head 1.1; branch 1.1.1; access; symbols netbsd-11-0-RC4:1.1.1.3 netbsd-11-0-RC3:1.1.1.3 netbsd-11-0-RC2:1.1.1.3 netbsd-11-0-RC1:1.1.1.3 perseant-exfatfs-base-20250801:1.1.1.3 netbsd-11:1.1.1.3.0.18 netbsd-11-base:1.1.1.3 netbsd-10-1-RELEASE:1.1.1.3 perseant-exfatfs-base-20240630:1.1.1.3 perseant-exfatfs:1.1.1.3.0.16 perseant-exfatfs-base:1.1.1.3 netbsd-8-3-RELEASE:1.1.1.2 netbsd-9-4-RELEASE:1.1.1.3 netbsd-10-0-RELEASE:1.1.1.3 netbsd-10-0-RC6:1.1.1.3 netbsd-10-0-RC5:1.1.1.3 netbsd-10-0-RC4:1.1.1.3 netbsd-10-0-RC3:1.1.1.3 netbsd-10-0-RC2:1.1.1.3 netbsd-10-0-RC1:1.1.1.3 netbsd-10:1.1.1.3.0.14 netbsd-10-base:1.1.1.3 netbsd-9-3-RELEASE:1.1.1.3 gmp-6-2-1:1.1.1.3 cjep_sun2x-base1:1.1.1.3 cjep_sun2x:1.1.1.3.0.12 cjep_sun2x-base:1.1.1.3 cjep_staticlib_x-base1:1.1.1.3 netbsd-9-2-RELEASE:1.1.1.3 cjep_staticlib_x:1.1.1.3.0.10 cjep_staticlib_x-base:1.1.1.3 netbsd-9-1-RELEASE:1.1.1.3 gmp-6-2-0:1.1.1.3 phil-wifi-20200421:1.1.1.3 phil-wifi-20200411:1.1.1.3 is-mlppp:1.1.1.3.0.8 is-mlppp-base:1.1.1.3 phil-wifi-20200406:1.1.1.3 netbsd-8-2-RELEASE:1.1.1.2 netbsd-9-0-RELEASE:1.1.1.3 netbsd-9-0-RC2:1.1.1.3 netbsd-9-0-RC1:1.1.1.3 phil-wifi-20191119:1.1.1.3 netbsd-9:1.1.1.3.0.6 netbsd-9-base:1.1.1.3 phil-wifi-20190609:1.1.1.3 netbsd-8-1-RELEASE:1.1.1.2 netbsd-8-1-RC1:1.1.1.2 pgoyette-compat-merge-20190127:1.1.1.3 pgoyette-compat-20190127:1.1.1.3 pgoyette-compat-20190118:1.1.1.3 pgoyette-compat-1226:1.1.1.3 pgoyette-compat-1126:1.1.1.3 pgoyette-compat-1020:1.1.1.3 pgoyette-compat-0930:1.1.1.3 pgoyette-compat-0906:1.1.1.3 netbsd-7-2-RELEASE:1.1.1.2 pgoyette-compat-0728:1.1.1.3 netbsd-8-0-RELEASE:1.1.1.2 phil-wifi:1.1.1.3.0.4 phil-wifi-base:1.1.1.3 pgoyette-compat-0625:1.1.1.3 netbsd-8-0-RC2:1.1.1.2 pgoyette-compat-0521:1.1.1.3 pgoyette-compat-0502:1.1.1.3 pgoyette-compat-0422:1.1.1.3 netbsd-8-0-RC1:1.1.1.2 pgoyette-compat-0415:1.1.1.3 pgoyette-compat-0407:1.1.1.3 pgoyette-compat-0330:1.1.1.3 pgoyette-compat-0322:1.1.1.3 pgoyette-compat-0315:1.1.1.3 netbsd-7-1-2-RELEASE:1.1.1.2 pgoyette-compat:1.1.1.3.0.2 pgoyette-compat-base:1.1.1.3 netbsd-7-1-1-RELEASE:1.1.1.2 matt-nb8-mediatek:1.1.1.2.0.22 matt-nb8-mediatek-base:1.1.1.2 gmp-6-1-2:1.1.1.3 perseant-stdc-iso10646:1.1.1.2.0.20 perseant-stdc-iso10646-base:1.1.1.2 netbsd-8:1.1.1.2.0.18 netbsd-8-base:1.1.1.2 prg-localcount2-base3:1.1.1.2 prg-localcount2-base2:1.1.1.2 prg-localcount2-base1:1.1.1.2 prg-localcount2:1.1.1.2.0.16 prg-localcount2-base:1.1.1.2 pgoyette-localcount-20170426:1.1.1.2 bouyer-socketcan-base1:1.1.1.2 pgoyette-localcount-20170320:1.1.1.2 netbsd-7-1:1.1.1.2.0.14 netbsd-7-1-RELEASE:1.1.1.2 netbsd-7-1-RC2:1.1.1.2 netbsd-7-nhusb-base-20170116:1.1.1.2 bouyer-socketcan:1.1.1.2.0.12 bouyer-socketcan-base:1.1.1.2 pgoyette-localcount-20170107:1.1.1.2 netbsd-7-1-RC1:1.1.1.2 pgoyette-localcount-20161104:1.1.1.2 netbsd-7-0-2-RELEASE:1.1.1.2 localcount-20160914:1.1.1.2 netbsd-7-nhusb:1.1.1.2.0.10 netbsd-7-nhusb-base:1.1.1.2 pgoyette-localcount-20160806:1.1.1.2 pgoyette-localcount-20160726:1.1.1.2 pgoyette-localcount:1.1.1.2.0.8 pgoyette-localcount-base:1.1.1.2 netbsd-7-0-1-RELEASE:1.1.1.2 netbsd-7-0:1.1.1.2.0.6 netbsd-7-0-RELEASE:1.1.1.2 netbsd-7-0-RC3:1.1.1.2 netbsd-7-0-RC2:1.1.1.2 netbsd-7-0-RC1:1.1.1.2 netbsd-6-0-6-RELEASE:1.1.1.1 netbsd-6-1-5-RELEASE:1.1.1.1 netbsd-7:1.1.1.2.0.4 netbsd-7-base:1.1.1.2 yamt-pagecache-base9:1.1.1.2 yamt-pagecache-tag8:1.1.1.1 netbsd-6-1-4-RELEASE:1.1.1.1 netbsd-6-0-5-RELEASE:1.1.1.1 tls-earlyentropy:1.1.1.2.0.2 tls-earlyentropy-base:1.1.1.2 riastradh-xf86-video-intel-2-7-1-pre-2-21-15:1.1.1.2 riastradh-drm2-base3:1.1.1.2 netbsd-6-1-3-RELEASE:1.1.1.1 netbsd-6-0-4-RELEASE:1.1.1.1 gmp-5-1-3:1.1.1.2 netbsd-6-1-2-RELEASE:1.1.1.1 netbsd-6-0-3-RELEASE:1.1.1.1 netbsd-6-1-1-RELEASE:1.1.1.1 riastradh-drm2-base2:1.1.1.1 riastradh-drm2-base1:1.1.1.1 riastradh-drm2:1.1.1.1.0.12 riastradh-drm2-base:1.1.1.1 netbsd-6-1:1.1.1.1.0.16 netbsd-6-0-2-RELEASE:1.1.1.1 netbsd-6-1-RELEASE:1.1.1.1 netbsd-6-1-RC4:1.1.1.1 netbsd-6-1-RC3:1.1.1.1 agc-symver:1.1.1.1.0.14 agc-symver-base:1.1.1.1 netbsd-6-1-RC2:1.1.1.1 netbsd-6-1-RC1:1.1.1.1 yamt-pagecache-base8:1.1.1.1 netbsd-6-0-1-RELEASE:1.1.1.1 yamt-pagecache-base7:1.1.1.1 matt-nb6-plus-nbase:1.1.1.1 yamt-pagecache-base6:1.1.1.1 netbsd-6-0:1.1.1.1.0.10 netbsd-6-0-RELEASE:1.1.1.1 netbsd-6-0-RC2:1.1.1.1 tls-maxphys:1.1.1.1.0.8 tls-maxphys-base:1.1.1.2 matt-nb6-plus:1.1.1.1.0.6 matt-nb6-plus-base:1.1.1.1 netbsd-6-0-RC1:1.1.1.1 yamt-pagecache-base5:1.1.1.1 yamt-pagecache-base4:1.1.1.1 netbsd-6:1.1.1.1.0.4 netbsd-6-base:1.1.1.1 yamt-pagecache-base3:1.1.1.1 yamt-pagecache-base2:1.1.1.1 yamt-pagecache:1.1.1.1.0.2 yamt-pagecache-base:1.1.1.1 gmp-5-0-2:1.1.1.1 gmp:1.1.1; locks; strict; comment @;; @; 1.1 date 2011.06.20.05.54.39; author mrg; state Exp; branches 1.1.1.1; next ; 1.1.1.1 date 2011.06.20.05.54.39; author mrg; state Exp; branches 1.1.1.1.2.1 1.1.1.1.8.1; next 1.1.1.2; 1.1.1.2 date 2013.11.29.07.49.48; author mrg; state Exp; branches; next 1.1.1.3; commitid L2Av4PuGmdoL39fx; 1.1.1.3 date 2017.08.22.09.40.49; author mrg; state Exp; branches; next ; commitid W5kmAIk8hwVpSb4A; 1.1.1.1.2.1 date 2014.05.22.14.09.01; author yamt; state Exp; branches; next ; commitid nx2BSsHy0NPeAxBx; 1.1.1.1.8.1 date 2014.08.19.23.59.50; author tls; state Exp; branches; next ; commitid jTnpym9Qu0o4R1Nx; desc @@ 1.1 log @Initial revision @ text @dnl IA-64 mpn_add_n/mpn_sub_n -- mpn addition and subtraction. dnl Copyright 2003, 2004, 2005 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: 2.67 C Itanium 2: 1.25 C TODO C * Consider using special code for small n, using something like C "switch (8 * (n >= 8) + (n mod 8))" to enter it and feed-in code. C INPUT PARAMETERS define(`rp',`r32') define(`up',`r33') define(`vp',`r34') define(`n',`r35') ifdef(`OPERATION_add_n',` define(ADDSUB, add) define(PRED, ltu) define(INCR, 1) define(LIM, -1) define(func, mpn_add_n) ') ifdef(`OPERATION_sub_n',` define(ADDSUB, sub) define(PRED, gtu) define(INCR, -1) define(LIM, 0) define(func, mpn_sub_n) ') C Some useful aliases for registers we use define(`u0',`r14') define(`u1',`r15') define(`u2',`r16') define(`u3',`r17') define(`u4',`r18') define(`u5',`r19') define(`u6',`r20') define(`u7',`r21') define(`v0',`r24') define(`v1',`r25') define(`v2',`r26') define(`v3',`r27') define(`v4',`r28') define(`v5',`r29') define(`v6',`r30') define(`v7',`r31') define(`w0',`r22') define(`w1',`r9') define(`w2',`r8') define(`w3',`r23') define(`w4',`r22') define(`w5',`r9') define(`w6',`r8') define(`w7',`r23') define(`rpx',`r3') MULFUNC_PROLOGUE(mpn_add_n mpn_sub_n) ASM_START() PROLOGUE(func) .prologue .save ar.lc, r2 .body ifdef(`HAVE_ABI_32',` addp4 rp = 0, rp C M I addp4 up = 0, up C M I addp4 vp = 0, vp C M I zxt4 n = n C I ;; ') {.mmi C 00 ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov.i r2 = ar.lc C I0 } {.mmi and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -8, n C M I ;; } {.mmi C 01 cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I } {.bbb (p6) br.dptk .Lb001 C B (p7) br.dptk .Lb010 C B (p8) br.dptk .Lb011 C B ;; } {.mmi C 02 cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I } {.bbb (p9) br.dptk .Lb100 C B (p10) br.dptk .Lb101 C B (p11) br.dptk .Lb110 C B ;; } C 03 {.mmb cmp.eq p12, p0 = 7, r14 C M I add n = -1, n C loop count M I (p12) br.dptk .Lb111 C B } .Lb000: ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 add rpx = 8, rp C M I ;; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; ld8 v4 = [vp], 8 C M01 ld8 u4 = [up], 8 C M01 cmp.PRED p7, p0 = w1, r10 C M I ;; ld8 v5 = [vp], 8 C M01 ld8 u5 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I ;; ld8 v6 = [vp], 8 C M01 ld8 u6 = [up], 8 C M01 cmp.PRED p8, p0 = w2, u2 C M I ;; ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 cmp.PRED p9, p0 = w3, u3 C M I (p7) cmp.eq.or p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I (p14) br.cond.dptk .Lcj8 C B ;; .grt8: ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; add r11 = 512, vp ld8 v2 = [vp], 8 C M01 add r10 = 512, up ld8 u2 = [up], 8 C M01 nop.i 0 nop.b 0 ;; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov.i ar.lc = n C I0 br .LL000 C B .Lb001: add rpx = 16, rp C M I ADDSUB w0 = r10, r11 C M I (p15) br.cond.dpnt .grt1 C B ;; cmp.PRED p6, p0 = w0, r10 C M I mov r8 = 0 C M I br .Lcj1 C B .grt1: ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.ne p9, p0 = r0, r0 C read near Loop ;; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov.i ar.lc = n C I0 ;; ld8 v4 = [vp], 8 C M01 ld8 u4 = [up], 8 C M01 cmp.PRED p6, p0 = w0, r10 C M I ;; ld8 v5 = [vp], 8 C M01 ld8 u5 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I ;; ld8 v6 = [vp], 8 C M01 ld8 u6 = [up], 8 C M01 cmp.PRED p7, p0 = w1, u1 C M I ;; ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I ;; add r11 = 512, vp ld8 v0 = [vp], 8 C M01 add r10 = 512, up ld8 u0 = [up], 8 C M01 br.cloop.dptk .Loop C B br .Lcj9 C B .Lb010: ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 add rpx = 24, rp C M I ADDSUB w7 = r10, r11 C M I (p15) br.cond.dpnt .grt2 C B ;; cmp.PRED p9, p0 = w7, r10 C M I ADDSUB w0 = u0, v0 C M I br .Lcj2 C B .grt2: ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ;; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov.i ar.lc = n C I0 ;; ld8 v4 = [vp], 8 C M01 ld8 u4 = [up], 8 C M01 ;; ld8 v5 = [vp], 8 C M01 ld8 u5 = [up], 8 C M01 cmp.PRED p9, p0 = w7, r10 C M I ;; ld8 v6 = [vp], 8 C M01 ld8 u6 = [up], 8 C M01 ADDSUB w0 = u0, v0 C M I ;; add r11 = 512, vp ld8 v7 = [vp], 8 C M01 add r10 = 512, up ld8 u7 = [up], 8 C M01 br .LL01x C B .Lb011: ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 ADDSUB w6 = r10, r11 C M I ;; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br.cond.dpnt .grt3 C B ;; cmp.PRED p8, p0 = w6, r10 C M I ADDSUB w7 = u7, v7 C M I ;; st8 [rp] = w6, 8 C M23 cmp.PRED p9, p0 = w7, u7 C M I br .Lcj3 C B .grt3: ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 add rpx = 32, rp C M I ;; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.PRED p8, p0 = w6, r10 C M I ;; ld8 v4 = [vp], 8 C M01 ld8 u4 = [up], 8 C M01 mov.i ar.lc = n C I0 ADDSUB w7 = u7, v7 C M I nop.i 0 nop.b 0 ;; ld8 v5 = [vp], 8 C M01 ld8 u5 = [up], 8 C M01 cmp.PRED p9, p0 = w7, u7 C M I ;; add r11 = 512, vp ld8 v6 = [vp], 8 C M01 add r10 = 512, up ld8 u6 = [up], 8 C M01 (p8) cmp.eq.or p9, p0 = LIM, w7 C M I ;; ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 (p8) add w7 = INCR, w7 C M I st8 [rp] = w6, 8 C M23 ADDSUB w0 = u0, v0 C M I br .LL01x C B .Lb100: ld8 v6 = [vp], 8 C M01 ld8 u6 = [up], 8 C M01 add rpx = 8, rp C M I ;; ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 ADDSUB w5 = r10, r11 C M I ;; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br.cond.dpnt .grt4 C B ;; cmp.PRED p7, p0 = w5, r10 C M I ADDSUB w6 = u6, v6 C M I ;; cmp.PRED p8, p0 = w6, u6 C M I ADDSUB w7 = u7, v7 C M I br .Lcj4 C B .grt4: ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 cmp.PRED p7, p0 = w5, r10 C M I ;; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w6 = u6, v6 C M I ;; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.PRED p8, p0 = w6, u6 C M I ;; ld8 v4 = [vp], 8 C M01 ld8 u4 = [up], 8 C M01 mov.i ar.lc = n C I0 ;; ld8 v5 = [vp], 8 C M01 ld8 u5 = [up], 8 C M01 ADDSUB w7 = u7, v7 C M I ;; add r11 = 512, vp ld8 v6 = [vp], 8 C M01 add r10 = 512, up ld8 u6 = [up], 8 C M01 cmp.PRED p9, p0 = w7, u7 C M I ;; ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 (p7) cmp.eq.or p8, p0 = LIM, w6 C M I (p7) add w6 = INCR, w6 C M I br .LL100 C B .Lb101: ld8 v5 = [vp], 8 C M01 ld8 u5 = [up], 8 C M01 add rpx = 16, rp C M I ;; ld8 v6 = [vp], 8 C M01 ld8 u6 = [up], 8 C M01 ADDSUB w4 = r10, r11 C M I ;; ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 cmp.PRED p6, p0 = w4, r10 C M I ;; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w5 = u5, v5 C M I shr.u n = n, 3 C I0 (p15) br.cond.dpnt .grt5 C B ;; cmp.PRED p7, p0 = w5, u5 C M I ADDSUB w6 = u6, v6 C M I br .Lcj5 C B .grt5: ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ;; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov.i ar.lc = n C I0 ;; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.PRED p7, p0 = w5, u5 C M I ;; ld8 v4 = [vp], 8 C M01 ld8 u4 = [up], 8 C M01 ADDSUB w6 = u6, v6 C M I ;; add r11 = 512, vp ld8 v5 = [vp], 8 C M01 add r10 = 512, up ld8 u5 = [up], 8 C M01 br .LL101 C B .Lb110: ld8 v4 = [vp], 8 C M01 ld8 u4 = [up], 8 C M01 add rpx = 24, rp C M I ;; ld8 v5 = [vp], 8 C M01 ld8 u5 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; ld8 v6 = [vp], 8 C M01 ld8 u6 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 cmp.PRED p9, p0 = w3, r10 C M I ;; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w4 = u4, v4 C M I (p14) br.cond.dptk .Lcj67 C B ;; .grt6: ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 mov.i ar.lc = n C I0 cmp.PRED p9, p0 = w3, r10 C M I nop.i 0 nop.b 0 ;; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w4 = u4, v4 C M I ;; add r11 = 512, vp ld8 v3 = [vp], 8 C M01 add r10 = 512, up ld8 u3 = [up], 8 C M01 br .LL11x C B .Lb111: ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 add rpx = 32, rp C M I ;; ld8 v4 = [vp], 8 C M01 ld8 u4 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; ld8 v5 = [vp], 8 C M01 ld8 u5 = [up], 8 C M01 cmp.PRED p8, p0 = w2, r10 C M I ;; ld8 v6 = [vp], 8 C M01 ld8 u6 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; ld8 v7 = [vp], 8 C M01 ld8 u7 = [up], 8 C M01 cmp.PRED p9, p0 = w3, u3 C M I ;; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br.cond.dpnt .grt7 C B ;; st8 [rp] = w2, 8 C M23 (p8) cmp.eq.or p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I ADDSUB w4 = u4, v4 C M I br .Lcj67 C B .grt7: ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 (p8) cmp.eq.or p9, p0 = LIM, w3 C M I nop.i 0 nop.b 0 ;; add r11 = 512, vp ld8 v2 = [vp], 8 C M01 add r10 = 512, up ld8 u2 = [up], 8 C M01 (p8) add w3 = INCR, w3 C M I nop.b 0 ;; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov.i ar.lc = n C I0 st8 [rp] = w2, 8 C M23 ADDSUB w4 = u4, v4 C M I br .LL11x C B C *** MAIN LOOP START *** ALIGN(32) .Loop: ld8 v1 = [vp], 8 C M01 cmp.PRED p7, p0 = w1, u1 C M I (p9) cmp.eq.or p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; ld8 v2 = [vp], 8 C M01 cmp.PRED p8, p0 = w2, u2 C M I (p6) cmp.eq.or p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.PRED p9, p0 = w3, u3 C M I (p7) cmp.eq.or p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; .LL000: st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmp.eq.or p9, p0 = LIM, w3 C M I lfetch [r10], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w4 = u4, v4 C M I ;; .LL11x: st8 [rp] = w3, 8 C M23 ld8 v4 = [vp], 8 C M01 cmp.PRED p6, p0 = w4, u4 C M I ld8 u4 = [up], 8 C M01 ADDSUB w5 = u5, v5 C M I ;; ld8 v5 = [vp], 8 C M01 cmp.PRED p7, p0 = w5, u5 C M I (p9) cmp.eq.or p6, p0 = LIM, w4 C M I ld8 u5 = [up], 8 C M01 (p9) add w4 = INCR, w4 C M I ADDSUB w6 = u6, v6 C M I ;; .LL101: ld8 v6 = [vp], 8 C M01 cmp.PRED p8, p0 = w6, u6 C M I (p6) cmp.eq.or p7, p0 = LIM, w5 C M I ld8 u6 = [up], 8 C M01 (p6) add w5 = INCR, w5 C M I ADDSUB w7 = u7, v7 C M I ;; st8 [rp] = w4, 8 C M23 ld8 v7 = [vp], 8 C M01 cmp.PRED p9, p0 = w7, u7 C M I (p7) cmp.eq.or p8, p0 = LIM, w6 C M I ld8 u7 = [up], 8 C M01 (p7) add w6 = INCR, w6 C M I ;; .LL100: st8 [rp] = w5, 16 C M23 st8 [rpx] = w6, 32 C M23 (p8) cmp.eq.or p9, p0 = LIM, w7 C M I lfetch [r11], 64 (p8) add w7 = INCR, w7 C M I ADDSUB w0 = u0, v0 C M I ;; .LL01x: st8 [rp] = w7, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.PRED p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br.cloop.dptk .Loop C B ;; C *** MAIN LOOP END *** cmp.PRED p7, p0 = w1, u1 C M I (p9) cmp.eq.or p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; .Lcj9: cmp.PRED p8, p0 = w2, u2 C M I (p6) cmp.eq.or p7, p0 = LIM, w1 C M I st8 [rp] = w0, 8 C M23 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; cmp.PRED p9, p0 = w3, u3 C M I (p7) cmp.eq.or p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I ;; .Lcj8: st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmp.eq.or p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I ADDSUB w4 = u4, v4 C M I ;; .Lcj67: st8 [rp] = w3, 8 C M23 cmp.PRED p6, p0 = w4, u4 C M I ADDSUB w5 = u5, v5 C M I ;; cmp.PRED p7, p0 = w5, u5 C M I (p9) cmp.eq.or p6, p0 = LIM, w4 C M I (p9) add w4 = INCR, w4 C M I ADDSUB w6 = u6, v6 C M I ;; .Lcj5: cmp.PRED p8, p0 = w6, u6 C M I (p6) cmp.eq.or p7, p0 = LIM, w5 C M I st8 [rp] = w4, 8 C M23 (p6) add w5 = INCR, w5 C M I ADDSUB w7 = u7, v7 C M I ;; .Lcj4: cmp.PRED p9, p0 = w7, u7 C M I (p7) cmp.eq.or p8, p0 = LIM, w6 C M I (p7) add w6 = INCR, w6 C M I ;; st8 [rp] = w5, 16 C M23 st8 [rpx] = w6, 32 C M23 .Lcj3: (p8) cmp.eq.or p9, p0 = LIM, w7 C M I (p8) add w7 = INCR, w7 C M I ADDSUB w0 = u0, v0 C M I ;; .Lcj2: st8 [rp] = w7, 8 C M23 cmp.PRED p6, p0 = w0, u0 C M I ;; (p9) cmp.eq.or p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I mov r8 = 0 C M I ;; .Lcj1: st8 [rp] = w0, 8 C M23 mov.i ar.lc = r2 C I0 (p6) mov r8 = 1 C M I br.ret.sptk.many b0 C B EPILOGUE() ASM_END() @ 1.1.1.1 log @initial import of GMP 5.0.2. GNU MP is a library for arbitrary precision arithmetic, operating on signed integers, rational numbers, and floating point numbers. It has a rich set of functions, and the functions have a regular interface. GMP is necessary for GCC >= 4.2. @ text @@ 1.1.1.1.8.1 log @Rebase to HEAD as of a few days ago. @ text @d3 1 a3 3 dnl Contributed to the GNU project by Torbjorn