microblaze: Fix __muldi3 function for little-endian.
__muldi3 was written for big endian platforms. Code contained half word read/write instructions which are not compatible with little endian cpu. Asm __muldi3 implementation is replaced by C version. Signed-off-by: Michal Simek <monstr@monstr.eu>
This commit is contained in:
Michal Simek
parent
17b9314687
commit
3370d82f3b
|
|
@ -1,121 +0,0 @@
|
|||
#include <linux/linkage.h>
|
||||
|
||||
/*
|
||||
* Multiply operation for 64 bit integers, for devices with hard multiply
|
||||
* Input : Operand1[H] in Reg r5
|
||||
* Operand1[L] in Reg r6
|
||||
* Operand2[H] in Reg r7
|
||||
* Operand2[L] in Reg r8
|
||||
* Output: Result[H] in Reg r3
|
||||
* Result[L] in Reg r4
|
||||
*
|
||||
* Explaination:
|
||||
*
|
||||
* Both the input numbers are divided into 16 bit number as follows
|
||||
* op1 = A B C D
|
||||
* op2 = E F G H
|
||||
* result = D * H
|
||||
* + (C * H + D * G) << 16
|
||||
* + (B * H + C * G + D * F) << 32
|
||||
* + (A * H + B * G + C * F + D * E) << 48
|
||||
*
|
||||
* Only 64 bits of the output are considered
|
||||
*/
|
||||
|
||||
.text
|
||||
.globl __muldi3
|
||||
.type __muldi3, @function
|
||||
.ent __muldi3
|
||||
|
||||
__muldi3:
|
||||
addi r1, r1, -40
|
||||
|
||||
/* Save the input operands on the caller's stack */
|
||||
swi r5, r1, 44
|
||||
swi r6, r1, 48
|
||||
swi r7, r1, 52
|
||||
swi r8, r1, 56
|
||||
|
||||
/* Store all the callee saved registers */
|
||||
sw r20, r1, r0
|
||||
swi r21, r1, 4
|
||||
swi r22, r1, 8
|
||||
swi r23, r1, 12
|
||||
swi r24, r1, 16
|
||||
swi r25, r1, 20
|
||||
swi r26, r1, 24
|
||||
swi r27, r1, 28
|
||||
|
||||
/* Load all the 16 bit values for A thru H */
|
||||
lhui r20, r1, 44 /* A */
|
||||
lhui r21, r1, 46 /* B */
|
||||
lhui r22, r1, 48 /* C */
|
||||
lhui r23, r1, 50 /* D */
|
||||
lhui r24, r1, 52 /* E */
|
||||
lhui r25, r1, 54 /* F */
|
||||
lhui r26, r1, 56 /* G */
|
||||
lhui r27, r1, 58 /* H */
|
||||
|
||||
/* D * H ==> LSB of the result on stack ==> Store1 */
|
||||
mul r9, r23, r27
|
||||
swi r9, r1, 36 /* Pos2 and Pos3 */
|
||||
|
||||
/* Hi (Store1) + C * H + D * G ==> Store2 ==> Pos1 and Pos2 */
|
||||
/* Store the carry generated in position 2 for Pos 3 */
|
||||
lhui r11, r1, 36 /* Pos2 */
|
||||
mul r9, r22, r27 /* C * H */
|
||||
mul r10, r23, r26 /* D * G */
|
||||
add r9, r9, r10
|
||||
addc r12, r0, r0
|
||||
add r9, r9, r11
|
||||
addc r12, r12, r0 /* Store the Carry */
|
||||
shi r9, r1, 36 /* Store Pos2 */
|
||||
swi r9, r1, 32
|
||||
lhui r11, r1, 32
|
||||
shi r11, r1, 34 /* Store Pos1 */
|
||||
|
||||
/* Hi (Store2) + B * H + C * G + D * F ==> Store3 ==> Pos0 and Pos1 */
|
||||
mul r9, r21, r27 /* B * H */
|
||||
mul r10, r22, r26 /* C * G */
|
||||
mul r7, r23, r25 /* D * F */
|
||||
add r9, r9, r11
|
||||
add r9, r9, r10
|
||||
add r9, r9, r7
|
||||
swi r9, r1, 32 /* Pos0 and Pos1 */
|
||||
|
||||
