diff options
author | Pedro Alvarez <pedro.alvarez@codethink.co.uk> | 2016-05-27 17:39:31 +0100 |
---|---|---|
committer | Pedro Alvarez <pedro.alvarez@codethink.co.uk> | 2016-05-27 17:53:32 +0100 |
commit | 26c75cf8267919f81a1759c9c965a52c660233f9 (patch) | |
tree | cf2a39cf56c2c8ac45760854413ab233e6263974 /gmp/mpn/sparc64/rshift.asm | |
parent | 56892c1d217baea02092b51a09bbc924130ca84c (diff) | |
download | gcc-tarball-26c75cf8267919f81a1759c9c965a52c660233f9.tar.gz |
go to gmp 4.3.2baserock/pedroalvarez/gcc-5.3.0-gmp432
Diffstat (limited to 'gmp/mpn/sparc64/rshift.asm')
-rw-r--r-- | gmp/mpn/sparc64/rshift.asm | 255 |
1 files changed, 131 insertions, 124 deletions
diff --git a/gmp/mpn/sparc64/rshift.asm b/gmp/mpn/sparc64/rshift.asm index 3f8e11fee7..691fe012d3 100644 --- a/gmp/mpn/sparc64/rshift.asm +++ b/gmp/mpn/sparc64/rshift.asm @@ -1,142 +1,149 @@ dnl SPARC v9 mpn_rshift -dnl Contributed to the GNU project by David Miller. - -dnl Copyright 2013 Free Software Foundation, Inc. +dnl Copyright 1996, 2000, 2001, 2002, 2003 Free Software Foundation, Inc. dnl This file is part of the GNU MP Library. -dnl + dnl The GNU MP Library is free software; you can redistribute it and/or modify -dnl it under the terms of either: -dnl -dnl * the GNU Lesser General Public License as published by the Free -dnl Software Foundation; either version 3 of the License, or (at your -dnl option) any later version. -dnl -dnl or -dnl -dnl * the GNU General Public License as published by the Free Software -dnl Foundation; either version 2 of the License, or (at your option) any -dnl later version. -dnl -dnl or both in parallel, as here. -dnl +dnl it under the terms of the GNU Lesser General Public License as published +dnl by the Free Software Foundation; either version 3 of the License, or (at +dnl your option) any later version. + dnl The GNU MP Library is distributed in the hope that it will be useful, but dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY -dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License -dnl for more details. -dnl -dnl You should have received copies of the GNU General Public License and the -dnl GNU Lesser General Public License along with the GNU MP Library. If not, -dnl see https://www.gnu.org/licenses/. +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public +dnl License for more details. + +dnl You should have received a copy of the GNU Lesser General Public License +dnl along with the GNU MP Library. If not, see http://www.gnu.org/licenses/. + include(`../config.m4') -C cycles/limb -C UltraSPARC 1&2: 2 -C UltraSPARC 3: 2.5 -C UltraSPARC T1: 17.5 -C UltraSPARC T3: 8 -C UltraSPARC T4: 3 +C cycles/limb +C UltraSPARC 1&2: 2 +C UltraSPARC 3: 3.25 C INPUT PARAMETERS -define(`rp', `%i0') -define(`up', `%i1') -define(`n', `%i2') -define(`cnt', `%i3') - -define(`tcnt', `%i4') -define(`retval', `%i5') -define(`u0', `%l0') -define(`u1', `%l1') -define(`r0', `%l6') -define(`r1', `%l7') -define(`u0_off', `%o0') -define(`u1_off', `%o1') -define(`r0_off', `%o2') -define(`r1_off', `%o3') +define(`rp',`%i0') +define(`up',`%i1') +define(`n',`%i2') +define(`cnt',`%i3') + +define(`u0',`%l0') +define(`u1',`%l2') +define(`u2',`%l4') +define(`u3',`%l6') + +define(`tnc',`%i4') + +define(`fanop',`fitod %f0,%f2') dnl A quasi nop running in the FA pipe +define(`fmnop',`fmuld %f0,%f0,%f4') dnl A quasi nop running in the FM pipe ASM_START() REGISTER(%g2,#scratch) REGISTER(%g3,#scratch) PROLOGUE(mpn_rshift) - save %sp, -176, %sp - - sllx n, 3, n - sub %g0, cnt, tcnt - - add up, n, up - add rp, n, rp - - neg n, n - sub up, (2 * 8), u0_off - sub rp, (5 * 8), r0_off - - ldx [n + up], u1 C WAS: up + 0 - sub u0_off, (1 * 8), u1_off - sub r0_off, (1 * 8), r1_off - - subcc n, -(3 * 8), n - sllx u1, tcnt, retval - - bg,pn %xcc, L(end12) - srlx u1, cnt, %l3 - - ldx [n + u0_off], u0 C WAS: up + 0 - subcc n, -(2 * 8), n - - ldx [n + u1_off], u1 C WAS: up + 8 - - bg,pn %xcc, L(end34) - sllx u0, tcnt, %l4 - - b,a L(top) - ALIGN(16) -L(top): - srlx u0, cnt, %l2 - or %l3, %l4, r0 - - ldx [n + u0_off], u0 C WAS: up + 0 - sllx u1, tcnt, %l5 - - stx r0, [n + r0_off] C WAS: rp + 0 - subcc n, -(2 * 8), n - - srlx u1, cnt, %l3 - or %l2, %l5, r1 - - ldx [n + u1_off], u1 C WAS: up + 8 - sllx u0, tcnt, %l4 - - ble,pt %xcc, L(top) - stx r1, [n + r1_off] C WAS: rp + 8 - -L(end34): - srlx u0, cnt, %l2 - or %l3, %l4, r0 - - sllx u1, tcnt, %l5 - stx r0, [n + r0_off] C WAS: rp + 0 - - or %l2, %l5, r1 - sub n, -(2 * 8), %o5 - - srlx u1, cnt, %l3 - stx r1, [%o5 + r1_off] C WAS: rp + 8 - -L(end12): - andcc n, 8, %g0 - bz,pn %xcc, L(done) - nop - - ldx [n + u0_off], u1 - sllx u1, tcnt, %l4 - or %l3, %l4, r0 - stx r0, [r0_off + 24] - srlx u1, cnt, %l3 -L(done): - stx %l3, [r0_off + 32] - + save %sp,-160,%sp + + sub %g0,cnt,tnc C negate shift count + ldx [up],u3 C load first limb + subcc n,5,n + sllx u3,tnc,%i5 C compute function result + srlx u3,cnt,%g3 + bl,pn %icc,.Lend1234 + fanop + + subcc n,4,n + ldx [up+8],u0 + ldx [up+16],u1 + add up,32,up + ldx [up-8],u2 + ldx [up+0],u3 + sllx u0,tnc,%g2 + + bl,pn %icc,.Lend5678 + fanop + + b,a .Loop + .align 16 +.Loop: + srlx u0,cnt,%g1 + or %g3,%g2,%g3 + ldx [up+8],u0 + fanop +C -- + sllx u1,tnc,%g2 + subcc n,4,n + stx %g3,[rp+0] + fanop +C -- + srlx u1,cnt,%g3 + or %g1,%g2,%g1 + ldx [up+16],u1 + fanop +C -- + sllx u2,tnc,%g2 + stx %g1,[rp+8] + add up,32,up + fanop +C -- + srlx u2,cnt,%g1 + or %g3,%g2,%g3 + ldx [up-8],u2 + fanop +C -- + sllx u3,tnc,%g2 + stx %g3,[rp+16] + add rp,32,rp + fanop +C -- + srlx u3,cnt,%g3 + or %g1,%g2,%g1 + ldx [up+0],u3 + fanop +C -- + sllx u0,tnc,%g2 + stx %g1,[rp-8] + bge,pt %icc,.Loop + fanop +C -- +.Lend5678: + srlx u0,cnt,%g1 + or %g3,%g2,%g3 + sllx u1,tnc,%g2 + stx %g3,[rp+0] + srlx u1,cnt,%g3 + or %g1,%g2,%g1 + sllx u2,tnc,%g2 + stx %g1,[rp+8] + srlx u2,cnt,%g1 + or %g3,%g2,%g3 + sllx u3,tnc,%g2 + stx %g3,[rp+16] + add rp,32,rp + srlx u3,cnt,%g3 C carry... + or %g1,%g2,%g1 + stx %g1,[rp-8] + +.Lend1234: + addcc n,4,n + bz,pn %icc,.Lret + fanop +.Loop0: + add rp,8,rp + subcc n,1,n + ldx [up+8],u3 + add up,8,up + sllx u3,tnc,%g2 + or %g3,%g2,%g3 + stx %g3,[rp-8] + srlx u3,cnt,%g3 + bnz,pt %icc,.Loop0 + fanop +.Lret: + stx %g3,[rp+0] + mov %i5,%i0 ret - restore retval, 0, %o0 -EPILOGUE() + restore +EPILOGUE(mpn_rshift) |