Granlund. dnl Copyright 2003, 2004, 2005, 2010, 2011 Free Software Foundation, Inc. a28 6 C * The non-nc code was trimmed cycle for cycle to its current state. It is C probably hard to save more that an odd cycle there. The nc code is much C rawer (since tune/speed doesn't have any applicable direct measurements). C * Without the nc entry points, this becomes around 1800 bytes of object C code; the nc code adds over 1000 bytes. We should perhaps sacrifice a C few cycles for the non-nc code and let it fall into the nc code. d31 4 a34 5 define(`rp', `r32') define(`up', `r33') define(`vp', `r34') define(`n', `r35') define(`cy', `r36') d38 1 a38 1 define(CND, ltu) d41 1 a41 3 define(LIM2, 0) define(func, mpn_add_n) define(func_nc, mpn_add_nc) d45 1 a45 1 define(CND, gtu) d48 1 a48 3 define(LIM2, -1) define(func, mpn_sub_n) define(func_nc, mpn_sub_nc) a50 3 define(cmpeqor, `cmp.eq.or') define(PFDIST, 500) d53 1 d55 3 a57 1 define(`w0',`r28') define(`w1',`r29') define(`w2',`r30') define(`w3',`r31') a58 1 define(`upadv',`r20') define(`vpadv',`r21') d60 1 a60 1 MULFUNC_PROLOGUE(mpn_add_n mpn_add_nc mpn_sub_n mpn_sub_nc) d63 1 a63 1 PROLOGUE(func_nc) d68 4 a71 4 addp4 rp = 0, rp C M I addp4 up = 0, up C M I addp4 vp = 0, vp C M I zxt4 n = n C I d74 9 a82 7 {.mmi; ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov r2 = ar.lc C I0 }{.mmi; and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -6, n C M I d85 9 a93 11 .mmi; add upadv = PFDIST, up C Merging these lines into the feed-in add vpadv = PFDIST, vp C code could save a cycle per call at mov r23 = cy C the expense of code size. ;; {.mmi; cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I }{.bbb (p6) br.dptk .Lc001 C B (p7) br.dptk .Lc010 C B (p8) br.dptk .Lc011 C B d96 4 a99 15 {.mmi; cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I }{.bbb (p9) br.dptk .Lc100 C B (p10) br.dptk .Lc101 C B (p11) br.dptk .Lc110 C B ;; }{.mmi; ld8 r19 = [vp], 8 C M01 ld8 r18 = [up], 8 C M01 cmp.ne p13, p0 = 0, cy C copy cy to p13 M I }{.mmb; cmp.eq p12, p0 = 7, r14 C M I nop 0 (p12) br.dptk .Lc111 C B ;; d101 10 a110 326 .Lc000: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add vpadv = PFDIST, vp C M I ld8 v0 = [vp], 8 C M01 mov ar.lc = n C I0 .mmi; ld8 u0 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I nop 0 ;; .mmi; add upadv = PFDIST, up C M I ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r18, r19 C M I add rpx = 8, rp C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r18 C M I (p13) cmpeqor p7, p0 = LIM, w1 C M I .mmi; ld8 u2 = [up], 8 C M01 (p13) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m0) .Lc001: .mmi; (p15) ld8 v1 = [vp], 8 C M01 (p15) ld8 u1 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I .mmb; nop 0 nop 0 (p15) br 1f ;; .mmi; cmp.ne p9, p0 = 0, r23 C M I mov r8 = 0 cmp.CND p6, p0 = w0, r10 C M I ;; .mmb; (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I br L(cj1) C B 1: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov ar.lc = n C I0 .mmi; nop 0 cmp.ne p9, p0 = 0, r23 C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I add rpx = 16, rp C M I .mmb; ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br L(c1) C B .Lc010: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 mov r8 = 0 C M I .mmb; ADDSUB w3 = r10, r11 C M I cmp.ne p8, p0 = 0, r23 C M I (p15) br 1f C B ;; .mmi; cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I (p8) add w3 = INCR, w3 C M I ;; .mmb; cmp.CND p6, p0 = w0, u0 C M I (p8) cmpeqor p9, p0 = LIM2, w3 C M I br L(cj2) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ;; .mmi; (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I .mmb; add rpx = 24, rp C M I nop 0 br L(m23) C B .Lc011: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmi; ADDSUB w2 = r10, r11 C M I cmp.ne p7, p0 = 0, r23 C M I nop 0 ;; .mmb; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br 1f C B .mmi; cmp.CND p8, p0 = w2, r10 C M I ADDSUB w3 = u3, v3 C M I nop 0 ;; .mmb; (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I br L(cj3) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I mov ar.lc = n C I0 .mmi; ld8 u3 = [up], 8 C M01 (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m23) .Lc100: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmi; ADDSUB w1 = r10, r11 C M I nop 0 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 add rpx = 8, rp C M I .mmi; cmp.ne p6, p0 = 0, r23 C M I cmp.CND p7, p0 = w1, r10 C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I .mmb; (p6) cmpeqor p7, p0 = LIM, w1 C M I (p6) add w1 = INCR, w1 C M I (p14) br L(cj4) ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I nop 0 .mmi; ld8 u2 = [up], 8 C M01 nop 0 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m4) .Lc101: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I .mmi; cmp.ne p9, p0 = 0, r23 C M I add rpx = 16, rp C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I ld8 u0 = [up], 8 C M01 .mbb; ADDSUB w1 = u1, v1 C M I (p15) br L(c5) C B br L(end) C B .Lc110: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up C M I add vpadv = PFDIST, vp C M I mov ar.lc = n C I0 .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w0 = u0, v0 C M I .mmi; cmp.CND p9, p0 = w3, r10 C M I cmp.ne p8, p0 = 0, r23 C M I add rpx = 24, rp C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 nop 0 .mmb; (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I br L(m67) C B .Lc111: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up C M I ld8 v1 = [vp], 8 C M01 mov ar.lc = n C I0 .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I nop 0 ;; .mmi; add vpadv = PFDIST, vp C M I ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = r18, r19 C M I nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r18 C M I (p13) cmpeqor p8, p0 = LIM, w2 C M I .mmi; ld8 u3 = [up], 8 C M01 (p13) add w2 = INCR, w2 C M I nop 0 ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m67) EPILOGUE() ASM_START() PROLOGUE(func) .prologue .save ar.lc, r2 .body ifdef(`HAVE_ABI_32',` addp4 rp = 0, rp C M I addp4 up = 0, up C M I addp4 vp = 0, vp C M I zxt4 n = n C I ;; ') {.mmi; ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov r2 = ar.lc C I0 }{.mmi; and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -6, n C M I ;; }{.mmi; cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I }{.bbb (p6) br.dptk .Lb001 C B (p7) br.dptk .Lb010 C B (p8) br.dptk .Lb011 C B ;; }{.mmi; cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I }{.bbb (p9) br.dptk .Lb100 C B (p10) br.dptk .Lb101 C B (p11) br.dptk .Lb110 C B ;; }{.mmi; ld8 r19 = [vp], 8 C M01 ld8 r18 = [up], 8 C M01 cmp.ne p13, p0 = r0, r0 C clear "CF" M I }{.mmb; cmp.eq p12, p0 = 7, r14 C M I mov r23 = 0 C M I (p12) br.dptk .Lb111 C B ;; a112 269 .Lb000: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I mov ar.lc = n C I0 .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r18, r19 C M I add rpx = 8, rp C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp cmp.CND p8, p0 = w2, r18 C M I .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m0) C B ALIGN(32) .Lb001: .mmi; ADDSUB w0 = r10, r11 C M I (p15) ld8 v1 = [vp], 8 C M01 mov r8 = 0 C M I ;; .mmb; cmp.CND p6, p0 = w0, r10 C M I (p15) ld8 u1 = [up], 8 C M01 (p14) br L(cj1) C B ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp shr.u n = n, 3 C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I ;; .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I ADDSUB w2 = u2, v2 C M I .mmb; ld8 u1 = [up], 8 C M01 add rpx = 16, rp C M I br L(m1) C B ALIGN(32) .Lb010: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmb; ADDSUB w3 = r10, r11 C M I nop 0 (p15) br L(gt2) C B ;; .mmi; cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I mov r8 = 0 C M I ;; .mmb; nop 0 cmp.CND p6, p0 = w0, u0 C M I br L(cj2) C B L(gt2): .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 nop 0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I .mmb; ld8 u3 = [up], 8 C M01 add rpx = 24, rp C M I br L(m23) C B ALIGN(32) .Lb011: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; .mmb; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br 1f C B .mmb; cmp.CND p8, p0 = w2, r10 C M I ADDSUB w3 = u3, v3 C M I br L(cj3) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp ADDSUB w3 = u3, v3 C M I .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I mov ar.lc = n C I0 .mmi; ld8 u3 = [up], 8 C M01 nop 0 nop 0 ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m23) C B ALIGN(32) .Lb100: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I .mmb; nop 0 ADDSUB w2 = u2, v2 C M I (p14) br L(cj4) C B ;; L(gt4): .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I nop 0 .