Dropped MMX support
Was useful a decade ago but now profiling shows it's actually slower than just plain compiler-optimized code so the extra maintenance cost is not justified.
This commit is contained in:
Duilio Protti
parent
c165721f5f
commit
ec804c0f57
36
configure.ac
36
configure.ac
|
|
@ -52,46 +52,10 @@ AC_C_CONST
|
||||||
AC_C_INLINE
|
AC_C_INLINE
|
||||||
AC_C_BIGENDIAN(AC_MSG_WARN([*** You have a big endian system, Infinity have not been tested on these systems]),,)
|
AC_C_BIGENDIAN(AC_MSG_WARN([*** You have a big endian system, Infinity have not been tested on these systems]),,)
|
||||||
|
|
||||||
AC_CHECK_SIZEOF(long long)
|
|
||||||
if test x$ac_cv_sizeof_long_long = x8; then
|
|
||||||
:
|
|
||||||
else
|
|
||||||
AC_MSG_ERROR([
|
|
||||||
*** Infinity requires a 64 bit long long type. You might want to consider
|
|
||||||
*** using the GNU C compiler.
|
|
||||||
])
|
|
||||||
fi
|
|
||||||
|
|
||||||
AC_CHECK_SIZEOF([size_t])
|
|
||||||
AC_MSG_CHECKING([whether compiler is 32 or 64 bit])
|
|
||||||
if test x$ac_cv_sizeof_size_t = x8; then
|
|
||||||
AC_MSG_RESULT([64])
|
|
||||||
compiler_width=64
|
|
||||||
else
|
|
||||||
AC_MSG_RESULT([32])
|
|
||||||
compiler_width=32
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Check for library functions.
|
# Check for library functions.
|
||||||
AC_CHECK_FUNCS([floor sqrt])
|
AC_CHECK_FUNCS([floor sqrt])
|
||||||
|
|
||||||
# Arguments to specify certain features.
|
# Arguments to specify certain features.
|
||||||
AC_ARG_ENABLE([mmx],
|
|
||||||
AS_HELP_STRING([--enable-mmx],[use MMX if available and if building with a 32 bit compiler @<:@default=enabled@:>@]),
|
|
||||||
[mmx=$enableval],
|
|
||||||
[mmx=yes])
|
|
||||||
AC_MSG_CHECKING([whether to enable MMX])
|
|
||||||
if test x$mmx = xyes; then
|
|
||||||
if test x$compiler_width = x32; then
|
|
||||||
AC_MSG_RESULT([yes])
|
|
||||||
AC_DEFINE([MMX_DETECTION], [1], [Activate MMX Extensions support])
|
|
||||||
else
|
|
||||||
AC_MSG_RESULT([no, was requested but feature is not supported with a 64bit compiler])
|
|
||||||
fi
|
|
||||||
else
|
|
||||||
AC_MSG_RESULT([no])
|
|
||||||
fi
|
|
||||||
|
|
||||||
AC_ARG_ENABLE([debug],
|
AC_ARG_ENABLE([debug],
|
||||||
AS_HELP_STRING([--enable-debug],[turn on debug mode @<:@default=disabled@:>@]),
|
AS_HELP_STRING([--enable-debug],[turn on debug mode @<:@default=disabled@:>@]),
|
||||||
[debug=$enableval],
|
[debug=$enableval],
|
||||||
|
|
|
||||||
|
|
@ -20,8 +20,7 @@ libinfinity_la_SOURCES = \
|
||||||
compute.c compute.h \
|
compute.c compute.h \
|
||||||
display.c display.h \
|
display.c display.h \
|
||||||
effects.c effects.h \
|
effects.c effects.h \
|
||||||
cputest.c cputest.h \
|
music-player.h types.h
|
||||||
mmx.h music-player.h types.h
|
|
||||||
|
|
||||||
libinfinite_la_SOURCES = audacious.cc
|
libinfinite_la_SOURCES = audacious.cc
|
||||||
libinfinite_la_LDFLAGS = ${CXX}
|
libinfinite_la_LDFLAGS = ${CXX}
|
||||||
|
|
|
||||||
|
|
@ -19,9 +19,6 @@
|
||||||
#include "compute.h"
|
#include "compute.h"
|
||||||
#include "config.h"
|
#include "config.h"
|
||||||
#include "types.h"
|
#include "types.h"
|
||||||
#ifdef MMX_DETECTION
|
|
||||||
#include "mmx.h"
|
|
||||||
#endif
|
|
||||||
|
|
||||||
typedef struct t_coord {
|
typedef struct t_coord {
|
||||||
gint32 x, y;
|
gint32 x, y;
|
||||||
|
|
@ -274,48 +271,3 @@ inline byte *compute_surface(t_interpol *vector, gint32 width, gint32 height)
|
||||||
|
|
||||||
return surface1;
|
return surface1;
|
||||||
}
|
}
|
||||||
|
|
||||||
#if MMX_DETECTION
|
|
||||||
inline byte *compute_surface_mmx(t_interpol *vector, gint32 width, gint32 height)
|
|
||||||
{
|
|
||||||
/*@unused@*/
|
|
||||||
volatile mmx_t mm0, mm1, mm2;
|
|
||||||
volatile mmx_t offsets, r;
|
|
||||||
t_interpol *interpol;
|
|
||||||
gint32 i, j, color;
|
|
||||||
gint32 add_dest = 0;
|
|
||||||
guint32 add_src;
|
|
||||||
register byte *ptr_pix;
|
|
||||||
byte *ptr_swap;
|
|
||||||
|
|
||||||
for (j = 0; j < height; ++j)
|
|
||||||
for (i = 0; i < width; ++i) {
|
|
||||||
interpol = &vector[add_dest];
|
|
||||||
add_src = (interpol->coord & 0xFFFF) * width + (interpol->coord >> 16);
