From fe62ba37a30b83be7e2a63b667fd519ca7e1b28d Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 26 Feb 2013 15:49:51 -0800 Subject: arm: Add optimized submul_1 Written from scratch rather than copied from GMP, due to LGPL 2.1 vs GPL 3, but tested with the GMP testsuite. This is 50% faster than the generic code as measured on Cortex-A15. It is 25% slower than the current GMP routine on the same core. --- ports/ChangeLog.arm | 1 + ports/sysdeps/arm/submul_1.S | 68 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) create mode 100644 ports/sysdeps/arm/submul_1.S (limited to 'ports') diff --git a/ports/ChangeLog.arm b/ports/ChangeLog.arm index a701215024..9470af2414 100644 --- a/ports/ChangeLog.arm +++ b/ports/ChangeLog.arm @@ -1,5 +1,6 @@ 2013-03-06 Richard Henderson + * sysdeps/arm/submul_1.S: New file. * sysdeps/arm/addmul_1.S: New file. * sysdeps/arm/armv6t2/ffs.S: New file. * sysdeps/arm/armv6t2/ffsll.S: New file. diff --git a/ports/sysdeps/arm/submul_1.S b/ports/sysdeps/arm/submul_1.S new file mode 100644 index 0000000000..3805eca9be --- /dev/null +++ b/ports/sysdeps/arm/submul_1.S @@ -0,0 +1,68 @@ +/* mpn_submul_1 -- multiply and subtract bignums. + Copyright (C) 2013 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C 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 + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library. If not, see + . */ + +#include + + .syntax unified + .text + +@ cycles/limb +@ StrongArm ? +@ Cortex-A8 ? +@ Cortex-A9 ? +@ Cortex-A15 4 + +/* mp_limb_t mpn_submul_1(res_ptr, src1_ptr, size, s2_limb) */ + +ENTRY (__mpn_submul_1) + push { r4, r5, r6, r7 } + cfi_adjust_cfa_offset (16) + cfi_rel_offset (r4, 0) + cfi_rel_offset (r5, 4) + cfi_rel_offset (r6, 8) + cfi_rel_offset (r7, 12) + + ldr r6, [r1], #4 + ldr r7, [r0] + mov r4, #0 /* init carry in */ + b 1f +0: + ldr r6, [r1], #4 /* load next ul */ + adds r5, r5, r4 /* (lpl, c) = lpl + cl */ + adc r4, ip, #0 /* cl = hpl + c */ + subs r5, r7, r5 /* (lpl, !c) = rl - lpl */ + ldr r7, [r0, #4] /* load next rl */ + it cc + addcc r4, r4, #1 /* cl += !c */ + str r5, [r0], #4 +1: + umull r5, ip, r6, r3 /* (hpl, lpl) = ul * vl */ + subs r2, r2, #1 + bne 0b + + adds r5, r5, r4 /* (lpl, c) = lpl + cl */ + adc r4, ip, #0 /* cl = hpl + c */ + subs r5, r7, r5 /* (lpl, !c) = rl - lpl */ + str r5, [r0], #4 + it cc + addcc r4, r4, #1 /* cl += !c */ + mov r0, r4 /* return carry */ + + pop { r4, r5, r6, r7 } + DO_RET (lr) +END (__mpn_submul_1) -- cgit 1.4.1