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I add rpx = 8, rp C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m4) C B ALIGN(32) .Lb101: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp add rpx = 16, rp C M I ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I nop 0 .mmb; ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I (p14) br L(cj5) C B ;; L(gt5): .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I mov ar.lc = n C I0 .mmb; ld8 u1 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I br L(m5) C B ALIGN(32) .Lb110: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I .mmb; ld8 u3 = [up], 8 C M01 add rpx = 24, rp C M I br L(m67) C B ALIGN(32) .Lb111: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I mov ar.lc = n C I0 .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = r18, r19 C M I nop 0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp nop 0 .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.CND p9, p0 = w3, r18 C M I ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m67) C B d114 364 d481 68 a548 70 L(top): L(c5): ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I (p9) cmpeqor p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; L(m5): ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I (p6) cmpeqor p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; L(m4): st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I lfetch [upadv], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I ;; L(m23): st8 [rp] = w3, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I nop.b 0 ;; L(c1): ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I (p9) cmpeqor p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; L(m1): ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I (p6) cmpeqor p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; L(m0): st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I lfetch [vpadv], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I ;; L(m67): st8 [rp] = w3, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br.cloop.dptk L(top) C B d552 58 a609 42 L(end): .mmi; (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I mov ar.lc = r2 C I0 L(cj5): .mmi; cmp.CND p7, p0 = w1, u1 C M I ADDSUB w2 = u2, v2 C M I nop 0 ;; .mmi; st8 [rp] = w0, 8 C M23 (p6) cmpeqor p7, p0 = LIM, w1 C M I (p6) add w1 = INCR, w1 C M I L(cj4): .mmi; cmp.CND p8, p0 = w2, u2 C M I ADDSUB w3 = u3, v3 C M I nop 0 ;; .mmi; st8 [rp] = w1, 8 C M23 (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I L(cj3): .mmi; cmp.CND p9, p0 = w3, u3 C M I ADDSUB w0 = u0, v0 C M I nop 0 ;; .mmi; st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I .mmi; cmp.CND p6, p0 = w0, u0 C M I nop 0 mov r8 = 0 C M I ;; L(cj2): .mmi; st8 [rp] = w3, 8 C M23 (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I ;; L(cj1): .mmb; st8 [rp] = w0, 8 C M23 (p6) mov r8 = 1 C M I br.ret.sptk.many b0 C B @ 1.1.1.1.2.1 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 @d3 1 a3 3 dnl Contributed to the GNU project by Torbjorn Granlund. dnl Copyright 2003, 2004, 2005, 2010, 2011 Free Software Foundation, Inc. a28 6 C * The non-nc code was trimmed cycle for cycle to its current state. It is C probably hard to save more that an odd cycle there. The nc code is much C rawer (since tune/speed doesn't have any applicable direct measurements). C * Without the nc entry points, this becomes around 1800 bytes of object C code; the nc code adds over 1000 bytes. We should perhaps sacrifice a C few cycles for the non-nc code and let it fall into the nc code. d31 4 a34 5 define(`rp', `r32') define(`up', `r33') define(`vp', `r34') define(`n', `r35') define(`cy', `r36') d38 1 a38 1 define(CND, ltu) d41 1 a41 3 define(LIM2, 0) define(func, mpn_add_n) define(func_nc, mpn_add_nc) d45 1 a45 1 define(CND, gtu) d48 1 a48 3 define(LIM2, -1) define(func, mpn_sub_n) define(func_nc, mpn_sub_nc) a50 3 define(cmpeqor, `cmp.eq.or') define(PFDIST, 500) d53 1 d55 3 a57 1 define(`w0',`r28') define(`w1',`r29') define(`w2',`r30') define(`w3',`r31') a58 1 define(`upadv',`r20') define(`vpadv',`r21') d60 1 a60 1 MULFUNC_PROLOGUE(mpn_add_n mpn_add_nc mpn_sub_n mpn_sub_nc) d63 1 a63 1 PROLOGUE(func_nc) d68 4 a71 4 addp4 rp = 0, rp C M I addp4 up = 0, up C M I addp4 vp = 0, vp C M I zxt4 n = n C I d74 9 a82 7 {.mmi; ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov r2 = ar.lc C I0 }{.mmi; and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -6, n C M I d85 9 a93 11 .mmi; add upadv = PFDIST, up C Merging these lines into the feed-in add vpadv = PFDIST, vp C code could save a cycle per call at mov r23 = cy C the expense of code size. ;; {.mmi; cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I }{.bbb (p6) br.dptk .Lc001 C B (p7) br.dptk .Lc010 C B (p8) br.dptk .Lc011 C B d96 4 a99 15 {.mmi; cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I }{.bbb (p9) br.dptk .Lc100 C B (p10) br.dptk .Lc101 C B (p11) br.dptk .Lc110 C B ;; }{.mmi; ld8 r19 = [vp], 8 C M01 ld8 r18 = [up], 8 C M01 cmp.ne p13, p0 = 0, cy C copy cy to p13 M I }{.mmb; cmp.eq p12, p0 = 7, r14 C M I nop 0 (p12) br.dptk .Lc111 C B ;; d101 10 a110 326 .Lc000: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add vpadv = PFDIST, vp C M I ld8 v0 = [vp], 8 C M01 mov ar.lc = n C I0 .mmi; ld8 u0 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I nop 0 ;; .mmi; add upadv = PFDIST, up C M I ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r18, r19 C M I add rpx = 8, rp C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r18 C M I (p13) cmpeqor p7, p0 = LIM, w1 C M I .mmi; ld8 u2 = [up], 8 C M01 (p13) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m0) .Lc001: .mmi; (p15) ld8 v1 = [vp], 8 C M01 (p15) ld8 u1 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I .mmb; nop 0 nop 0 (p15) br 1f ;; .mmi; cmp.ne p9, p0 = 0, r23 C M I mov r8 = 0 cmp.CND p6, p0 = w0, r10 C M I ;; .mmb; (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I br L(cj1) C B 1: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov ar.lc = n C I0 .mmi; nop 0 cmp.ne p9, p0 = 0, r23 C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I add rpx = 16, rp C M I .mmb; ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br L(c1) C B .Lc010: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 mov r8 = 0 C M I .mmb; ADDSUB w3 = r10, r11 C M I cmp.ne p8, p0 = 0, r23 C M I (p15) br 1f C B ;; .mmi; cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I (p8) add w3 = INCR, w3 C M I ;; .mmb; cmp.CND p6, p0 = w0, u0 C M I (p8) cmpeqor p9, p0 = LIM2, w3 C M I br L(cj2) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ;; .mmi; (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I .mmb; add rpx = 24, rp C M I nop 0 br L(m23) C B .Lc011: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmi; ADDSUB w2 = r10, r11 C M I cmp.ne p7, p0 = 0, r23 C M I nop 0 ;; .mmb; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br 1f C B .mmi; cmp.CND p8, p0 = w2, r10 C M I ADDSUB w3 = u3, v3 C M I nop 0 ;; .mmb; (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I br L(cj3) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I mov ar.lc = n C I0 .mmi; ld8 u3 = [up], 8 C M01 (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m23) .Lc100: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmi; ADDSUB w1 = r10, r11 C M I nop 0 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 add rpx = 8, rp C M I .mmi; cmp.ne p6, p0 = 0, r23 C M I cmp.CND p7, p0 = w1, r10 C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I .mmb; (p6) cmpeqor p7, p0 = LIM, w1 C M I (p6) add w1 = INCR, w1 C M I (p14) br L(cj4) ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I nop 0 .mmi; ld8 u2 = [up], 8 C M01 nop 0 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m4) .Lc101: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I .mmi; cmp.ne p9, p0 = 0, r23 C M I add rpx = 16, rp C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I ld8 u0 = [up], 8 C M01 .mbb; ADDSUB w1 = u1, v1 C M I (p15) br L(c5) C B br L(end) C B .Lc110: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up C M I add vpadv = PFDIST, vp C M I mov ar.lc = n C I0 .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w0 = u0, v0 C M I .mmi; cmp.CND p9, p0 = w3, r10 C M I cmp.ne p8, p0 = 0, r23 C M I add rpx = 24, rp C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 nop 0 .mmb; (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I br L(m67) C B .Lc111: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up C M I ld8 v1 = [vp], 8 C M01 mov ar.lc = n C I0 .