|
|
||||||
ptr_pix = &((byte *)surface1)[add_src];
|
|
||||||
((guint16 *)&offsets)[0] = (guint16) * (ptr_pix + width + 1);
|
|
||||||
((guint16 *)&offsets)[1] = (guint16) * (ptr_pix + width);
|
|
||||||
((guint16 *)&offsets)[2] = (guint16) * (ptr_pix + 1);
|
|
||||||
((guint16 *)&offsets)[3] = (guint16) * (ptr_pix);
|
|
||||||
/* MMX mode entry */
|
|
||||||
movd_m2r(interpol->weight, mm1);
|
|
||||||
movq_m2r(offsets, mm2);
|
|
||||||
pxor_r2r(mm0, mm0);
|
|
||||||
punpcklbw_r2r(mm0, mm1);
|
|
||||||
pmaddwd_r2r(mm1, mm2);
|
|
||||||
movq_r2m(mm2, r);
|
|
||||||
emms();
|
|
||||||
/* MMX mode exit */
|
|
||||||
color = (((gint32 *)&r)[0] + ((gint32 *)&r)[1]) >> 8;
|
|
||||||
if (color > 255)
|
|
||||||
surface2[add_dest] = 255;
|
|
||||||
else
|
|
||||||
surface2[add_dest] = (byte)color;
|
|
||||||
++add_dest;
|
|
||||||
}
|
|
||||||
ptr_swap = surface1;
|
|
||||||
surface1 = surface2;
|
|
||||||
surface2 = ptr_swap;
|
|
||||||
return surface1;
|
|
||||||
}
|
|
||||||
#endif /* MMX_DETECTION */
|
|
||||||
|
|
|
||||||
|
|
@ -73,6 +73,5 @@ void compute_resize(gint32 width, gint32 height);
|
||||||
void compute_generate_vector_field(vector_field_t *vector_field);
|
void compute_generate_vector_field(vector_field_t *vector_field);
|
||||||
|
|
||||||
byte *compute_surface(t_interpol *vector, gint32 width, gint32 height);
|
byte *compute_surface(t_interpol *vector, gint32 width, gint32 height);
|
||||||
byte *compute_surface_mmx(t_interpol *vector, gint32 width, gint32 height);
|
|
||||||
|
|
||||||
#endif /* __INFINITY_COMPUTE__ */
|
#endif /* __INFINITY_COMPUTE__ */
|
||||||
|
|
|
||||||
181
src/cputest.c
181
src/cputest.c
|
|
@ -1,181 +0,0 @@
|
||||||
#include "config.h"
|
|
||||||
#include "cputest.h"
|
|
||||||
#include "glib.h"
|
|
||||||
|
|
||||||
// This code is 32-bit only
|
|
||||||
|
|
||||||
/* ebx saving is necessary for PIC. gcc seems unable to see it alone */
|
|
||||||
#if MMX_DETECTION
|
|
||||||
#define cpuid(index, eax, ebx, ecx, edx) \
|
|
||||||
__asm __volatile \
|
|
||||||
("movl %%ebx, %%esi\n\t" \
|
|
||||||
"cpuid\n\t" \
|
|
||||||
"xchgl %%ebx, %%esi" \
|
|
||||||
: "=a" (eax), "=S" (ebx), \
|
|
||||||
"=c" (ecx), "=d" (edx) \
|
|
||||||
: "0" (index));
|
|
||||||
#endif
|
|
||||||
|
|
||||||
|
|
||||||
/* Function to test if multimedia instructions are supported... */
|
|
||||||
int mm_support(void)
|
|
||||||
{
|
|
||||||
#if MMX_DETECTION
|
|
||||||
int rval;
|
|
||||||
int eax, ebx, ecx, edx;
|
|
||||||
|
|
||||||
__asm__ __volatile__ (
|
|
||||||
/* See if CPUID instruction is supported ... */
|
|
||||||
/* ... Get copies of EFLAGS into eax and ecx */
|
|
||||||
"pushf\n\t"
|
|
||||||
"popl %0\n\t"
|
|
||||||
"movl %0, %1\n\t"
|
|
||||||
|
|
||||||
/* ... Toggle the ID bit in one copy and store */
|
|
||||||
/* to the EFLAGS reg */
|
|
||||||
"xorl $0x200000, %0\n\t"
|
|
||||||
"push %0\n\t"
|
|
||||||
"popf\n\t"
|
|
||||||
|
|
||||||
/* ... Get the (hopefully modified) EFLAGS */
|
|
||||||
"pushf\n\t"
|
|
||||||
"popl %0\n\t"
|
|
||||||
: "=a" (eax), "=c" (ecx)
|
|
||||||
:
|
|
||||||
: "cc"
|
|
||||||
);
|
|
||||||
|
|
||||||
if (eax == ecx)
|
|
||||||
return 0; /* CPUID not supported */
|
|
||||||
|
|
||||||
cpuid(0, eax, ebx, ecx, edx);
|
|
||||||
|
|
||||||
if (ebx == 0x756e6547 &&
|
|
||||||
edx == 0x49656e69 &&
|
|
||||||
ecx == 0x6c65746e) {
|
|
||||||
/* intel */
|
|
||||||
inteltest:
|
|
||||||
cpuid(1, eax, ebx, ecx, edx);
|
|
||||||
if ((edx & 0x00800000) == 0)
|
|
||||||
return 0;
|
|
||||||
rval = MM_MMX;
|
|
||||||
if (edx & 0x02000000)
|
|
||||||
rval |= MM_MMXEXT | MM_SSE;
|
|
||||||
if (edx & 0x04000000)
|
|
||||||
rval |= MM_SSE2;
|
|
||||||
return rval;
|
|
||||||
} else if (ebx == 0x68747541 &&
|
|
||||||
edx == 0x69746e65 &&
|
|
||||||
ecx == 0x444d4163) {
|
|
||||||
/* AMD */
|
|
||||||
cpuid(0x80000000, eax, ebx, ecx, edx);
|
|
||||||
if ((guint32)eax < 0x80000001)
|
|
||||||
goto inteltest;
|
|
||||||
cpuid(0x80000001, eax, ebx, ecx, edx);
|
|
||||||
if ((edx & 0x00800000) == 0)
|
|
||||||
return 0;
|
|
||||||
rval = MM_MMX;
|
|
||||||
if (edx & 0x80000000)
|
|
||||||
rval |= MM_3DNOW;
|
|
||||||
