Functions for adding vectors.
More...
#include <m4ri/m4ri_config.h>
#include <m4ri/misc.h>
Go to the source code of this file.
|
static void | _mzd_combine8 (word *c, word const *t1, word const *t2, word const *t3, word const *t4, word const *t5, word const *t6, word const *t7, word const *t8, wi_t wide_in) |
|
static void | _mzd_combine6 (word *c, word const *t1, word const *t2, word const *t3, word const *t4, word const *t5, word const *t6, wi_t wide_in) |
|
static void | _mzd_combine5 (word *c, word const *t1, word const *t2, word const *t3, word const *t4, word const *t5, wi_t wide_in) |
|
static void | _mzd_combine4 (word *c, word const *t1, word const *t2, word const *t3, word const *t4, wi_t wide_in) |
|
static void | _mzd_combine3 (word *c, word const *t1, word const *t2, word const *t3, wi_t wide_in) |
|
static void | _mzd_combine2 (word *c, word const *t1, word const *t2, wi_t wide_in) |
|
static void | _mzd_combine (word *c, word const *t1, wi_t wide_in) |
|
static void _mzd_combine |
( |
word * |
c, |
|
|
word const * |
t1, |
|
|
wi_t |
wide_in |
|
) |
| |
|
inlinestatic |
Compute c[i] += t1[i] for 0 <= i < wide
static void _mzd_combine2 |
( |
word * |
c, |
|
|
word const * |
t1, |
|
|
word const * |
t2, |
|
|
wi_t |
wide_in |
|
) |
| |
|
inlinestatic |
Compute c[i] += t1[i] + t2[i] for 0 <= i < wide
static void _mzd_combine3 |
( |
word * |
c, |
|
|
word const * |
t1, |
|
|
word const * |
t2, |
|
|
word const * |
t3, |
|
|
wi_t |
wide_in |
|
) |
| |
|
inlinestatic |
Compute c[i] += t1[i] + t2[i] + t3[i] for 0 <= i < wide
static void _mzd_combine4 |
( |
word * |
c, |
|
|
word const * |
t1, |
|
|
word const * |
t2, |
|
|
word const * |
t3, |
|
|
word const * |
t4, |
|
|
wi_t |
wide_in |
|
) |
| |
|
inlinestatic |
Compute c[i] += t1[i] + t2[i] + t3[i] + t4[i] for 0 <= i < wide
Compute c[i] += t1[i] + t2[i] + t3[i] + t4[i] + t5[i] for 0 <= i < wide
Compute c[i] += t1[i] + t2[i] + t3[i] + t4[i] + t5[i] + t6[i] for 0 <= i < wide
Compute c[i] += t1[i] + t2[i] + t3[i] + t4[i] + t5[i] + t6[i] + t7[i] + t8[i] for 0 <= i < wide
- Todo:
- the non SSE2 version of this code is slow, replace by code from mzd_process_rows8