head 1.1; branch 1.1.1; access; symbols netbsd-11-0-RC4:1.1.1.2 netbsd-11-0-RC3:1.1.1.2 netbsd-11-0-RC2:1.1.1.2 netbsd-11-0-RC1:1.1.1.2 perseant-exfatfs-base-20250801:1.1.1.2 netbsd-11:1.1.1.2.0.18 netbsd-11-base:1.1.1.2 netbsd-10-1-RELEASE:1.1.1.2 perseant-exfatfs-base-20240630:1.1.1.2 perseant-exfatfs:1.1.1.2.0.16 perseant-exfatfs-base:1.1.1.2 netbsd-8-3-RELEASE:1.1.1.1 netbsd-9-4-RELEASE:1.1.1.2 netbsd-10-0-RELEASE:1.1.1.2 netbsd-10-0-RC6:1.1.1.2 netbsd-10-0-RC5:1.1.1.2 netbsd-10-0-RC4:1.1.1.2 netbsd-10-0-RC3:1.1.1.2 netbsd-10-0-RC2:1.1.1.2 netbsd-10-0-RC1:1.1.1.2 netbsd-10:1.1.1.2.0.14 netbsd-10-base:1.1.1.2 netbsd-9-3-RELEASE:1.1.1.2 gmp-6-2-1:1.1.1.2 cjep_sun2x-base1:1.1.1.2 cjep_sun2x:1.1.1.2.0.12 cjep_sun2x-base:1.1.1.2 cjep_staticlib_x-base1:1.1.1.2 netbsd-9-2-RELEASE:1.1.1.2 cjep_staticlib_x:1.1.1.2.0.10 cjep_staticlib_x-base:1.1.1.2 netbsd-9-1-RELEASE:1.1.1.2 gmp-6-2-0:1.1.1.2 phil-wifi-20200421:1.1.1.2 phil-wifi-20200411:1.1.1.2 is-mlppp:1.1.1.2.0.8 is-mlppp-base:1.1.1.2 phil-wifi-20200406:1.1.1.2 netbsd-8-2-RELEASE:1.1.1.1 netbsd-9-0-RELEASE:1.1.1.2 netbsd-9-0-RC2:1.1.1.2 netbsd-9-0-RC1:1.1.1.2 phil-wifi-20191119:1.1.1.2 netbsd-9:1.1.1.2.0.6 netbsd-9-base:1.1.1.2 phil-wifi-20190609:1.1.1.2 netbsd-8-1-RELEASE:1.1.1.1 netbsd-8-1-RC1:1.1.1.1 pgoyette-compat-merge-20190127:1.1.1.2 pgoyette-compat-20190127:1.1.1.2 pgoyette-compat-20190118:1.1.1.2 pgoyette-compat-1226:1.1.1.2 pgoyette-compat-1126:1.1.1.2 pgoyette-compat-1020:1.1.1.2 pgoyette-compat-0930:1.1.1.2 pgoyette-compat-0906:1.1.1.2 netbsd-7-2-RELEASE:1.1.1.1 pgoyette-compat-0728:1.1.1.2 netbsd-8-0-RELEASE:1.1.1.1 phil-wifi:1.1.1.2.0.4 phil-wifi-base:1.1.1.2 pgoyette-compat-0625:1.1.1.2 netbsd-8-0-RC2:1.1.1.1 pgoyette-compat-0521:1.1.1.2 pgoyette-compat-0502:1.1.1.2 pgoyette-compat-0422:1.1.1.2 netbsd-8-0-RC1:1.1.1.1 pgoyette-compat-0415:1.1.1.2 pgoyette-compat-0407:1.1.1.2 pgoyette-compat-0330:1.1.1.2 pgoyette-compat-0322:1.1.1.2 pgoyette-compat-0315:1.1.1.2 netbsd-7-1-2-RELEASE:1.1.1.1 pgoyette-compat:1.1.1.2.0.2 pgoyette-compat-base:1.1.1.2 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 gmp-6-1-2:1.1.1.2 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 @;; @; 1.1 date 2013.11.29.07.49.49; author mrg; state Exp; branches 1.1.1.1; next ; commitid L2Av4PuGmdoL39fx; 1.1.1.1 date 2013.11.29.07.49.49; author mrg; state Exp; branches 1.1.1.1.4.1 1.1.1.1.8.1; next 1.1.1.2; commitid L2Av4PuGmdoL39fx; 1.1.1.2 date 2017.08.22.09.40.49; author mrg; state Exp; branches; next ; commitid W5kmAIk8hwVpSb4A; 1.1.1.1.4.1 date 2013.11.29.07.49.49; author yamt; state dead; branches; next 1.1.1.1.4.2; commitid nx2BSsHy0NPeAxBx; 1.1.1.1.4.2 date 2014.05.22.14.09.04; author yamt; state Exp; branches; next ; commitid nx2BSsHy0NPeAxBx; 1.1.1.1.8.1 date 2013.11.29.07.49.49; author tls; state dead; branches; next 1.1.1.1.8.2; commitid jTnpym9Qu0o4R1Nx; 1.1.1.1.8.2 date 2014.08.19.23.59.54; author tls; state Exp; branches; next ; commitid jTnpym9Qu0o4R1Nx; desc @@ 1.1 log @Initial revision @ text @dnl Intel Atom mpn_addlshC_n/mpn_sublshC_n -- rp[] = up[] +- (vp[] << C) dnl Contributed to the GNU project by Marco Bodrato. dnl Copyright 2011 Free Software Foundation, Inc. dnl dnl This file is part of the GNU MP Library. dnl dnl The GNU MP Library is free software; you can redistribute it and/or dnl modify it under the terms of the GNU Lesser General Public License as dnl published by the Free Software Foundation; either version 3 of the dnl License, or (at your option) any later version. dnl dnl The GNU MP Library is distributed in the hope that it will be useful, dnl but WITHOUT ANY WARRANTY; without even the implied warranty of dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU dnl Lesser General Public License for more details. dnl 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 mp_limb_t mpn_addlshC_n_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size); C mp_limb_t mpn_addlshC_nc_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size, C mp_limb_t carry); C mp_limb_t mpn_sublshC_n_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size,); C mp_limb_t mpn_sublshC_nc_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size, C mp_signed_limb_t borrow); defframe(PARAM_CORB, 16) defframe(PARAM_SIZE, 12) defframe(PARAM_SRC, 8) defframe(PARAM_DST, 4) C mp_limb_t mpn_addlshC_n (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size,); C mp_limb_t mpn_addlshC_nc (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size, mp_limb_t carry); C mp_limb_t mpn_sublshC_n (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size,); C mp_limb_t mpn_sublshC_nc (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size, mp_limb_t borrow); C if src1 == dst, _ip1 is used C cycles/limb C dst!=src1,src2 dst==src1 C P5 C P6 model 0-8,10-12 C P6 model 9 (Banias) C P6 model 13 (Dothan) C P4 model 0 (Willamette) C P4 model 1 (?) C P4 model 2 (Northwood) C P4 model 3 (Prescott) C P4 model 4 (Nocona) C Intel Atom 7 6 C AMD K6 C AMD K7 C AMD K8 C AMD K10 defframe(GPARAM_CORB, 20) defframe(GPARAM_SIZE, 16) defframe(GPARAM_SRC2, 12) dnl re-use parameter space define(SAVE_EBP,`PARAM_SIZE') define(SAVE_EBX,`PARAM_SRC') define(SAVE_UP,`PARAM_DST') define(M, eval(m4_lshift(1,LSH))) define(`rp', `%edi') define(`up', `%esi') ASM_START() TEXT ALIGN(8) PROLOGUE(M4_ip_function_c) deflit(`FRAME',0) movl PARAM_CORB, %ecx movl %ecx, %edx shr $LSH, %edx andl $1, %edx M4_opp %edx, %ecx jmp L(start_nc) EPILOGUE() PROLOGUE(M4_ip_function) deflit(`FRAME',0) xor %ecx, %ecx xor %edx, %edx L(start_nc): push rp FRAME_pushl() mov PARAM_DST, rp mov up, SAVE_UP mov PARAM_SRC, up mov %ebx, SAVE_EBX mov PARAM_SIZE, %ebx C size L(inplace): incl %ebx C size + 1 shr %ebx C (size+1)\2 mov %ebp, SAVE_EBP jnc L(entry) C size odd add %edx, %edx C size even mov %ecx, %ebp mov (up), %ecx lea -4(rp), rp lea (%ebp,%ecx,M), %eax lea 4(up), up jmp L(enteven) ALIGN(16) L(oop): lea (%ecx,%eax,M), %ebp shr $RSH, %eax mov 4(up), %ecx add %edx, %edx lea 8(up), up M4_inst %ebp, (rp) lea (%eax,%ecx,M), %eax L(enteven): M4_inst %eax, 4(rp) lea 8(rp), rp sbb %edx, %edx