if (edx & 0x00400000)
|
|
||||||
rval |= MM_MMXEXT;
|
|
||||||
return rval;
|
|
||||||
} else if (ebx == 0x746e6543 &&
|
|
||||||
edx == 0x48727561 &&
|
|
||||||
ecx == 0x736c7561) { /* "CentaurHauls" */
|
|
||||||
/* VIA C3 */
|
|
||||||
cpuid(0x80000000, eax, ebx, ecx, edx);
|
|
||||||
if ((guint32)eax < 0x80000001)
|
|
||||||
goto inteltest;
|
|
||||||
cpuid(0x80000001, eax, ebx, ecx, edx);
|
|
||||||
rval = 0;
|
|
||||||
if (edx & (1 << 31))
|
|
||||||
rval |= MM_3DNOW;
|
|
||||||
if (edx & (1 << 23))
|
|
||||||
rval |= MM_MMX;
|
|
||||||
if (edx & (1 << 24))
|
|
||||||
rval |= MM_MMXEXT;
|
|
||||||
return rval;
|
|
||||||
} else if (ebx == 0x69727943 &&
|
|
||||||
edx == 0x736e4978 &&
|
|
||||||
ecx == 0x64616574) {
|
|
||||||
/* Cyrix Section */
|
|
||||||
/* See if extended CPUID level 80000001 is supported */
|
|
||||||
/* The value of CPUID/80000001 for the 6x86MX is undefined
|
|
||||||
* according to the Cyrix CPU Detection Guide (Preliminary
|
|
||||||
* Rev. 1.01 table 1), so we'll check the value of eax for
|
|
||||||
* CPUID/0 to see if standard CPUID level 2 is supported.
|
|
||||||
* According to the table, the only CPU which supports level
|
|
||||||
* 2 is also the only one which supports extended CPUID levels.
|
|
||||||
*/
|
|
||||||
if (eax != 2)
|
|
||||||
goto inteltest;
|
|
||||||
cpuid(0x80000001, eax, ebx, ecx, edx);
|
|
||||||
if ((eax & 0x00800000) == 0)
|
|
||||||
return 0;
|
|
||||||
rval = MM_MMX;
|
|
||||||
if (eax & 0x01000000)
|
|
||||||
rval |= MM_MMXEXT;
|
|
||||||
return rval;
|
|
||||||
} else {
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
#else /* not MMX_DETECTION */
|
|
||||||
return 0;
|
|
||||||
#endif
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
int mm_support_check_and_show()
|
|
||||||
{
|
|
||||||
int r;
|
|
||||||
gchar *msg, *tmp;
|
|
||||||
|
|
||||||
r = mm_support();
|
|
||||||
if (r & 0) {
|
|
||||||
g_message("Infinity: There is not MMX support\n");
|
|
||||||
return r;
|
|
||||||
}
|
|
||||||
msg = g_strdup("Infinity: Looking for Multimedia Extensions Support...");
|
|
||||||
if (r & MM_MMX) {
|
|
||||||
tmp = g_strconcat(msg, " MMX", NULL);
|
|
||||||
g_free(msg);
|
|
||||||
msg = tmp;
|
|
||||||
}
|
|
||||||
if (r & MM_3DNOW) {
|
|
||||||
tmp = g_strconcat(msg, " 3DNOW", NULL);
|
|
||||||
g_free(msg);
|
|
||||||
msg = tmp;
|
|
||||||
}
|
|
||||||
if (r & MM_MMXEXT) {
|
|
||||||
tmp = g_strconcat(msg, " MMX2", NULL);
|
|
||||||
g_free(msg);
|
|
||||||
msg = tmp;
|
|
||||||
}
|
|
||||||
/*
|
|
||||||
* for now this extensions are not used
|
|
||||||
* if (r & MM_SSE) {
|
|
||||||
* tmp = g_strconcat (msg, " SSE", 0);
|
|
||||||
* g_free (msg);
|
|
||||||
* msg = tmp;
|
|
||||||
* }
|
|
||||||
* if (r & MM_SSE2) {
|
|
||||||
* tmp = g_strconcat (msg, " SSE2", 0);
|
|
||||||
* g_free (msg);
|
|
||||||
* msg = tmp;
|
|
||||||
* }
|
|
||||||
*/
|
|
||||||
tmp = g_strconcat(msg, " detected", NULL);
|
|
||||||
g_free(msg);
|
|
||||||
msg = tmp;
|
|
||||||
g_message("%s", msg);
|
|
||||||
g_free(msg);
|
|
||||||
|
|
||||||
return r;
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
int mmx_ok(void)
|
|
||||||
{
|
|
||||||
return mm_support() & 0x1;
|
|
||||||
}
|
|
||||||
|
|
@ -1,29 +0,0 @@
|
||||||
/*
|
|
||||||
* Cpu detection code, extracted from mmx.h ((c)1997-99 by H. Dietz
|
|
||||||
* and R. Fisher). Converted to C and improved by Fabrice Bellard
|
|
||||||
*/
|
|
||||||
#ifndef _CPUTEST_H_
|
|
||||||
#define _CPUTEST_H_
|
|
||||||
|
|
||||||
|
|
||||||
#define MM_MMX 0x0001 /* standard MMX */
|
|
||||||
#define MM_3DNOW 0x0004 /* AMD 3DNOW */
|
|
||||||
#define MM_MMXEXT 0x0002 /* SSE integer functions or AMD MMX ext */
|
|
||||||
#define MM_SSE 0x0008 /* SSE functions */
|
|
||||||
#define MM_SSE2 0x0010 /* PIV SSE2 functions */
|
|
||||||
|
|
||||||
/* should be defined by architectures supporting
|
|
||||||
* one or more MultiMedia extension */
|
|
||||||
int mm_support(void);
|
|
||||||
|
|
||||||
/* return the result of mm_support and show the results
|
|
||||||
* to stdout */
|
|
||||||
int mm_support_check_and_show(void);
|
|
||||||
|
|
||||||
/* test if mmx instructions are supported...