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I nop 0 ;; .mmi; add vpadv = PFDIST, vp C M I ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = r18, r19 C M I nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r18 C M I (p13) cmpeqor p8, p0 = LIM, w2 C M I .mmi; ld8 u3 = [up], 8 C M01 (p13) add w2 = INCR, w2 C M I nop 0 ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m67) EPILOGUE() ASM_START() PROLOGUE(func) .prologue .save ar.lc, r2 .body ifdef(`HAVE_ABI_32',` addp4 rp = 0, rp C M I addp4 up = 0, up C M I addp4 vp = 0, vp C M I zxt4 n = n C I ;; ') {.mmi; ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov r2 = ar.lc C I0 }{.mmi; and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -6, n C M I ;; }{.mmi; cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I }{.bbb (p6) br.dptk .Lb001 C B (p7) br.dptk .Lb010 C B (p8) br.dptk .Lb011 C B ;; }{.mmi; cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I }{.bbb (p9) br.dptk .Lb100 C B (p10) br.dptk .Lb101 C B (p11) br.dptk .Lb110 C B ;; }{.mmi; ld8 r19 = [vp], 8 C M01 ld8 r18 = [up], 8 C M01 cmp.ne p13, p0 = r0, r0 C clear "CF" M I }{.mmb; cmp.eq p12, p0 = 7, r14 C M I mov r23 = 0 C M I (p12) br.dptk .Lb111 C B ;; a112 269 .Lb000: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I mov ar.lc = n C I0 .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r18, r19 C M I add rpx = 8, rp C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp cmp.CND p8, p0 = w2, r18 C M I .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m0) C B ALIGN(32) .Lb001: .mmi; ADDSUB w0 = r10, r11 C M I (p15) ld8 v1 = [vp], 8 C M01 mov r8 = 0 C M I ;; .mmb; cmp.CND p6, p0 = w0, r10 C M I (p15) ld8 u1 = [up], 8 C M01 (p14) br L(cj1) C B ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp shr.u n = n, 3 C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I ;; .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I ADDSUB w2 = u2, v2 C M I .mmb; ld8 u1 = [up], 8 C M01 add rpx = 16, rp C M I br L(m1) C B ALIGN(32) .Lb010: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmb; ADDSUB w3 = r10, r11 C M I nop 0 (p15) br L(gt2) C B ;; .mmi; cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I mov r8 = 0 C M I ;; .mmb; nop 0 cmp.CND p6, p0 = w0, u0 C M I br L(cj2) C B L(gt2): .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 nop 0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I .mmb; ld8 u3 = [up], 8 C M01 add rpx = 24, rp C M I br L(m23) C B ALIGN(32) .Lb011: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; .mmb; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br 1f C B .mmb; cmp.CND p8, p0 = w2, r10 C M I ADDSUB w3 = u3, v3 C M I br L(cj3) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp ADDSUB w3 = u3, v3 C M I .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I mov ar.lc = n C I0 .mmi; ld8 u3 = [up], 8 C M01 nop 0 nop 0 ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m23) C B ALIGN(32) .Lb100: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I .mmb; nop 0 ADDSUB w2 = u2, v2 C M I (p14) br L(cj4) C B ;; L(gt4): .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I nop 0 .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I add rpx = 8, rp C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m4) C B ALIGN(32) .Lb101: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp add rpx = 16, rp C M I ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I nop 0 .mmb; ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I (p14) br L(cj5) C B ;; L(gt5): .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I mov ar.lc = n C I0 .mmb; ld8 u1 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I br L(m5) C B ALIGN(32) .Lb110: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I .mmb; ld8 u3 = [up], 8 C M01 add rpx = 24, rp C M I br L(m67) C B ALIGN(32) .Lb111: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I mov ar.lc = n C I0 .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = r18, r19 C M I nop 0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp nop 0 .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.CND p9, p0 = w3, r18 C M I ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m67) C B d114 364 d481 68 a548 70 L(top): L(c5): ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I (p9) cmpeqor p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; L(m5): ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I (p6) cmpeqor p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; L(m4): st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I lfetch [upadv], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I ;; L(m23): st8 [rp] = w3, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I nop.b 0 ;; L(c1): ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I (p9) cmpeqor p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; L(m1): ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I (p6) cmpeqor p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; L(m0): st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I lfetch [vpadv], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I ;; L(m67): st8 [rp] = w3, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br.cloop.dptk L(top) C B d552 58 a609 42 L(end): .mmi; (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I mov ar.lc = r2 C I0 L(cj5): .mmi; cmp.CND p7, p0 = w1, u1 C M I ADDSUB w2 = u2, v2 C M I nop 0 ;; .mmi; st8 [rp] = w0, 8 C M23 (p6) cmpeqor p7, p0 = LIM, w1 C M I (p6) add w1 = INCR, w1 C M I L(cj4): .mmi; cmp.CND p8, p0 = w2, u2 C M I ADDSUB w3 = u3, v3 C M I nop 0 ;; .mmi; st8 [rp] = w1, 8 C M23 (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I L(cj3): .mmi; cmp.CND p9, p0 = w3, u3 C M I ADDSUB w0 = u0, v0 C M I nop 0 ;; .mmi; st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I .mmi; cmp.CND p6, p0 = w0, u0 C M I nop 0 mov r8 = 0 C M I ;; L(cj2): .mmi; st8 [rp] = w3, 8 C M23 (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I ;; L(cj1): .mmb; st8 [rp] = w0, 8 C M23 (p6) mov r8 = 1 C M I br.ret.sptk.many b0 C B @ 1.1.1.2 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 @d3 1 a3 3 dnl Contributed to the GNU project by Torbjorn Granlund. dnl Copyright 2003, 2004, 2005, 2010, 2011 Free Software Foundation, Inc. a28 6 C * The non-nc code was trimmed cycle for cycle to its current state. It is C probably hard to save more that an odd cycle there. The nc code is much C rawer (since tune/speed doesn't have any applicable direct measurements). C * Without the nc entry points, this becomes around 1800 bytes of object C code; the nc code adds over 1000 bytes. We should perhaps sacrifice a C few cycles for the non-nc code and let it fall into the nc code. d31 4 a34 5 define(`rp', `r32') define(`up', `r33') define(`vp', `r34') define(`n', `r35') define(`cy', `r36') d38 1 a38 1 define(CND, ltu) d41 1 a41 3 define(LIM2, 0) define(func, mpn_add_n) define(func_nc, mpn_add_nc) d45 1 a45 1 define(CND, gtu) d48 1 a48 3 define(LIM2, -1) define(func, mpn_sub_n) define(func_nc, mpn_sub_nc) a50 3 define(cmpeqor, `cmp.eq.or') define(PFDIST, 500) d53 1 d55 3 a57 1 define(`w0',`r28') define(`w1',`r29') define(`w2',`r30') define(`w3',`r31') a58 1 define(`upadv',`r20') define(`vpadv',`r21') d60 1 a60 1 MULFUNC_PROLOGUE(mpn_add_n mpn_add_nc mpn_sub_n mpn_sub_nc) d63 1 a63 1 PROLOGUE(func_nc) d68 4 a71 4 addp4 rp = 0, rp C M I addp4 up = 0, up C M I addp4 vp = 0, vp C M I zxt4 n = n C I d74 9 a82 7 {.mmi; ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov r2 = ar.lc C I0 }{.mmi; and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -6, n C M I d85 9 a93 11 .mmi; add upadv = PFDIST, up C Merging these lines into the feed-in add vpadv = PFDIST, vp C code could save a cycle per call at mov r23 = cy C the expense of code size. ;; {.mmi; cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I }{.bbb (p6) br.dptk .Lc001 C B (p7) br.dptk .Lc010 C B (p8) br.dptk .Lc011 C B d96 4 a99 15 {.mmi; cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I }{.bbb (p9) br.dptk .Lc100 C B (p10) br.dptk .Lc101 C B (p11) br.dptk .Lc110 C B ;; }{.mmi; ld8 r19 = [vp], 8 C M01 ld8 r18 = [up], 8 C M01 cmp.ne p13, p0 = 0, cy C copy cy to p13 M I }{.mmb; cmp.eq p12, p0 = 7, r14 C M I nop 0 (p12) br.dptk .Lc111 C B ;; d101 10 a110 326 .Lc000: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add vpadv = PFDIST, vp C M I ld8 v0 = [vp], 8 C M01 mov ar.lc = n C I0 .mmi; ld8 u0 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I nop 0 ;; .mmi; add upadv = PFDIST, up C M I ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r18, r19 C M I add rpx = 8, rp C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r18 C M I (p13) cmpeqor p7, p0 = LIM, w1 C M I .mmi; ld8 u2 = [up], 8 C M01 (p13) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m0) .Lc001: .mmi; (p15) ld8 v1 = [vp], 8 C M01 (p15) ld8 u1 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I .mmb; nop 0 nop 0 (p15) br 1f ;; .mmi; cmp.ne p9, p0 = 0, r23 C M I