shr $RSH, %ecx L(entry): mov (up), %eax decl %ebx jnz L(oop) lea (%ecx,%eax,M), %ebp shr $RSH, %eax shr %edx M4_inst %ebp, (rp) mov SAVE_UP, up adc $0, %eax mov SAVE_EBP, %ebp mov SAVE_EBX, %ebx pop rp FRAME_popl() ret EPILOGUE() PROLOGUE(M4_function_c) deflit(`FRAME',0) movl GPARAM_CORB, %ecx movl %ecx, %edx shr $LSH, %edx andl $1, %edx M4_opp %edx, %ecx jmp L(generic_nc) EPILOGUE() PROLOGUE(M4_function) deflit(`FRAME',0) xor %ecx, %ecx xor %edx, %edx L(generic_nc): push rp FRAME_pushl() mov PARAM_DST, rp mov up, SAVE_UP mov PARAM_SRC, up cmp rp, up mov %ebx, SAVE_EBX jne L(general) mov GPARAM_SIZE, %ebx C size mov GPARAM_SRC2, up jmp L(inplace) L(general): mov GPARAM_SIZE, %eax C size mov %ebx, SAVE_EBX incl %eax C size + 1 mov up, %ebx C vp mov GPARAM_SRC2, up C up shr %eax C (size+1)\2 mov %ebp, SAVE_EBP mov %eax, GPARAM_SIZE jnc L(entry2) C size odd add %edx, %edx C size even mov %ecx, %ebp mov (up), %ecx lea -4(rp), rp lea -4(%ebx), %ebx lea (%ebp,%ecx,M), %eax lea 4(up), up jmp L(enteven2) ALIGN(16) L(oop2): lea (%ecx,%eax,M), %ebp shr $RSH, %eax mov 4(up), %ecx add %edx, %edx lea 8(up), up mov (%ebx), %edx M4_inst %ebp, %edx lea (%eax,%ecx,M), %eax mov %edx, (rp) L(enteven2): mov 4(%ebx), %edx lea 8(%ebx), %ebx M4_inst %eax, %edx mov %edx, 4(rp) sbb %edx, %edx shr $RSH, %ecx lea 8(rp), rp L(entry2): mov (up), %eax decl GPARAM_SIZE jnz L(oop2) lea (%ecx,%eax,M), %ebp shr $RSH, %eax shr %edx mov (%ebx), %edx M4_inst %ebp, %edx mov %edx, (rp) mov SAVE_UP, up adc $0, %eax mov SAVE_EBP, %ebp mov SAVE_EBX, %ebx pop rp FRAME_popl() ret EPILOGUE() ASM_END() @ 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 @@ 1.1.1.2 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 @d6 1 a6 1 d9 9 a17 19 dnl The GNU MP Library is free software; you can redistribute it and/or modify dnl it under the terms of either: dnl dnl * the GNU Lesser General Public License as published by the Free dnl Software Foundation; either version 3 of the License, or (at your dnl option) any later version. dnl dnl or dnl dnl * the GNU General Public License as published by the Free Software dnl Foundation; either version 2 of the License, or (at your option) any dnl later version. dnl dnl or both in parallel, as here. dnl dnl The GNU MP Library is distributed in the hope that it will be useful, but dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License dnl for more details. d19 2 a20 3 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/. @ 1.1.1.1.8.1 log @file aorslshC_n.asm was added on branch tls-maxphys on 2014-08-19 23:59:54 +0000 @ text @d1 236 @ 1.1.1.1.8.2 log @Rebase to HEAD as of a few days ago. @ text @a0 236 dnl Intel Atom mpn_addlshC_n/mpn_sublshC_n -- rp[] = up[] +- (vp[] << C) dnl Contributed to the GNU project by Marco Bodrato. dnl Copyright 2011 Free Software Foundation, Inc. dnl dnl This file is part of the GNU MP Library. dnl dnl The GNU MP Library is free software; you can redistribute it and/or dnl modify it under the terms of the GNU Lesser General Public License as dnl published