BlazingDB uses GPUs to manipulate huge databases in no time
1–10 of 76 posts
Re: BlazingDB uses GPUs to manipulate huge databases in no time
#2It would be interesting to benchmark this against https://wiki.postgresql.org/wiki/PGStrom .
Re: BlazingDB uses GPUs to manipulate huge databases in no time
#3It would be interesting to benchmark this against https://wiki.postgresql.org/wiki/PGStrom .
And MapD, too.
Re: BlazingDB uses GPUs to manipulate huge databases in no time
#4This has been tried many times. Unless you are doing a computation with sufficient arithmetic intensity [0] the cost of shipping the data over PCIe and back dominates any gain you might get over a CPU.
[0] - http://www.nersc.gov/users/application-performance/measuring...
Re: BlazingDB uses GPUs to manipulate huge databases in no time
#5Sounds similar to what Netezza did with FPGA's but here with GPUs. So they may hit patents they say they are unaware of...
Re: BlazingDB uses GPUs to manipulate huge databases in no time
#6Re: BlazingDB uses GPUs to manipulate huge databases in no time
#7This has been tried many times. Unless you are doing a computation with sufficient arithmetic intensity [0] the cost of shipping the data over PCIe and back dominates any gain you might get over a CPU. [0] - http://www.nersc.gov/users/application-performance/measuring...
You would need a GPU with an onboard SSD (exists). Or GPUs and drivers with the ability to talk directly to infiniband hardware (exists).
Or the ability to not be ridiculously wasteful of existing resources (also exists).
Your naysaying doesn't make you smart. Your naysaying makes you cut off from learning a different, better way of doing things.
Re: BlazingDB uses GPUs to manipulate huge databases in no time
#8Several companies have implemented databases on GPUs but there is a good technical reason that the approach has never really caught on, and some of these companies even migrated to selling the same platform on CPUs only.
The weakness of GPU databases is that while they have fantastic internal bandwidth, their network to the rest of the hardware in a server system is over PCIe, which generally isn't going to be as good as what a CPU has and databases tend to be bandwidth bound. This is a real bottleneck and trying to work around it makes the entire software stack clunky.
I once asked the designer of a good GPU database what the "no bullshit" performance numbers were relative to CPU. He told me GPU was about 4x the throughput of CPU, which is very good, but after you added in the extra hardware costs, power costs, engineering complexity etc, the overall economics were about the same to a first approximation. And so he advised me to not waste my time considering GPU architectures for databases outside of some exotic, narrow use cases where the economics still made sense. Which was completely sensible.
For data intensive processing, like databases, you don't want your engine to live on a coprocessor. No matter how attractive the coprocessor, the connectivity to the rest of the system extracts a big enough price that it is rarely worth it.
Re: BlazingDB uses GPUs to manipulate huge databases in no time
#9This has been tried many times. Unless you are doing a computation with sufficient arithmetic intensity [0] the cost of shipping the data over PCIe and back dominates any gain you might get over a CPU. [0] - http://www.nersc.gov/users/application-performance/measuring...
You would need a GPU with an onboard SSD (exists). Or GPUs and drivers with the ability to talk directly to infiniband hardware (exists). Or the ability to not be ridiculously wasteful of existing resources (also exists). Your naysaying doesn't make you smart. Your naysaying makes you cut off from learning a different, better way of doing things.
Seems like a smarter response to me. Go ahead and use a GPU database if you want?? I have yet to see a good use case of one though.
Re: BlazingDB uses GPUs to manipulate huge databases in no time
#10This has been tried many times. Unless you are doing a computation with sufficient arithmetic intensity [0] the cost of shipping the data over PCIe and back dominates any gain you might get over a CPU. [0] - http://www.nersc.gov/users/application-performance/measuring...
Seems like a great application of AMD's Fiji GPU w/onboard flash: http://www.anandtech.com/show/10518/amd-announces-radeon-pro...