mov r8 = 0 cmp.CND p6, p0 = w0, r10 C M I ;; .mmb; (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I br L(cj1) C B 1: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov ar.lc = n C I0 .mmi; nop 0 cmp.ne p9, p0 = 0, r23 C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I add rpx = 16, rp C M I .mmb; ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br L(c1) C B .Lc010: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 mov r8 = 0 C M I .mmb; ADDSUB w3 = r10, r11 C M I cmp.ne p8, p0 = 0, r23 C M I (p15) br 1f C B ;; .mmi; cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I (p8) add w3 = INCR, w3 C M I ;; .mmb; cmp.CND p6, p0 = w0, u0 C M I (p8) cmpeqor p9, p0 = LIM2, w3 C M I br L(cj2) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ;; .mmi; (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I .mmb; add rpx = 24, rp C M I nop 0 br L(m23) C B .Lc011: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmi; ADDSUB w2 = r10, r11 C M I cmp.ne p7, p0 = 0, r23 C M I nop 0 ;; .mmb; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br 1f C B .mmi; cmp.CND p8, p0 = w2, r10 C M I ADDSUB w3 = u3, v3 C M I nop 0 ;; .mmb; (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I br L(cj3) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I mov ar.lc = n C I0 .mmi; ld8 u3 = [up], 8 C M01 (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m23) .Lc100: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmi; ADDSUB w1 = r10, r11 C M I nop 0 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 add rpx = 8, rp C M I .mmi; cmp.ne p6, p0 = 0, r23 C M I cmp.CND p7, p0 = w1, r10 C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I .mmb; (p6) cmpeqor p7, p0 = LIM, w1 C M I (p6) add w1 = INCR, w1 C M I (p14) br L(cj4) ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I nop 0 .mmi; ld8 u2 = [up], 8 C M01 nop 0 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m4) .Lc101: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I .mmi; cmp.ne p9, p0 = 0, r23 C M I add rpx = 16, rp C M I nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I ld8 u0 = [up], 8 C M01 .mbb; ADDSUB w1 = u1, v1 C M I (p15) br L(c5) C B br L(end) C B .Lc110: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up C M I add vpadv = PFDIST, vp C M I mov ar.lc = n C I0 .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w0 = u0, v0 C M I .mmi; cmp.CND p9, p0 = w3, r10 C M I cmp.ne p8, p0 = 0, r23 C M I add rpx = 24, rp C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 nop 0 .mmb; (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I br L(m67) C B .Lc111: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up C M I ld8 v1 = [vp], 8 C M01 mov ar.lc = n C I0 .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I nop 0 ;; .mmi; add vpadv = PFDIST, vp C M I ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = r18, r19 C M I nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r18 C M I (p13) cmpeqor p8, p0 = LIM, w2 C M I .mmi; ld8 u3 = [up], 8 C M01 (p13) add w2 = INCR, w2 C M I nop 0 ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m67) EPILOGUE() ASM_START() PROLOGUE(func) .prologue .save ar.lc, r2 .body ifdef(`HAVE_ABI_32',` addp4 rp = 0, rp C M I addp4 up = 0, up C M I addp4 vp = 0, vp C M I zxt4 n = n C I ;; ') {.mmi; ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov r2 = ar.lc C I0 }{.mmi; and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -6, n C M I ;; }{.mmi; cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I }{.bbb (p6) br.dptk .Lb001 C B (p7) br.dptk .Lb010 C B (p8) br.dptk .Lb011 C B ;; }{.mmi; cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I }{.bbb (p9) br.dptk .Lb100 C B (p10) br.dptk .Lb101 C B (p11) br.dptk .Lb110 C B ;; }{.mmi; ld8 r19 = [vp], 8 C M01 ld8 r18 = [up], 8 C M01 cmp.ne p13, p0 = r0, r0 C clear "CF" M I }{.mmb; cmp.eq p12, p0 = 7, r14 C M I mov r23 = 0 C M I (p12) br.dptk .Lb111 C B ;; a112 269 .Lb000: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I mov ar.lc = n C I0 .mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r18, r19 C M I add rpx = 8, rp C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp cmp.CND p8, p0 = w2, r18 C M I .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m0) C B ALIGN(32) .Lb001: .mmi; ADDSUB w0 = r10, r11 C M I (p15) ld8 v1 = [vp], 8 C M01 mov r8 = 0 C M I ;; .mmb; cmp.CND p6, p0 = w0, r10 C M I (p15) ld8 u1 = [up], 8 C M01 (p14) br L(cj1) C B ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp shr.u n = n, 3 C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov ar.lc = n C I0 ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I ;; .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I ADDSUB w2 = u2, v2 C M I .mmb; ld8 u1 = [up], 8 C M01 add rpx = 16, rp C M I br L(m1) C B ALIGN(32) .Lb010: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 .mmb; ADDSUB w3 = r10, r11 C M I nop 0 (p15) br L(gt2) C B ;; .mmi; cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I mov r8 = 0 C M I ;; .mmb; nop 0 cmp.CND p6, p0 = w0, u0 C M I br L(cj2) C B L(gt2): .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 nop 0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I .mmb; ld8 u3 = [up], 8 C M01 add rpx = 24, rp C M I br L(m23) C B ALIGN(32) .Lb011: .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; .mmb; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br 1f C B .mmb; cmp.CND p8, p0 = w2, r10 C M I ADDSUB w3 = u3, v3 C M I br L(cj3) C B 1: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp ADDSUB w3 = u3, v3 C M I .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I mov ar.lc = n C I0 .mmi; ld8 u3 = [up], 8 C M01 nop 0 nop 0 ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m23) C B ALIGN(32) .Lb100: .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I .mmb; nop 0 ADDSUB w2 = u2, v2 C M I (p14) br L(cj4) C B ;; L(gt4): .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I nop 0 .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I add rpx = 8, rp C M I ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I .mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m4) C B ALIGN(32) .Lb101: .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp add rpx = 16, rp C M I ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I nop 0 .mmb; ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I (p14) br L(cj5) C B ;; L(gt5): .mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I mov ar.lc = n C I0 .mmb; ld8 u1 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I br L(m5) C B ALIGN(32) .Lb110: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 .mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 nop 0 ;; .mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I .mmb; ld8 u3 = [up], 8 C M01 add rpx = 24, rp C M I br L(m67) C B ALIGN(32) .Lb111: .mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; .mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; .mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I mov ar.lc = n C I0 .mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = r18, r19 C M I nop 0 ;; .mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp nop 0 .mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.CND p9, p0 = w3, r18 C M I ;; .mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I .mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m67) C B d114 364 d481 68 a548 70 L(top): L(c5): ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I (p9) cmpeqor p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; L(m5): ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I (p6) cmpeqor p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; L(m4): st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I lfetch [upadv], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I ;; L(m23): st8 [rp] = w3, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I nop.b 0 ;; L(c1): ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I (p9) cmpeqor p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; L(m1): ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I (p6) cmpeqor p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; L(m0): st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I lfetch [vpadv], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I ;; L(m67): st8 [rp] = w3, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br.cloop.dptk L(top) C B d552 58 a609 42 L(end): .mmi; (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I mov ar.lc = r2 C I0 L(cj5): .mmi; cmp.CND p7, p0 = w1, u1 C M I ADDSUB w2 = u2, v2 C M I nop 0 ;; .mmi; st8 [rp] = w0, 8 C M23 (p6) cmpeqor p7, p0 = LIM, w1 C M I (p6) add w1 = INCR, w1 C M I L(cj4): .mmi; cmp.CND p8, p0 = w2, u2 C M I ADDSUB w3 = u3, v3 C M I nop 0 ;; .mmi; st8 [rp] = w1, 8 C M23 (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I L(cj3): .mmi; cmp.CND p9, p0 = w3, u3 C M I ADDSUB w0 = u0, v0 C M I nop 0 ;; .mmi; st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I .mmi; cmp.CND p6, p0 = w0, u0 C M I nop 0 mov r8 = 0 C M I ;; L(cj2): .mmi; st8 [rp] = w3, 8 C M23 (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I ;; L(cj1): .mmb; st8 [rp] = w0, 8 C M23 (p6) mov r8 = 1 C M I br.ret.sptk.many b0 C B @ 1.1.1.3 log @initial import of GMP 6.1.2. main changes from 5.1.3 below. notes: - support for thumb-less ARM chips was in our port of 5.1.3, but a similar method has been provided upstream now - someone should look at the AVX failure reports, and fix them Changes between GMP version 6.1.0 and 6.1.1 FEATURES * Work around faulty cpuid on some recent Intel chips (this allows GMP to run on Skylake Pentiums). * Support thumb-less ARM chips. Changes between GMP version 6.0.