231 lines
5.1 KiB
ArmAsm
231 lines
5.1 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */
|
|
#include <linux/linkage.h>
|
|
#include <asm/asmmacro.h>
|
|
#include <asm/core.h>
|
|
|
|
#if !XCHAL_HAVE_MUL16 && !XCHAL_HAVE_MUL32 && !XCHAL_HAVE_MAC16
|
|
#define XCHAL_NO_MUL 1
|
|
#endif
|
|
|
|
ENTRY(__umulsidi3)
|
|
|
|
#ifdef __XTENSA_CALL0_ABI__
|
|
abi_entry(32)
|
|
s32i a12, sp, 16
|
|
s32i a13, sp, 20
|
|
s32i a14, sp, 24
|
|
s32i a15, sp, 28
|
|
#elif XCHAL_NO_MUL
|
|
/* This is not really a leaf function; allocate enough stack space
|
|
to allow CALL12s to a helper function. */
|
|
abi_entry(32)
|
|
#else
|
|
abi_entry_default
|
|
#endif
|
|
|
|
#ifdef __XTENSA_EB__
|
|
#define wh a2
|
|
#define wl a3
|
|
#else
|
|
#define wh a3
|
|
#define wl a2
|
|
#endif /* __XTENSA_EB__ */
|
|
|
|
/* This code is taken from the mulsf3 routine in ieee754-sf.S.
|
|
See more comments there. */
|
|
|
|
#if XCHAL_HAVE_MUL32_HIGH
|
|
mull a6, a2, a3
|
|
muluh wh, a2, a3
|
|
mov wl, a6
|
|
|
|
#else /* ! MUL32_HIGH */
|
|
|
|
#if defined(__XTENSA_CALL0_ABI__) && XCHAL_NO_MUL
|
|
/* a0 and a8 will be clobbered by calling the multiply function
|
|
but a8 is not used here and need not be saved. */
|
|
s32i a0, sp, 0
|
|
#endif
|
|
|
|
#if XCHAL_HAVE_MUL16 || XCHAL_HAVE_MUL32
|
|
|
|
#define a2h a4
|
|
#define a3h a5
|
|
|
|
/* Get the high halves of the inputs into registers. */
|
|
srli a2h, a2, 16
|
|
srli a3h, a3, 16
|
|
|
|
#define a2l a2
|
|
#define a3l a3
|
|
|
|
#if XCHAL_HAVE_MUL32 && !XCHAL_HAVE_MUL16
|
|
/* Clear the high halves of the inputs. This does not matter
|
|
for MUL16 because the high bits are ignored. */
|
|
extui a2, a2, 0, 16
|
|
extui a3, a3, 0, 16
|
|
#endif
|
|
#endif /* MUL16 || MUL32 */
|
|
|
|
|
|
#if XCHAL_HAVE_MUL16
|
|
|
|
#define do_mul(dst, xreg, xhalf, yreg, yhalf) \
|
|
mul16u dst, xreg ## xhalf, yreg ## yhalf
|
|
|
|
#elif XCHAL_HAVE_MUL32
|
|
|
|
#define do_mul(dst, xreg, xhalf, yreg, yhalf) \
|
|
mull dst, xreg ## xhalf, yreg ## yhalf
|
|
|
|
#elif XCHAL_HAVE_MAC16
|
|
|
|
/* The preprocessor insists on inserting a space when concatenating after
|
|
a period in the definition of do_mul below. These macros are a workaround
|
|
using underscores instead of periods when doing the concatenation. */
|
|
#define umul_aa_ll umul.aa.ll
|
|
#define umul_aa_lh umul.aa.lh
|
|
#define umul_aa_hl umul.aa.hl
|
|
#define umul_aa_hh umul.aa.hh
|
|
|
|
#define do_mul(dst, xreg, xhalf, yreg, yhalf) \
|
|
umul_aa_ ## xhalf ## yhalf xreg, yreg; \
|
|
rsr dst, ACCLO
|
|
|
|
#else /* no multiply hardware */
|
|
|
|
#define set_arg_l(dst, src) \
|
|
extui dst, src, 0, 16
|
|
#define set_arg_h(dst, src) \
|
|
srli dst, src, 16
|
|
|
|
#ifdef __XTENSA_CALL0_ABI__
|
|
#define do_mul(dst, xreg, xhalf, yreg, yhalf) \
|
|
set_arg_ ## xhalf (a13, xreg); \
|
|
set_arg_ ## yhalf (a14, yreg); \
|
|
call0 .Lmul_mulsi3; \
|
|
mov dst, a12
|
|
#else
|
|
#define do_mul(dst, xreg, xhalf, yreg, yhalf) \
|
|
