From f41c80910d631bacdaf39ec6d11272db79c59d38 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Sun, 24 Aug 1997 10:55:18 +0000 Subject: Update. 1997-08-24 12:24 Ulrich Drepper * configure.in (INSTALL): Quote `$'. * libc.map: Add __xpg_basename. * csu/Makefile (initfini.s): Disable optimization. * elf/dl-deps.c: Implement handling of DL_FILTER. * elf/dl-load.c (_dl_init_paths): Add error check. * intl/finddomain.c (_nl_find_domain): Correct comment. * intl/localealias.c: Include not . * libio/stdio.h: Make {,v}snprintf available if __USE_BSD. Change extern inline functions to work correctly in C++. * locale/iso-4217.def: Update for more recent ISO 4217 version. * locale/loadlocale.c (_nl_load_locale): Add cast. * manual/message.texi: Finish gettext section. * posix/getopt_init.c: Don't use relative #include path. (__getopt_clean_environment): Change function to take pointer to environment as argument. Optimize generation of test string a bit. * sysdeps/unix/sysv/linux/init-first.c: Call __getopt_clean_environment with additional argument. * poisx/glob.c: Add prototype for next_brace_sub. * sysdeps/generic/dl-sysdep.c: Recognize AT_BASE value on auxiliary vector. * sysdeps/i386/dl-machine.h (elf_machine_load_address): Rewrite to not generate relocation entry. Suggested by Richard Henderson. (ELF_MACHINE_BEFORE_RTLD_RELOC): Removed. (elf_machine_runtime_setup): Add .aligns. * sysdeps/i386/fpu/fraiseexcpt.c: Add volatile to asms. * sysdeps/i386/fpu/bits/mathinline.h: Partially undo change of 1997-08-14 03:14. gcc 2.7.2* is really broken in some aspects. * sysdeps/standalone/i386/i386.h: Clean up asm statements a bit. * sysdeps/standalone/i960/i960ca.h: Likewise. 1997-08-22 19:04 Richard Henderson * elf/rtld.c (_dl_start): Init _dl_rtld_map.l_opencount due to undocumented test addition in _dl_map_object. Support ET_EXEC versions of ld.so, for debugging at least: * elf/dl-load.c (_dl_map_object): Add_name_to_object could get called despite the DT_SONAME != NULL test, segfaulting. Simplify the code here as well. * elf/dl-lookup.c (do_lookup): Skip objects with no symtab. (_dl_setup_hash): Likewise for hash tables. * elf/dl-version.c (_dl_check_map_versions): Likewise for strtabs. * elf/rtld.c (_dl_start): Likewise for rpath. (_dl_rtld_libname2): New variable. (dl_main): Use it to add an soname for ourselves when we don't have one of our own. Base it on the target's .interp. (dl_main): Again, skip printing of objects that don't have strtabs. Sparc 32 merge: * elf/dl-runtime.c (ELF_FIXUP_RETURN_VALUE): Provide default value. (fixup): Simplify code. Use ELF_FIXUP_RETURN_VALUE. (profile_fixup): Likewise, though this still needs fixing for Sparc32 and PPC. * sysdeps/powerpc/dl-machine.h: Transmute ELF_FIXUP_RETURNS_ADDRESS to ELF_FIXUP_RETURN_VALUE. * sysdeps/sparc/sparc32/dl-machine.h: Implement lazy relocation. Fix up _dl_start_user to handle _dl_skip_args properly. Use _dl_hwcap to determine if "flush" is available/needed. * sysdeps/sparc/configure.in: Remove. It doesn't actually do anything anymore, and what it did do is done somewhere else. * sysdeps/sparc/configure: Likewise. * sysdeps/sparc/fpu/bits/mathdef.h (FP_ILOGB0, FP_ILOGBNAN): New. * sysdeps/sparc/fpu/fraiseexcpt.c: Rearrange