* and 6.1.0 BUGS FIXED * The public function mpn_com is now correctly declared in gmp.h. * Healed possible failures of mpn_sec_sqr for non-cryptographic sizes for some obsolete CPUs. * Various problems related to precision for mpf have been fixed. * Fixed ABI incompatible stack alignment in calls from assembly code. * Fixed PIC bug in popcount affecting Intel processors using the 32-bit ABI. SPEEDUPS * Speedup for Intel Broadwell and Skylake through assembly code making use of new ADX instructions. * Square root is now faster when the remainder is not needed. Also the speed to compute the k-th root improved, for small sizes. FEATURES * New C++ functions gcd and lcm for mpz_class. * New public mpn functions mpn_divexact_1, mpn_zero_p, and mpn_cnd_swap. * New public mpq_cmp_z function, to efficiently compare rationals with integers. * Support for more 32-bit arm processors. * Support for AVX-less modern x86 CPUs. (Such support might be missing either because the CPU vendor chose to disable AVX, or because the running kernel lacks AVX context switch support.) * Support for NetBSD under Xen; we switch off AVX unconditionally under NetBSD since a bug in NetBSD makes AVX fail under Xen. MISC * Tuned values for FFT multiplications are provided for larger number on many platforms. Changes between GMP version 5.1.* and 6.0.0 BUGS FIXED * The function mpz_invert now considers any number invertible in Z/1Z. * The mpn multiply code now handles operands of more than 2^31 limbs correctly. (Note however that the mpz code is limited to 2^32 bits on 32-bit hosts and 2^37 bits on 64-bit hosts.) SPEEDUPS * Plain division of large operands is faster and more monotonous in operand size. * Major speedup for ARM, in particular ARM Cortex-A15, thanks to improved assembly. * Speedup for Intel Sandy Bridge, Ivy Bridge, Haswell, thanks to rewritten and vastly expanded assembly support. Speedup also for the older Core 2 and Nehalem. * Faster mixed arithmetic between mpq_class and double. FEATURES * Support for new Intel and AMD CPUs. * New public functions mpn_sec_mul and mpn_sec_sqr, implementing side-channel silent multiplication and squaring. * New public functions mpn_sec_div_qr and mpn_sec_div_r, implementing side-channel silent division. * New public functions mpn_cnd_add_n and mpn_cnd_sub_n. Side-channel silent conditional addition and subtraction. * New public function mpn_sec_powm, implementing side-channel silent modexp. * New public function mpn_sec_invert, implementing side-channel silent modular inversion. * Better support for applications which use the mpz_t type, but nevertheless need to call some of the lower-level mpn functions. See the documentation for mpz_limbs_read and related functions. @ text @d5 1 a5 1 dnl Copyright 2003-2005, 2010, 2011 Free Software Foundation, Inc. d8 1 a8 1 dnl d10 4 a13 14 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 d16 5 a20 6 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/. d33 1 a33 1 C cruder (since tune/speed doesn't have any applicable direct measurements). d64 1 d82 4 a85 6 addp4 rp = 0, rp C M I addp4 up = 0, up C M I nop.i 0 addp4 vp = 0, vp C M I nop.m 0 zxt4 n = n C I d89 35 a123 31 {.mmi; ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov r2 = ar.lc C I0 }{.mmi; and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -6, n C M I ;; }{.mmi; add upadv = PFDIST, up C Merging these lines into the feed-in add vpadv = PFDIST, vp C code could save a cycle per call at mov r23 = cy C the expense of code size. ;; }{.mmi; cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I }{.bbb; (p6) br.dptk .Lc001 C B (p7) br.dptk .Lc010 C B (p8) br.dptk .Lc011 C B ;; }{.mmi; cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I }{.bbb; (p9) br.dptk .Lc100 C B (p10) br.dptk .Lc101 C B (p11) br.dptk .Lc110 C B ;; }{.mmi; ld8 r19 = [vp], 8 C M01 ld8 r18 = [up], 8 C M01 cmp.ne p13, p0 = 0, cy C copy cy to p13 M I }{.mmb; cmp.eq p12, p0 = 7, r14 C M I nop 0 (p12) br.dptk .Lc111 C B d128 32 a159 32 {.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; add vpadv = PFDIST, vp C M I ld8 v0 = [vp], 8 C M01 mov ar.lc = n C I0 }{.mmi; ld8 u0 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I nop 0 ;; }{.mmi; add upadv = PFDIST, up C M I ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I }{.mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r18, r19 C M I add rpx = 8, rp C M I ;; }{.mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r18 C M I (p13) cmpeqor p7, p0 = LIM, w1 C M I }{.mmi; ld8 u2 = [up], 8 C M01 (p13) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I }{.mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m0) } d162 35 a196 34 {.mmi; (p15) ld8 v1 = [vp], 8 C M01 (p15) ld8 u1 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I }{.mmb; nop 0 nop 0 (p15) br L(0) ;; }{.mmi; cmp.ne p9, p0 = 0, r23 C M I mov r8 = 0 cmp.CND p6, p0 = w0, r10 C M I ;; }{.mmb; (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I br L(cj1) C B } L(0): {.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov ar.lc = n C I0 }{.mmi; nop 0 cmp.ne p9, p0 = 0, r23 C M I nop 0 ;; }{.mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I add rpx = 16, rp C M I }{.mmb; ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br L(c1) C B } d199 35 a233 35 {.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 mov r8 = 0 C M I }{.mmb; ADDSUB w3 = r10, r11 C M I cmp.ne p8, p0 = 0, r23 C M I (p15) br L(1) C B ;; }{.mmi; cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I (p8) add w3 = INCR, w3 C M I ;; }{.mmb; cmp.CND p6, p0 = w0, u0 C M I (p8) cmpeqor p9, p0 = LIM2, w3 C M I br L(cj2) C B } L(1): {.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov ar.lc = n C I0 ;; }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ;; }{.mmi; (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I }{.mmb; add rpx = 24, rp C M I nop 0 br L(m23) C B } d236 42 a277 41 {.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 }{.mmi; ADDSUB w2 = r10, r11 C M I cmp.ne p7, p0 = 0, r23 C M I nop 0 ;; }{.mmb; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br L(2) C B }{.mmi; cmp.CND p8, p0 = w2, r10 C M I ADDSUB w3 = u3, v3 C M I nop 0 ;; }{.mmb; (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I br L(cj3) C B } L(2): {.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I mov ar.lc = n C I0 }{.mmi; ld8 u3 = [up], 8 C M01 (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I ;; }{.mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I }{.mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m23) } d280 40 a319 39 {.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 }{.mmi; ADDSUB w1 = r10, r11 C M I nop 0 nop 0 ;; }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 add rpx = 8, rp C M I }{.mmi; cmp.ne p6, p0 = 0, r23 C M I cmp.CND p7, p0 = w1, r10 C M I nop 0 ;; }{.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I }{.mmb; (p6) cmpeqor p7, p0 = LIM, w1 C M I (p6) add w1 = INCR, w1 C M I (p14) br L(cj4) ;; }{.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 mov ar.lc = n C I0 ;; }{.mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I nop 0 }{.mmi; ld8 u2 = [up], 8 C M01 nop 0 ADDSUB w3 = u3, v3 C M I ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I }{.mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m4) } d322 22 a343 22 {.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 mov ar.lc = n C I0 ;; }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I }{.mmi; cmp.ne p9, p0 = 0, r23 C M I add rpx = 16, rp C M I nop 0 ;; }{.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I }{.mbb; ADDSUB w1 = u1, v1 C M I (p15) br L(c5) C B br L(end) C B } d346 26 a371 25 {.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; add upadv = PFDIST, up C M I add vpadv = PFDIST, vp C M I mov ar.lc = n C I0 }{.