by the Free Software Foundation; either version 3 of the dnl License, or (at your option) any later version. dnl dnl The GNU MP Library is distributed in the hope that it will be useful, dnl but WITHOUT ANY WARRANTY; without even the implied warranty of dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU dnl Lesser General Public License for more details. dnl 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 mp_limb_t mpn_addlshC_n_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size); C mp_limb_t mpn_addlshC_nc_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size, C mp_limb_t carry); C mp_limb_t mpn_sublshC_n_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size,); C mp_limb_t mpn_sublshC_nc_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size, C mp_signed_limb_t borrow); defframe(PARAM_CORB, 16) defframe(PARAM_SIZE, 12) defframe(PARAM_SRC, 8) defframe(PARAM_DST, 4) C mp_limb_t mpn_addlshC_n (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size,); C mp_limb_t mpn_addlshC_nc (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size, mp_limb_t carry); C mp_limb_t mpn_sublshC_n (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size,); C mp_limb_t mpn_sublshC_nc (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size, mp_limb_t borrow); C if src1 == dst, _ip1 is used C cycles/limb C dst!=src1,src2 dst==src1 C P5 C P6 model 0-8,10-12 C P6 model 9 (Banias) C P6 model 13 (Dothan) C P4 model 0 (Willamette) C P4 model 1 (?) C P4 model 2 (Northwood) C P4 model 3 (Prescott) C P4 model 4 (Nocona) C Intel Atom 7 6 C AMD K6 C AMD K7 C AMD K8 C AMD K10 defframe(GPARAM_CORB, 20) defframe(GPARAM_SIZE, 16) defframe(GPARAM_SRC2, 12) dnl re-use parameter space define(SAVE_EBP,`PARAM_SIZE') define(SAVE_EBX,`PARAM_SRC') define(SAVE_UP,`PARAM_DST') define(M, eval(m4_lshift(1,LSH))) define(`rp', `%edi') define(`up', `%esi') ASM_START() TEXT ALIGN(8) PROLOGUE(M4_ip_function_c) deflit(`FRAME',0) movl PARAM_CORB, %ecx movl %ecx, %edx shr $LSH, %edx andl $1, %edx M4_opp %edx, %ecx jmp L(start_nc) EPILOGUE() PROLOGUE(M4_ip_function) deflit(`FRAME',0) xor %ecx, %ecx xor %edx, %edx L(start_nc): push rp FRAME_pushl() mov PARAM_DST, rp mov up, SAVE_UP mov PARAM_SRC, up mov %ebx, SAVE_EBX mov PARAM_SIZE, %ebx C size L(inplace): incl %ebx C size + 1 shr %ebx C (size+1)\2 mov %ebp, SAVE_EBP jnc L(entry) C size odd add %edx, %edx C size even mov %ecx, %ebp mov (up), %ecx lea -4(rp), rp lea (%ebp,%ecx,M), %eax lea 4(up), up jmp L(enteven) ALIGN(16) L(oop): lea (%ecx,%eax,M), %ebp shr $RSH, %eax mov 4(up), %ecx add %edx, %edx lea 8(up), up M4_inst %ebp, (rp) lea (%eax,%ecx,M), %eax L(enteven): M4_inst %eax, 4(rp) lea 8(rp), rp sbb %edx, %edx shr $RSH, %ecx L(entry): mov (up), %eax decl %ebx jnz L(oop) lea (%ecx,%eax,M), %ebp shr $RSH, %eax shr %edx M4_inst %ebp, (rp) mov SAVE_UP, up adc $0, %eax mov SAVE_EBP, %ebp mov SAVE_EBX, %ebx pop rp FRAME_popl() ret EPILOGUE() PROLOGUE(M4_function_c) deflit(`FRAME',0) movl GPARAM_CORB, %ecx movl %ecx, %edx shr $LSH, %edx andl $1, %edx M4_opp %edx, %ecx jmp L(generic_nc) EPILOGUE() PROLOGUE(M4_function) deflit(`FRAME',0) xor %ecx, %ecx xor %edx, %edx L(generic_nc): push rp FRAME_pushl() mov PARAM_DST, rp mov up, SAVE_UP mov PARAM_SRC, up cmp rp, up mov %ebx, SAVE_EBX jne L(general) mov GPARAM_SIZE, %ebx C size mov GPARAM_SRC2, up jmp L(inplace) L(general): mov GPARAM_SIZE, %eax C size mov %ebx, SAVE_EBX incl %eax C size + 1 mov up, %ebx C vp mov GPARAM_SRC2, up C up shr %eax C (size+1)\2 mov %ebp, SAVE_EBP mov %eax, GPARAM_SIZE jnc L(entry2) C size odd add %edx, %edx C size even mov %ecx, %ebp mov (up), %ecx lea -4(rp), rp lea -4(%ebx), %ebx lea (%ebp,%ecx,M), %eax lea 4(up), up jmp L(enteven2) ALIGN(16) L(oop2): lea (%ecx,%eax,M), %ebp shr $RSH, %eax mov 4(up), %ecx add %edx, %edx lea 8(up), up mov (%ebx), %edx M4_inst %ebp, %edx lea (%eax,%ecx,M), %eax mov %edx, (rp) L(enteven2): mov 4(%ebx), %edx lea 8(%ebx), %ebx M4_inst %eax, %edx mov %edx, 4(rp) sbb %edx, %edx shr $RSH, %ecx lea 8(rp), rp L(entry2): mov (up), %eax decl GPARAM_SIZE jnz L(oop2) lea (%ecx,%eax,M), %ebp shr $RSH, %eax shr %edx mov (%ebx), %edx M4_inst %ebp, %edx mov %edx, (rp) mov SAVE_UP, up adc $0, %eax mov SAVE_EBP, %ebp mov SAVE_EBX, %ebx pop rp FRAME_popl() ret EPILOGUE() ASM_END() @ 1.1.1.1.4.1 log @file aorslshC_n.asm was added on branch yamt-pagecache on 2014-05-22 14:09:04 +0000 @ text @d1 236 @ 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 236 dnl Intel Atom mpn_addlshC_n/mpn_sublshC_n -- rp[] = up[] +- (vp[] << C) dnl Contributed to the GNU project by Marco Bodrato. dnl Copyright 2011 Free Software Foundation, Inc. dnl dnl This file is part of the GNU MP Library. dnl dnl The GNU MP Library is free software; you can redistribute it and/or dnl modify it under the terms of the GNU Lesser General Public License as dnl published by the Free Software Foundation; either version 3 of the dnl License, or (at your option) any later version. dnl dnl The GNU MP Library is distributed in the hope that it will be useful, dnl but WITHOUT ANY WARRANTY; without even the implied warranty of dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU dnl Lesser General Public License for more details. dnl 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 mp_limb_t mpn_addlshC_n_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size); C mp_limb_t mpn_addlshC_nc_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size, C mp_limb_t carry); C mp_limb_t mpn_sublshC_n_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size,); C mp_limb_t mpn_sublshC_nc_ip1 (mp_ptr dst, mp_srcptr src, mp_size_t size, C mp_signed_limb_t borrow); defframe(PARAM_CORB, 16) defframe(PARAM_SIZE, 12) defframe(PARAM_SRC, 8) defframe(PARAM_DST, 4) C mp_limb_t mpn_addlshC_n (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size,); C mp_limb_t mpn_addlshC_nc (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size, mp_limb_t carry); C mp_limb_t mpn_sublshC_n (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size,); C mp_limb_t mpn_sublshC_nc (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, C mp_size_t size, mp_limb_t borrow); C if src1 == dst, _ip1 is used C cycles/limb C dst!