/* Hi (Store3) + A * H + B * G + C * F + D * E ==> Store3 ==> Pos0 */
|
||||
lhui r11, r1, 32 /* Pos0 */
|
||||
mul r9, r20, r27 /* A * H */
|
||||
mul r10, r21, r26 /* B * G */
|
||||
mul r7, r22, r25 /* C * F */
|
||||
mul r8, r23, r24 /* D * E */
|
||||
add r9, r9, r11
|
||||
add r9, r9, r10
|
||||
add r9, r9, r7
|
||||
add r9, r9, r8
|
||||
sext16 r9, r9 /* Sign extend the MSB */
|
||||
shi r9, r1, 32
|
||||
|
||||
/* Move results to r3 and r4 */
|
||||
lhui r3, r1, 32
|
||||
add r3, r3, r12
|
||||
shi r3, r1, 32
|
||||
lwi r3, r1, 32 /* Hi Part */
|
||||
lwi r4, r1, 36 /* Lo Part */
|
||||
|
||||
/* Restore Callee saved registers */
|
||||
lw r20, r1, r0
|
||||
lwi r21, r1, 4
|
||||
lwi r22, r1, 8
|
||||
lwi r23, r1, 12
|
||||
lwi r24, r1, 16
|
||||
lwi r25, r1, 20
|
||||
lwi r26, r1, 24
|
||||
lwi r27, r1, 28
|
||||
|
||||
/* Restore Frame and return */
|
||||
rtsd r15, 8
|
||||
addi r1, r1, 40
|
||||
|
||||
.size __muldi3, . - __muldi3
|
||||
.end __muldi3
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
#include <linux/module.h>
|
||||
|
||||
#include "libgcc.h"
|
||||
|
||||
#define DWtype long long
|
||||
#define UWtype unsigned long
|
||||
#define UHWtype unsigned short
|
||||
|
||||
#define W_TYPE_SIZE 32
|
||||
|
||||
#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2))
|
||||
#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1))
|
||||
#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2))
|
||||
|
||||
/* If we still don't have umul_ppmm, define it using plain C. */
|
||||
#if !defined(umul_ppmm)
|
||||
#define umul_ppmm(w1, w0, u, v) \
|
||||
do { \
|
||||
UWtype __x0, __x1, __x2, __x3; \
|
||||
UHWtype __ul, __vl, __uh, __vh; \
|
||||
\
|
||||
__ul = __ll_lowpart(u); \
|
||||
__uh = __ll_highpart(u); \
|
||||
__vl = __ll_lowpart(v); \
|
||||
__vh = __ll_highpart(v); \
|
||||
\
|
||||
__x0 = (UWtype) __ul * __vl; \
|
||||
__x1 = (UWtype) __ul * __vh; \
|
||||
__x2 = (UWtype) __uh * __vl; \
|
||||
__x3 = (UWtype) __uh * __vh; \
|
||||
\
|
||||
__x1 += __ll_highpart(__x0); /* this can't give carry */\
|
||||
__x1 += __x2; /* but this indeed can */ \
|
||||
if (__x1 < __x2) /* did we get it? */ \
|
||||
__x3 += __ll_B; /* yes, add it in the proper pos */ \
|
||||
\
|
||||
(w1) = __x3 + __ll_highpart(__x1); \
|
||||
(w0) = __ll_lowpart(__x1) * __ll_B + __ll_lowpart(__x0);\
|
||||
} while (0)
|
||||
#endif
|
||||
|
||||
#if !defined(__umulsidi3)
|
||||
#define __umulsidi3(u, v) ({ \
|
||||
DWunion __w; \
|
||||
umul_ppmm(__w.s.high, __w.s.low, u, v); \
|
||||
__w.ll; \
|
||||
})
|
||||
#endif
|
||||
|
||||
DWtype __muldi3(DWtype u, DWtype v)
|
||||
{
|
||||
const DWunion uu = {.ll = u};
|
||||
const DWunion vv = {.ll = v};
|
||||
DWunion w = {.ll = __umulsidi3(uu.s.low, vv.s.low)};
|
||||
|
||||
w.s.high += ((UWtype) uu.s.low * (UWtype) vv.s.high
|
||||
+ (UWtype) uu.s.high * (UWtype) vv.s.low);
|
||||
|
||||
return w.ll;
|
||||
}
|
||||
Loading…
Reference in New Issue