|
|
||||||
* returns 1 if MMX instructions are supported, 0 otherwise */
|
|
||||||
int mmx_ok(void);
|
|
||||||
|
|
||||||
extern unsigned int mm_flags;
|
|
||||||
|
|
||||||
#endif /* _CPUTEST_H_ */
|
|
||||||
|
|
@ -313,15 +313,6 @@ inline void display_blur(guint32 vector_index)
|
||||||
display_surface();
|
display_surface();
|
||||||
}
|
}
|
||||||
|
|
||||||
#if MMX_DETECTION
|
|
||||||
inline void display_blur_mmx(guint32 vector_index)
|
|
||||||
{
|
|
||||||
surface1 = compute_surface_mmx(&(vector_field->vector[vector_index]),
|
|
||||||
vector_field->width, vector_field->height);
|
|
||||||
display_surface();
|
|
||||||
}
|
|
||||||
#endif
|
|
||||||
|
|
||||||
void spectral(t_effect *current_effect)
|
void spectral(t_effect *current_effect)
|
||||||
{
|
{
|
||||||
gint32 i, halfheight, halfwidth;
|
gint32 i, halfheight, halfwidth;
|
||||||
|
|
|
||||||
|
|
@ -72,7 +72,6 @@ void display_show(void);
|
||||||
|
|
||||||
void change_color(gint32 old_p, gint32 p, gint32 w);
|
void change_color(gint32 old_p, gint32 p, gint32 w);
|
||||||
void display_blur(guint32 vector_index);
|
void display_blur(guint32 vector_index);
|
||||||
void display_blur_mmx(guint32 vector_index);
|
|
||||||
void spectral(t_effect *current_effect);
|
void spectral(t_effect *current_effect);
|
||||||
void curve(t_effect *current_effect);
|
void curve(t_effect *current_effect);
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -27,10 +27,6 @@
|
||||||
#include "infinity.h"
|
#include "infinity.h"
|
||||||
#include "types.h"
|
#include "types.h"
|
||||||
|
|
||||||
#if MMX_DETECTION
|
|
||||||
#include "cputest.h"
|
|
||||||
#endif
|
|
||||||
|
|
||||||
#define wrap(a) (a < 0 ? 0 : (a > 255 ? 255 : a))
|
#define wrap(a) (a < 0 ? 0 : (a > 255 ? 255 : a))
|
||||||
#define next_effect() (t_last_effect++)
|
#define next_effect() (t_last_effect++)
|
||||||
#define next_color() (t_last_color++)
|
#define next_color() (t_last_color++)
|
||||||
|
|
@ -313,15 +309,11 @@ static int renderer(void *arg)
|
||||||
gint32 frame_length;
|
gint32 frame_length;
|
||||||
gint32 fps, new_fps;
|
gint32 fps, new_fps;
|
||||||
gint32 t_between_effects, t_between_colors;
|
gint32 t_between_effects, t_between_colors;
|
||||||
gint32 has_mmx = 0;
|
|
||||||
|
|
||||||
fps = params->get_max_fps();
|
fps = params->get_max_fps();
|
||||||
frame_length = calculate_frame_length_usecs(fps, __LINE__);
|
frame_length = calculate_frame_length_usecs(fps, __LINE__);
|
||||||
t_between_effects = params->get_effect_interval();
|
t_between_effects = params->get_effect_interval();
|
||||||
t_between_colors = params->get_color_interval();
|
t_between_colors = params->get_color_interval();
|
||||||
#if MMX_DETECTION
|
|
||||||
has_mmx = mm_support_check_and_show();
|
|
||||||
#endif
|
|
||||||
initializing = FALSE;
|
initializing = FALSE;
|
||||||
for (;; ) { /* ever... */
|
for (;; ) { /* ever... */
|
||||||
if (!visible) {
|
if (!visible) {
|
||||||
|
|
@ -347,10 +339,7 @@ static int renderer(void *arg)
|
||||||
G_UNLOCK(resizing);
|
G_UNLOCK(resizing);
|
||||||
}
|
}
|
||||||
t_begin = g_get_monotonic_time();
|
t_begin = g_get_monotonic_time();
|
||||||
if (has_mmx)
|
display_blur(width * height * current_effect.num_effect);
|
||||||
display_blur_mmx(width * height * current_effect.num_effect);
|
|
||||||
else
|
|
||||||
display_blur(width * height * current_effect.num_effect);
|
|
||||||
spectral(¤t_effect);
|
spectral(¤t_effect);
|
||||||
curve(¤t_effect);
|
curve(¤t_effect);
|
||||||
if (t_last_color <= 32)
|
if (t_last_color <= 32)
|
||||||
|
|
|
||||||
537
src/mmx.h
537
src/mmx.h
|
|
@ -1,537 +0,0 @@
|
||||||
/* mmx.h
|
|
||||||
*
|
|
||||||
* MultiMedia eXtensions GCC interface library for IA32.
|
|
||||||
*
|
|
||||||
* To use this library, simply include this header file
|
|
||||||
* and compile with GCC. You MUST have inlining enabled
|
|
||||||
* in order for mmx_ok() to work; this can be done by
|
|
||||||
* simply using -O on the GCC command line.
|
|
||||||
*
|
|
||||||
* Compiling with -DMMX_TRACE will cause detailed trace
|
|
||||||
* output to be sent to stderr for each mmx operation.
