On 06/19/2017 11:51 AM, Jakub Jelinek wrote: > On Mon, Jun 19, 2017 at 11:45:13AM -0600, Jeff Law wrote: >> On 06/19/2017 11:29 AM, Jakub Jelinek wrote: >>> >>> Also, on i?86 orq $0, (%rsp) or orl $0, (%esp) is used to probe stack, >>> while it is shorter, is it actually faster or as slow as movq $0, (%rsp) >>> or movl $0, (%esp) ? >> Florian raised this privately to me as well. THere's a couple issues. >> >> 1. Is there a performance penalty/gain for sub-word operations? If not, >> we can improve things slighly there. Even if it's performance >> neutral we can probably do better on code size. > > CCing Uros and Honza here, I believe there are at least on x86 penalties > for 2-byte, maybe for 1-byte and then sometimes some stalls when you > write or read in a different size from a recent write or read. Obviously, I'll go with whatever Honza & Uros say is the most efficient. This stuff would be highly localized and is easily tweaked into whatever final form we want.
> >> Thus I find myself rethinking is this a probing policy option or should >> it just be another variant of -fstack-check=<something>. > > Yeah, IMHO it is just another way of stack probing next to generic and > specific, and for users it would be easier to write -fstack-check=whatever > than -fstack-check -fstack-check-probe=whatever That's essentially where I'm leaning now. The difficulty is in selecting a name. ISTM that -fstack-check=specific becomes horribly bad though. It should really be -fstack-check=ada or somesuch. jeff
