Cool stuff! How does it compare performance-wise to the same code (no SIMD/threads) compiled natively?
-
-
-
I haven't benchmarked it yet but will let you know when I do. My guess is that it's nowhere near as fast as native, but I'm hoping adding SIMD and threads will help get it closer to native speeds.
Kraj razgovora
Novi razgovor -
-
-
What is the size of the data used?
-
For this example, it's a very small dataset, aligning ~500 reads to the lambda genome (8MB .bt2 files). I haven't tried with something larger like the human genome but my guess is that it wouldn't perform well at that scale.
Kraj razgovora
Novi razgovor -
-
-
cc
@BenLangmead because I think Ben Langmead would be interested in seeing this - Još 1 odgovor
Novi razgovor -
-
That is...nuts. Wow!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Noice!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Niiiiiice!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

This is still preliminary (I disabled SIMD and threads) but I'd like to figure out how this could be useful as a sandbox on the web; ideas are welcome!