|
|
||||||
* This adds lots of code, and obviously slows execution to
|
|
||||||
* a crawl, but can be very useful for debugging.
|
|
||||||
*
|
|
||||||
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY
|
|
||||||
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT
|
|
||||||
* LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTABILITY
|
|
||||||
* AND FITNESS FOR ANY PARTICULAR PURPOSE.
|
|
||||||
*
|
|
||||||
* 1997-99 by H. Dietz and R. Fisher
|
|
||||||
*
|
|
||||||
* Notes:
|
|
||||||
* It appears that the latest gas has the pand problem fixed, therefore
|
|
||||||
* I'll undefine BROKEN_PAND by default.
|
|
||||||
*/
|
|
||||||
|
|
||||||
#ifndef _MMX_H_
|
|
||||||
#define _MMX_H_
|
|
||||||
|
|
||||||
|
|
||||||
/* Warning: at this writing, the version of GAS packaged
|
|
||||||
* with most Linux distributions does not handle the
|
|
||||||
* parallel AND operation mnemonic correctly. If the
|
|
||||||
* symbol BROKEN_PAND is defined, a slower alternative
|
|
||||||
* coding will be used. If execution of mmxtest results
|
|
||||||
* in an illegal instruction fault, define this symbol.
|
|
||||||
*/
|
|
||||||
#undef BROKEN_PAND
|
|
||||||
|
|
||||||
|
|
||||||
/* The type of an value that fits in an MMX register
|
|
||||||
* (note that long long constant values MUST be suffixed
|
|
||||||
* by LL and unsigned long long values by ULL, lest
|
|
||||||
* they be truncated by the compiler)
|
|
||||||
*/
|
|
||||||
typedef union {
|
|
||||||
gint64 q; /* Quadword (64-bit) value */
|
|
||||||
guint64 uq; /* Unsigned Quadword */
|
|
||||||
gint32 d[2]; /* 2 Doubleword (32-bit) values */
|
|
||||||
guint32 ud[2]; /* 2 Unsigned Doubleword */
|
|
||||||
gint16 w[4]; /* 4 Word (16-bit) values */
|
|
||||||
guint16 uw[4]; /* 4 Unsigned Word */
|
|
||||||
gchar b[8]; /* 8 Byte (8-bit) values */
|
|
||||||
guchar ub[8]; /* 8 Unsigned Byte */
|
|
||||||
gfloat s[2]; /* Single-precision (32-bit) value */
|
|
||||||
} __attribute__ ((aligned(8))) mmx_t; /* On an 8-byte (64-bit) boundary */
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
/* Helper functions for the instruction macros that follow...
|
|
||||||
* (note that memory-to-register, m2r, instructions are nearly
|
|
||||||
* as efficient as register-to-register, r2r, instructions;
|
|
||||||
* however, memory-to-memory instructions are really simulated
|
|
||||||
* as a convenience, and are only 1/3 as efficient)
|
|
||||||
*/
|
|
||||||
#ifdef MMX_TRACE
|
|
||||||
|
|
||||||
/* Include the stuff for printing a trace to stderr...
|
|
||||||
*/
|
|
||||||
|
|
||||||
#include <stdio.h>
|
|
||||||
|
|
||||||
#define mmx_i2r(op, imm, reg) \
|
|
||||||
{ \
|
|
||||||
mmx_t mmx_trace; \
|
|
||||||
mmx_trace.uq = (imm); \
|
|
||||||
printf(#op "_i2r(" #imm "=0x%08x%08x, ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
__asm__ __volatile__ ("movq %%" #reg ", %0" \
|
|
||||||
: "=X" (mmx_trace) \
|
|
||||||
: /* nothing */); \
|
|
||||||
printf(#reg "=0x%08x%08x) => ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
__asm__ __volatile__ (#op " %0, %%" #reg \
|
|
||||||
: /* nothing */ \
|
|
||||||
: "X" (imm)); \
|
|
||||||
__asm__ __volatile__ ("movq %%" #reg ", %0" \
|
|
||||||
: "=X" (mmx_trace) \
|
|
||||||
: /* nothing */); \
|
|
||||||
printf(#reg "=0x%08x%08x\n", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
}
|
|
||||||
|
|
||||||
#define mmx_m2r(op, mem, reg) \
|
|
||||||
{ \
|
|
||||||
mmx_t mmx_trace; \
|
|
||||||
mmx_trace = (mem); \
|
|
||||||
printf(#op "_m2r(" #mem "=0x%08x%08x, ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
__asm__ __volatile__ ("movq %%" #reg ", %0" \
|
|
||||||
: "=X" (mmx_trace) \
|
|
||||||
: /* nothing */); \
|
|
||||||
printf(#reg "=0x%08x%08x) => ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
__asm__ __volatile__ (#op " %0, %%" #reg \
|
|
||||||
: /* nothing */ \
|
|
||||||
: "X" (mem)); \
|
|
||||||
__asm__ __volatile__ ("movq %%" #reg ", %0" \
|
