Re:BlazingDB uses GPUs to manipulate huge databases in no time
by Johnny555 on Tuesday September 13, 2016 @12:11AM
(#12485581)
Once you read and prune out the dataset to only include the relevant data, then what's left for the GPU to do?
[ Parent
| on HN ]
Re:BlazingDB uses GPUs to manipulate huge databases in no time
by j1vms on Tuesday September 13, 2016 @12:50AM
(#12485704)
The transformation to GPU-ready would not be as trivial and effectively redundant as pruning the data of course. It would be produce a secondary data structure, like an index on a column, though in this case of course destined to be processed within the math-oriented, high-branch-cost setting of a GPU.
Re:BlazingDB uses GPUs to manipulate huge databases in no time
by lmeyerov on Tuesday September 13, 2016 @03:26AM
(#12486193)
This is basically the bread and butter of columnar compute systems, not just GPU ones. GPUs ones just get to throw more compute at them, and thus do even better for these kinds of space/time trade-offs. Interestingly, most big data systems are increasingly columnar.