On Wed, May 27, 2009 at 8:37 AM, Mike Gerdts <mgerdts at gmail.com> wrote: > I'm trying to understand how to interpret SPARC branching instructions > presented by mdb and am having some troubles. > > On snv_111a I see: > >> libc.so.1`fclose::dis > libc.so.1`fclose: ? ? ? ? ? ? ? save ? ? ?%sp, -0x60, %sp > libc.so.1`fclose+4: ? ? ? ? ? ? orcc ? ? ?%g0, %i0, %i1 > libc.so.1`fclose+8: ? ? ? ? ? ? bne,pn ? ?%icc, +0x10 ? > <libc.so.1`fclose+0x18> > libc.so.1`fclose+0xc: ? ? ? ? ? nop > libc.so.1`fclose+0x10: ? ? ? ? ?ret > libc.so.1`fclose+0x14: ? ? ? ? ?restore ? %g0, -0x1, %o0 > libc.so.1`fclose+0x18: ? ? ? ? ?call ? ? ?+0x8 ? ? ? ? > ?<libc.so.1`fclose+0x20> > ... > > At fclose+8, the instruction is saying to "branch to fclose+0x18" if > thingA is not equal to thingB. ?Presumably thingA is %icc (which > itself is still a mystery to me) but I have no idea what thingB is. > > Similar code in s10 looks a bit different. I am not sure how much of > the differences are due to mdb and how much are due to truly different > code. > >> libc.so.1`fclose::dis > libc.so.1`fclose: ? ? ? ? ? ? ? save ? ? ?%sp, -0x60, %sp > libc.so.1`fclose+4: ? ? ? ? ? ? orcc ? ? ?%g0, %i0, %i1 > libc.so.1`fclose+8: ? ? ? ? ? ? bne ? ? ? +0x10 ? ? ? ? > <libc.so.1`fclose+0x18> > libc.so.1`fclose+0xc: ? ? ? ? ? mov ? ? ? %o7, %i3 > libc.so.1`fclose+0x10: ? ? ? ? ?ret > libc.so.1`fclose+0x14: ? ? ? ? ?restore ? %g0, -0x1, %o0 > libc.so.1`fclose+0x18: ? ? ? ? ?call ? ? ?+0x8 ? ? ? ? > ?<libc.so.1`fclose+0x20> > ... > > I assume the lack of ",pn" at fclose+8 in the s10 code is a legitimate > difference. ?What about the missing %icc? ?Is %icc implied? ?If not, > what is "thingA" in this case? > > Also, if there is a better place to ask questions about SPARC assembly > language, a pointer would be most appreciated. > > Thanks in advance, > Mike
A good reference would be http://opensparc-t2.sunsource.net/specs/UA2007-current-draft-HP-EXT.pdf -- it covers everything the sparcv9 reference does, plus the new bits for Niagra. Though I don't believe anything's published for Rock yet (although you can get a hint if you look at the sparc disassembler source history).