for smaller code. * sysdeps/sparc/sparc32/Makefile: Fix sparc->sparc/sparc32 bits in divrem expansions. * sysdeps/unix/sysv/linux/sparc/sparc32/sysdep.h (END, LOC): New definitions for assembly syntax differences. * sysdeps/sparc/sparc32/__longjmp.S: %g6,%g7 are reserved to the "system". Use %g2,%g3 instead. Use new local label macro. * sysdeps/sparc/sparc32/add_n.S: Use and ENTRY, END, and LOC for proper assembly headers/footers. * sysdeps/sparc/sparc32/addmul_1.S: Likewise. * sysdeps/sparc/sparc32/alloca.S: Likewise. * sysdeps/sparc/sparc32/dotmul.S: Likewise. * sysdeps/sparc/sparc32/lshift.S: Likewise. * sysdeps/sparc/sparc32/mul_1.S: Likewise. * sysdeps/sparc/sparc32/rshift.S: Likewise. * sysdeps/sparc/sparc32/sparcv8/addmul_1.S: Likewise. * sysdeps/sparc/sparc32/sparcv8/mul_1.S: Likewise. * sysdeps/sparc/sparc32/sparcv8/submul_1.S: Likewise. * sysdeps/sparc/sparc32/sparcv8/udiv_qrnnd.S: Likewise. * sysdeps/sparc/sparc32/sub_n.S: Likewise. * sysdeps/sparc/sparc32/submul_1.S: Likewise. * sysdeps/sparc/sparc32/udiv_qrnnd.S: Likewise. * sysdeps/sparc/sparc32/umul.S: Likewise. * sysdeps/sparc/sparc32/divrem.m4: Likewise. * sysdeps/sparc/sparc32/rem.S: Regenerate. * sysdeps/sparc/sparc32/sdiv.S: Regenerate. * sysdeps/sparc/sparc32/udiv.S: Regenerate. * sysdeps/sparc/sparc32/urem.S: Regenerate. * sysdeps/sparc/sparc32/sparcv8/dotmul.S: New file. * sysdeps/sparc/sparc32/sparcv8/rem.S: New file. * sysdeps/sparc/sparc32/sparcv8/sdiv.S: New file. * sysdeps/sparc/sparc32/sparcv8/udiv.S: New file. * sysdeps/sparc/sparc32/sparcv8/umul.S: New file. * sysdeps/sparc/sparc32/sparcv8/urem.S: New file. * sysdeps/sparc/sparc32/bsd-_setjmp.S: Dike out. * sysdeps/sparc/sparc32/bsd-setjmp.S: Likewise. * sysdeps/sparc/sparc32/setjmp.S: Add _setjmp and setjmp entry points. * sysdeps/unix/sysv/linux/sparc/sparc32/__sigtrampoline.S: Clean up PIC code. * sysdeps/sparc/sparc32/elf/start.S: New file, slightly modified from the sparc64 version. * sysdeps/sparc/sparc32/elf/start.c: Removed. * sysdeps/unix/sysv/linux/sparc/sparc32/init-first.h: Rewrite in assembly based on the sparc64 version. * sysdeps/sparc/sparc32/fpu/bits/fenv.h: Duh. Use proper syntax for manipulating %fsr. * sysdeps/sparc/sparc32/fpu/fpu_control.h: Make IEEE conformance be the default. * elf/elf.h (HWCAP_SPARC_*): New definitions. * elf/rtld.c (_dl_hwcap): New variable. * sysdeps/generic/dl-sysdep.c (_dl_sysdep_start): Record AT_HWCAP. * sysdeps/unix/sysv/linux/sparc/sparc32/getpagesize.c: New file. Attempt to get hold of the page size based on what we might have been told at startup time in _dl_pagesize. This will be obsolete when I finish the kernel hooks for a proper sysconf(), stay tuned. Sparc 64 merge: * sysdeps/sparc/sparc64/dl-machine.h (ELF_FIXUP_RETURN_VALUE): New. Figure out the right thing to return based on the .plt format. * sysdeps/sparc/sparc64/fpu/fpu_control.h: Update comment. * sysdeps/unix/sysv/linux/sparc/sparc64/bits/types.h (__dev_t): Should have been 64-bits wide. * sysdeps/unix/sysv/linux/sparc/sparc64/init-first.h: sll->sllx, optimize for branch delay slot usage. 1997-08-22 Andreas Schwab * csu/Makefile ($(objpfx)crt%.o): Fix a missing *.so -> *.os change. 