| To: | Richard Sandiford <rdsandiford@googlemail.com> |
|---|---|
| Subject: | Re: [PATCH]: R10000 Needs LL/SC Workaround in Gcc |
| From: | "Maciej W. Rozycki" <macro@linux-mips.org> |
| Date: | Sat, 1 Nov 2008 20:33:03 +0000 (GMT) |
| Cc: | Kumba <kumba@gentoo.org>, Ralf Baechle <ralf@linux-mips.org>, gcc-patches@gcc.gnu.org, Linux MIPS List <linux-mips@linux-mips.org> |
| In-reply-to: | <87abcjibsl.fsf@firetop.home> |
| Original-recipient: | rfc822;linux-mips@linux-mips.org |
| References: | <490A90F4.6040601@gentoo.org> <490C05A9.9070707@gentoo.org> <87abcjibsl.fsf@firetop.home> |
| Sender: | linux-mips-bounce@linux-mips.org |
| User-agent: | Alpine 1.10 (LFD 962 2008-03-14) |
On Sat, 1 Nov 2008, Richard Sandiford wrote: > There are two ways we could handle this: > > - Make -mfix-r10000 require -mbranch-likely. (It mustn't _imply_ > -mbranch-likely. It should simply check that -mbranch-likely is > already in effect.) > > - Make -mfix-r10000 insert nops when -mbranch-likely is not in effect. If I recall right, these is something special about the pipeline in this context making the branch-likely instructions the only ones that work. Which would make the option you proposed first the only viable. I am not absolutely sure and I have no reference handy. Perhaps Ralf or someone at linux-mips will know? Maciej |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [PATCH]: R10000 Needs LL/SC Workaround in Gcc, Richard Sandiford |
|---|---|
| Next by Date: | Re: [PATCH]: R10000 Needs LL/SC Workaround in Gcc, Ralf Baechle |
| Previous by Thread: | Re: [PATCH]: R10000 Needs LL/SC Workaround in Gcc, Ralf Baechle |
| Next by Thread: | Re: [PATCH]: R10000 Needs LL/SC Workaround in Gcc, Ralf Baechle |
| Indexes: | [Date] [Thread] [Top] [All Lists] |