diff options
Diffstat (limited to 'gmp/mpn/x86/atom')
30 files changed, 3720 insertions, 0 deletions
diff --git a/gmp/mpn/x86/atom/aorrlsh1_n.asm b/gmp/mpn/x86/atom/aorrlsh1_n.asm new file mode 100644 index 0000000000..cd1a650022 --- /dev/null +++ b/gmp/mpn/x86/atom/aorrlsh1_n.asm @@ -0,0 +1,53 @@ +dnl Intel Atom mpn_rsblsh1_n -- rp[] = (vp[] << 1) - up[] + +dnl Contributed to the GNU project by Marco Bodrato. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +define(LSH, 1) +define(RSH, 31) + +ifdef(`OPERATION_addlsh1_n', ` + define(M4_inst, adc) + define(M4_opp, sub) + define(M4_function, mpn_addlsh1_n) + define(M4_function_c, mpn_addlsh1_nc) +',`ifdef(`OPERATION_rsblsh1_n', ` + define(M4_inst, sbb) + define(M4_opp, add) + define(M4_function, mpn_rsblsh1_n) + define(M4_function_c, mpn_rsblsh1_nc) +',`m4_error(`Need OPERATION_addlsh1_n or OPERATION_rsblsh1_n +')')') + +MULFUNC_PROLOGUE(mpn_addlsh1_n mpn_addlsh1_nc mpn_rsblsh1_n mpn_rsblsh1_nc) + +include_mpn(`x86/atom/aorrlshC_n.asm') diff --git a/gmp/mpn/x86/atom/aorrlsh2_n.asm b/gmp/mpn/x86/atom/aorrlsh2_n.asm new file mode 100644 index 0000000000..10f4419de9 --- /dev/null +++ b/gmp/mpn/x86/atom/aorrlsh2_n.asm @@ -0,0 +1,53 @@ +dnl Intel Atom mpn_addlsh2_n/mpn_rsblsh2_n -- rp[] = (vp[] << 2) +- up[] + +dnl Contributed to the GNU project by Marco Bodrato. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +define(LSH, 2) +define(RSH, 30) + +ifdef(`OPERATION_addlsh2_n', ` + define(M4_inst, adcl) + define(M4_opp, subl) + define(M4_function, mpn_addlsh2_n) + define(M4_function_c, mpn_addlsh2_nc) +',`ifdef(`OPERATION_rsblsh2_n', ` + define(M4_inst, sbbl) + define(M4_opp, addl) + define(M4_function, mpn_rsblsh2_n) + define(M4_function_c, mpn_rsblsh2_nc) +',`m4_error(`Need OPERATION_addlsh2_n or OPERATION_rsblsh2_n +')')') + +MULFUNC_PROLOGUE(mpn_addlsh2_n mpn_addlsh2_nc mpn_rsblsh2_n mpn_rsblsh2_nc) + +include_mpn(`x86/atom/aorrlshC_n.asm') diff --git a/gmp/mpn/x86/atom/aorrlshC_n.asm b/gmp/mpn/x86/atom/aorrlshC_n.asm new file mode 100644 index 0000000000..71cfe490d6 --- /dev/null +++ b/gmp/mpn/x86/atom/aorrlshC_n.asm @@ -0,0 +1,156 @@ +dnl Intel Atom mpn_addlshC_n/mpn_rsblshC_n -- rp[] = (vp[] << C) +- up[] + +dnl Contributed to the GNU project by Marco Bodrato. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +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_rsblshC_n (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, +C mp_size_t size); +C mp_limb_t mpn_rsblshC_nc (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, +C mp_size_t size, mp_signed_limb_t carry); + +C cycles/limb +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 6 +C AMD K6 +C AMD K7 +C AMD K8 +C AMD K10 + +defframe(PARAM_CORB, 20) +defframe(PARAM_SIZE, 16) +defframe(PARAM_DBLD, 12) +defframe(PARAM_SRC, 8) +defframe(PARAM_DST, 4) + +dnl re-use parameter space +define(VAR_COUNT,`PARAM_SIZE') +define(SAVE_EBP,`PARAM_DBLD') +define(SAVE_VP,`PARAM_SRC') +define(SAVE_UP,`PARAM_DST') + +define(M, eval(m4_lshift(1,LSH))) +define(`rp', `%edi') +define(`up', `%esi') +define(`vp', `%ebx') + +ASM_START() + TEXT + ALIGN(8) + +PROLOGUE(M4_function_c) +deflit(`FRAME',0) + movl PARAM_CORB, %eax + movl %eax, %edx + shr $LSH, %edx + andl $1, %edx + M4_opp %edx, %eax + jmp L(start_nc) +EPILOGUE() + +PROLOGUE(M4_function) +deflit(`FRAME',0) + + xor %eax, %eax + xor %edx, %edx +L(start_nc): + push rp FRAME_pushl() + + mov PARAM_SIZE, %ecx C size + mov PARAM_DST, rp + mov up, SAVE_UP + incl %ecx C size + 1 + mov PARAM_SRC, up + mov vp, SAVE_VP + shr %ecx C (size+1)\2 + mov PARAM_DBLD, vp + mov %ebp, SAVE_EBP + mov %ecx, VAR_COUNT + jnc L(entry) C size odd + + shr %edx C size even + mov (vp), %ecx + lea 4(vp), vp + lea (%eax,%ecx,M), %edx + mov %ecx, %eax + lea -4(up), up + lea -4(rp), rp + jmp L(enteven) + + ALIGN(16) +L(oop): + lea (%eax,%ecx,M), %ebp + shr $RSH, %ecx + mov 4(vp), %eax + shr %edx + lea 8(vp), vp + M4_inst (up), %ebp + lea (%ecx,%eax,M), %edx + mov %ebp, (rp) +L(enteven): + M4_inst 4(up), %edx + lea 8(up), up + mov %edx, 4(rp) + adc %edx, %edx + shr $RSH, %eax + lea 8(rp), rp +L(entry): + mov (vp), %ecx + decl VAR_COUNT + jnz L(oop) + + lea (%eax,%ecx,M), %ebp + shr $RSH, %ecx + shr %edx + mov SAVE_VP, vp + M4_inst (up), %ebp + mov %ecx, %eax + mov SAVE_UP, up + M4_inst $0, %eax + mov %ebp, (rp) + mov SAVE_EBP, %ebp + pop rp FRAME_popl() + ret +EPILOGUE() + +ASM_END() diff --git a/gmp/mpn/x86/atom/aors_n.asm b/gmp/mpn/x86/atom/aors_n.asm new file mode 100644 index 0000000000..45ec287c3a --- /dev/null +++ b/gmp/mpn/x86/atom/aors_n.asm @@ -0,0 +1,159 @@ +dnl Intel Atom mpn_add_n/mpn_sub_n -- rp[] = up[] +- vp[]. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl Contributed to the GNU project by Marco Bodrato. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C cycles/limb +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 3 +C AMD K6 +C AMD K7 +C AMD K8 +C AMD K10 + +ifdef(`OPERATION_add_n', ` + define(M4_inst, adcl) + define(M4_function_n, mpn_add_n) + define(M4_function_nc, mpn_add_nc) + define(M4_description, add) +',`ifdef(`OPERATION_sub_n', ` + define(M4_inst, sbbl) + define(M4_function_n, mpn_sub_n) + define(M4_function_nc, mpn_sub_nc) + define(M4_description, subtract) +',`m4_error(`Need OPERATION_add_n or OPERATION_sub_n +')')') + +MULFUNC_PROLOGUE(mpn_add_n mpn_add_nc mpn_sub_n mpn_sub_nc) + +C mp_limb_t M4_function_n (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, +C mp_size_t size); +C mp_limb_t M4_function_nc (mp_ptr dst, mp_srcptr src1, mp_srcptr src2, +C mp_size_t size, mp_limb_t carry); +C +C Calculate src1,size M4_description src2,size, and store the result in +C dst,size. The return value is the carry bit from the top of the result (1 +C or 0). +C +C The _nc version accepts 1 or 0 for an initial carry into the low limb of +C the calculation. Note values other than 1 or 0 here will lead to garbage +C results. + +defframe(PARAM_CARRY,20) +defframe(PARAM_SIZE, 16) +defframe(PARAM_SRC2, 12) +defframe(PARAM_SRC1, 8) +defframe(PARAM_DST, 4) + +dnl re-use parameter space +define(SAVE_RP,`PARAM_SIZE') +define(SAVE_VP,`PARAM_SRC1') +define(SAVE_UP,`PARAM_DST') + +define(`rp', `%edi') +define(`up', `%esi') +define(`vp', `%ebx') +define(`cy', `%ecx') +define(`r1', `%ecx') +define(`r2', `%edx') + +ASM_START() + TEXT + ALIGN(16) +deflit(`FRAME',0) + +PROLOGUE(M4_function_n) + xor cy, cy C carry +L(start): + mov PARAM_SIZE, %eax C size + mov rp, SAVE_RP + mov PARAM_DST, rp + mov up, SAVE_UP + mov PARAM_SRC1, up + shr %eax C size >> 1 + mov vp, SAVE_VP + mov PARAM_SRC2, vp + jz L(one) C size == 1 + jc L(three) C size % 2 == 1 + + shr cy + mov (up), r2 + lea 4(up), up + lea 4(vp), vp + lea -4(rp), rp + jmp L(entry) +L(one): + shr cy + mov (up), r1 + jmp L(end) +L(three): + shr cy + mov (up), r1 + + ALIGN(16) +L(oop): + M4_inst (vp), r1 + lea 8(up), up + mov -4(up), r2 + lea 8(vp), vp + mov r1, (rp) +L(entry): + M4_inst -4(vp), r2 + lea 8(rp), rp + dec %eax + mov (up), r1 + mov r2, -4(rp) + jnz L(oop) + +L(end): C %eax is zero here + mov SAVE_UP, up + M4_inst (vp), r1 + mov SAVE_VP, vp + mov r1, (rp) + adc %eax, %eax + mov SAVE_RP, rp + ret +EPILOGUE() + +PROLOGUE(M4_function_nc) + mov PARAM_CARRY, cy C carry + jmp L(start) +EPILOGUE() +ASM_END() diff --git a/gmp/mpn/x86/atom/aorslshC_n.asm b/gmp/mpn/x86/atom/aorslshC_n.asm new file mode 100644 index 0000000000..75ace65e51 --- /dev/null +++ b/gmp/mpn/x86/atom/aorslshC_n.asm @@ -0,0 +1,247 @@ +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 This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +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() diff --git a/gmp/mpn/x86/atom/bdiv_q_1.asm b/gmp/mpn/x86/atom/bdiv_q_1.asm new file mode 100644 index 0000000000..31e908ec44 --- /dev/null +++ b/gmp/mpn/x86/atom/bdiv_q_1.asm @@ -0,0 +1,35 @@ +dnl Intel Atom mpn_bdiv_q_1, mpn_pi1_bdiv_q_1 -- schoolbook Hensel +dnl division by 1-limb divisor, returning quotient only. