head 1.2; access; symbols perseant-exfatfs-base-20250801:1.2 perseant-exfatfs-base-20240630:1.2 perseant-exfatfs:1.2.0.8 perseant-exfatfs-base:1.2 netbsd-8-3-RELEASE:1.1.1.1 cjep_sun2x:1.2.0.6 cjep_sun2x-base:1.2 cjep_staticlib_x-base1:1.2 cjep_staticlib_x:1.2.0.4 cjep_staticlib_x-base:1.2 phil-wifi-20200421:1.2 phil-wifi-20200411:1.2 phil-wifi-20200406:1.2 netbsd-8-2-RELEASE:1.1.1.1 netbsd-8-1-RELEASE:1.1.1.1 netbsd-8-1-RC1:1.1.1.1 pgoyette-compat-merge-20190127:1.2 pgoyette-compat-20190127:1.2 pgoyette-compat-20190118:1.2 pgoyette-compat-1226:1.2 pgoyette-compat-1126:1.2 pgoyette-compat-1020:1.2 pgoyette-compat-0930:1.2 pgoyette-compat-0906:1.2 netbsd-7-2-RELEASE:1.1.1.1 pgoyette-compat-0728:1.2 netbsd-8-0-RELEASE:1.1.1.1 pgoyette-compat-0625:1.2 netbsd-8-0-RC2:1.1.1.1 pgoyette-compat-0521:1.2 pgoyette-compat-0502:1.2 pgoyette-compat-0422:1.2 netbsd-8-0-RC1:1.1.1.1 pgoyette-compat-0415:1.2 pgoyette-compat-0407:1.2 pgoyette-compat-0330:1.2 pgoyette-compat-0322:1.2 pgoyette-compat-0315:1.2 netbsd-7-1-2-RELEASE:1.1.1.1 pgoyette-compat:1.2.0.2 pgoyette-compat-base:1.2 netbsd-7-1-1-RELEASE:1.1.1.1 matt-nb8-mediatek:1.1.1.1.0.26 matt-nb8-mediatek-base:1.1.1.1 perseant-stdc-iso10646:1.1.1.1.0.24 perseant-stdc-iso10646-base:1.1.1.1 netbsd-8:1.1.1.1.0.22 netbsd-8-base:1.1.1.1 prg-localcount2-base3:1.1.1.1 prg-localcount2-base2:1.1.1.1 prg-localcount2-base1:1.1.1.1 prg-localcount2:1.1.1.1.0.20 prg-localcount2-base:1.1.1.1 pgoyette-localcount-20170426:1.1.1.1 bouyer-socketcan-base1:1.1.1.1 pgoyette-localcount-20170320:1.1.1.1 netbsd-7-1:1.1.1.1.0.18 netbsd-7-1-RELEASE:1.1.1.1 netbsd-7-1-RC2:1.1.1.1 netbsd-7-nhusb-base-20170116:1.1.1.1 bouyer-socketcan:1.1.1.1.0.16 bouyer-socketcan-base:1.1.1.1 pgoyette-localcount-20170107:1.1.1.1 netbsd-7-1-RC1:1.1.1.1 pgoyette-localcount-20161104:1.1.1.1 netbsd-7-0-2-RELEASE:1.1.1.1 localcount-20160914:1.1.1.1 netbsd-7-nhusb:1.1.1.1.0.14 netbsd-7-nhusb-base:1.1.1.1 pgoyette-localcount-20160806:1.1.1.1 pgoyette-localcount-20160726:1.1.1.1 pgoyette-localcount:1.1.1.1.0.12 pgoyette-localcount-base:1.1.1.1 netbsd-7-0-1-RELEASE:1.1.1.1 netbsd-7-0:1.1.1.1.0.10 netbsd-7-0-RELEASE:1.1.1.1 netbsd-7-0-RC3:1.1.1.1 netbsd-7-0-RC2:1.1.1.1 netbsd-7-0-RC1:1.1.1.1 tls-maxphys-base:1.1.1.1 tls-maxphys:1.1.1.1.0.8 netbsd-7:1.1.1.1.0.6 netbsd-7-base:1.1.1.1 yamt-pagecache:1.1.1.1.0.4 yamt-pagecache-base9:1.1.1.1 tls-earlyentropy:1.1.1.1.0.2 tls-earlyentropy-base:1.1.1.1 riastradh-xf86-video-intel-2-7-1-pre-2-21-15:1.1.1.1 riastradh-drm2-base3:1.1.1.1 gmp-5-1-3:1.1.1.1 gmp:1.1.1; locks; strict; comment @;; @; 1.2 date 2017.08.22.09.55.45; author mrg; state dead; branches; next 1.1; commitid DVNRZh45aSIRZb4A; 1.1 date 2013.11.29.07.49.48; author mrg; state Exp; branches 1.1.1.1; next ; commitid L2Av4PuGmdoL39fx; 1.1.1.1 date 2013.11.29.07.49.48; author