|
||||||
: "=X" (mmx_trace) \
|
|
||||||
: /* nothing */); \
|
|
||||||
printf(#reg "=0x%08x%08x\n", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
}
|
|
||||||
|
|
||||||
#define mmx_r2m(op, reg, mem) \
|
|
||||||
{ \
|
|
||||||
mmx_t mmx_trace; \
|
|
||||||
__asm__ __volatile__ ("movq %%" #reg ", %0" \
|
|
||||||
: "=X" (mmx_trace) \
|
|
||||||
: /* nothing */); \
|
|
||||||
printf(#op "_r2m(" #reg "=0x%08x%08x, ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
mmx_trace = (mem); \
|
|
||||||
printf(#mem "=0x%08x%08x) => ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
__asm__ __volatile__ (#op " %%" #reg ", %0" \
|
|
||||||
: "=X" (mem) \
|
|
||||||
: /* nothing */); \
|
|
||||||
mmx_trace = (mem); \
|
|
||||||
printf(#mem "=0x%08x%08x\n", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
}
|
|
||||||
|
|
||||||
#define mmx_r2r(op, regs, regd) \
|
|
||||||
{ \
|
|
||||||
mmx_t mmx_trace; \
|
|
||||||
__asm__ __volatile__ ("movq %%" #regs ", %0" \
|
|
||||||
: "=X" (mmx_trace) \
|
|
||||||
: /* nothing */); \
|
|
||||||
printf(#op "_r2r(" #regs "=0x%08x%08x, ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
__asm__ __volatile__ ("movq %%" #regd ", %0" \
|
|
||||||
: "=X" (mmx_trace) \
|
|
||||||
: /* nothing */); \
|
|
||||||
printf(#regd "=0x%08x%08x) => ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
__asm__ __volatile__ (#op " %" #regs ", %" #regd); \
|
|
||||||
__asm__ __volatile__ ("movq %%" #regd ", %0" \
|
|
||||||
: "=X" (mmx_trace) \
|
|
||||||
: /* nothing */); \
|
|
||||||
printf(#regd "=0x%08x%08x\n", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
}
|
|
||||||
|
|
||||||
#define mmx_m2m(op, mems, memd) \
|
|
||||||
{ \
|
|
||||||
mmx_t mmx_trace; \
|
|
||||||
mmx_trace = (mems); \
|
|
||||||
printf(#op "_m2m(" #mems "=0x%08x%08x, ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
mmx_trace = (memd); \
|
|
||||||
printf(#memd "=0x%08x%08x) => ", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
__asm__ __volatile__ ("movq %0, %%mm0\n\t" \
|
|
||||||
#op " %1, %%mm0\n\t" \
|
|
||||||
"movq %%mm0, %0" \
|
|
||||||
: "=X" (memd) \
|
|
||||||
: "X" (mems)); \
|
|
||||||
mmx_trace = (memd); \
|
|
||||||
printf(#memd "=0x%08x%08x\n", \
|
|
||||||
mmx_trace.d[1], mmx_trace.d[0]); \
|
|
||||||
}
|
|
||||||
|
|
||||||
#else
|
|
||||||
|
|
||||||
/* These macros are a lot simpler without the tracing...
|
|
||||||
*/
|
|
||||||
|
|
||||||
#define mmx_i2r(op, imm, reg) \
|
|
||||||
__asm__ __volatile__ (#op " %0, %%" #reg \
|
|
||||||
: /* nothing */ \
|
|
||||||
: "X" (imm))
|
|
||||||
|
|
||||||
#define mmx_m2r(op, mem, reg) \
|
|
||||||
__asm__ __volatile__ (#op " %0, %%" #reg \
|
|
||||||
: /* nothing */ \
|
|
||||||
: "X" (mem))
|
|
||||||
|
|
||||||
#define mmx_r2m(op, reg, mem) \
|
|
||||||
__asm__ __volatile__ (#op " %%" #reg ", %0" \
|
|
||||||
: "=X" (mem) \
|
|
||||||
: /* nothing */)
|
|
||||||
|
|
||||||
#define mmx_r2r(op, regs, regd) \
|
|
||||||
__asm__ __volatile__ (#op " %" #regs ", %" #regd)
|
|
||||||
|
|
||||||
#define mmx_m2m(op, mems, memd) \
|
|
||||||
__asm__ __volatile__ ("movq %0, %%mm0\n\t" \
|
|
||||||
#op " %1, %%mm0\n\t" \
|
|
||||||
"movq %%mm0, %0" \
|
|
||||||
: "=X" (memd) \
|
|
||||||
: "X" (mems))
|
|
||||||
|
|
||||||
#endif
|
|
||||||
|
|
||||||
|
|
||||||
/* 1x64 MOVe Quadword
|
|
||||||
* (this is both a load and a store...
|
|
||||||
* in fact, it is the only way to store)
|
|
||||||
*/
|
|
||||||
#define movq_m2r(var, reg) mmx_m2r(movq, var, reg)
|
|
||||||
#define movq_r2m(reg, var) mmx_r2m(movq, reg, var)
|
|
||||||
#define movq_r2r(regs, regd) mmx_r2r(movq, regs, regd)
|
|
||||||
#define movq(vars, vard) \
|
|
||||||
__asm__ __volatile__ ("movq %1, %%mm0\n\t" \
|
|
||||||
"movq %%mm0, %0" \
|
|
||||||
: "=X" (vard) \
|
|
||||||
: "X" (vars))
|
|
||||||
|
|
||||||
|
|
||||||
/* 1x32 MOVe Doubleword
|
|
||||||
* (like movq, this is both load and store...
