Messages in this thread | | | Subject | Re: static_branch/jump_label vs branch merging | From | David Malcolm <> | Date | Fri, 09 Apr 2021 07:55:42 -0400 |
| |
On Fri, 2021-04-09 at 13:12 +0200, Peter Zijlstra wrote: > On Fri, Apr 09, 2021 at 11:57:22AM +0200, Ard Biesheuvel wrote: > > On Thu, 8 Apr 2021 at 18:53, Peter Zijlstra <peterz@infradead.org> > > wrote: > > > > Is there *any* way in which we can have the compiler recognise > > > that the > > > asm_goto only depends on its arguments and have it merge the > > > branches > > > itself? > > > > > > I do realize that asm-goto being volatile this is a fairly huge > > > ask, but > > > I figured I should at least raise the issue, if only to raise > > > awareness. > > > > > > > Wouldn't that require the compiler to interpret the contents of the > > asm() block? > > Yeah, this is more or less asking for ponies :-) One option would be > some annotation that conveys the desired semantics without it having > to > untangle the mess in the asm block. > > The thing the compiler needs to know is that the branch is constant > for > any @key, and hence allow the obvious optimizations. I'm not sure if > this is something compiler folks would be even willing to consider, > but > I figured asking never hurts. >
Sorry if this is a dumb question, but does the function attribute: __attribute__ ((pure)) help here? It's meant to allow multiple calls to a predicate to be merged - though I'd be nervous of using it here, the predicate isn't 100% pure, since AIUI the whole point of what you've built is for predicates that very rarely change - but can change occasionally.
Hope this is constructive Dave
| |