mrg; state Exp; branches 1.1.1.1.4.1 1.1.1.1.8.1; next ; commitid L2Av4PuGmdoL39fx; 1.1.1.1.4.1 date 2013.11.29.07.49.48; author yamt; state dead; branches; next 1.1.1.1.4.2; commitid nx2BSsHy0NPeAxBx; 1.1.1.1.4.2 date 2014.05.22.14.09.01; author yamt; state Exp; branches; next ; commitid nx2BSsHy0NPeAxBx; 1.1.1.1.8.1 date 2013.11.29.07.49.48; author tls; state dead; branches; next 1.1.1.1.8.2; commitid jTnpym9Qu0o4R1Nx; 1.1.1.1.8.2 date 2014.08.19.23.59.50; author tls; state Exp; branches; next ; commitid jTnpym9Qu0o4R1Nx; desc @@ 1.2 log @merge GMP 6.1.2. @ text @dnl IA-64 mpn_tabselect. dnl Copyright 2011 Free Software Foundation, Inc. dnl This file is part of the GNU MP Library. dnl The GNU MP Library is free software; you can redistribute it and/or modify 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 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 Itanium: ? C Itanium 2: 2.5 C NOTES C * Using software pipelining could trivially yield 2 c/l without unrolling, C or 1+epsilon with unrolling. (This code was modelled after the powerpc64 C code, for simplicity.) C mpn_tabselect (mp_limb_t *rp, mp_limb_t *tp, mp_size_t n, mp_size_t nents, mp_size_t which) define(`rp', `r32') define(`tp', `r33') define(`n', `r34') define(`nents', `r35') define(`which', `r36') define(`mask', `r8') define(`rp1', `r32') define(`tp1', `r33') define(`rp2', `r14') define(`tp2', `r15') ASM_START() TEXT ALIGN(16) PROLOGUE(mpn_tabselect) .prologue .save ar.lc, r2 .body ifdef(`HAVE_ABI_32',` .mmi; addp4 rp = 0, rp C M I addp4 tp = 0, tp C M I zxt4 n = n C I .mii; nop 0 zxt4 nents = nents C I zxt4 which = which C I ;; ') .mmi; add rp2 = 8, rp1 add tp2 = 8, tp1 add r6 = -2, n ;; .mmi; cmp.eq p10, p0 = 1, n and r9 = 1, n C set cr0 for use in inner loop shr.u r6 = r6, 1 C inner loop count ;; .mmi; cmp.eq p8, p0 = 0, r9 sub which = nents, which shl n = n, 3 ;; L(outer): .mmi cmp.eq p6, p7 = which, nents C are we at the selected table entry? nop 0 mov ar.lc = r6 C I0 ;; .mmb; (p6) mov mask = -1 (p7) mov mask = 0 (p8) br.dptk L(top) C branch to loop entry if n even ;; .mmi; ld8 r16 = [tp1], 8 add tp2 = 8, tp2 nop 0 ;; .mmi; ld8 r18 = [rp1] and r16 = r16, mask nop 0 ;; .mmi; andcm r18 = r18, mask ;; or r16 = r16, r18 nop 0 ;; .mmb; st8 [rp1] = r16, 8 add rp2 = 8, rp2 (p10) br.dpnt L(end) ALIGN(32) L(top): .mmi; ld8 r16 = [tp1], 16 ld8 r17 = [tp2], 16 nop 0 ;; .mmi; ld8 r18 = [rp1] and r16 = r16, mask nop 0 .mmi; ld8 r19 = [rp2] and r17 = r17, mask nop 0 ;; .mmi; andcm r18 = r18, mask andcm r19 = r19, mask nop 0 ;; .mmi; or r16 = r16, r18 or r17 = r17, r19 nop 0 ;; .mmb; st8 [rp1] = r16, 16 st8 [rp2] = r17, 16 br.cloop.dptk L(top) ;; L(end): .mmi; sub rp1 = rp1, n C move rp back to beginning sub rp2 = rp2, n C move rp back to beginning cmp.ne p9, p0 = 1, nents .mmb; add