=src1,src2 dst==src1 C P5 C P6 model 0-8,10-12 C P6 model 9 (Banias) C P6 model 13 (Dothan) C P4 model 0 (Willamette) C P4 model 1 (?) C P4 model 2 (Northwood) C P4 model 3 (Prescott) C P4 model 4 (Nocona) C Intel Atom 7 6 C AMD K6 C AMD K7 C AMD K8 C AMD K10 defframe(GPARAM_CORB, 20) defframe(GPARAM_SIZE, 16) defframe(GPARAM_SRC2, 12) dnl re-use parameter space define(SAVE_EBP,`PARAM_SIZE') define(SAVE_EBX,`PARAM_SRC') define(SAVE_UP,`PARAM_DST') define(M, eval(m4_lshift(1,LSH))) define(`rp', `%edi') define(`up', `%esi') ASM_START() TEXT ALIGN(8) PROLOGUE(M4_ip_function_c) deflit(`FRAME',0) movl PARAM_CORB, %ecx movl %ecx, %edx shr $LSH, %edx andl $1, %edx M4_opp %edx, %ecx jmp L(start_nc) EPILOGUE() PROLOGUE(M4_ip_function) deflit(`FRAME',0) xor %ecx, %ecx xor %edx, %edx L(start_nc): push rp FRAME_pushl() mov PARAM_DST, rp mov up, SAVE_UP mov PARAM_SRC, up mov %ebx, SAVE_EBX mov PARAM_SIZE, %ebx C size L(inplace): incl %ebx C size + 1 shr %ebx C (size+1)\2 mov %ebp, SAVE_EBP jnc L(entry) C size odd add %edx, %edx C size even mov %ecx, %ebp mov (up), %ecx lea -4(rp), rp lea (%ebp,%ecx,M), %eax lea 4(up), up jmp L(enteven) ALIGN(16) L(oop): lea (%ecx,%eax,M), %ebp shr $RSH, %eax mov 4(up), %ecx add %edx, %edx lea 8(up), up M4_inst %ebp, (rp) lea (%eax,%ecx,M), %eax L(enteven): M4_inst %eax, 4(rp) lea 8(rp), rp sbb %edx, %edx shr $RSH, %ecx L(entry): mov (up), %eax decl %ebx jnz L(oop) lea (%ecx,%eax,M), %ebp shr $RSH, %eax shr %edx M4_inst %ebp, (rp) mov SAVE_UP, up adc $0, %eax mov SAVE_EBP, %ebp mov SAVE_EBX, %ebx pop rp FRAME_popl() ret EPILOGUE() PROLOGUE(M4_function_c) deflit(`FRAME',0) movl GPARAM_CORB, %ecx movl %ecx, %edx shr $LSH, %edx andl $1, %edx M4_opp %edx, %ecx jmp L(generic_nc) EPILOGUE() PROLOGUE(M4_function) deflit(`FRAME',0) xor %ecx, %ecx xor %edx, %edx L(generic_nc): push rp FRAME_pushl() mov PARAM_DST, rp mov up, SAVE_UP mov PARAM_SRC, up cmp rp, up mov %ebx, SAVE_EBX jne L(general) mov GPARAM_SIZE, %ebx C size mov GPARAM_SRC2, up jmp L(inplace) L(general): mov GPARAM_SIZE, %eax C size mov %ebx, SAVE_EBX incl %eax C size + 1 mov up, %ebx C vp mov GPARAM_SRC2, up C up shr %eax C (size+1)\2 mov %ebp, SAVE_EBP mov %eax, GPARAM_SIZE jnc L(entry2) C size odd add %edx, %edx C size even mov %ecx, %ebp mov (up), %ecx lea -4(rp), rp lea -4(%ebx), %ebx lea (%ebp,%ecx,M), %eax lea 4(up), up jmp L(enteven2) ALIGN(16) L(oop2): lea (%ecx,%eax,M), %ebp shr $RSH, %eax mov 4(up), %ecx add %edx, %edx lea 8(up), up mov (%ebx), %edx M4_inst %ebp, %edx lea (%eax,%ecx,M), %eax mov %edx, (rp) L(enteven2): mov 4(%ebx), %edx lea 8(%ebx), %ebx M4_inst %eax, %edx mov %edx, 4(rp) sbb %edx, %edx shr $RSH, %ecx lea 8(rp), rp L(entry2): mov (up), %eax decl GPARAM_SIZE jnz L(oop2) lea (%ecx,%eax,M), %ebp shr $RSH, %eax shr %edx mov (%ebx), %edx M4_inst %ebp, %edx mov %edx, (rp) mov SAVE_UP, up adc $0, %eax mov SAVE_EBP, %ebp mov SAVE_EBX, %ebx pop rp FRAME_popl() ret EPILOGUE() ASM_END() @