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_bdiv_q_1 mpn_pi1_bdiv_q_1) +include_mpn(`x86/pentium/bdiv_q_1.asm') diff --git a/gmp/mpn/x86/atom/cnd_add_n.asm b/gmp/mpn/x86/atom/cnd_add_n.asm new file mode 100644 index 0000000000..50bf2ad64b --- /dev/null +++ b/gmp/mpn/x86/atom/cnd_add_n.asm @@ -0,0 +1,113 @@ +dnl X86 mpn_cnd_add_n optimised for Intel Atom. + +dnl Copyright 2013 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C cycles/limb +C P5 ? +C P6 model 0-8,10-12 ? +C P6 model 9 (Banias) ? +C P6 model 13 (Dothan) ? +C P4 model 0-1 (Willamette) ? +C P4 model 2 (Northwood) ? +C P4 model 3-4 (Prescott) ? +C Intel atom 4.67 +C AMD K6 ? +C AMD K7 ? +C AMD K8 ? + + +define(`rp', `%edi') +define(`up', `%esi') +define(`vp', `%ebp') +define(`n', `%ecx') +define(`cnd', `20(%esp)') + +ASM_START() + TEXT + ALIGN(16) +PROLOGUE(mpn_cnd_add_n) + push %edi + push %esi + push %ebx + push %ebp + + mov cnd, %eax C make cnd into a mask (1) + mov 24(%esp), rp + neg %eax C make cnd into a mask (1) + mov 28(%esp), up + sbb %eax, %eax C make cnd into a mask (1) + mov 32(%esp), vp + mov %eax, cnd C make cnd into a mask (1) + mov 36(%esp), n + + xor %edx, %edx + + shr $1, n + jnc L(top) + + mov 0(vp), %eax + and cnd, %eax + lea 4(vp), vp + add 0(up), %eax + lea 4(rp), rp + lea 4(up), up + sbb %edx, %edx + mov %eax, -4(rp) + inc n + dec n + je L(end) + +L(top): sbb %edx, %edx + mov 0(vp), %eax + and cnd, %eax + lea 8(vp), vp + lea 8(rp), rp + mov -4(vp), %ebx + and cnd, %ebx + add %edx, %edx + adc 0(up), %eax + lea 8(up), up + mov %eax, -8(rp) + adc -4(up), %ebx + dec n + mov %ebx, -4(rp) + jne L(top) + +L(end): mov $0, %eax + adc %eax, %eax + + pop %ebp + pop %ebx + pop %esi + pop %edi + ret +EPILOGUE() +ASM_END() diff --git a/gmp/mpn/x86/atom/cnd_sub_n.asm b/gmp/mpn/x86/atom/cnd_sub_n.asm new file mode 100644 index 0000000000..221bedca37 --- /dev/null +++ b/gmp/mpn/x86/atom/cnd_sub_n.asm @@ -0,0 +1,124 @@ +dnl X86 mpn_cnd_sub_n optimised for Intel Atom. + +dnl Copyright 2013 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C cycles/limb +C P5 ? +C P6 model 0-8,10-12 ? +C P6 model 9 (Banias) ? +C P6 model 13 (Dothan) ? +C P4 model 0-1 (Willamette) ? +C P4 model 2 (Northwood) ? +C P4 model 3-4 (Prescott) ? +C Intel atom 5.67 +C AMD K6 ? +C AMD K7 ? +C AMD K8 ? + + +define(`rp', `%edi') +define(`up', `%esi') +define(`vp', `%ebp') +define(`n', `%ecx') +define(`cnd', `20(%esp)') + +ASM_START() + TEXT + ALIGN(16) +PROLOGUE(mpn_cnd_sub_n) + push %edi + push %esi + push %ebx + push %ebp + + mov cnd, %eax C make cnd into a mask (1) + mov 24(%esp), rp + neg %eax C make cnd into a mask (1) + mov 28(%esp), up + sbb %eax, %eax C make cnd into a mask (1) + mov 32(%esp), vp + mov %eax, cnd C make cnd into a mask (1) + mov 36(%esp), n + + xor %edx, %edx + + inc n + shr n + jnc L(ent) + + mov 0(vp), %eax + and cnd, %eax + lea 4(vp), vp + mov 0(up), %edx + sub %eax, %edx + lea 4(rp), rp + lea 4(up), up + mov %edx, -4(rp) + sbb %edx, %edx C save cy + +L(ent): mov 0(vp), %ebx + and cnd, %ebx + add %edx, %edx C restore cy + mov 0(up), %edx + dec n + je L(end) + +L(top): sbb %ebx, %edx + mov 4(vp), %eax + mov %edx, 0(rp) + sbb %edx, %edx C save cy + mov 8(vp), %ebx + lea 8(up), up + and cnd, %ebx + and cnd, %eax + add %edx, %edx C restore cy + mov -4(up), %edx + lea 8(rp), rp + sbb %eax, %edx + mov %edx, -4(rp) + dec n + mov 0(up), %edx + lea 8(vp), vp + jne L(top) + +L(end): sbb %ebx, %edx + mov %edx, 0(rp) + + mov $0, %eax + adc %eax, %eax + + pop %ebp + pop %ebx + pop %esi + pop %edi + ret +EPILOGUE() +ASM_END() diff --git a/gmp/mpn/x86/atom/dive_1.asm b/gmp/mpn/x86/atom/dive_1.asm new file mode 100644 index 0000000000..71036a15a4 --- /dev/null +++ b/gmp/mpn/x86/atom/dive_1.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_divexact_1 -- mpn by limb exact division. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_divexact_1) +include_mpn(`x86/pentium/dive_1.asm') diff --git a/gmp/mpn/x86/atom/gmp-mparam.h b/gmp/mpn/x86/atom/gmp-mparam.h new file mode 100644 index 0000000000..45df12806c --- /dev/null +++ b/gmp/mpn/x86/atom/gmp-mparam.h @@ -0,0 +1,201 @@ +/* Intel Atom/32 gmp-mparam.h -- Compiler/machine parameter header file. + +Copyright 1991, 1993, 1994, 2000-2011, 2014 Free Software Foundation, Inc. + +This file is part of the GNU MP Library. + +The GNU MP Library is free software; you can redistribute it and/or modify +it under the terms of either: + + * the GNU Lesser General Public License as published by the Free + Software Foundation; either version 3 of the License, or (at your + option) any later version. + +or + + * the GNU General Public License as published by the Free Software + Foundation; either version 2 of the License, or (at your option) any + later version. + +or both in parallel, as here. + +The GNU MP Library is distributed in the hope that it will be useful, but +WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +for more details. + +You should have received copies of the GNU General Public License and the +GNU Lesser General Public License along with the GNU MP Library. If not, +see https://www.gnu.org/licenses/. */ + +#define GMP_LIMB_BITS 32 +#define GMP_LIMB_BYTES 4 + +/* 1667 MHz Pineview (Atom D510) */ +/* FFT tuning limit = 25000000 */ +/* Generated by tuneup.c, 2014-03-14, gcc 4.5 */ + +#define MOD_1_NORM_THRESHOLD 3 +#define MOD_1_UNNORM_THRESHOLD 5 +#define MOD_1N_TO_MOD_1_1_THRESHOLD 11 +#define MOD_1U_TO_MOD_1_1_THRESHOLD 5 +#define MOD_1_1_TO_MOD_1_2_THRESHOLD 10 +#define MOD_1_2_TO_MOD_1_4_THRESHOLD 0 /* never mpn_mod_1s_2p */ +#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 13 +#define USE_PREINV_DIVREM_1 1 /* native */ +#define DIV_QR_1N_PI1_METHOD 1 +#define DIV_QR_1_NORM_THRESHOLD 4 +#define DIV_QR_1_UNNORM_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIV_QR_2_PI2_THRESHOLD MP_SIZE_T_MAX /* never */ +#define DIVEXACT_1_THRESHOLD 0 /* always (native) */ +#define BMOD_1_TO_MOD_1_THRESHOLD 31 + +#define MUL_TOOM22_THRESHOLD 20 +#define MUL_TOOM33_THRESHOLD 74 +#define MUL_TOOM44_THRESHOLD 178 +#define MUL_TOOM6H_THRESHOLD 270 +#define MUL_TOOM8H_THRESHOLD 399 + +#define MUL_TOOM32_TO_TOOM43_THRESHOLD 73 +#define MUL_TOOM32_TO_TOOM53_THRESHOLD 122 +#define MUL_TOOM42_TO_TOOM53_THRESHOLD 115 +#define MUL_TOOM42_TO_TOOM63_THRESHOLD 127 +#define MUL_TOOM43_TO_TOOM54_THRESHOLD 106 + +#define SQR_BASECASE_THRESHOLD 0 /* always (native) */ +#define SQR_TOOM2_THRESHOLD 30 +#define SQR_TOOM3_THRESHOLD 105 +#define SQR_TOOM4_THRESHOLD 178 +#define SQR_TOOM6_THRESHOLD 303 +#define SQR_TOOM8_THRESHOLD 527 + +#define MULMID_TOOM42_THRESHOLD 54 + +#define MULMOD_BNM1_THRESHOLD 13 +#define SQRMOD_BNM1_THRESHOLD 18 + +#define MUL_FFT_MODF_THRESHOLD 380 /* k = 5 */ +#define MUL_FFT_TABLE3 \ + { { 380, 5}, { 19, 6}, { 10, 5}, { 21, 6}, \ + { 11, 5}, { 23, 6}, { 21, 7}, { 11, 6}, \ + { 25, 7}, { 13, 6}, { 27, 7}, { 15, 6}, \ + { 31, 7}, { 21, 8}, { 11, 7}, { 27, 8}, \ + { 15, 7}, { 35, 8}, { 19, 7}, { 39, 8}, \ + { 23, 7}, { 47, 8}, { 27, 9}, { 15, 8}, \ + { 39, 9}, { 23, 8}, { 51,10}, { 15, 9}, \ + { 31, 8}, { 67, 9}, { 39, 8}, { 79, 9}, \ + { 47, 8}, { 95,10}, { 31, 9}, { 79,10}, \ + { 47, 9}, { 95,11}, { 31,10}, { 63, 9}, \ + { 127, 8}, { 255, 9}, { 135,10}, { 79, 9}, \ + { 159,10}, { 95, 9}, { 191,11}, { 63,10}, \ + { 127, 9}, { 255, 8}, { 511, 9}, { 271,10}, \ + { 143, 9}, { 287, 8}, { 575,10}, { 159,11}, \ + { 95,10}, { 191, 9}, { 383,12}, { 63,11}, \ + { 127,10}, { 255, 9}, { 511,10}, { 271, 9}, \ + { 543,10}, { 287, 9}, { 575,10}, { 303,11}, \ + { 159,10}, { 319, 9}, { 639,10}, { 335, 9}, \ + { 671,10}, { 351, 9}, { 703,11}, { 191,10}, \ + { 383, 9}, { 767,10}, { 415, 9}, { 831,11}, \ + { 223,10}, { 447,12}, { 127,11}, { 255,10}, \ + { 543,11}, { 287,10}, { 607, 9}, { 1215,11}, \ + { 319,10}, { 671,11}, { 351,10}, { 703,12}, \ + { 191,11}, { 383,10}, { 767,11}, { 415,10}, \ + { 831,11}, { 447,13}, { 127,12}, { 255,11}, \ + { 543,10}, { 1087,11}, { 607,10}, { 1215,12}, \ + { 319,11}, { 735,12}, { 383,11}, { 831,12}, \ + { 447,11}, { 959,13}, { 255,12}, { 511,11}, \ + { 1087,12}, { 575,11}, { 1151,12}, { 703,11}, \ + { 1471,13}, { 383,12}, { 831,11}, { 1663,12}, \ + { 959,14}, { 255,13}, { 511,12}, { 1215,13}, \ + { 639,12}, { 1471,11}, { 2943,13}, { 767,12}, \ + { 1663,13}, { 895,12}, { 1919,14}, { 511,13}, \ + { 1023,12}, { 2111,13}, { 1151,12}, { 2431,13}, \ + { 1407,12}, { 2943,14}, { 767,13}, { 1663,12}, \ + { 3455,13}, { 1919,15}, { 511,14}, { 1023,13}, \ + { 2431,14}, { 1279,13}, { 2943,12}, { 5887,14}, \ + { 16384,15}, { 32768,16} } +#define MUL_FFT_TABLE3_SIZE 150 +#define MUL_FFT_THRESHOLD 4544 + +#define SQR_FFT_MODF_THRESHOLD 340 /* k = 5 */ +#define SQR_FFT_TABLE3 \ + { { 340, 5}, { 21, 6}, { 11, 5}, { 23, 6}, \ + { 12, 5}, { 25, 6}, { 21, 7}, { 11, 6}, \ + { 25, 7}, { 13, 6}, { 27, 7}, { 15, 6}, \ + { 31, 7}, { 21, 8}, { 11, 7}, { 27, 8}, \ + { 15, 7}, { 35, 8}, { 19, 7}, { 41, 8}, \ + { 23, 7}, { 47, 8}, { 27, 9}, { 15, 8}, \ + { 39, 9}, { 23, 8}, { 51,10}, { 15, 9}, \ + { 31, 8}, { 63, 9}, { 39, 8}, { 79, 9}, \ + { 47,10}, { 31, 9}, { 79,10}, { 47, 9}, \ + { 95,11}, { 31,10}, { 63, 9}, { 127, 8}, \ + { 255,10}, { 79, 9}, { 159, 8}, { 319,10}, \ + { 95, 9}, { 191,11}, { 63,10}, { 127, 9}, \ + { 255, 8}, { 511, 9}, { 271,10}, { 143, 9}, \ + { 287, 8}, { 575, 9}, { 303, 8}, { 607,10}, \ + { 159, 9}, { 319,11}, { 95,10}, { 191, 9}, \ + { 383,12}, { 63,11}, { 127,10}, { 255, 9}, \ + { 511,10}, { 271, 9}, { 543,10}, { 287, 9}, \ + { 575,10}, { 303, 9}, { 607,10}, { 319, 9}, \ + { 639,10}, { 335, 9}, { 671,10}, { 351, 9}, \ + { 703,11}, { 191,10}, { 383, 9}, { 767,10}, \ + { 415,11}, { 223,10}, { 447,12}, { 127,11}, \ + { 255,10}, { 543,11}, { 287,10}, { 607,11}, \ + { 319,10}, { 671,11}, { 351,10}, { 703,12}, \ + { 191,11}, { 383,10}, { 767,11}, { 415,10}, \ + { 831,11}, { 479,13}, { 127,12}, { 255,11}, \ + { 543,10}, { 1087,11}, { 607,12}, { 319,11}, \ + { 671,10}, { 1343,11}, { 735,12}, { 383,11}, \ + { 831,12}, { 447,11}, { 959,13}, { 255,12}, \ + { 511,11}, { 1087,12}, { 575,11}, { 1215,12}, \ + { 639,11}, { 1343,12}, { 703,11}, { 1407,13}, \ + { 383,12}, { 831,11}, { 1663,12}, { 959,14}, \ + { 255,13}, { 511,12}, { 1215,13}, { 639,12}, \ + { 1471,13}, { 767,12}, { 1663,13}, { 895,12}, \ + { 1791,14}, { 511,13}, { 1023,12}, { 2111,13}, \ + { 1151,12}, { 2431,13}, { 1407,14}, { 767,13}, \ + { 1663,12}, { 3455,13}, { 1791,15}, { 511,14}, \ + { 1023,13}, { 2431,14}, { 1279,13}, { 2943,12}, \ + { 5887,14}, { 16384,15}, { 32768,16} } +#define SQR_FFT_TABLE3_SIZE 151 +#define SQR_FFT_THRESHOLD 2880 + +#define MULLO_BASECASE_THRESHOLD 6 +#define MULLO_DC_THRESHOLD 48 +#define MULLO_MUL_N_THRESHOLD 8907 + +#define DC_DIV_QR_THRESHOLD 59 +#define DC_DIVAPPR_Q_THRESHOLD 250 +#define DC_BDIV_QR_THRESHOLD 59 +#define DC_BDIV_Q_THRESHOLD 169 + +#define INV_MULMOD_BNM1_THRESHOLD 38 +#define INV_NEWTON_THRESHOLD 246 +#define INV_APPR_THRESHOLD 246 + +#define BINV_NEWTON_THRESHOLD 276 +#define REDC_1_TO_REDC_N_THRESHOLD 67 + +#define MU_DIV_QR_THRESHOLD 1334 +#define MU_DIVAPPR_Q_THRESHOLD 1442 +#define MUPI_DIV_QR_THRESHOLD 114 +#define MU_BDIV_QR_THRESHOLD 1142 +#define MU_BDIV_Q_THRESHOLD 1334 + +#define POWM_SEC_TABLE 1,22,98,416,1378 + +#define MATRIX22_STRASSEN_THRESHOLD 13 +#define HGCD_THRESHOLD 133 +#define HGCD_APPR_THRESHOLD 169 +#define HGCD_REDUCE_THRESHOLD 2479 +#define GCD_DC_THRESHOLD 460 +#define GCDEXT_DC_THRESHOLD 342 +#define JACOBI_BASE_METHOD 3 + +#define GET_STR_DC_THRESHOLD 12 +#define GET_STR_PRECOMPUTE_THRESHOLD 23 +#define SET_STR_DC_THRESHOLD 321 +#define SET_STR_PRECOMPUTE_THRESHOLD 1099 + +#define FAC_DSC_THRESHOLD 198 +#define FAC_ODD_THRESHOLD 34 diff --git a/gmp/mpn/x86/atom/logops_n.asm b/gmp/mpn/x86/atom/logops_n.asm new file mode 100644 index 0000000000..3cb6d7310c --- /dev/null +++ b/gmp/mpn/x86/atom/logops_n.asm @@ -0,0 +1,151 @@ +dnl Intel Atom mpn_and_n,...,mpn_xnor_n -- bitwise logical operations. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl Contributed to the GNU project by Marco Bodrato. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C cycles/limb +C op nop opn +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 3 3.5 3.5 +C AMD K6 +C AMD K7 +C AMD K8 +C AMD K10 + +define(M4_choose_op, +`ifdef(`OPERATION_$1',` +define(`M4_function', `mpn_$1') +define(`M4_want_pre', `$4') +define(`M4_inst', `$3') +define(`M4_want_post',`$2') +')') +define(M4pre, `ifelse(M4_want_pre, yes,`$1')') +define(M4post,`ifelse(M4_want_post,yes,`$1')') + +M4_choose_op( and_n, , andl, ) +M4_choose_op( andn_n, , andl, yes) +M4_choose_op( nand_n, yes, andl, ) +M4_choose_op( ior_n, , orl, ) +M4_choose_op( iorn_n, , orl, yes) +M4_choose_op( nior_n, yes, orl, ) +M4_choose_op( xor_n, , xorl, ) +M4_choose_op( xnor_n, yes, xorl, ) + +ifdef(`M4_function',, +`m4_error(`Unrecognised or undefined OPERATION symbol +')') + +MULFUNC_PROLOGUE(mpn_and_n mpn_andn_n mpn_nand_n mpn_ior_n mpn_iorn_n mpn_nior_n mpn_xor_n mpn_xnor_n) + +C void M4_function (mp_ptr dst, mp_srcptr src2, mp_srcptr src1, mp_size_t size); +C + +defframe(PARAM_SIZE, 16) +defframe(PARAM_SRC1, 12) +defframe(PARAM_SRC2, 8) +defframe(PARAM_DST, 4) + +dnl re-use parameter space +define(SAVE_RP,`PARAM_SIZE') +define(SAVE_VP,`PARAM_SRC1') +define(SAVE_UP,`PARAM_DST') + +define(`rp', `%edi') +define(`up', `%esi') +define(`vp', `%ebx') +define(`cnt', `%eax') +define(`r1', `%ecx') +define(`r2', `%edx') + +ASM_START() + TEXT + ALIGN(16) +deflit(`FRAME',0) + +PROLOGUE(M4_function) + mov PARAM_SIZE, cnt C size + mov rp, SAVE_RP + mov PARAM_DST, rp + mov up, SAVE_UP + mov PARAM_SRC1, up + shr cnt C size >> 1 + mov vp, SAVE_VP + mov PARAM_SRC2, vp + mov (up), r1 + jz L(end) C size == 1 + jnc L(even) C size % 2 == 0 + + ALIGN(16) +L(oop): +M4pre(` notl_or_xorl_GMP_NUMB_MASK(r1)') + M4_inst (vp), r1 + lea 8(up), up + mov -4(up), r2 +M4post(` notl_or_xorl_GMP_NUMB_MASK(r1)') + lea 8(vp), vp + mov r1, (rp) +L(entry): +M4pre(` notl_or_xorl_GMP_NUMB_MASK(r2)') + M4_inst -4(vp), r2 + lea 8(rp), rp +M4post(` notl_or_xorl_GMP_NUMB_MASK(r2)') + dec cnt + mov (up), r1 + mov r2, -4(rp) + jnz L(oop) + +L(end): +M4pre(` notl_or_xorl_GMP_NUMB_MASK(r1)') + mov SAVE_UP, up + M4_inst (vp), r1 +M4post(`notl_or_xorl_GMP_NUMB_MASK(r1)') + mov SAVE_VP, vp + mov r1, (rp) + mov SAVE_RP, rp + ret + +L(even): + mov r1, r2 + lea 4(up), up + lea 4(vp), vp + lea -4(rp), rp + jmp L(entry) +EPILOGUE() +ASM_END() diff --git a/gmp/mpn/x86/atom/lshift.asm b/gmp/mpn/x86/atom/lshift.asm new file mode 100644 index 0000000000..f2c70dd3e8 --- /dev/null +++ b/gmp/mpn/x86/atom/lshift.asm @@ -0,0 +1,218 @@ +dnl Intel Atom mpn_lshift -- mpn left shift. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C mp_limb_t mpn_lshift (mp_ptr dst, mp_srcptr src, mp_size_t size, +C unsigned cnt); + +C cycles/limb +C cnt!=1 cnt==1 +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 5 2.5 +C AMD K6 +C AMD K7 +C AMD K8 +C AMD K10 + +defframe(PARAM_CNT, 16) +defframe(PARAM_SIZE,12) +defframe(PARAM_SRC, 8) +defframe(PARAM_DST, 4) + +dnl re-use parameter space +define(SAVE_UP,`PARAM_CNT') +define(VAR_COUNT,`PARAM_SIZE') +define(SAVE_EBX,`PARAM_SRC') +define(SAVE_EBP,`PARAM_DST') + +define(`rp', `%edi') +define(`up', `%esi') +define(`cnt', `%ecx') + +ASM_START() + TEXT + ALIGN(8) +deflit(`FRAME',0) +PROLOGUE(mpn_lshift) + mov PARAM_CNT, cnt + mov PARAM_SIZE, %edx + mov up, SAVE_UP + mov PARAM_SRC, up + push rp FRAME_pushl() + mov PARAM_DST, rp + +C We can use faster code for shift-by-1 under certain conditions. + cmp $1,cnt + jne L(normal) + cmpl rp, up + jnc L(special) C jump if s_ptr + 1 >= res_ptr + leal (up,%edx,4),%eax + cmpl %eax,rp + jnc L(special) C jump if res_ptr >= s_ptr + size + +L(normal): + lea -4(up,%edx,4), up + mov %ebx, SAVE_EBX + lea -4(rp,%edx,4), rp + + shr %edx + mov (up), %eax + mov %edx, VAR_COUNT + jnc L(evn) + + mov %eax, %ebx + shl %cl, %ebx + neg cnt + shr %cl, %eax + test %edx, %edx + jnz L(gt1) + mov %ebx, (rp) + jmp L(quit) + +L(gt1): mov %ebp, SAVE_EBP + push %eax + mov -4(up), %eax + mov %eax, %ebp + shr %cl, %eax + jmp L(lo1) + +L(evn): mov %ebp, SAVE_EBP + neg cnt + mov %eax, %ebp + mov -4(up), %edx + shr %cl, %eax + mov %edx, %ebx + shr %cl, %edx + neg cnt + decl VAR_COUNT + lea 4(rp), rp + lea -4(up), up + jz L(end) + push %eax FRAME_pushl() + + ALIGN(8) +L(top): shl %cl, %ebp + or %ebp, %edx + shl %cl, %ebx + neg cnt + mov -4(up), %eax + mov %eax, %ebp + mov %edx, -4(rp) + shr %cl, %eax + lea -8(rp), rp +L(lo1): mov -8(up), %edx + or %ebx, %eax + mov %edx, %ebx + shr %cl, %edx + lea -8(up), up + neg cnt + mov %eax, (rp) + decl VAR_COUNT + jg L(top) + + pop %eax FRAME_popl() +L(end): + shl %cl, %ebp + shl %cl, %ebx + or %ebp, %edx + mov SAVE_EBP, %ebp + mov %edx, -4(rp) + mov %ebx, -8(rp) + +L(quit): + mov SAVE_UP, up + mov SAVE_EBX, %ebx + pop rp FRAME_popl() + ret + +L(special): +deflit(`FRAME',4) + lea 3(%edx), %eax C size + 3 + dec %edx C size - 1 + mov (up), %ecx + shr $2, %eax C (size + 3) / 4 + and $3, %edx C (size - 1) % 4 + jz L(goloop) C jmp if size == 1 (mod 4) + shr %edx + jnc L(odd) C jum if size == 3 (mod 4) + + add %ecx, %ecx + lea 4(up), up + mov %ecx, (rp) + mov (up), %ecx + lea 4(rp), rp + + dec %edx + jnz L(goloop) C jump if size == 0 (mod 4) +L(odd): lea -8(up), up + lea -8(rp), rp + jmp L(sentry) C reached if size == 2 or 3 (mod 4) + +L(sloop): + adc %ecx, %ecx + mov 4(up), %edx + mov %ecx, (rp) + adc %edx, %edx + mov 8(up), %ecx + mov %edx, 4(rp) +L(sentry): + adc %ecx, %ecx + mov 12(up), %edx + mov %ecx, 8(rp) + adc %edx, %edx + lea 16(up), up + mov %edx, 12(rp) + lea 16(rp), rp + mov (up), %ecx +L(goloop): + decl %eax + jnz L(sloop) + +L(squit): + adc %ecx, %ecx + mov %ecx, (rp) + adc %eax, %eax + + mov SAVE_UP, up + pop rp FRAME_popl() + ret +EPILOGUE() +ASM_END() diff --git a/gmp/mpn/x86/atom/lshiftc.asm b/gmp/mpn/x86/atom/lshiftc.asm new file mode 100644 index 0000000000..5be53ed19d --- /dev/null +++ b/gmp/mpn/x86/atom/lshiftc.asm @@ -0,0 +1,159 @@ +dnl Intel Atom mpn_lshiftc -- mpn left shift with complement. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C mp_limb_t mpn_lshiftc (mp_ptr dst, mp_srcptr src, mp_size_t size, +C unsigned cnt); + +C cycles/limb +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 5.5 +C AMD K6 +C AMD K7 +C AMD K8 +C AMD K10 + +defframe(PARAM_CNT, 16) +defframe(PARAM_SIZE,12) +defframe(PARAM_SRC, 8) +defframe(PARAM_DST, 4) + +dnl re-use parameter space +define(SAVE_UP,`PARAM_CNT') +define(VAR_COUNT,`PARAM_SIZE') +define(SAVE_EBX,`PARAM_SRC') +define(SAVE_EBP,`PARAM_DST') + +define(`rp', `%edi') +define(`up', `%esi') +define(`cnt', `%ecx') + +ASM_START() + TEXT + +PROLOGUE(mpn_lshiftc) +deflit(`FRAME',0) + mov PARAM_CNT, cnt + mov PARAM_SIZE, %edx + mov up, SAVE_UP + mov PARAM_SRC, up + push rp FRAME_pushl() + mov PARAM_DST, rp + + lea -4(up,%edx,4), up + mov %ebx, SAVE_EBX + lea -4(rp,%edx,4), rp + + shr %edx + mov (up), %eax + mov %edx, VAR_COUNT + jnc L(evn) + + mov %eax, %ebx + shl %cl, %ebx + neg cnt + shr %cl, %eax + test %edx, %edx + jnz L(gt1) + not %ebx + mov %ebx, (rp) + jmp L(quit) + +L(gt1): mov %ebp, SAVE_EBP + push %eax + mov -4(up), %eax + mov %eax, %ebp + shr %cl, %eax + jmp L(lo1) + +L(evn): mov %ebp, SAVE_EBP + neg cnt + mov %eax, %ebp + mov -4(up), %edx + shr %cl, %eax + mov %edx, %ebx + shr %cl, %edx + neg cnt + decl VAR_COUNT + lea 4(rp), rp + lea -4(up), up + jz L(end) + push %eax FRAME_pushl() + +L(top): shl %cl, %ebp + or %ebp, %edx + shl %cl, %ebx + neg cnt + not %edx + mov -4(up), %eax + mov %eax, %ebp + mov %edx, -4(rp) + shr %cl, %eax + lea -8(rp), rp +L(lo1): mov -8(up), %edx + or %ebx, %eax + mov %edx, %ebx + shr %cl, %edx + not %eax + lea -8(up), up + neg cnt + mov %eax, (rp) + decl VAR_COUNT + jg L(top) + + pop %eax FRAME_popl() +L(end): + shl %cl, %ebp + shl %cl, %ebx + or %ebp, %edx + mov SAVE_EBP, %ebp + not %edx + not %ebx + mov %edx, -4(rp) + mov %ebx, -8(rp) + +L(quit): + mov SAVE_UP, up + mov SAVE_EBX, %ebx + pop rp FRAME_popl() + ret +EPILOGUE() +ASM_END() diff --git a/gmp/mpn/x86/atom/mmx/copyd.asm b/gmp/mpn/x86/atom/mmx/copyd.asm new file mode 100644 index 0000000000..b80fb033fe --- /dev/null +++ b/gmp/mpn/x86/atom/mmx/copyd.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_copyd -- copy limb vector, decrementing. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_copyd) +include_mpn(`x86/k7/mmx/copyd.asm') diff --git a/gmp/mpn/x86/atom/mmx/copyi.asm b/gmp/mpn/x86/atom/mmx/copyi.asm new file mode 100644 index 0000000000..49b6b8d662 --- /dev/null +++ b/gmp/mpn/x86/atom/mmx/copyi.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_copyi -- copy limb vector, incrementing. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_copyi) +include_mpn(`x86/k7/mmx/copyi.asm') diff --git a/gmp/mpn/x86/atom/mmx/hamdist.asm b/gmp/mpn/x86/atom/mmx/hamdist.asm new file mode 100644 index 0000000000..3fe8253240 --- /dev/null +++ b/gmp/mpn/x86/atom/mmx/hamdist.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_hamdist -- hamming distance. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_hamdist) +include_mpn(`x86/k7/mmx/popham.asm') diff --git a/gmp/mpn/x86/atom/mod_34lsub1.asm b/gmp/mpn/x86/atom/mod_34lsub1.asm new file mode 100644 index 0000000000..6d57ba385d --- /dev/null +++ b/gmp/mpn/x86/atom/mod_34lsub1.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_mod_34lsub1 -- remainder modulo 2^24-1. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_mod_34lsub1) +include_mpn(`x86/p6/mod_34lsub1.asm') diff --git a/gmp/mpn/x86/atom/mode1o.asm b/gmp/mpn/x86/atom/mode1o.asm new file mode 100644 index 0000000000..c9ee6bd2db --- /dev/null +++ b/gmp/mpn/x86/atom/mode1o.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_modexact_1_odd -- exact division style remainder. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_modexact_1_odd mpn_modexact_1c_odd) +include_mpn(`x86/pentium/mode1o.asm') diff --git a/gmp/mpn/x86/atom/rshift.asm b/gmp/mpn/x86/atom/rshift.asm new file mode 100644 index 0000000000..1cb5dbefe9 --- /dev/null +++ b/gmp/mpn/x86/atom/rshift.asm @@ -0,0 +1,152 @@ +dnl Intel Atom mpn_rshift -- mpn right shift. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl Converted from AMD64 by Marco Bodrato. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C mp_limb_t mpn_rshift (mp_ptr dst, mp_srcptr src, mp_size_t size, +C unsigned cnt); + +C cycles/limb +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 5 +C AMD K6 +C AMD K7 +C AMD K8 +C AMD K10 + +defframe(PARAM_CNT, 16) +defframe(PARAM_SIZE,12) +defframe(PARAM_SRC, 8) +defframe(PARAM_DST, 4) + +dnl re-use parameter space +define(SAVE_UP,`PARAM_CNT') +define(VAR_COUNT,`PARAM_SIZE') +define(SAVE_EBX,`PARAM_SRC') +define(SAVE_EBP,`PARAM_DST') + +define(`rp', `%edi') +define(`up', `%esi') +define(`cnt', `%ecx') + +ASM_START() + TEXT + ALIGN(8) +deflit(`FRAME',0) +PROLOGUE(mpn_rshift) + mov PARAM_CNT, cnt + mov PARAM_SIZE, %edx + mov up, SAVE_UP + mov PARAM_SRC, up + push rp FRAME_pushl() + mov PARAM_DST, rp + mov %ebx, SAVE_EBX + + shr %edx + mov (up), %eax + mov %edx, VAR_COUNT + jnc L(evn) + + mov %eax, %ebx + shr %cl, %ebx + neg cnt + shl %cl, %eax + test %edx, %edx + jnz L(gt1) + mov %ebx, (rp) + jmp L(quit) + +L(gt1): mov %ebp, SAVE_EBP + push %eax + mov 4(up), %eax + mov %eax, %ebp + shl %cl, %eax + jmp L(lo1) + +L(evn): mov %ebp, SAVE_EBP + neg cnt + mov %eax, %ebp + mov 4(up), %edx + shl %cl, %eax + mov %edx, %ebx + shl %cl, %edx + neg cnt + decl VAR_COUNT + lea -4(rp), rp + lea 4(up), up + jz L(end) + push %eax FRAME_pushl() + + ALIGN(8) +L(top): shr %cl, %ebp + or %ebp, %edx + shr %cl, %ebx + neg cnt + mov 4(up), %eax + mov %eax, %ebp + mov %edx, 4(rp) + shl %cl, %eax + lea 8(rp), rp +L(lo1): mov 8(up), %edx + or %ebx, %eax + mov %edx, %ebx + shl %cl, %edx + lea 8(up), up + neg cnt + mov %eax, (rp) + decl VAR_COUNT + jg L(top) + + pop %eax FRAME_popl() +L(end): + shr %cl, %ebp + shr %cl, %ebx + or %ebp, %edx + mov SAVE_EBP, %ebp + mov %edx, 4(rp) + mov %ebx, 8(rp) + +L(quit): + mov SAVE_UP, up + mov SAVE_EBX, %ebx + pop rp FRAME_popl() + ret +EPILOGUE() +ASM_END() diff --git a/gmp/mpn/x86/atom/sse2/aorsmul_1.asm b/gmp/mpn/x86/atom/sse2/aorsmul_1.asm new file mode 100644 index 0000000000..969a14a919 --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/aorsmul_1.asm @@ -0,0 +1,174 @@ +dnl x86-32 mpn_addmul_1 and mpn_submul_1 optimised for Intel Atom. + +dnl Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C cycles/limb +C cycles/limb +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 8 +C AMD K6 +C AMD K7 - +C AMD K8 +C AMD K10 + +define(`rp', `%edi') +define(`up', `%esi') +define(`n', `%ecx') + +ifdef(`OPERATION_addmul_1',` + define(ADDSUB, add) + define(func_1, mpn_addmul_1) + define(func_1c, mpn_addmul_1c)') +ifdef(`OPERATION_submul_1',` + define(ADDSUB, sub) + define(func_1, mpn_submul_1) + define(func_1c, mpn_submul_1c)') + +MULFUNC_PROLOGUE(mpn_addmul_1 mpn_addmul_1c mpn_submul_1 mpn_submul_1c) + + TEXT + ALIGN(16) +PROLOGUE(func_1) + xor %edx, %edx +L(ent): push %edi + push %esi + push %ebx + mov 16(%esp), rp + mov 20(%esp), up + mov 24(%esp), n + movd 28(%esp), %mm7 + test $1, n + jz L(fi0or2) + movd (up), %mm0 + pmuludq %mm7, %mm0 + shr $2, n + jnc L(fi1) + +L(fi3): lea -8(up), up + lea -8(rp), rp + movd 12(up), %mm1 + movd %mm0, %ebx + pmuludq %mm7, %mm1 + add $1, n C increment and clear carry + jmp L(lo3) + +L(fi1): movd %mm0, %ebx + jz L(wd1) + movd 4(up), %mm1 + pmuludq %mm7, %mm1 + jmp L(lo1) + +L(fi0or2): + movd (up), %mm1 + pmuludq %mm7, %mm1 + shr $2, n + movd 4(up), %mm0 + jc L(fi2) + lea -4(up), up + lea -4(rp), rp + movd %mm1, %eax + pmuludq %mm7, %mm0 + jmp L(lo0) + +L(fi2): lea 4(up), up + add $1, n C increment and clear carry + movd %mm1, %eax + lea -12(rp), rp + jmp L(lo2) + +C ALIGN(16) C alignment seems irrelevant +L(top): movd 4(up), %mm1 + adc $0, %edx + ADDSUB %eax, 12(rp) + movd %mm0, %ebx + pmuludq %mm7, %mm1 + lea 16(rp), rp +L(lo1): psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + ADDSUB %ebx, (rp) +L(lo0): psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + movd %mm0, %ebx + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + ADDSUB %eax, 4(rp) +L(lo3): psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + ADDSUB %ebx, 8(rp) +L(lo2): psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + pmuludq %mm7, %mm0 + dec n + jnz L(top) + +L(end): adc n, %edx C n is zero here + ADDSUB %eax, 12(rp) + movd %mm0, %ebx + lea 16(rp), rp +L(wd1): psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %eax + adc n, %eax + ADDSUB %ebx, (rp) + emms + adc n, %eax + pop %ebx + pop %esi + pop %edi + ret +EPILOGUE() +PROLOGUE(func_1c) + mov 20(%esp), %edx C carry + jmp L(ent) +EPILOGUE() diff --git a/gmp/mpn/x86/atom/sse2/bdiv_dbm1c.asm b/gmp/mpn/x86/atom/sse2/bdiv_dbm1c.asm new file mode 100644 index 0000000000..782e914019 --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/bdiv_dbm1c.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_bdiv_dbm1. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_bdiv_dbm1c) +include_mpn(`x86/pentium4/sse2/bdiv_dbm1c.asm') diff --git a/gmp/mpn/x86/atom/sse2/divrem_1.asm b/gmp/mpn/x86/atom/sse2/divrem_1.asm new file mode 100644 index 0000000000..f84709a22e --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/divrem_1.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_divrem_1 -- mpn by limb division. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_preinv_divrem_1 mpn_divrem_1c mpn_divrem_1) +include_mpn(`x86/pentium4/sse2/divrem_1.asm') diff --git a/gmp/mpn/x86/atom/sse2/mod_1_1.asm b/gmp/mpn/x86/atom/sse2/mod_1_1.asm new file mode 100644 index 0000000000..ae6581d9b6 --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/mod_1_1.asm @@ -0,0 +1,34 @@ +dnl Intel Atom/SSE2 mpn_mod_1_1. + +dnl Copyright 2009, 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_mod_1_1p) +include_mpn(`x86/pentium4/sse2/mod_1_1.asm') diff --git a/gmp/mpn/x86/atom/sse2/mod_1_4.asm b/gmp/mpn/x86/atom/sse2/mod_1_4.asm new file mode 100644 index 0000000000..31faa3f0a3 --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/mod_1_4.asm @@ -0,0 +1,34 @@ +dnl Intel Atom/SSE2 mpn_mod_1_4. + +dnl Copyright 2009, 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_mod_1s_4p) +include_mpn(`x86/pentium4/sse2/mod_1_4.asm') diff --git a/gmp/mpn/x86/atom/sse2/mul_1.asm b/gmp/mpn/x86/atom/sse2/mul_1.asm new file mode 100644 index 0000000000..aa3bb974bb --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/mul_1.asm @@ -0,0 +1,124 @@ +dnl Intel Atom mpn_mul_1. + +dnl Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C cycles/limb +C cycles/limb +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 7.5 +C AMD K6 - +C AMD K7 - +C AMD K8 +C AMD K10 + +defframe(PARAM_CARRY,20) +defframe(PARAM_MUL, 16) +defframe(PARAM_SIZE, 12) +defframe(PARAM_SRC, 8) +defframe(PARAM_DST, 4) + +define(`rp', `%edx') +define(`up', `%esi') +define(`n', `%ecx') + +ASM_START() + TEXT + ALIGN(16) +deflit(`FRAME',0) + +PROLOGUE(mpn_mul_1c) + movd PARAM_CARRY, %mm6 C carry + jmp L(ent) +EPILOGUE() + + ALIGN(8) C for compact code +PROLOGUE(mpn_mul_1) + pxor %mm6, %mm6 +L(ent): push %esi FRAME_pushl() + mov PARAM_SRC, up + mov PARAM_SIZE, %eax C size + movd PARAM_MUL, %mm7 + movd (up), %mm0 + mov %eax, n + and $3, %eax + pmuludq %mm7, %mm0 + mov PARAM_DST, rp + jz L(lo0) + cmp $2, %eax + lea -16(up,%eax,4),up + lea -16(rp,%eax,4),rp + jc L(lo1) + jz L(lo2) + jmp L(lo3) + + ALIGN(16) +L(top): movd (up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp +L(lo0): paddq %mm0, %mm6 + movd 4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, (rp) + psrlq $32, %mm6 +L(lo3): paddq %mm0, %mm6 + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, 4(rp) + psrlq $32, %mm6 +L(lo2): paddq %mm0, %mm6 + movd 12(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, 8(rp) + psrlq $32, %mm6 +L(lo1): paddq %mm0, %mm6 + sub $4, n + movd %mm6, 12(rp) + lea 16(up), up + ja L(top) + + psrlq $32, %mm6 + movd %mm6, %eax + emms + pop %esi FRAME_popl() + ret +EPILOGUE() +ASM_END() diff --git a/gmp/mpn/x86/atom/sse2/mul_basecase.asm b/gmp/mpn/x86/atom/sse2/mul_basecase.asm new file mode 100644 index 0000000000..97d3aeb5ad --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/mul_basecase.asm @@ -0,0 +1,501 @@ +dnl x86 mpn_mul_basecase -- Multiply two limb vectors and store the result in +dnl a third limb vector. + +dnl Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C TODO +C * Check if 'jmp N(%esp)' is well-predicted enough to allow us to combine the +C 4 large loops into one; we could use it for the outer loop branch. +C * Optimise code outside of inner loops. +C * Write combined addmul_1 feed-in a wind-down code, and use when iterating +C outer each loop. ("Overlapping software pipelining") +C * Postpone push of ebx until we know vn > 1. Perhaps use caller-saves regs +C for inlined mul_1, allowing us to postpone all pushes. +C * Perhaps write special code for vn <= un < M, for some small M. + +C void mpn_mul_basecase (mp_ptr wp, +C mp_srcptr xp, mp_size_t xn, +C mp_srcptr yp, mp_size_t yn); +C + +define(`rp', `%edi') +define(`up', `%esi') +define(`un', `%ecx') +define(`vp', `%ebp') +define(`vn', `36(%esp)') + + TEXT + ALIGN(16) +PROLOGUE(mpn_mul_basecase) + push %edi + push %esi + push %ebx + push %ebp + mov 20(%esp), rp + mov 24(%esp), up + mov 28(%esp), un + mov 32(%esp), vp + + movd (up), %mm0 + movd (vp), %mm7 + pmuludq %mm7, %mm0 + pxor %mm6, %mm6 + + mov un, %eax + and $3, %eax + jz L(of0) + cmp $2, %eax + jc L(of1) + jz L(of2) + +C ================================================================ + jmp L(m3) + ALIGN(16) +L(lm3): movd -4(up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp + paddq %mm0, %mm6 + movd (up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -4(rp) + psrlq $32, %mm6 +L(m3): paddq %mm0, %mm6 + movd 4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, (rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, 4(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + sub $4, un + movd %mm6, 8(rp) + lea 16(up), up + ja L(lm3) + + psrlq $32, %mm6 + movd %mm6, 12(rp) + + decl vn + jz L(done) + lea -8(rp), rp + +L(ol3): mov 28(%esp), un + neg un + lea 4(vp), vp + movd (vp), %mm7 C read next V limb + mov 24(%esp), up + lea 16(rp,un,4), rp + + movd (up), %mm0 + pmuludq %mm7, %mm0 + sar $2, un + movd 4(up), %mm1 + movd %mm0, %ebx + pmuludq %mm7, %mm1 + lea -8(up), up + xor %edx, %edx C zero edx and CF + jmp L(a3) + +L(la3): movd 4(up), %mm1 + adc $0, %edx + add %eax, 12(rp) + movd %mm0, %ebx + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + add %ebx, (rp) + psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + movd %mm0, %ebx + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + add %eax, 4(rp) +L(a3): psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + add %ebx, 8(rp) + psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + pmuludq %mm7, %mm0 + inc un + jnz L(la3) + + adc un, %edx C un is zero here + add %eax, 12(rp) + movd %mm0, %ebx + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %eax + adc un, %eax + add %ebx, 16(rp) + adc un, %eax + mov %eax, 20(rp) + + decl vn + jnz L(ol3) + jmp L(done) + +C ================================================================ + ALIGN(16) +L(lm0): movd (up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp +L(of0): paddq %mm0, %mm6 + movd 4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, (rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, 4(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd 12(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, 8(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + sub $4, un + movd %mm6, 12(rp) + lea 16(up), up + ja L(lm0) + + psrlq $32, %mm6 + movd %mm6, 16(rp) + + decl vn + jz L(done) + lea -4(rp), rp + +L(ol0): mov 28(%esp), un + neg un + lea 4(vp), vp + movd (vp), %mm7 C read next V limb + mov 24(%esp), up + lea 20(rp,un,4), rp + + movd (up), %mm1 + pmuludq %mm7, %mm1 + sar $2, un + movd 4(up), %mm0 + lea -4(up), up + movd %mm1, %eax + pmuludq %mm7, %mm0 + xor %edx, %edx C zero edx and CF + jmp L(a0) + +L(la0): movd 4(up), %mm1 + adc $0, %edx + add %eax, 12(rp) + movd %mm0, %ebx + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + add %ebx, (rp) +L(a0): psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + movd %mm0, %ebx + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + add %eax, 4(rp) + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + add %ebx, 8(rp) + psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + pmuludq %mm7, %mm0 + inc un + jnz L(la0) + + adc un, %edx C un is zero here + add %eax, 12(rp) + movd %mm0, %ebx + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %eax + adc un, %eax + add %ebx, 16(rp) + adc un, %eax + mov %eax, 20(rp) + + decl vn + jnz L(ol0) + jmp L(done) + +C ================================================================ + ALIGN(16) +L(lm1): movd -12(up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp + paddq %mm0, %mm6 + movd -8(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -12(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd -4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -8(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd (up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -4(rp) + psrlq $32, %mm6 +L(of1): paddq %mm0, %mm6 + sub $4, un + movd %mm6, (rp) + lea 16(up), up + ja L(lm1) + + psrlq $32, %mm6 + movd %mm6, 4(rp) + + decl vn + jz L(done) + lea -16(rp), rp + +L(ol1): mov 28(%esp), un + neg un + lea 4(vp), vp + movd (vp), %mm7 C read next V limb + mov 24(%esp), up + lea 24(rp,un,4), rp + + movd (up), %mm0 + pmuludq %mm7, %mm0 + sar $2, un + movd %mm0, %ebx + movd 4(up), %mm1 + pmuludq %mm7, %mm1 + xor %edx, %edx C zero edx and CF + inc un + jmp L(a1) + +L(la1): movd 4(up), %mm1 + adc $0, %edx + add %eax, 12(rp) + movd %mm0, %ebx + pmuludq %mm7, %mm1 + lea 16(rp), rp +L(a1): psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + add %ebx, (rp) + psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + movd %mm0, %ebx + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + add %eax, 4(rp) + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + add %ebx, 8(rp) + psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + pmuludq %mm7, %mm0 + inc un + jnz L(la1) + + adc un, %edx C un is zero here + add %eax, 12(rp) + movd %mm0, %ebx + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %eax + adc un, %eax + add %ebx, 16(rp) + adc un, %eax + mov %eax, 20(rp) + + decl vn + jnz L(ol1) + jmp L(done) + +C ================================================================ + ALIGN(16) +L(lm2): movd -8(up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp + paddq %mm0, %mm6 + movd -4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -8(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd (up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -4(rp) + psrlq $32, %mm6 +L(of2): paddq %mm0, %mm6 + movd 4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, (rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + sub $4, un + movd %mm6, 4(rp) + lea 16(up), up + ja L(lm2) + + psrlq $32, %mm6 + movd %mm6, 8(rp) + + decl vn + jz L(done) + lea -12(rp), rp + +L(ol2): mov 28(%esp), un + neg un + lea 4(vp), vp + movd (vp), %mm7 C read next V limb + mov 24(%esp), up + lea 12(rp,un,4), rp + + movd (up), %mm1 + pmuludq %mm7, %mm1 + sar $2, un + movd 4(up), %mm0 + lea 4(up), up + movd %mm1, %eax + xor %edx, %edx C zero edx and CF + jmp L(lo2) + +L(la2): movd 4(up), %mm1 + adc $0, %edx + add %eax, 12(rp) + movd %mm0, %ebx + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + add %ebx, (rp) + psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + movd %mm0, %ebx + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + add %eax, 4(rp) + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %edx + movd %mm1, %eax + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + add %ebx, 8(rp) +L(lo2): psrlq $32, %mm1 + adc %edx, %eax + movd %mm1, %edx + pmuludq %mm7, %mm0 + inc un + jnz L(la2) + + adc un, %edx C un is zero here + add %eax, 12(rp) + movd %mm0, %ebx + psrlq $32, %mm0 + adc %edx, %ebx + movd %mm0, %eax + adc un, %eax + add %ebx, 16(rp) + adc un, %eax + mov %eax, 20(rp) + + decl vn + jnz L(ol2) +C jmp L(done) + +C ================================================================ +L(done): + emms + pop %ebp + pop %ebx + pop %esi + pop %edi + ret +EPILOGUE() diff --git a/gmp/mpn/x86/atom/sse2/popcount.asm b/gmp/mpn/x86/atom/sse2/popcount.asm new file mode 100644 index 0000000000..7847aec8e6 --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/popcount.asm @@ -0,0 +1,35 @@ +dnl Intel Atom mpn_popcount -- population count. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + + +MULFUNC_PROLOGUE(mpn_popcount) +include_mpn(`x86/pentium4/sse2/popcount.asm') diff --git a/gmp/mpn/x86/atom/sse2/sqr_basecase.asm b/gmp/mpn/x86/atom/sse2/sqr_basecase.asm new file mode 100644 index 0000000000..af19ed854d --- /dev/null +++ b/gmp/mpn/x86/atom/sse2/sqr_basecase.asm @@ -0,0 +1,634 @@ +dnl x86 mpn_sqr_basecase -- square an mpn number, optimised for atom. + +dnl Contributed to the GNU project by Torbjorn Granlund and Marco Bodrato. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +C TODO +C * Check if 'jmp N(%esp)' is well-predicted enough to allow us to combine the +C 4 large loops into one; we could use it for the outer loop branch. +C * Optimise code outside of inner loops. +C * Write combined addmul_1 feed-in a wind-down code, and use when iterating +C outer each loop. ("Overlapping software pipelining") +C * Perhaps use caller-saves regs for inlined mul_1, allowing us to postpone +C all pushes. +C * Perhaps write special code for n < M, for some small M. +C * Replace inlined addmul_1 with smaller code from aorsmul_1.asm, or perhaps +C with even less pipelined code. +C * We run the outer loop until we have a 2-limb by 1-limb addmul_1 left. +C Consider breaking out earlier, saving high the cost of short loops. + +C void mpn_sqr_basecase (mp_ptr wp, +C mp_srcptr xp, mp_size_t xn); + +define(`rp', `%edi') +define(`up', `%esi') +define(`n', `%ecx') + +define(`un', `%ebp') + + TEXT + ALIGN(16) +PROLOGUE(mpn_sqr_basecase) + push %edi + push %esi + mov 12(%esp), rp + mov 16(%esp), up + mov 20(%esp), n + + lea 4(rp), rp C write triangular product starting at rp[1] + dec n + movd (up), %mm7 + + jz L(one) + lea 4(up), up + push %ebx + push %ebp + mov n, %eax + + movd (up), %mm0 + neg n + pmuludq %mm7, %mm0 + pxor %mm6, %mm6 + mov n, un + + and $3, %eax + jz L(of0) + cmp $2, %eax + jc L(of1) + jz L(of2) + +C ================================================================ + jmp L(m3) + ALIGN(16) +L(lm3): movd -4(up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp + paddq %mm0, %mm6 + movd (up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -4(rp) + psrlq $32, %mm6 +L(m3): paddq %mm0, %mm6 + movd 4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, (rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, 4(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + add $4, un + movd %mm6, 8(rp) + lea 16(up), up + js L(lm3) + + psrlq $32, %mm6 + movd %mm6, 12(rp) + + inc n +C jz L(done) + lea -12(up), up + lea 4(rp), rp + jmp L(ol2) + +C ================================================================ + ALIGN(16) +L(lm0): movd (up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp +L(of0): paddq %mm0, %mm6 + movd 4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, (rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, 4(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd 12(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, 8(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + add $4, un + movd %mm6, 12(rp) + lea 16(up), up + js L(lm0) + + psrlq $32, %mm6 + movd %mm6, 16(rp) + + inc n +C jz L(done) + lea -8(up), up + lea 8(rp), rp + jmp L(ol3) + +C ================================================================ + ALIGN(16) +L(lm1): movd -12(up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp + paddq %mm0, %mm6 + movd -8(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -12(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd -4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -8(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd (up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -4(rp) + psrlq $32, %mm6 +L(of1): paddq %mm0, %mm6 + add $4, un + movd %mm6, (rp) + lea 16(up), up + js L(lm1) + + psrlq $32, %mm6 + movd %mm6, 4(rp) + + inc n + jz L(done) C goes away when we add special n=2 code + lea -20(up), up + lea -4(rp), rp + jmp L(ol0) + +C ================================================================ + ALIGN(16) +L(lm2): movd -8(up), %mm0 + pmuludq %mm7, %mm0 + psrlq $32, %mm6 + lea 16(rp), rp + paddq %mm0, %mm6 + movd -4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -8(rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + movd (up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, -4(rp) + psrlq $32, %mm6 +L(of2): paddq %mm0, %mm6 + movd 4(up), %mm0 + pmuludq %mm7, %mm0 + movd %mm6, (rp) + psrlq $32, %mm6 + paddq %mm0, %mm6 + add $4, un + movd %mm6, 4(rp) + lea 16(up), up + js L(lm2) + + psrlq $32, %mm6 + movd %mm6, 8(rp) + + inc n +C jz L(done) + lea -16(up), up +C lea (rp), rp +C jmp L(ol1) + +C ================================================================ + +L(ol1): lea 4(up,n,4), up + movd (up), %mm7 C read next U invariant limb + lea 8(rp,n,4), rp + mov n, un + + movd 4(up), %mm1 + pmuludq %mm7, %mm1 + sar $2, un + movd %mm1, %ebx + inc un + jz L(re1) + + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + xor %edx, %edx C zero edx and CF + jmp L(a1) + +L(la1): adc $0, %edx + add %ebx, 12(rp) + movd %mm0, %eax + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + add %eax, (rp) +L(a1): psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %edx + movd %mm0, %eax + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + add %ebx, 4(rp) + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + add %eax, 8(rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %edx + pmuludq %mm7, %mm0 + inc un + movd 4(up), %mm1 + jnz L(la1) + + adc un, %edx C un is zero here + add %ebx, 12(rp) + movd %mm0, %eax + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + adc un, %edx + add %eax, (rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %eax + adc un, %eax + add %ebx, 4(rp) + adc un, %eax + mov %eax, 8(rp) + + inc n + +C ================================================================ + +L(ol0): lea (up,n,4), up + movd 4(up), %mm7 C read next U invariant limb + lea 4(rp,n,4), rp + mov n, un + + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + sar $2, un + movd 12(up), %mm1 + movd %mm0, %eax + pmuludq %mm7, %mm1 + xor %edx, %edx C zero edx and