1997-08-20 Andreas Jaeger * math/libm-test.c (identities): Change epsilon. * sysdeps/i386/fpu/bits/mathinline.h: Correct arguments to fabs, fabsf, fabsl, __fabsl. * sysdeps/libm-i387/e_remainderl.S: Pop extra value from FPU stack. * sysdeps/libm-ieee754/s_csinhl.c: Include . --- sysdeps/sparc/sparc32/udiv.S | 186 +++++++++++++++++++++---------------------- 1 file changed, 90 insertions(+), 96 deletions(-) (limited to 'sysdeps/sparc/sparc32/udiv.S') diff --git a/sysdeps/sparc/sparc32/udiv.S b/sysdeps/sparc/sparc32/udiv.S index 4a7d152..0dd48f3 100644 --- a/sysdeps/sparc/sparc32/udiv.S +++ b/sysdeps/sparc/sparc32/udiv.S @@ -37,16 +37,8 @@ -#include "sysdep.h" -#ifdef __linux__ -#include -#else -#ifdef __svr4__ +#include #include -#else -#include -#endif -#endif ENTRY(.udiv) @@ -63,11 +55,11 @@ ENTRY(.udiv) 1: cmp %o3, %o5 ! if %o1 exceeds %o0, done - blu Lgot_result ! (and algorithm fails otherwise) + blu LOC(got_result) ! (and algorithm fails otherwise) clr %o2 sethi %hi(1 << (32 - 4 - 1)), %g1 cmp %o3, %g1 - blu Lnot_really_big + blu LOC(not_really_big) clr %o4 ! Here the dividend is >= 2**(31-N) or so. We must be careful here, @@ -78,15 +70,15 @@ ENTRY(.udiv) 1: cmp %o5, %g1 bgeu 3f - mov 1, %g7 + mov 1, %g2 sll %o5, 4, %o5 b 1b add %o4, 1, %o4 - ! Now compute %g7. + ! Now compute %g2. 2: addcc %o5, %o5, %o5 - bcc Lnot_too_big - add %g7, 1, %g7 + bcc LOC(not_too_big) + add %g2, 1, %g2 ! We get here if the %o1 overflowed while shifting. ! This means that %o3 has the high-order bit set. @@ -94,20 +86,20 @@ ENTRY(.udiv) sll %g1, 4, %g1 ! high order bit srl %o5, 1, %o5 ! rest of %o5 add %o5, %g1, %o5 - b Ldo_single_div - sub %g7, 1, %g7 + b LOC(do_single_div) + sub %g2, 1, %g2 - Lnot_too_big: + LOC(not_too_big): 3: cmp %o5, %o3 blu 2b nop - be Ldo_single_div + be LOC(do_single_div) nop /* NB: these are commented out in the V8-Sparc manual as well */ /* (I do not understand this) */ ! %o5 > %o3: went too far: back up 1 step ! srl %o5, 1, %o5 - ! dec %g7 + ! dec %g2 ! do single-bit divide steps ! ! We have to be careful here. We know that %o3 >= %o5, so we can do the @@ -116,15 +108,15 @@ ENTRY(.udiv) ! order bit set in the first step, just falling into the regular ! division loop will mess up the first time around. ! So we unroll slightly... - Ldo_single_div: - subcc %g7, 1, %g7 - bl Lend_regular_divide + LOC(do_single_div): + subcc %g2, 1, %g2 + bl LOC(end_regular_divide) nop sub %o3, %o5, %o3 mov 1, %o2 - b Lend_single_divloop + b LOC(end_single_divloop) nop - Lsingle_divloop: + LOC(single_divloop): sll %o2, 1, %o2 bl 1f srl %o5, 1, %o5 @@ -136,217 +128,219 @@ ENTRY(.udiv) add %o3, %o5, %o3 sub %o2, 1, %o2 2: - Lend_single_divloop: - subcc %g7, 1, %g7 - bge Lsingle_divloop + LOC(end_single_divloop): + subcc %g2, 1, %g2 + bge LOC(single_divloop) tst %o3 - b,a Lend_regular_divide + b,a LOC(end_regular_divide) -Lnot_really_big: +LOC(not_really_big): 1: sll %o5, 4, %o5 cmp %o5, %o3 bleu 1b addcc %o4, 1, %o4 - be Lgot_result + be LOC(got_result) sub %o4, 1, %o4 tst %o3 ! set up for initial iteration -Ldivloop: +LOC(divloop): sll %o2, 4, %o2 ! depth 1, accumulated bits 0 - bl L.1.16 + bl LOC(1.16) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 ! depth 2, accumulated bits 1 - bl L.2.17 + bl LOC(2.17) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 ! depth 3, accumulated bits 3 - bl L.3.19 + bl LOC(3.19) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 ! depth 4, accumulated bits 7 - bl L.4.23 + bl LOC(4.23) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 b 9f add %o2, (7*2+1), %o2 - -L.4.23: + +LOC(4.23): ! remainder is negative addcc %o3,%o5,%o3 b 9f add %o2, (7*2-1), %o2 - - -L.3.19: + + +LOC(3.19): ! remainder is negative addcc %o3,%o5,%o3 ! depth 4, accumulated bits 5 - bl L.4.21 + bl LOC(4.21) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 b 9f add %o2, (5*2+1), %o2 - -L.4.21: + +LOC(4.21): ! remainder is negative addcc %o3,%o5,%o3 b 9f add %o2, (5*2-1), %o2 - - - -L.2.17: + + + +LOC(2.17): ! remainder is negative addcc %o3,%o5,%o3 ! depth 3, accumulated bits 1 - bl L.3.17 + bl LOC(3.17) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 ! depth 4, accumulated bits 3 - bl L.4.19 + bl LOC(4.19) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 b 9f add %o2, (3*2+1), %o2 - -L.4.19: + +LOC(4.19): ! remainder is negative addcc %o3,%o5,%o3 b 9f add %o2, (3*2-1), %o2 - - -L.3.17: + + +LOC(3.17): ! remainder is negative addcc %o3,%o5,%o3 ! depth 4, accumulated bits 1 - bl L.4.17 + bl LOC(4.17) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 b 9f add %o2, (1*2+1), %o2 - -L.4.17: + +LOC(4.17): ! remainder is negative addcc %o3,%o5,%o3 b 9f add %o2, (1*2-1), %o2 - - - - -L.1.16: + + + + +LOC(1.16): ! remainder is negative addcc %o3,%o5,%o3 ! depth 2, accumulated bits -1 - bl L.2.15 + bl LOC(2.15) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 ! depth 3, accumulated bits -1 - bl L.3.15 + bl LOC(3.15) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 ! depth 4, accumulated bits -1 - bl L.4.15 + bl LOC(4.15) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 b 9f add %o2, (-1*2+1), %o2 - -L.4.15: + +LOC(4.15): ! remainder is negative addcc %o3,%o5,%o3 b 9f add %o2, (-1*2-1), %o2 - - -L.3.15: + + +LOC(3.15): ! remainder is negative addcc %o3,%o5,%o3 ! depth 4, accumulated bits -3 - bl L.4.13 + bl LOC(4.13) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 b 9f add %o2, (-3*2+1), %o2 - -L.4.13: + +LOC(4.13): ! remainder is negative addcc %o3,%o5,%o3 b 9f add %o2, (-3*2-1), %o2 - - - -L.2.15: + + + +LOC(2.15): ! remainder is negative addcc %o3,%o5,%o3 ! depth 3, accumulated bits -3 - bl L.3.13 + bl LOC(3.13) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 ! depth 4, accumulated bits -5 - bl L.4.11 + bl LOC(4.11) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 b 9f add %o2, (-5*2+1), %o2 - -L.4.11: + +LOC(4.11): ! remainder is negative addcc %o3,%o5,%o3 b 9f add %o2, (-5*2-1), %o2 - - -L.3.13: + + +LOC(3.13): ! remainder is negative addcc %o3,%o5,%o3 ! depth 4, accumulated bits -7 - bl L.4.9 + bl LOC(4.9) srl %o5,1,%o5 ! remainder is positive subcc %o3,%o5,%o3 b 9f add %o2, (-7*2+1), %o2 - -L.4.9: + +LOC(4.9): ! remainder is negative addcc %o3,%o5,%o3 b 9f add %o2, (-7*2-1), %o2 - - - - + + + + 9: -Lend_regular_divide: +LOC(end_regular_divide): subcc %o4, 1, %o4 - bge Ldivloop + bge LOC(divloop) tst %o3 - bl,a Lgot_result + bl,a LOC(got_result) ! non-restoring fixup here (one instruction only!) sub %o2, 1, %o2 -Lgot_result: +LOC(got_result): retl mov %o2, %o0 + +END(.udiv) -- cgit v1.1