From b15cb495054a40644197395fb6a94daa4b0e81cb Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Sun, 15 Oct 2000 06:50:42 +0000 Subject: Update. 2000-10-14 Ulrich Drepper * math/libm-test.inc (frexp_test): Add L suffix also to parameters. (hypot_test): Likewise. * sysdeps/generic/printf_fphex.c: Compute width of decimal point string correctly. Handle padding correctly. * sysdeps/ia64/fpu/printf_fphex.c: Use sizeof in _itowa parameters correctly. * sysdeps/ieee754/ldbl-128/printf_fphex.c: Likewise. * sysdeps/ieee754/ldbl-96/printf_fphex.c: Likewise. 2000-10-12 Alan Modra * FAQ.in: Add --start-group and --end-group. 2000-10-12 Alan Modra * malloc/memusage.c: Conditionalize stack usage calculation on stack direction. 2000-10-12 Alan Modra * config.h.in: Add ASM_LINE_SEP. * configure.in: Add test for comment and line separators. * include/libc-symbols.h: Define and use ASM_LINE_SEP, and add tabs to placate some hppa assemblers. * sysdeps/hppa/sysdep.h: Likewise. * sysdeps/gnu/siglist.c: Insert \n and \t into inline asm. * sysdeps/unix/sysv/linux/errlist.c: Likewise. 2000-10-12 David Huggins-Daines * sysdeps/unix/sysv/linux/Makefile: Include in $(sysdep_headers). * sysdeps/unix/sysv/linux/bits/initspin.h: Dummy version for non-threaded platforms. 2000-10-12 David Huggins-Daines * configure.in: Add definitions for hppa. * elf/elf.h: Add PLABEL32 relocation for hppa ELF32, comments for IPLT and EPLT relocations. * shlib-versions: Version symbol definitions for hppa-linux. * sysdeps/unix/sysv/linux/configure.in: Define $arch_minimum_kernel for hppa. 2000-10-12 David Huggins-Daines * sysdeps/hppa/Makefile: New file. * sysdeps/hppa/Versions: New file. * sysdeps/hppa/setjmp.S: New file. * sysdeps/hppa/__longjmp.S: New file. * sysdeps/hppa/bits/setjmp.h: New file. * sysdeps/hppa/frame.h: New file. * sysdeps/hppa/add_n.s: Don't use %r19 (linkage table pointer). * sysdeps/hppa/sub_n.s: Likewise. * sysdeps/hppa/lshift.s: Likewise. * sysdeps/hppa/rshift.s: Likewise. * sysdeps/hppa/udiv_qrnnd.s: Likewise. * sysdeps/hppa/hppa1.1/addmul_1.s: Likewise. * sysdeps/hppa/hppa1.1/submul_1.s: Likewise. * sysdeps/hppa/hppa1.1/mul_1.s: Likewise. * sysdeps/hppa/hppa1.1/udiv_qrnnd.s: Likewise. * sysdeps/hppa/dl-machine.h: New file. * sysdeps/hppa/dl-fptr.c: New file (note that this is almost identical to the IA-64 one). * sysdeps/hppa/dl-lookupcfg.h: Likewise. * sysdeps/hppa/dl-symaddr.c: Likewise. * sysdeps/hppa/elf/initfini.c: New file. * sysdeps/hppa/elf/start.S: New file. * sysdeps/hppa/fpu/bits/fenv.h: New file. * sysdeps/hppa/fpu/fclrexcpt.c: New file. * sysdeps/hppa/fpu/fedisblxcpt.c: New file. * sysdeps/hppa/fpu/feenablxcpt.c: New file. * sysdeps/hppa/fpu/fegetenv.c: New file. * sysdeps/hppa/fpu/fegetexcept.c: New file. * sysdeps/hppa/fpu/fegetround.c: New file. * sysdeps/hppa/fpu/feholdexcpt.c: New file. * sysdeps/hppa/fpu/fesetenv.c: New file. * sysdeps/hppa/fpu/fesetround.c: New file. * sysdeps/hppa/fpu/feupdateenv.c: New file. * sysdeps/hppa/fpu/fegetexcptflg.c: New file. * sysdeps/hppa/fpu/fraiseexcpt.c: New file. * sysdeps/hppa/fpu/fsetexcptflg.c: New file. * sysdeps/hppa/fpu/ftestexcept.c: New file. * sysdeps/unix/sysv/linux/hppa/Makefile: New file. * sysdeps/unix/sysv/linux/hppa/Versions: New file. * sysdeps/unix/sysv/linux/hppa/syscalls.list: New