: post #3

Should say CUDA instead of GPU.

That's true. Anyone knows how good are the CUDA -> OpenCL translators? Or has an open CUDA compiler has been written (LLVM front end, likely)? So, in a nutshell, is it possible to run CUDA on a non-nVidia GPU nowadays (AMD or else)?

otoy.com claimed to have developed a CUDA -> OpenCL and CUDA -> CPU compiler, but they've not released anything and they've been very quite about it for the past 9 month or so.

There's also this: https://github.com/vtsynergy/CU2CL but I know nothing about it.

Re: Alenka: GPU database engine

#15

Post by floatboth »

MayeulC wrote: post #8
gcp wrote: post #3

Should say CUDA instead of GPU.

That's true. Anyone knows how good are the CUDA -> OpenCL translators? Or has an open CUDA compiler has been written (LLVM front end, likely)? So, in a nutshell, is it possible to run CUDA on a non-nVidia GPU nowadays (AMD or else)?

https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/blo...

CUDA → HIP translator. HIP is an abstraction over CUDA and AMD's HCC: https://github.com/RadeonOpenCompute/hcc/wiki

Re: Alenka: GPU database engine

#17

Post by zer0t3ch »

nrjdhsbsid wrote: post #12

I keep hearing the promise of GPU databases but they don't seem to be terribly useful for most real world workloads. It reminds me of the big hoopla for GPU h264 encoders. When they came out everyone realized the quality was worse and not much faster. Some things don't lend themselves to parallel processing, notably anything linear like transactions. I mean yeah the GPU can sort a hundred billion items a second but h…

> everyone realized the quality was worse and not much faster

I can't speak for the h264 situation, as I wasn't involved at the time, but with the newer h265 hardware, it is obnoxiously faster with minimal (in terms of end-user, not distributor) quality loss.

Re: Alenka: GPU database engine

#18

Post by floatboth »

nrjdhsbsid wrote: post #12

I keep hearing the promise of GPU databases but they don't seem to be terribly useful for most real world workloads. It reminds me of the big hoopla for GPU h264 encoders. When they came out everyone realized the quality was worse and not much faster. Some things don't lend themselves to parallel processing, notably anything linear like transactions. I mean yeah the GPU can sort a hundred billion items a second but h…

> GPU h264 encoders

Are there any GPU (shader) encoders?

There are dedicated fixed-function hardware encoders (VCE and NVENC) on graphics cards, and they're very popular, because they're the best way to record game footage if you don't have dedicated capture hardware. You don't want x264/5 hogging the CPU when you're playing games!

Re: Alenka: GPU database engine

#20

Post by rotten »

keknaut wrote: post #5
general_ai wrote: post #4

Calling this a "database" is a bit of an exaggeration.

why?

We don't really call pandas a database either. It looks like a data processing tool/library. "real" databases have integrated persistence models, as well as discussions and design tradeoffs regarding ACID transactions and scalability. There are query planners and indexes, constraints (type, value, foreign key) and other logic that can help enforce business rules around the data. There are triggers and embedded functions too.

Still, it is pretty cool technology and I think something that will be integrated with a "real" database near you sometime soon.

Post reply on HN