diff options
Diffstat (limited to 'libgcc/config/arm/lib1funcs.S')
| -rw-r--r-- | libgcc/config/arm/lib1funcs.S | 365 |
1 files changed, 192 insertions, 173 deletions
diff --git a/libgcc/config/arm/lib1funcs.S b/libgcc/config/arm/lib1funcs.S index e4b73ca..e8d2158 100644 --- a/libgcc/config/arm/lib1funcs.S +++ b/libgcc/config/arm/lib1funcs.S @@ -22,6 +22,10 @@ a copy of the GCC Runtime Library Exception along with this program; see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ +/* Everything in this file should now use unified syntax. */ + + .syntax unified + /* An executable stack is *not* required for these functions. */ #if defined(__ELF__) && defined(__linux__) .section .note.GNU-stack,"",%progbits @@ -270,7 +274,7 @@ LSYM(Lend_fde): #ifdef NOT_ISA_TARGET_32BIT push {r0, lr} - mov r0, #0 + movs r0, #0 bl SYM(__aeabi_idiv0) @ We know we are not on armv4t, so pop pc is safe. pop {r1, pc} @@ -310,7 +314,7 @@ LSYM(Lend_fde): push { r1, lr } 98: cfi_push 98b - __\name, 0xe, -0x4, 0x8 bl SYM (__div0) - mov r0, #0 @ About as wrong as it could be. + movs r0, #0 @ About as wrong as it could be. #if defined (__INTERWORKING__) pop { r1, r2 } bx r2 @@ -349,7 +353,7 @@ SYM (\name): #define THUMB_FUNC .thumb_func #define THUMB_CODE .force_thumb # if defined(__thumb2__) -#define THUMB_SYNTAX .syntax divided +#define THUMB_SYNTAX # else #define THUMB_SYNTAX # endif @@ -725,8 +729,8 @@ pc .req r15 /* ------------------------------------------------------------------------ */ .macro THUMB_DIV_MOD_BODY modulo @ Load the constant 0x10000000 into our work register. - mov work, #1 - lsl work, #28 + movs work, #1 + lsls work, #28 LSYM(Loop1): @ Unless the divisor is very big, shift it up in multiples of @ four bits, since this is the amount of unwinding in the main @@ -736,12 +740,12 @@ LSYM(Loop1): bhs LSYM(Lbignum) cmp divisor, dividend bhs LSYM(Lbignum) - lsl divisor, #4 - lsl curbit, #4 + lsls divisor, #4 + lsls curbit, #4 b LSYM(Loop1) LSYM(Lbignum): @ Set work to 0x80000000 - lsl work, #3 + lsls work, #3 LSYM(Loop2): @ For very big divisors, we must shift it a bit at a time, or @ we will be in danger of overflowing. @@ -749,8 +753,8 @@ LSYM(Loop2): bhs LSYM(Loop3) cmp divisor, dividend bhs LSYM(Loop3) - lsl divisor, #1 - lsl curbit, #1 + lsls divisor, #1 + lsls curbit, #1 b LSYM(Loop2) LSYM(Loop3): @ Test for possible subtractions ... @@ -758,39 +762,39 @@ LSYM(Loop3): @ ... On the final pass, this may subtract too much from the dividend, @ so keep track of which subtractions are done, we can fix them up @ afterwards. - mov overdone, #0 + movs overdone, #0 cmp dividend, divisor blo LSYM(Lover1) - sub dividend, dividend, divisor + subs dividend, dividend, divisor LSYM(Lover1): - lsr work, divisor, #1 + lsrs work, divisor, #1 cmp dividend, work blo LSYM(Lover2) - sub dividend, dividend, work + subs dividend, dividend, work mov ip, curbit - mov work, #1 - ror curbit, work - orr overdone, curbit + movs work, #1 + rors curbit, work + orrs overdone, curbit mov curbit, ip LSYM(Lover2): - lsr work, divisor, #2 + lsrs work, divisor, #2 cmp dividend, work blo LSYM(Lover3) - sub