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w0 = u0, v0 C M I }{.mmi; cmp.CND p9, p0 = w3, r10 C M I cmp.ne p8, p0 = 0, r23 C M I add rpx = 24, rp C M I ;; }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 nop 0 }{.mmb; (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I br L(m67) C B } d374 33 a406 32 {.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; add upadv = PFDIST, up C M I ld8 v1 = [vp], 8 C M01 mov ar.lc = n C I0 }{.mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I nop 0 ;; }{.mmi; add vpadv = PFDIST, vp C M I ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I }{.mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = r18, r19 C M I nop 0 ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r18 C M I (p13) cmpeqor p8, p0 = LIM, w2 C M I }{.mmi; ld8 u3 = [up], 8 C M01 (p13) add w2 = INCR, w2 C M I nop 0 ;; }{.mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I }{.mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m67) } d409 1 d415 4 a418 6 addp4 rp = 0, rp C M I addp4 up = 0, up C M I nop.i 0 addp4 vp = 0, vp C M I nop.m 0 zxt4 n = n C I d422 29 a450 27 {.mmi; ld8 r11 = [vp], 8 C M01 ld8 r10 = [up], 8 C M01 mov r2 = ar.lc C I0 }{.mmi; and r14 = 7, n C M I cmp.lt p15, p14 = 8, n C M I add n = -6, n C M I ;; }{.mmi; cmp.eq p6, p0 = 1, r14 C M I cmp.eq p7, p0 = 2, r14 C M I cmp.eq p8, p0 = 3, r14 C M I }{.bbb; (p6) br.dptk .Lb001 C B (p7) br.dptk .Lb010 C B (p8) br.dptk .Lb011 C B ;; }{.mmi; cmp.eq p9, p0 = 4, r14 C M I cmp.eq p10, p0 = 5, r14 C M I cmp.eq p11, p0 = 6, r14 C M I }{.bbb; (p9) br.dptk .Lb100 C B (p10) br.dptk .Lb101 C B (p11) br.dptk .Lb110 C B ;; }{.mmi; ld8 r19 = [vp], 8 C M01 ld8 r18 = [up], 8 C M01 cmp.ne p13, p0 = r0, r0 C clear "CF" M I }{.mmb; cmp.eq p12, p0 = 7, r14 C M I mov r23 = 0 C M I (p12) br.dptk .Lb111 C B d455 29 a483 29 {.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; }{.mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I mov ar.lc = n C I0 }{.mmi; ld8 u1 = [up], 8 C M01 ADDSUB w2 = r18, r19 C M I add rpx = 8, rp C M I ;; }{.mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp cmp.CND p8, p0 = w2, r18 C M I }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I }{.mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m0) C B } d487 30 a516 30 {.mmi; ADDSUB w0 = r10, r11 C M I (p15) ld8 v1 = [vp], 8 C M01 mov r8 = 0 C M I ;; }{.mmb; cmp.CND p6, p0 = w0, r10 C M I (p15) ld8 u1 = [up], 8 C M01 (p14) br L(cj1) C B ;; }{.mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp shr.u n = n, 3 C I0 }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I ;; }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 mov ar.lc = n C I0 ;; }{.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I ;; }{.mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I ADDSUB w2 = u2, v2 C M I }{.mmb; ld8 u1 = [up], 8 C M01 add rpx = 16, rp C M I br L(m1) C B } d520 14 a533 15 {.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 }{.mmb; ADDSUB w3 = r10, r11 C M I nop 0 (p15) br L(gt2) C B ;; }{.mmi; cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I mov r8 = 0 C M I ;; }{.mmb; nop 0 cmp.CND p6, p0 = w0, u0 C M I br L(cj2) C B } d535 18 a552 18 {.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 nop 0 ;; }{.mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 nop 0 ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I }{.mmb; ld8 u3 = [up], 8 C M01 add rpx = 24, rp C M I br L(m23) C B } d556 37 a592 37 {.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; }{.mmb; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 (p15) br L(3) C B }{.mmb; cmp.CND p8, p0 = w2, r10 C M I ADDSUB w3 = u3, v3 C M I br L(cj3) C B } L(3): {.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp ADDSUB w3 = u3, v3 C M I }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I mov ar.lc = n C I0 }{.mmi; ld8 u3 = [up], 8 C M01 nop 0 nop 0 ;; }{.mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I }{.mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m23) C B } d596 14 a609 14 {.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 ADDSUB w1 = r10, r11 C M I ;; }{.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 cmp.CND p7, p0 = w1, r10 C M I }{.mmb; nop 0 ADDSUB w2 = u2, v2 C M I (p14) br L(cj4) C B a610 1 } d612 21 a632 21 {.mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 }{.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 nop 0 ;; }{.mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I nop 0 }{.mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = u3, v3 C M I add rpx = 8, rp C M I ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I }{.mmb; ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I br L(m4) C B } d636 21 a656 21 {.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 ADDSUB w0 = r10, r11 C M I ;; }{.mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp add rpx = 16, rp C M I }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 nop 0 ;; }{.mmi; ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, r10 C M I nop 0 }{.mmb; ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I (p14) br L(cj5) C B a657 1 } d659 7 a665 7 {.mmi; ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I mov ar.lc = n C I0 }{.mmb; ld8 u1 = [up], 8 C M01 ADDSUB w2 = u2, v2 C M I br L(m5) C B } d669 22 a690 22 {.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w3 = r10, r11 C M I ;; }{.mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp mov ar.lc = n C I0 }{.mmi; ld8 v2 = [vp], 8 C M01 ld8 u2 = [up], 8 C M01 nop 0 ;; }{.mmi; ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, r10 C M I ADDSUB w0 = u0, v0 C M I }{.mmb; ld8 u3 = [up], 8 C M01 add rpx = 24, rp C M I br L(m67) C B } d694 30 a723 29 {.mmi; ld8 v0 = [vp], 8 C M01 ld8 u0 = [up], 8 C M01 shr.u n = n, 3 C I0 ;; }{.mmi; ld8 v1 = [vp], 8 C M01 ld8 u1 = [up], 8 C M01 ADDSUB w2 = r10, r11 C M I ;; }{.mmi; ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, r10 C M I mov ar.lc = n C I0 }{.mmi; ld8 u2 = [up], 8 C M01 ADDSUB w3 = r18, r19 C M I nop 0 ;; }{.mmi; add upadv = PFDIST, up add vpadv = PFDIST, vp nop 0 }{.mmi; ld8 v3 = [vp], 8 C M01 ld8 u3 = [up], 8 C M01 cmp.CND p9, p0 = w3, r18 C M I ;; }{.mmi; add rpx = 32, rp C M I st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I }{.mmb; (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I br L(m67) C B } d728 69 a796 69 L(c5): ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I (p9) cmpeqor p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; L(m5): ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I (p6) cmpeqor p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; L(m4): st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I lfetch [upadv], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I ;; L(m23): st8 [rp] = w3, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I nop.b 0 ;; L(c1): ld8 v1 = [vp], 8 C M01 cmp.CND p7, p0 = w1, u1 C M I (p9) cmpeqor p6, p0 = LIM, w0 C M I ld8 u1 = [up], 8 C M01 (p9) add w0 = INCR, w0 C M I ADDSUB w2 = u2, v2 C M I ;; L(m1): ld8 v2 = [vp], 8 C M01 cmp.CND p8, p0 = w2, u2 C M I (p6) cmpeqor p7, p0 = LIM, w1 C M I ld8 u2 = [up], 8 C M01 (p6) add w1 = INCR, w1 C M I ADDSUB w3 = u3, v3 C M I ;; st8 [rp] = w0, 8 C M23 ld8 v3 = [vp], 8 C M01 cmp.CND p9, p0 = w3, u3 C M I (p7) cmpeqor p8, p0 = LIM, w2 C M I ld8 u3 = [up], 8 C M01 (p7) add w2 = INCR, w2 C M I ;; L(m0): st8 [rp] = w1, 16 C M23 st8 [rpx] = w2, 32 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I lfetch [vpadv], 64 (p8) add w3 = INCR, w3 C M I ADDSUB w0 = u0, v0 C M I ;; L(m67): st8 [rp] = w3, 8 C M23 ld8 v0 = [vp], 8 C M01 cmp.CND p6, p0 = w0, u0 C M I ld8 u0 = [up], 8 C M01 ADDSUB w1 = u1, v1 C M I br.cloop.dptk L(top) C B d801 4 a804 4 {.mmi; (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I mov ar.lc = r2 C I0 } d806 7 a812 8 {.mmi; cmp.CND p7, p0 = w1, u1 C M I ADDSUB w2 = u2, v2 C M I nop 0 ;; }{.mmi; st8 [rp] = w0, 8 C M23 (p6) cmpeqor p7, p0 = LIM, w1 C M I (p6) add w1 = INCR, w1 C M I } d814 7 a820 8 {.mmi; cmp.CND p8, p0 = w2, u2 C M I ADDSUB w3 = u3, v3 C M I nop 0 ;; }{.mmi; st8 [rp] = w1, 8 C M23 (p7) cmpeqor p8, p0 = LIM, w2 C M I (p7) add w2 = INCR, w2 C M I } d822 10 a831 10 {.mmi; cmp.CND p9, p0 = w3, u3 C M I ADDSUB w0 = u0, v0 C M I nop 0 ;; }{.mmi; st8 [rp] = w2, 8 C M23 (p8) cmpeqor p9, p0 = LIM, w3 C M I (p8) add w3 = INCR, w3 C M I }{.mmi; cmp.CND p6, p0 = w0, u0 C M I nop 0 mov r8 = 0 C M I a832 1 } d834 3 a836 3 {.mmi; st8 [rp] = w3, 8 C M23 (p9) cmpeqor p6, p0 = LIM, w0 C M I (p9) add w0 = INCR, w0 C M I a837 1 } d839 3 a841 4 {.mmb; st8 [rp] = w0, 8 C M23 (p6) mov r8 = 1 C M I br.ret.sptk.many b0 C B } @