|
|
||||||
* but is most useful for moving things between
|
|
||||||
* mmx registers and ordinary registers)
|
|
||||||
*/
|
|
||||||
#define movd_m2r(var, reg) mmx_m2r(movd, var, reg)
|
|
||||||
#define movd_r2m(reg, var) mmx_r2m(movd, reg, var)
|
|
||||||
#define movd_r2r(regs, regd) mmx_r2r(movd, regs, regd)
|
|
||||||
#define movd(vars, vard) \
|
|
||||||
__asm__ __volatile__ ("movd %1, %%mm0\n\t" \
|
|
||||||
"movd %%mm0, %0" \
|
|
||||||
: "=X" (vard) \
|
|
||||||
: "X" (vars))
|
|
||||||
|
|
||||||
|
|
||||||
/* 2x32, 4x16, and 8x8 Parallel ADDs
|
|
||||||
*/
|
|
||||||
#define paddd_m2r(var, reg) mmx_m2r(paddd, var, reg)
|
|
||||||
#define paddd_r2r(regs, regd) mmx_r2r(paddd, regs, regd)
|
|
||||||
#define paddd(vars, vard) mmx_m2m(paddd, vars, vard)
|
|
||||||
|
|
||||||
#define paddw_m2r(var, reg) mmx_m2r(paddw, var, reg)
|
|
||||||
#define paddw_r2r(regs, regd) mmx_r2r(paddw, regs, regd)
|
|
||||||
#define paddw(vars, vard) mmx_m2m(paddw, vars, vard)
|
|
||||||
|
|
||||||
#define paddb_m2r(var, reg) mmx_m2r(paddb, var, reg)
|
|
||||||
#define paddb_r2r(regs, regd) mmx_r2r(paddb, regs, regd)
|
|
||||||
#define paddb(vars, vard) mmx_m2m(paddb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 4x16 and 8x8 Parallel ADDs using Saturation arithmetic
|
|
||||||
*/
|
|
||||||
#define paddsw_m2r(var, reg) mmx_m2r(paddsw, var, reg)
|
|
||||||
#define paddsw_r2r(regs, regd) mmx_r2r(paddsw, regs, regd)
|
|
||||||
#define paddsw(vars, vard) mmx_m2m(paddsw, vars, vard)
|
|
||||||
|
|
||||||
#define paddsb_m2r(var, reg) mmx_m2r(paddsb, var, reg)
|
|
||||||
#define paddsb_r2r(regs, regd) mmx_r2r(paddsb, regs, regd)
|
|
||||||
#define paddsb(vars, vard) mmx_m2m(paddsb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 4x16 and 8x8 Parallel ADDs using Unsigned Saturation arithmetic
|
|
||||||
*/
|
|
||||||
#define paddusw_m2r(var, reg) mmx_m2r(paddusw, var, reg)
|
|
||||||
#define paddusw_r2r(regs, regd) mmx_r2r(paddusw, regs, regd)
|
|
||||||
#define paddusw(vars, vard) mmx_m2m(paddusw, vars, vard)
|
|
||||||
|
|
||||||
#define paddusb_m2r(var, reg) mmx_m2r(paddusb, var, reg)
|
|
||||||
#define paddusb_r2r(regs, regd) mmx_r2r(paddusb, regs, regd)
|
|
||||||
#define paddusb(vars, vard) mmx_m2m(paddusb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 2x32, 4x16, and 8x8 Parallel SUBs
|
|
||||||
*/
|
|
||||||
#define psubd_m2r(var, reg) mmx_m2r(psubd, var, reg)
|
|
||||||
#define psubd_r2r(regs, regd) mmx_r2r(psubd, regs, regd)
|
|
||||||
#define psubd(vars, vard) mmx_m2m(psubd, vars, vard)
|
|
||||||
|
|
||||||
#define psubw_m2r(var, reg) mmx_m2r(psubw, var, reg)
|
|
||||||
#define psubw_r2r(regs, regd) mmx_r2r(psubw, regs, regd)
|
|
||||||
#define psubw(vars, vard) mmx_m2m(psubw, vars, vard)
|
|
||||||
|
|
||||||
#define psubb_m2r(var, reg) mmx_m2r(psubb, var, reg)
|
|
||||||
#define psubb_r2r(regs, regd) mmx_r2r(psubb, regs, regd)
|
|
||||||
#define psubb(vars, vard) mmx_m2m(psubb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 4x16 and 8x8 Parallel SUBs using Saturation arithmetic
|
|
||||||
*/
|
|
||||||
#define psubsw_m2r(var, reg) mmx_m2r(psubsw, var, reg)
|
|
||||||
#define psubsw_r2r(regs, regd) mmx_r2r(psubsw, regs, regd)
|
|
||||||
#define psubsw(vars, vard) mmx_m2m(psubsw, vars, vard)
|
|
||||||
|
|
||||||
#define psubsb_m2r(var, reg) mmx_m2r(psubsb, var, reg)
|
|
||||||
#define psubsb_r2r(regs, regd) mmx_r2r(psubsb, regs, regd)
|
|
||||||
#define psubsb(vars, vard) mmx_m2m(psubsb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 4x16 and 8x8 Parallel SUBs using Unsigned Saturation arithmetic
|
|
||||||
*/
|
|
||||||
#define psubusw_m2r(var, reg) mmx_m2r(psubusw, var, reg)
|
|
||||||
#define psubusw_r2r(regs, regd) mmx_r2r(psubusw, regs, regd)
|
|
||||||
#define psubusw(vars, vard) mmx_m2m(psubusw, vars, vard)
|
|
||||||
|
|
||||||
#define psubusb_m2r(var, reg) mmx_m2r(psubusb, var, reg)
|
|
||||||
#define psubusb_r2r(regs, regd) mmx_r2r(psubusb, regs, regd)
|
|
||||||
#define psubusb(vars, vard) mmx_m2m(psubusb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 4x16 Parallel MULs giving Low 4x16 portions of results
|
|
||||||
*/
|
|
||||||
#define pmullw_m2r(var, reg) mmx_m2r(pmullw, var, reg)
|
|
||||||
#define pmullw_r2r(regs, regd) mmx_r2r(pmullw, regs, regd)
|
|
||||||
#define pmullw(vars, vard) mmx_m2m(pmullw, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 4x16 Parallel MULs giving High 4x16 portions of results