file. * sysdeps/unix/sysv/linux/hppa/sysdep.c: New file. * sysdeps/unix/sysv/linux/hppa/sysdep.h: New file. * sysdeps/unix/sysv/linux/hppa/bits/fcntl.h: New file. * sysdeps/unix/sysv/linux/hppa/bits/ioctls.h: New file. * sysdeps/unix/sysv/linux/hppa/bits/mman.h: New file. * sysdeps/unix/sysv/linux/hppa/bits/sigaction.h: New file. * sysdeps/unix/sysv/linux/hppa/bits/signum.h: New file. * sysdeps/unix/sysv/linux/hppa/brk.c: New file. * sysdeps/unix/sysv/linux/hppa/clone.S: New file. * sysdeps/unix/sysv/linux/hppa/socket.S: New file. * sysdeps/unix/sysv/linux/hppa/syscall.S: New file. * sysdeps/unix/sysv/linux/hppa/setrlimit.c: New file. * sysdeps/unix/sysv/linux/hppa/getrlimit.c: New file. * sysdeps/unix/sysv/linux/hppa/getrlimit64.c: New file. * sysdeps/unix/sysv/linux/hppa/kernel_sigaction.h: New file. * sysdeps/unix/sysv/linux/hppa/kernel_stat.h: New file. * sysdeps/unix/sysv/linux/hppa/mmap.c: New file. * sysdeps/unix/sysv/linux/hppa/profil-counter.h: New file. * sysdeps/unix/sysv/linux/hppa/procfs.h: New file. * sysdeps/unix/sysv/linux/hppa/ucontext.h: New file. * sysdeps/unix/sysv/linux/hppa/umount.c: New file. 2000-10-12 Alan Modra * sysdeps/hppa/hppa1.1/Implies: New file. * sysdeps/hppa/memusage.h: New file. --- sysdeps/hppa/hppa1.1/submul_1.s | 102 ++++++++++++++++++++-------------------- 1 file changed, 52 insertions(+), 50 deletions(-) (limited to 'sysdeps/hppa/hppa1.1/submul_1.s') diff --git a/sysdeps/hppa/hppa1.1/submul_1.s b/sysdeps/hppa/hppa1.1/submul_1.s index a4a385467e..f2c19c7bc8 100644 --- a/sysdeps/hppa/hppa1.1/submul_1.s +++ b/sysdeps/hppa/hppa1.1/submul_1.s @@ -1,77 +1,78 @@ -; HP-PA-1.1 __mpn_submul_1 -- Multiply a limb vector with a limb and -; subtract the result from a second limb vector. +;! HP-PA-1.1 __mpn_submul_1 -- Multiply a limb vector with a limb and +;! subtract the result from a second limb vector. -; Copyright (C) 1992, 1993, 1994 Free Software Foundation, Inc. +;! Copyright (C) 1992, 1993, 1994 Free Software Foundation, Inc. -; This file is part of the GNU MP Library. +;! This file is part of the GNU MP Library. -; The GNU MP Library is free software; you can redistribute it and/or modify -; it under the terms of the GNU Library General Public License as published by -; the Free Software Foundation; either version 2 of the License, or (at your -; option) any later version. +;! The GNU MP Library is free software; you can redistribute it and/or modify +;! it under the terms of the GNU Library General Public License as published by +;! the Free Software Foundation; either version 2 of the License, or (at your +;! option) any later version. -; The GNU MP Library is distributed in the hope that it will be useful, but -; WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY -; or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Library General Public -; License for more details. +;! The GNU MP Library is distributed in the hope that it will be useful, but +;! WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +;! or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Library General Public +;! License for more details. -; You should have received a copy of the GNU Library General Public License -; along with the GNU MP Library; see the file COPYING.LIB. If not, write to -; the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, -; MA 