Displaying 8 results from an estimated 8 matches for "minimum_dependency_distance".
2014 Aug 19
2
[LLVMdev] Proposal for ""llvm.mem.vectorize.safelen"
...but we've not really thought about it yet.
Regarding the proposal, I'm in favor. I don't like using the name 'savelen' however. I can forgive OpenMP for choosing such a short name because people need to type it, but I'd prefer that the metadata have a more-descriptive name. minimum_dependency_distance is perhaps better.
-Hal
>
> Can we translate llvm.mem.vectorize.safelen into an invariant on k
> similarly as to what you're proposing that the programmer should
> ensure?
>
> Cheers,
> Roel
>
> [0] http://comments.gmane.org/gmane.comp.compilers.llvm.devel/749...
2014 Aug 20
6
[LLVMdev] Proposal for ""llvm.mem.vectorize.safelen"
...idth
so that some processing infrastructure can be shared easily.
> I don't like using the name 'safelen' however. I can forgive OpenMP
> for choosing such a short name because people need to type it,
> but I'd prefer that the metadata have a more-descriptive name.
> minimum_dependency_distance is perhaps better.
I'm open to naming suggestions, though I'm wondering if sticking with
what is now a term of art in OpenMP might be the least of all evils,
because the semantics turn out to be a little more subtle than
just a minimum dependence distance. My current wording of the seman...
2014 Aug 20
2
[LLVMdev] LLVM CreateStructGEP type assert error
...e.width
so that some processing infrastructure can be shared easily.
> I don't like using the name 'safelen' however. I can forgive OpenMP
> for choosing such a short name because people need to type it,
> but I'd prefer that the metadata have a more-descriptive name.
> minimum_dependency_distance is perhaps better.
I'm open to naming suggestions, though I'm wondering if sticking with
what is now a term of art in OpenMP might be the least of all evils,
because the semantics turn out to be a little more subtle than
just a minimum dependence distance. My current wording of the semant...
2014 Aug 20
2
[LLVMdev] LLVM CreateStructGEP type assert error
...cessing infrastructure can be shared easily.
>
> > I don't like using the name 'safelen' however. I can forgive OpenMP
> > for choosing such a short name because people need to type it,
> > but I'd prefer that the metadata have a more-descriptive name.
> > minimum_dependency_distance is perhaps better.
>
> I'm open to naming suggestions, though I'm wondering if sticking with
> what is now a term of art in OpenMP might be the least of all evils,
> because the semantics turn out to be a little more subtle than
> just a minimum dependence distance. My curre...
2014 Aug 20
2
[LLVMdev] LLVM CreateStructGEP type assert error
...n be shared easily.
> >
> > > I don't like using the name 'safelen' however. I can forgive OpenMP
> > > for choosing such a short name because people need to type it,
> > > but I'd prefer that the metadata have a more-descriptive name.
> > > minimum_dependency_distance is perhaps better.
> >
> > I'm open to naming suggestions, though I'm wondering if sticking with
> > what is now a term of art in OpenMP might be the least of all evils,
> > because the semantics turn out to be a little more subtle than
> > just a minimum depen...
2014 Aug 20
3
[LLVMdev] Proposal for ""llvm.mem.vectorize.safelen"
...n be shared easily.
> >
> >> I don't like using the name 'safelen' however. I can forgive OpenMP
> >> for choosing such a short name because people need to type it,
> >> but I'd prefer that the metadata have a more-descriptive name.
> >> minimum_dependency_distance is perhaps better.
> >
> > I'm open to naming suggestions, though I'm wondering if sticking with
> > what is now a term of art in OpenMP might be the least of all evils,
> > because the semantics turn out to be a little more subtle than
> > just a minimum dep...
2014 Aug 20
2
[LLVMdev] LLVM CreateStructGEP type assert error
...> >
> > > > I don't like using the name 'safelen' however. I can forgive OpenMP
> > > > for choosing such a short name because people need to type it,
> > > > but I'd prefer that the metadata have a more-descriptive name.
> > > > minimum_dependency_distance is perhaps better.
> > >
> > > I'm open to naming suggestions, though I'm wondering if sticking with
> > > what is now a term of art in OpenMP might be the least of all evils,
> > > because the semantics turn out to be a little more subtle than
> >...
2014 Aug 12
7
[LLVMdev] Proposal for ""llvm.mem.vectorize.safelen"
Julia and OpenMP 4.0 have features where the user can bless a loop as
having no memory dependences that prevent vectorization, thus enabling
vectorization of loops not amenable to compile-time or run-time
dependence analysis. LLVM currently has no metadata to express such,
as explained further below.
I'd like to propose new metadata that enables front-ends to tell the
vectorizer that