...this also helped me find a bug in @Intel's Intrisics guide (described in the README). Possibly of interest to @geofflangdale @trav_downs @lemire @jkeiser2
Prikaži ovu nit
My latest little 1-day project: generating a Z3 SAT model of x86 intrinsics from Intel's documentation. This can help prove SIMD code correct, find lookup table values, etc.https://github.com/zwegner/x86-sat
-
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Very interesting! How much of the spec does your model cover? And how big is your model in SMT?
-
Model size obviously depends a lot on the intrinsic and what you're doing with it. My code is not particularly good on this front, either. Intel's code very often iteratively assigns to different bits in a vector, which ends up being an awful mess in my code
- Još 13 drugih odgovora
Novi razgovor -
-
-
Nice! I wrote a PEG grammar for their syntax that I still haven't quite finished (lots of small errors/inconsistencies in their pseudocode make the last 1% progressively harder to finish). https://github.com/zbjornson/iop/blob/master/grammar.pegjs … Was intended for
@lemire 's visualizer -
Cool! I'm not sure how exhaustive my grammar is, but from a quick look we seem to support a similar subset
Kraj razgovora
Novi razgovor -
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.