02111-1307, USA. +;! You should have received a copy of the GNU Library General Public License +;! along with the GNU MP Library; see the file COPYING.LIB. If not, write to +;! the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, +;! MA 02111-1307, USA. -; INPUT PARAMETERS -; res_ptr r26 -; s1_ptr r25 -; size r24 -; s2_limb r23 +;! INPUT PARAMETERS +;! res_ptr r26 +;! s1_ptr r25 +;! size r24 +;! s2_limb r23 -; This runs at 12 cycles/limb on a PA7000. With the used instructions, it -; can not become faster due to data cache contention after a store. On the -; PA7100 it runs at 11 cycles/limb, and that can not be improved either, -; since only the xmpyu does not need the integer pipeline, so the only -; dual-issue we will get are addc+xmpyu. Unrolling could gain a cycle/limb -; on the PA7100. +;! This runs at 12 cycles/limb on a PA7000. With the used instructions, it +;! can not become faster due to data cache contention after a store. On the +;! PA7100 it runs at 11 cycles/limb, and that can not be improved either, +;! since only the xmpyu does not need the integer pipeline, so the only +;! dual-issue we will get are addc+xmpyu. Unrolling could gain a cycle/limb +;! on the PA7100. -; There are some ideas described in mul_1.s that applies to this code too. +;! There are some ideas described in mul_1.s that applies to this code too. -; It seems possible to make this run as fast as __mpn_addmul_1, if we use -; sub,>>= %r29,%r19,%r22 -; addi 1,%r28,%r28 -; but that requires reworking the hairy software pipeline... +;! It seems possible to make this run as fast as __mpn_addmul_1, if we use +;! sub,>>= %r29,%r20,%r22 +;! addi 1,%r28,%r28 +;! but that requires reworking the hairy software pipeline... - .code + .text .export __mpn_submul_1 -__mpn_submul_1 +__mpn_submul_1: .proc .callinfo frame=64,no_calls .entry ldo 64(%r30),%r30 fldws,ma 4(%r25),%fr5 - stw %r23,-16(%r30) ; move s2_limb ... + stw %r23,-16(%r30) ;! move s2_limb ... addib,= -1,%r24,L$just_one_limb - fldws -16(%r30),%fr4 ; ... into fr4 - add %r0,%r0,%r0 ; clear carry + fldws -16(%r30),%fr4 ;! ... into fr4 + add %r0,%r0,%r0 ;! clear carry xmpyu %fr4,%fr5,%fr6 fldws,ma 4(%r25),%fr7 fstds %fr6,-16(%r30) xmpyu %fr4,%fr7,%fr8 - ldw -12(%r30),%r19 ; least significant limb in product + ldw -12(%r30),%r20 ;! least significant limb in product ldw -16(%r30),%r28 fstds %fr8,-16(%r30) addib,= -1,%r24,L$end ldw -12(%r30),%r1 -; Main loop -L$loop ldws 0(%r26),%r29 +;! Main loop +L$loop: + ldws 0(%r26),%r29 fldws,ma 4(%r25),%fr5 - sub %r29,%r19,%r22 - add %r22,%r19,%r0 + sub %r29,%r20,%r22 + add %r22,%r20,%r0 stws,ma %r22,4(%r26) - addc %r28,%r1,%r19 + addc %r28,%r1,%r20 xmpyu %fr4,%fr5,%fr6 ldw -16(%r30),%r28 fstds %fr6,-16(%r30) @@ -79,22 +80,23 @@ L$loop ldws 0(%r26),%r29 addib,<> -1,%r24,L$loop ldw -12(%r30),%r1 -L$end ldw 0(%r26),%r29 - sub %r29,%r19,%r22 - add %r22,%r19,%r0 +L$end: + ldw 0(%r26),%r29 + sub %r29,%r20,%r22 + add %r22,%r20,%r0 stws,ma %r22,4(%r26) - addc %r28,%r1,%r19 + addc %r28,%r1,%r20 ldw -16(%r30),%r28 ldws 0(%r26),%r29 addc %r0,%r28,%r28 - sub %r29,%r19,%r22 - add %r22,%r19,%r0 + sub %r29,%r20,%r22 + add %r22,%r20,%r0 stws,ma %r22,4(%r26) addc %r0,%r28,%r28 bv 0(%r2) ldo -64(%r30),%r30 -L$just_one_limb +L$just_one_limb: xmpyu %fr4,%fr5,%fr6 ldw 0(%r26),%r29 fstds %fr6,-16(%r30) -- cgit 1.4.1