dividend, dividend, work + subs dividend, dividend, work mov ip, curbit - mov work, #2 - ror curbit, work - orr overdone, curbit + movs work, #2 + rors curbit, work + orrs overdone, curbit mov curbit, ip LSYM(Lover3): - lsr work, divisor, #3 + lsrs work, divisor, #3 cmp dividend, work blo LSYM(Lover4) - sub dividend, dividend, work + subs dividend, dividend, work mov ip, curbit - mov work, #3 - ror curbit, work - orr overdone, curbit + movs work, #3 + rors curbit, work + orrs overdone, curbit mov curbit, ip LSYM(Lover4): mov ip, curbit @@ -800,46 +804,46 @@ LSYM(Lover4): @ since the "bit" will have been shifted out at the bottom. cmp dividend, divisor blo LSYM(Lover1) - sub dividend, dividend, divisor - orr result, result, curbit + subs dividend, dividend, divisor + orrs result, result, curbit LSYM(Lover1): - lsr work, divisor, #1 + lsrs work, divisor, #1 cmp dividend, work blo LSYM(Lover2) - sub dividend, dividend, work - lsr work, curbit, #1 - orr result, work + subs dividend, dividend, work + lsrs work, curbit, #1 + orrs result, work LSYM(Lover2): - lsr work, divisor, #2 + lsrs work, divisor, #2 cmp dividend, work blo LSYM(Lover3) - sub dividend, dividend, work - lsr work, curbit, #2 - orr result, work + subs dividend, dividend, work + lsrs work, curbit, #2 + orrs result, work LSYM(Lover3): - lsr work, divisor, #3 + lsrs work, divisor, #3 cmp dividend, work blo LSYM(Lover4) - sub dividend, dividend, work - lsr work, curbit, #3 - orr result, work + subs dividend, dividend, work + lsrs work, curbit, #3 + orrs result, work LSYM(Lover4): .endif cmp dividend, #0 @ Early termination? beq LSYM(Lover5) - lsr curbit, #4 @ No, any more bits to do? + lsrs curbit, #4 @ No, any more bits to do? beq LSYM(Lover5) - lsr divisor, #4 + lsrs divisor, #4 b LSYM(Loop3) LSYM(Lover5): .if \modulo @ Any subtractions that we should not have done will be recorded in @ the top three bits of "overdone". Exactly which were not needed @ are governed by the position of the bit, stored in ip. - mov work, #0xe - lsl work, #28 - and overdone, work + movs work, #0xe + lsls work, #28 + ands overdone, work beq LSYM(Lgot_result) @ If we terminated early, because dividend became zero, then the @@ -849,33 +853,33 @@ LSYM(Lover5): @ the bit in ip could be in the top two bits which might then match @ with one of the smaller RORs. mov curbit, ip - mov work, #0x7 + movs work, #0x7 tst curbit, work beq LSYM(Lgot_result) mov curbit, ip - mov work, #3 - ror curbit, work + movs work, #3 + rors curbit, work tst overdone, curbit beq LSYM(Lover6) - lsr work, divisor, #3 - add dividend, work + lsrs work, divisor, #3 + adds dividend, work LSYM(Lover6): mov curbit, ip - mov work, #2 - ror curbit, work + movs work, #2 + rors curbit, work tst overdone, curbit beq LSYM(Lover7) - lsr work, divisor, #2 - add dividend, work + lsrs work, divisor, #2 + adds dividend, work LSYM(Lover7): mov curbit, ip - mov work, #1 - ror curbit, work + movs work, #1 + rors curbit, work tst overdone, curbit beq LSYM(Lgot_result) - lsr work, divisor, #1 - add dividend, work + lsrs work, divisor, #1 + adds dividend, work .endif LSYM(Lgot_result): .endm @@ -885,7 +889,7 @@ LSYM(Lgot_result): /* Branch to div(n), and jump to label if curbit is lo than divisior. */ .macro BranchToDiv n, label - lsr curbit, dividend, \n + lsrs curbit, dividend, \n cmp curbit, divisor blo \label .endm @@ -893,13 +897,13 @@ LSYM(Lgot_result): /* Body of div(n). Shift the divisor in n bits and compare the divisor and dividend. Update the dividend as the substruction result. */ .macro DoDiv n - lsr curbit, dividend, \n + lsrs curbit, dividend, \n cmp curbit, divisor bcc 1f - lsl curbit, divisor, \n - sub dividend, dividend, curbit + lsls curbit, divisor, \n + subs dividend, dividend, curbit -1: adc result, result +1: adcs result, result .endm /* The body of division with positive divisor. Unless the divisor is very @@ -907,29 +911,29 @@ LSYM(Lgot_result): unwinding in the main division loop. Continue shifting until the divisor is larger than the dividend. */ .macro THUMB1_Div_Positive - mov result, #0 + movs result, #0 BranchToDiv #1, LSYM(Lthumb1_div1) BranchToDiv #4, LSYM(Lthumb1_div4) BranchToDiv #8, LSYM(Lthumb1_div8) BranchToDiv #12, LSYM(Lthumb1_div12) BranchToDiv #16, LSYM(Lthumb1_div16) LSYM(Lthumb1_div_large_positive): - mov result, #0xff - lsl divisor, divisor, #8 + movs result, #0xff + lsls divisor, divisor, #8 rev result, result - lsr curbit, dividend, #16 + lsrs curbit, dividend, #16 cmp curbit, divisor blo 1f - asr result, #8 - lsl divisor, divisor, #8 + asrs result, #8 + lsls divisor, divisor, #8 beq LSYM(Ldivbyzero_waypoint) -1: lsr curbit, dividend, #12 +1: lsrs curbit, dividend, #12 cmp curbit, divisor blo LSYM(Lthumb1_div12) b LSYM(Lthumb1_div16) LSYM(Lthumb1_div_loop): - lsr divisor, divisor, #8 + lsrs divisor, divisor, #8 LSYM(Lthumb1_div16): Dodiv #15 Dodiv #14 @@ -954,11 +958,11 @@ LSYM(Lthumb1_div3): LSYM(Lthumb1_div2): Dodiv #1 LSYM(Lthumb1_div1): - sub divisor, dividend, divisor + subs divisor, dividend, divisor bcs 1f cpy divisor, dividend -1: adc result, result +1: adcs result, result cpy dividend, result RET @@ -970,43 +974,43 @@ LSYM(Ldivbyzero_waypoint): THUMB1_Div_Positive except that the shift steps are in multiples of six bits. */ .macro THUMB1_Div_Negative - lsr result, divisor, #31 + lsrs result, divisor, #31 beq 1f - neg divisor, divisor + negs divisor, divisor -1: asr curbit, dividend, #32 +1: asrs curbit, dividend, #32 bcc 2f - neg dividend, dividend + negs dividend, dividend -2: eor curbit, result - mov result, #0 +2: eors curbit, result + movs result, #0 cpy ip, curbit BranchToDiv #4, LSYM(Lthumb1_div_negative4) BranchToDiv #8, LSYM(Lthumb1_div_negative8) LSYM(Lthumb1_div_large): - mov result, #0xfc - lsl divisor, divisor, #6 + movs result, #0xfc + lsls divisor, divisor, #6 rev result, result - lsr curbit, dividend, #8 + lsrs curbit, dividend, #8 cmp curbit, divisor blo LSYM(Lthumb1_div_negative8) - lsl divisor, divisor, #6 - asr result, result, #6 + lsls divisor, divisor, #6 + asrs result, result, #6 cmp curbit, divisor blo LSYM(Lthumb1_div_negative8) - lsl divisor, divisor, #6 - asr result, result, #6 + lsls divisor, divisor, #6 + asrs result, result, #6 