nents = -1, nents nop 0 (p9) br.dptk L(outer) ;; .mib; nop 0 nop 0 br.ret.sptk.many b0 EPILOGUE() @ 1.1 log @Initial revision @ text @@ 1.1.1.1 log @initial import GMP 5.1.3 sources. changes include: fixes for: - mpn_sbpi1_div_qr_sec and mpn_sbpi1_div_r_sec - mpz_powm_ui - AMD family 11h - mpz_powm_sec and mpn_powm_sec - ASSERT() fixes - gcd, gcdext, and invert function fixes - some PPC division operations @ text @@ 1.1.1.1.8.1 log @file tabselect.asm was added on branch tls-maxphys on 2014-08-19 23:59:50 +0000 @ text @d1 139 @ 1.1.1.1.8.2 log @Rebase to HEAD as of a few days ago. @ text @a0 139 dnl IA-64 mpn_tabselect. dnl Copyright 2011 Free Software Foundation, Inc. dnl This file is part of the GNU MP Library. dnl The GNU MP Library is free software; you can redistribute it and/or modify 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 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 Itanium: ? C Itanium 2: 2.5 C NOTES C * Using software pipelining could trivially yield 2 c/l without unrolling, C or 1+epsilon with unrolling. (This code was modelled after the powerpc64 C code, for simplicity.) C mpn_tabselect (mp_limb_t *rp, mp_limb_t *tp, mp_size_t n, mp_size_t nents, mp_size_t which) define(`rp', `r32') define(`tp', `r33') define(`n', `r34') define(`nents', `r35') define(`which', `r36') define(`mask', `r8') define(`rp1', `r32') define(`tp1', `r33') define(`rp2', `r14') define(`tp2', `r15') ASM_START() TEXT ALIGN(16) PROLOGUE(mpn_tabselect) .prologue .save ar.lc, r2 .body ifdef(`HAVE_ABI_32',` .mmi; addp4 rp = 0, rp C M I addp4 tp = 0, tp C M I zxt4 n = n C I .mii; nop 0 zxt4 nents = nents C I zxt4 which = which C I ;; ') .mmi; add rp2 = 8, rp1 add tp2 = 8, tp1 add r6 = -2, n ;; .mmi; cmp.eq p10, p0 = 1, n and r9 = 1, n C set cr0 for use in inner loop shr.u r6 = r6, 1 C inner loop count ;; .mmi; cmp.eq p8, p0 = 0, r9 sub which = nents, which shl n = n, 3 ;; L(outer): .mmi cmp.eq p6, p7 = which, nents C are we at the selected table entry? nop 0 mov ar.lc = r6 C I0 ;; .mmb; (p6) mov mask = -1 (p7) mov mask = 0 (p8) br.dptk L(top) C branch to loop entry if n even ;; .mmi; ld8 r16 = [tp1], 8 add tp2 = 8, tp2 nop 0 ;; .mmi; ld8 r18 = [rp1] and r16 = r16, mask nop 0 ;; .mmi; andcm r18 = r18, mask ;; or r16 = r16, r18 nop 0 ;; .mmb; st8 [rp1] = r16, 8 add rp2 = 8, rp2 (p10) br.dpnt L(end) ALIGN(32) L(top): .mmi; ld8 r16 = [tp1], 16 ld8 r17 = [tp2], 16 nop 0 ;; .mmi; ld8 r18 = [rp1] and r16 = r16, mask nop 0 .mmi; ld8 r19 = [rp2] and r17 = r17, mask nop 0 ;; .mmi; andcm r18 = r18, mask andcm r19 = r19, mask nop 0 ;; .mmi; or r16 = r16, r18 or r17 = r17, r19 nop 0 ;; .mmb; st8 [rp1] = r16, 16 st8 [rp2] = r17, 16 br.cloop.dptk L(top) ;; L(end): .mmi; sub rp1 = rp1, n C move rp back to beginning sub rp2 = rp2, n C move rp back to beginning cmp.ne p9, p0 = 1, nents .mmb; add nents = -1, nents nop 0 (p9) br.dptk L(outer) ;; .mib; nop 0 nop 0 br.ret.sptk.many b0 EPILOGUE() @ 1.1.1.1.4.1 log @file tabselect.asm was added on branch yamt-pagecache on 2014-05-22 14:09:01 +0000 @ text @d1 139 @ 1.1.1.1.4.2 log @sync with head. for a reference, the tree before this commit was tagged as yamt-pagecache-tag8. this commit was splitted into small chunks to avoid a limitation of cvs. ("Protocol error: too many arguments") @ text @a0 139 dnl IA-64 mpn_tabselect. dnl Copyright 2011 Free Software Foundation, Inc. dnl This file is part of the GNU MP Library. dnl The GNU MP Library is free software; you can redistribute it and/or modify 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 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 Itanium: ? C Itanium 2: 2.5 C NOTES C * Using software pipelining could trivially yield 2 c/l without unrolling, C or 1+epsilon with unrolling. (This code was modelled after the powerpc64 C code, for simplicity.) C mpn_tabselect (mp_limb_t *rp, mp_limb_t *tp, mp_size_t n, mp_size_t nents, mp_size_t which) define(`rp', `r32') define(`tp', `r33') define(`n', `r34') define(`nents', `r35') define(`which', `r36') define(`mask', `r8') define(`rp1', `r32') define(`tp1', `r33') define(`rp2', `r14') define(`tp2', `r15') ASM_START() TEXT ALIGN(16) PROLOGUE(mpn_tabselect) .prologue .save ar.lc, r2 .body ifdef(`HAVE_ABI_32',` .mmi; addp4 rp = 0, rp C M I addp4 tp = 0, tp C M I zxt4 n = n C I .mii; nop 0 zxt4 nents = nents C I zxt4 which = which C I ;; ') .mmi; add rp2 = 8, rp1 add tp2 = 8, tp1 add r6 = -2, n ;; .mmi; cmp.eq p10, p0 = 1, n and r9 = 1, n C set cr0 for use in inner loop shr.u r6 = r6, 1 C inner loop count ;; .mmi; cmp.eq p8, p0 = 0, r9 sub which = nents, which shl n = n, 3 ;; L(outer): .mmi cmp.eq p6, p7 = which, nents C are we at the selected table entry? nop 0 mov ar.lc = r6 C I0 ;; .mmb; (p6) mov mask = -1 (p7) mov mask = 0 (p8) br.dptk L(top) C branch to loop entry if n even ;; .mmi; ld8 r16 = [tp1], 8 add tp2 = 8, tp2 nop 0 ;; .mmi; ld8 r18 = [rp1] and r16 = r16, mask nop 0 ;; .mmi; andcm r18 = r18, mask ;; or r16 = r16, r18 nop 0 ;; .mmb; st8 [rp1] = r16, 8 add rp2 = 8, rp2 (p10) br.dpnt L(end) ALIGN(32) L(top): .mmi; ld8 r16 = [tp1], 16 ld8 r17 = [tp2], 16 nop 0 ;; .mmi; ld8 r18 = [rp1] and r16 = r16, mask nop 0 .mmi; ld8 r19 = [rp2] and r17 = r17, mask nop 0 ;; .mmi; andcm r18 = r18, mask andcm r19 = r19, mask nop 0 ;; .mmi; or r16 = r16, r18 or r17 = r17, r19 nop 0 ;; .mmb; st8 [rp1] = r16, 16 st8 [rp2] = r17, 16 br.cloop.dptk L(top) ;; L(end): .mmi; sub rp1 = rp1, n C move rp back to beginning sub rp2 = rp2, n C move rp back to beginning cmp.ne p9, p0 = 1, nents .mmb; add nents = -1, nents nop 0 (p9) br.dptk L(outer) ;; .mib; nop 0 nop 0 br.ret.sptk.many b0 EPILOGUE() @