HPC
MapR smashes MinuteSort benchmark on Google Compute
While supercomputers and workstations have Linpack to rank their number-crunching performance, when it comes to sorting algorithms to rank Big Data systems, there is a collection of tests known as the Sort Benchmarks. And this year it looks like Hadoop is back on top after commercial distie MapR Technologies beat the MinuteSort …
This topic is closed for new posts.
some wrong figure there?
Microsoft could chew through 1,401GB of data in the [Daytona mode] test in 29 seconds and in Indy mode it could do 1,470GB in 59.4 seconds.
I take it there's a mistake here somewhere if after tuning the performance drops by ~50%?
Re: some wrong figure there?
Probably just a typographical error.
Then again, it *is* Microsoft after all...
Re: some wrong figure there?
Yup. It was 59 seconds, not 29 seconds. Not enough coffee.
Re: some wrong figure there?
Hmm... I don't think that coffee makes servers go any faster. Maybe some Wash and Go? (with the emphasis on the "Go" part")
Really? "Smashes?"
I fail to see how a 2103 node Google Compute setup besting a 256 node Microsoft setup by single digit % can be reported as "Smashes Benchmark".....
Re: Really? "Smashes?"
They had nearly the same number of threads. That was 8,192 physical for the Microsoft server setup and 8,396 virtual threads in the Google cloud. It is not clear how many physical nodes it took to make the Google setup, of course.
This topic is closed for new posts.