cmp curbit, divisor blo LSYM(Lthumb1_div_negative8) - lsl divisor, divisor, #6 + lsls divisor, divisor, #6 beq LSYM(Ldivbyzero_negative) - asr result, result, #6 + asrs result, result, #6 b LSYM(Lthumb1_div_negative8) LSYM(Lthumb1_div_negative_loop): - lsr divisor, divisor, #6 + lsrs divisor, divisor, #6 LSYM(Lthumb1_div_negative8): DoDiv #7 DoDiv #6 @@ -1017,28 +1021,28 @@ LSYM(Lthumb1_div_negative4): DoDiv #2 bcs LSYM(Lthumb1_div_negative_loop) DoDiv #1 - sub divisor, dividend, divisor + subs divisor, dividend, divisor bcs 1f cpy divisor, dividend 1: cpy curbit, ip - adc result, result - asr curbit, curbit, #1 + adcs result, result + asrs curbit, curbit, #1 cpy dividend, result bcc 2f - neg dividend, dividend + negs dividend, dividend cmp curbit, #0 2: bpl 3f - neg divisor, divisor + negs divisor, divisor 3: RET LSYM(Ldivbyzero_negative): cpy curbit, ip - asr curbit, curbit, #1 + asrs curbit, curbit, #1 bcc LSYM(Ldiv0) - neg dividend, dividend + negs dividend, dividend .endm #endif /* ARM Thumb version. */ @@ -1056,8 +1060,8 @@ LSYM(Ldivbyzero_negative): cmp divisor, #0 beq LSYM(Ldiv0) LSYM(udivsi3_skip_div0_test): - mov curbit, #1 - mov result, #0 + movs curbit, #1 + movs result, #0 push { work } cmp dividend, divisor @@ -1065,7 +1069,7 @@ LSYM(udivsi3_skip_div0_test): THUMB_DIV_MOD_BODY 0 - mov r0, result + movs r0, result pop { work } RET @@ -1184,7 +1188,7 @@ ARM_FUNC_START aeabi_uidivmod cmp divisor, #0 beq LSYM(Ldiv0) - mov curbit, #1 + movs curbit, #1 cmp dividend, divisor bhs LSYM(Lover10) RET @@ -1263,7 +1267,7 @@ LSYM(Lover12): #else LSYM(divsi3_skip_div0_test): cpy curbit, dividend - orr curbit, divisor + orrs curbit, divisor bmi LSYM(Lthumb1_div_negative) LSYM(Lthumb1_div_positive): @@ -1395,11 +1399,11 @@ ARM_FUNC_START aeabi_idivmod FUNC_START modsi3 - mov curbit, #1 + movs curbit, #1 cmp divisor, #0 beq LSYM(Ldiv0) bpl LSYM(Lover10) - neg divisor, divisor @ Loops below use unsigned. + negs divisor, divisor @ Loops below use unsigned. LSYM(Lover10): push { work } @ Need to save the sign of the dividend, unfortunately, we need @@ -1408,7 +1412,7 @@ LSYM(Lover10): push { dividend } cmp dividend, #0 bpl LSYM(Lover11) - neg dividend, dividend + negs dividend, dividend LSYM(Lover11): cmp dividend, divisor blo LSYM(Lgot_result) @@ -1418,7 +1422,7 @@ LSYM(Lover11): pop { work } cmp work, #0 bpl LSYM(Lover12) - neg dividend, dividend + negs dividend, dividend LSYM(Lover12): pop { work } RET @@ -1540,12 +1544,12 @@ LSYM(Lover12): address, so just clear pc..pc+1. */ #if defined __thumb__ && !defined __thumb2__ push {r7} - mov r7, #0xf - lsl r7, #16 - add r7, #2 + movs r7, #0xf + lsls r7, #16 + adds r7, #2 adr r0, . + 4 - add r1, r0, #1 - mov r2, #0 + adds r1, r0, #1 + movs r2, #0 svc 0 pop {r7} #else @@ -1595,17 +1599,17 @@ LSYM(Lover12): FUNC_ALIAS aeabi_llsr lshrdi3 #ifdef __thumb__ - lsr al, r2 - mov r3, ah - lsr ah, r2 + lsrs al, r2 + movs r3, ah + lsrs ah, r2 mov ip, r3 - sub r2, #32 - lsr r3, r2 - orr al, r3 - neg r2, r2 + subs r2, #32 + lsrs r3, r2 + orrs al, r3 + negs r2, r2 mov r3, ip - lsl r3, r2 - orr al, r3 + lsls r3, r2 + orrs al, r3 RET #else subs r3, r2, #32 @@ -1627,21 +1631,21 @@ LSYM(Lover12): FUNC_ALIAS aeabi_lasr ashrdi3 #ifdef __thumb__ - lsr al, r2 - mov r3, ah - asr ah, r2 - sub r2, #32 + lsrs al, r2 + movs r3, ah + asrs ah, r2 + subs r2, #32 @ If r2 is negative at this point the following step would OR @ the sign bit into all of AL. That's not what we want... bmi 1f mov ip, r3 - asr r3, r2 - orr al, r3 + asrs r3, r2 + orrs al, r3 mov r3, ip 1: - neg r2, r2 - lsl r3, r2 - orr al, r3 + negs r2, r2 + lsls r3, r2 + orrs al, r3 RET #else subs r3, r2, #32 @@ -1664,17 +1668,17 @@ LSYM(Lover12): FUNC_ALIAS aeabi_llsl ashldi3 #ifdef __thumb__ - lsl ah, r2 - mov r3, al - lsl al, r2 + lsls ah, r2 + movs r3, al + lsls al, r2 mov ip, r3 - sub r2, #32 - lsl r3, r2 - orr ah, r3 - neg r2, r2 + subs r2, #32 + lsls r3, r2 + orrs ah, r3 + negs r2, r2 mov r3, ip - lsr r3, r2 - orr ah, r3 + lsrs r3, r2 + orrs ah, r3 RET #else subs r3, r2, #32 @@ -1695,26 +1699,26 @@ LSYM(Lover12): #ifdef L_clzsi2 #ifdef NOT_ISA_TARGET_32BIT FUNC_START clzsi2 - mov r1, #28 - mov r3, #1 - lsl r3, r3, #16 + movs r1, #28 + movs r3, #1 + lsls r3, r3, #16 cmp r0, r3 /* 0x10000 */ bcc 2f - lsr r0, r0, #16 - sub r1, r1, #16 -2: lsr r3, r3, #8 + lsrs r0, r0, #16 + subs r1, r1, #16 +2: lsrs r3, r3, #8 cmp r0, r3 /* #0x100 */ bcc 2f - lsr r0, r0, #8 - sub r1, r1, #8 -2: lsr r3, r3, #4 + lsrs r0, r0, #8 + subs r1, r1, #8 +2: lsrs r3, r3, #4 cmp r0, r3 /* #0x10 */ bcc 2f - lsr r0, r0, #4 - sub r1, r1, #4 + lsrs r0, r0, #4 + subs r1, r1, #4 2: adr r2, 1f ldrb r0, [r2, r0] - add r0, r0, r1 + adds r0, r0, r1 bx lr .align 2 1: @@ -1757,34 +1761,49 @@ ARM_FUNC_START clzsi2 # ifdef NOT_ISA_TARGET_32BIT FUNC_START clzdi2 push {r4, lr} -# else + cmp xxh, #0 + bne 1f +# ifdef __ARMEB__ + movs r0, xxl + bl __clzsi2 + adds r0, r0, #32 + b 2f +1: + bl __clzsi2 +# else + bl __clzsi2 + adds r0, r0, #32 + b 2f +1: + movs r0, xxh + bl __clzsi2 +# endif +2: + pop {r4, pc} +# else /* NOT_ISA_TARGET_32BIT */ ARM_FUNC_START clzdi2 do_push {r4, lr} -# endif cmp xxh, #0 bne 1f -# ifdef __ARMEB__ +# ifdef __ARMEB__ mov r0, xxl bl __clzsi2 add r0, r0, #32 b 2f 1: bl __clzsi2 -# else +# else bl __clzsi2 add r0, r0, #32 b 2f 1: mov r0, xxh bl __clzsi2 -# endif +# endif 2: -# ifdef NOT_ISA_TARGET_32BIT - pop {r4, pc} -# else RETLDM r4 -# endif FUNC_END clzdi2 +# endif /* NOT_ISA_TARGET_32BIT */ #else /* defined (__ARM_FEATURE_CLZ) */ @@ -1803,28 +1822,28 @@ ARM_FUNC_START clzdi2 #ifdef L_ctzsi2 #ifdef NOT_ISA_TARGET_32BIT FUNC_START ctzsi2 - neg r1, r0 - and r0, r0, r1 - mov r1, #28 - mov r3, #1 - lsl r3, r3, #16 + negs r1, r0 + ands r0, r0, r1 + movs r1, #28 + movs r3, #1 + lsls r3, r3, #16 cmp r0, r3 /* 0x10000 */ bcc 2f - lsr r0, r0, #16 - sub r1, r1, #16 -2: lsr r3, r3, #8 + lsrs r0, r0, #16 + subs r1, r1, #16 +2: lsrs r3, r3, #8 cmp r0, r3 /* #0x100 */ bcc 2f - lsr r0, r0, #8 - sub r1, r1, #8 -2: lsr r3, r3, #4 + lsrs r0, r0, #8 + subs r1, r1, #8 +2: lsrs r3, r3, #4 cmp r0, r3 /* #0x10 */ bcc 2f - lsr r0, r0, #4 - sub r1, r1, #4 + lsrs r0, r0, #4 + subs r1, r1, #4 2: adr r2, 1f ldrb r0, [r2, r0] - sub r0, r0, r1 + subs r0, r0, r1 bx lr .align 2 1: |