set_arg_ ## xhalf (a14, xreg); \
|
|
set_arg_ ## yhalf (a15, yreg); \
|
|
call12 .Lmul_mulsi3; \
|
|
mov dst, a14
|
|
#endif /* __XTENSA_CALL0_ABI__ */
|
|
|
|
#endif /* no multiply hardware */
|
|
|
|
/* Add pp1 and pp2 into a6 with carry-out in a9. */
|
|
do_mul(a6, a2, l, a3, h) /* pp 1 */
|
|
do_mul(a11, a2, h, a3, l) /* pp 2 */
|
|
movi a9, 0
|
|
add a6, a6, a11
|
|
bgeu a6, a11, 1f
|
|
addi a9, a9, 1
|
|
1:
|
|
/* Shift the high half of a9/a6 into position in a9. Note that
|
|
this value can be safely incremented without any carry-outs. */
|
|
ssai 16
|
|
src a9, a9, a6
|
|
|
|
/* Compute the low word into a6. */
|
|
do_mul(a11, a2, l, a3, l) /* pp 0 */
|
|
sll a6, a6
|
|
add a6, a6, a11
|
|
bgeu a6, a11, 1f
|
|
addi a9, a9, 1
|
|
1:
|
|
/* Compute the high word into wh. */
|
|
do_mul(wh, a2, h, a3, h) /* pp 3 */
|
|
add wh, wh, a9
|
|
mov wl, a6
|
|
|
|
#endif /* !MUL32_HIGH */
|
|
|
|
#if defined(__XTENSA_CALL0_ABI__) && XCHAL_NO_MUL
|
|
/* Restore the original return address. */
|
|
l32i a0, sp, 0
|
|
#endif
|
|
#ifdef __XTENSA_CALL0_ABI__
|
|
l32i a12, sp, 16
|
|
l32i a13, sp, 20
|
|
l32i a14, sp, 24
|
|
l32i a15, sp, 28
|
|
abi_ret(32)
|
|
#else
|
|
abi_ret_default
|
|
#endif
|
|
|
|
#if XCHAL_NO_MUL
|
|
|
|
.macro do_addx2 dst, as, at, tmp
|
|
#if XCHAL_HAVE_ADDX
|
|
addx2 \dst, \as, \at
|
|
#else
|
|
slli \tmp, \as, 1
|
|
add \dst, \tmp, \at
|
|
#endif
|
|
.endm
|
|
|
|
.macro do_addx4 dst, as, at, tmp
|
|
#if XCHAL_HAVE_ADDX
|
|
addx4 \dst, \as, \at
|
|
#else
|
|
slli \tmp, \as, 2
|
|
add \dst, \tmp, \at
|
|
#endif
|
|
.endm
|
|
|
|
.macro do_addx8 dst, as, at, tmp
|
|
#if XCHAL_HAVE_ADDX
|
|
addx8 \dst, \as, \at
|
|
#else
|
|
slli \tmp, \as, 3
|
|
add \dst, \tmp, \at
|
|
#endif
|
|
.endm
|
|
|
|
/* For Xtensa processors with no multiply hardware, this simplified
|
|
version of _mulsi3 is used for multiplying 16-bit chunks of
|
|
the floating-point mantissas. When using CALL0, this function
|
|
uses a custom ABI: the inputs are passed in a13 and a14, the
|
|
result is returned in a12, and a8 and a15 are clobbered. */
|
|
.align 4
|
|
.Lmul_mulsi3:
|
|
abi_entry_default
|
|
|
|
.macro mul_mulsi3_body dst, src1, src2, tmp1, tmp2
|
|
movi \dst, 0
|
|
1: add \tmp1, \src2, \dst
|
|
extui \tmp2, \src1, 0, 1
|
|
movnez \dst, \tmp1, \tmp2
|
|
|
|
do_addx2 \tmp1, \src2, \dst, \tmp1
|
|
extui \tmp2, \src1, 1, 1
|
|
movnez \dst, \tmp1, \tmp2
|
|
|
|
do_addx4 \tmp1, \src2, \dst, \tmp1
|
|
extui \tmp2, \src1, 2, 1
|
|
movnez \dst, \tmp1, \tmp2
|
|
|
|
do_addx8 \tmp1, \src2, \dst, \tmp1
|
|
extui \tmp2, \src1, 3, 1
|
|
movnez \dst, \tmp1, \tmp2
|
|
|
|
srli \src1, \src1, 4
|
|
slli \src2, \src2, 4
|
|
bnez \src1, 1b
|
|
.endm
|
|
|
|
#ifdef __XTENSA_CALL0_ABI__
|
|
mul_mulsi3_body a12, a13, a14, a15, a8
|
|
#else
|
|
/* The result will be written into a2, so save that argument in a4. */
|
|
mov a4, a2
|
|
mul_mulsi3_body a2, a4, a3, a5, a6
|
|
#endif
|
|
abi_ret_default
|
|
#endif /* XCHAL_NO_MUL */
|
|
|
|
ENDPROC(__umulsidi3)
|