1 ;; SPDX-License-Identifier: GPL-2.0-or-later 2 ;; Copyright 2011 Free Software Foundation, Inc. 3 ;; Contributed by Bernd Schmidt <bernds@codesourcery.com>. 4 ;; 5 6 #include <linux/linkage.h> 7 8 .text 9 ENTRY(__c6xabi_divremu) 10 ;; We use a series of up to 31 subc instructions. First, we find 11 ;; out how many leading zero bits there are in the divisor. This 12 ;; gives us both a shift count for aligning (shifting) the divisor 13 ;; to the, and the number of times we have to execute subc. 14 15 ;; At the end, we have both the remainder and most of the quotient 16 ;; in A4. The top bit of the quotient is computed first and is 17 ;; placed in A2. 18 19 ;; Return immediately if the dividend is zero. Setting B4 to 1 20 ;; is a trick to allow us to leave the following insns in the jump 21 ;; delay slot without affecting the result. 22 mv .s2x A4, B1 23 24 [b1] lmbd .l2 1, B4, B1 25 ||[!b1] b .s2 B3 ; RETURN A 26 ||[!b1] mvk .d2 1, B4 27 28 ||[!b1] zero .s1 A5 29 mv .l1x B1, A6 30 || shl .s2 B4, B1, B4 31 32 ;; The loop performs a maximum of 28 steps, so we do the 33 ;; first 3 here. 34 cmpltu .l1x A4, B4, A2 35 [!A2] sub .l1x A4, B4, A4 36 || shru .s2 B4, 1, B4 37 || xor .s1 1, A2, A2 38 39 shl .s1 A2, 31, A2 40 || [b1] subc .l1x A4,B4,A4 41 || [b1] add .s2 -1, B1, B1 42 [b1] subc .l1x A4,B4,A4 43 || [b1] add .s2 -1, B1, B1 44 45 ;; RETURN A may happen here (note: must happen before the next branch) 46 __divremu0: 47 cmpgt .l2 B1, 7, B0 48 || [b1] subc .l1x A4,B4,A4 49 || [b1] add .s2 -1, B1, B1 50 [b1] subc .l1x A4,B4,A4 51 || [b1] add .s2 -1, B1, B1 52 || [b0] b .s1 __divremu0 53 [b1] subc .l1x A4,B4,A4 54 || [b1] add .s2 -1, B1, B1 55 [b1] subc .l1x A4,B4,A4 56 || [b1] add .s2 -1, B1, B1 57 [b1] subc .l1x A4,B4,A4 58 || [b1] add .s2 -1, B1, B1 59 [b1] subc .l1x A4,B4,A4 60 || [b1] add .s2 -1, B1, B1 61 [b1] subc .l1x A4,B4,A4 62 || [b1] add .s2 -1, B1, B1 63 ;; loop backwards branch happens here 64 65 ret .s2 B3 66 || mvk .s1 32, A1 67 sub .l1 A1, A6, A6 68 || extu .s1 A4, A6, A5 69 shl .s1 A4, A6, A4 70 shru .s1 A4, 1, A4 71 || sub .l1 A6, 1, A6 72 or .l1 A2, A4, A4 73 shru .s1 A4, A6, A4 74 nop 75 ENDPROC(__c6xabi_divremu) 76