CF + jmp L(a0) + +L(la0): adc $0, %edx + add %ebx, 12(rp) + movd %mm0, %eax + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + add %eax, (rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %edx + movd %mm0, %eax + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + add %ebx, 4(rp) +L(a0): psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + add %eax, 8(rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %edx + pmuludq %mm7, %mm0 + inc un + movd 4(up), %mm1 + jnz L(la0) + + adc un, %edx C un is zero here + add %ebx, 12(rp) + movd %mm0, %eax + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + adc un, %edx + add %eax, (rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %eax + adc un, %eax + add %ebx, 4(rp) + adc un, %eax + mov %eax, 8(rp) + + inc n + +C ================================================================ + +L(ol3): lea 12(up,n,4), up + movd -8(up), %mm7 C read next U invariant limb + lea (rp,n,4), rp C put rp back + mov n, un + + movd -4(up), %mm1 + pmuludq %mm7, %mm1 + sar $2, un + movd %mm1, %ebx + movd (up), %mm0 + xor %edx, %edx C zero edx and CF + jmp L(a3) + +L(la3): adc $0, %edx + add %ebx, 12(rp) + movd %mm0, %eax + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + add %eax, (rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %edx + movd %mm0, %eax + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + add %ebx, 4(rp) + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + add %eax, 8(rp) +L(a3): psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %edx + pmuludq %mm7, %mm0 + inc un + movd 4(up), %mm1 + jnz L(la3) + + adc un, %edx C un is zero here + add %ebx, 12(rp) + movd %mm0, %eax + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + adc un, %edx + add %eax, (rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %eax + adc un, %eax + add %ebx, 4(rp) + adc un, %eax + mov %eax, 8(rp) + + inc n + +C ================================================================ + +L(ol2): lea 8(up,n,4), up + movd -4(up), %mm7 C read next U invariant limb + lea 12(rp,n,4), rp + mov n, un + + movd (up), %mm0 + pmuludq %mm7, %mm0 + xor %edx, %edx + sar $2, un + movd 4(up), %mm1 + test un, un C clear carry + movd %mm0, %eax + pmuludq %mm7, %mm1 + inc un + jnz L(a2) + jmp L(re2) + +L(la2): adc $0, %edx + add %ebx, 12(rp) + movd %mm0, %eax + pmuludq %mm7, %mm1 + lea 16(rp), rp +L(a2): psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + movd 8(up), %mm0 + pmuludq %mm7, %mm0 + adc $0, %edx + add %eax, (rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %edx + movd %mm0, %eax + movd 12(up), %mm1 + pmuludq %mm7, %mm1 + adc $0, %edx + add %ebx, 4(rp) + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + lea 16(up), up + movd (up), %mm0 + adc $0, %edx + add %eax, 8(rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %edx + pmuludq %mm7, %mm0 + inc un + movd 4(up), %mm1 + jnz L(la2) + + adc un, %edx C un is zero here + add %ebx, 12(rp) + movd %mm0, %eax + pmuludq %mm7, %mm1 + lea 16(rp), rp + psrlq $32, %mm0 + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + adc un, %edx + add %eax, (rp) + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %eax + adc un, %eax + add %ebx, 4(rp) + adc un, %eax + mov %eax, 8(rp) + + inc n + jmp L(ol1) + +C ================================================================ +L(re2): psrlq $32, %mm0 + movd (up), %mm7 C read next U invariant limb + adc %edx, %eax + movd %mm0, %edx + movd %mm1, %ebx + adc un, %edx + add %eax, (rp) + lea 4(rp), rp + psrlq $32, %mm1 + adc %edx, %ebx + movd %mm1, %eax + movd 4(up), %mm1 + adc un, %eax + add %ebx, (rp) + pmuludq %mm7, %mm1 + adc un, %eax + mov %eax, 4(rp) + movd %mm1, %ebx + +L(re1): psrlq $32, %mm1 + add %ebx, 4(rp) + movd %mm1, %eax + adc un, %eax + xor n, n C make n zeroness assumption below true + mov %eax, 8(rp) + +L(done): C n is zero here + mov 24(%esp), up + mov 28(%esp), %eax + + movd (up), %mm0 + inc %eax + pmuludq %mm0, %mm0 + lea 4(up), up + mov 20(%esp), rp + shr %eax + movd %mm0, (rp) + psrlq $32, %mm0 + lea -12(rp), rp + mov %eax, 28(%esp) + jnc L(odd) + + movd %mm0, %ebp + movd (up), %mm0 + lea 8(rp), rp + pmuludq %mm0, %mm0 + lea -4(up), up + add 8(rp), %ebp + movd %mm0, %edx + adc 12(rp), %edx + rcr n + jmp L(ent) + +C ALIGN(16) C alignment seems irrelevant +L(top): movd (up), %mm1 + adc n, n + movd %mm0, %eax + pmuludq %mm1, %mm1 + movd 4(up), %mm0 + adc (rp), %eax + movd %mm1, %ebx + pmuludq %mm0, %mm0 + psrlq $32, %mm1 + adc 4(rp), %ebx + movd %mm1, %ebp + movd %mm0, %edx + adc 8(rp), %ebp + adc 12(rp), %edx + rcr n C FIXME: isn't this awfully slow on atom??? + adc %eax, (rp) + adc %ebx, 4(rp) +L(ent): lea 8(up), up + adc %ebp, 8(rp) + psrlq $32, %mm0 + adc %edx, 12(rp) +L(odd): decl 28(%esp) + lea 16(rp), rp + jnz L(top) + +L(end): adc n, n + movd %mm0, %eax + adc n, %eax + mov %eax, (rp) + +L(rtn): emms + pop %ebp + pop %ebx + pop %esi + pop %edi + ret + +L(one): pmuludq %mm7, %mm7 + movq %mm7, -4(rp) + emms + pop %esi + pop %edi + ret +EPILOGUE() diff --git a/gmp/mpn/x86/atom/sublsh1_n.asm b/gmp/mpn/x86/atom/sublsh1_n.asm new file mode 100644 index 0000000000..d3e7e5b5cb --- /dev/null +++ b/gmp/mpn/x86/atom/sublsh1_n.asm @@ -0,0 +1,34 @@ +dnl Intel Atom mpn_sublsh1_n -- rp[] = up[] - (vp[] << 1) + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +MULFUNC_PROLOGUE(mpn_sublsh1_n_ip1) +include_mpn(`x86/k7/sublsh1_n.asm') diff --git a/gmp/mpn/x86/atom/sublsh2_n.asm b/gmp/mpn/x86/atom/sublsh2_n.asm new file mode 100644 index 0000000000..79405cf9f4 --- /dev/null +++ b/gmp/mpn/x86/atom/sublsh2_n.asm @@ -0,0 +1,57 @@ +dnl Intel Atom mpn_addlsh2_n/mpn_sublsh2_n -- rp[] = up[] +- (vp[] << 2). + +dnl Contributed to the GNU project by Marco Bodrato. + +dnl Copyright 2011 Free Software Foundation, Inc. + +dnl This file is part of the GNU MP Library. +dnl +dnl The GNU MP Library is free software; you can redistribute it and/or modify +dnl it under the terms of either: +dnl +dnl * the GNU Lesser General Public License as published by the Free +dnl Software Foundation; either version 3 of the License, or (at your +dnl option) any later version. +dnl +dnl or +dnl +dnl * the GNU General Public License as published by the Free Software +dnl Foundation; either version 2 of the License, or (at your option) any +dnl later version. +dnl +dnl or both in parallel, as here. +dnl +dnl The GNU MP Library is distributed in the hope that it will be useful, but +dnl WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY +dnl or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License +dnl for more details. +dnl +dnl You should have received copies of the GNU General Public License and the +dnl GNU Lesser General Public License along with the GNU MP Library. If not, +dnl see https://www.gnu.org/licenses/. + +include(`../config.m4') + +define(LSH, 2) +define(RSH, 30) + +ifdef(`OPERATION_addlsh2_n', ` + define(M4_inst, adcl) + define(M4_opp, subl) + define(M4_function, mpn_addlsh2_n) + define(M4_function_c, mpn_addlsh2_nc) + define(M4_ip_function_c, mpn_addlsh2_nc_ip1) + define(M4_ip_function, mpn_addlsh2_n_ip1) +',`ifdef(`OPERATION_sublsh2_n', ` + define(M4_inst, sbbl) + define(M4_opp, addl) + define(M4_function, mpn_sublsh2_n) + define(M4_function_c, mpn_sublsh2_nc) + define(M4_ip_function_c, mpn_sublsh2_nc_ip1) + define(M4_ip_function, mpn_sublsh2_n_ip1) +',`m4_error(`Need OPERATION_addlsh2_n or OPERATION_sublsh2_n +')')') + +MULFUNC_PROLOGUE(mpn_sublsh2_n mpn_sublsh2_nc mpn_sublsh2_n_ip1 mpn_sublsh2_nc_ip1) + +include_mpn(`x86/atom/aorslshC_n.asm') |