|
|
||||||
*/
|
|
||||||
#define pmulhw_m2r(var, reg) mmx_m2r(pmulhw, var, reg)
|
|
||||||
#define pmulhw_r2r(regs, regd) mmx_r2r(pmulhw, regs, regd)
|
|
||||||
#define pmulhw(vars, vard) mmx_m2m(pmulhw, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 4x16->2x32 Parallel Mul-ADD
|
|
||||||
* (muls like pmullw, then adds adjacent 16-bit fields
|
|
||||||
* in the multiply result to make the final 2x32 result)
|
|
||||||
*/
|
|
||||||
#define pmaddwd_m2r(var, reg) mmx_m2r(pmaddwd, var, reg)
|
|
||||||
#define pmaddwd_r2r(regs, regd) mmx_r2r(pmaddwd, regs, regd)
|
|
||||||
#define pmaddwd(vars, vard) mmx_m2m(pmaddwd, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 1x64 bitwise AND
|
|
||||||
*/
|
|
||||||
#ifdef BROKEN_PAND
|
|
||||||
#define pand_m2r(var, reg) \
|
|
||||||
{ \
|
|
||||||
mmx_m2r(pandn, (mmx_t)-1LL, reg); \
|
|
||||||
mmx_m2r(pandn, var, reg); \
|
|
||||||
}
|
|
||||||
#define pand_r2r(regs, regd) \
|
|
||||||
{ \
|
|
||||||
mmx_m2r(pandn, (mmx_t)-1LL, regd); \
|
|
||||||
mmx_r2r(pandn, regs, regd) \
|
|
||||||
}
|
|
||||||
#define pand(vars, vard) \
|
|
||||||
{ \
|
|
||||||
movq_m2r(vard, mm0); \
|
|
||||||
mmx_m2r(pandn, (mmx_t)-1LL, mm0); \
|
|
||||||
mmx_m2r(pandn, vars, mm0); \
|
|
||||||
movq_r2m(mm0, vard); \
|
|
||||||
}
|
|
||||||
#else
|
|
||||||
#define pand_m2r(var, reg) mmx_m2r(pand, var, reg)
|
|
||||||
#define pand_r2r(regs, regd) mmx_r2r(pand, regs, regd)
|
|
||||||
#define pand(vars, vard) mmx_m2m(pand, vars, vard)
|
|
||||||
#endif
|
|
||||||
|
|
||||||
|
|
||||||
/* 1x64 bitwise AND with Not the destination
|
|
||||||
*/
|
|
||||||
#define pandn_m2r(var, reg) mmx_m2r(pandn, var, reg)
|
|
||||||
#define pandn_r2r(regs, regd) mmx_r2r(pandn, regs, regd)
|
|
||||||
#define pandn(vars, vard) mmx_m2m(pandn, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 1x64 bitwise OR
|
|
||||||
*/
|
|
||||||
#define por_m2r(var, reg) mmx_m2r(por, var, reg)
|
|
||||||
#define por_r2r(regs, regd) mmx_r2r(por, regs, regd)
|
|
||||||
#define por(vars, vard) mmx_m2m(por, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 1x64 bitwise eXclusive OR
|
|
||||||
*/
|
|
||||||
#define pxor_m2r(var, reg) mmx_m2r(pxor, var, reg)
|
|
||||||
#define pxor_r2r(regs, regd) mmx_r2r(pxor, regs, regd)
|
|
||||||
#define pxor(vars, vard) mmx_m2m(pxor, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 2x32, 4x16, and 8x8 Parallel CoMPare for EQuality
|
|
||||||
* (resulting fields are either 0 or -1)
|
|
||||||
*/
|
|
||||||
#define pcmpeqd_m2r(var, reg) mmx_m2r(pcmpeqd, var, reg)
|
|
||||||
#define pcmpeqd_r2r(regs, regd) mmx_r2r(pcmpeqd, regs, regd)
|
|
||||||
#define pcmpeqd(vars, vard) mmx_m2m(pcmpeqd, vars, vard)
|
|
||||||
|
|
||||||
#define pcmpeqw_m2r(var, reg) mmx_m2r(pcmpeqw, var, reg)
|
|
||||||
#define pcmpeqw_r2r(regs, regd) mmx_r2r(pcmpeqw, regs, regd)
|
|
||||||
#define pcmpeqw(vars, vard) mmx_m2m(pcmpeqw, vars, vard)
|
|
||||||
|
|
||||||
#define pcmpeqb_m2r(var, reg) mmx_m2r(pcmpeqb, var, reg)
|
|
||||||
#define pcmpeqb_r2r(regs, regd) mmx_r2r(pcmpeqb, regs, regd)
|
|
||||||
#define pcmpeqb(vars, vard) mmx_m2m(pcmpeqb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 2x32, 4x16, and 8x8 Parallel CoMPare for Greater Than
|
|
||||||
* (resulting fields are either 0 or -1)
|
|
||||||
*/
|
|
||||||
#define pcmpgtd_m2r(var, reg) mmx_m2r(pcmpgtd, var, reg)
|
|
||||||
#define pcmpgtd_r2r(regs, regd) mmx_r2r(pcmpgtd, regs, regd)
|
|
||||||
#define pcmpgtd(vars, vard) mmx_m2m(pcmpgtd, vars, vard)
|
|
||||||
|
|
||||||
#define pcmpgtw_m2r(var, reg) mmx_m2r(pcmpgtw, var, reg)
|
|
||||||
#define pcmpgtw_r2r(regs, regd) mmx_r2r(pcmpgtw, regs, regd)
|
|
||||||
#define pcmpgtw(vars, vard) mmx_m2m(pcmpgtw, vars, vard)
|
|
||||||
|
|
||||||
#define pcmpgtb_m2r(var, reg) mmx_m2r(pcmpgtb, var, reg)
|
|
||||||
#define pcmpgtb_r2r(regs, regd) mmx_r2r(pcmpgtb, regs, regd)
|
|
||||||
#define pcmpgtb(vars, vard) mmx_m2m(pcmpgtb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 1x64, 2x32, and 4x16 Parallel Shift Left Logical
|
|
||||||
*/
|
|
||||||
#define psllq_i2r(imm, reg) mmx_i2r(psllq, imm, reg)
|
|
||||||
#define psllq_m2r(var, reg) mmx_m2r(psllq, var, reg)
|
|
||||||
#define psllq_r2r(regs, regd) mmx_r2r(psllq, regs, regd)
|
|
||||||
#define psllq(vars, vard) mmx_m2m(psllq, vars, vard)
|
|
||||||
|
|
||||||
#define pslld_i2r(imm, reg) mmx_i2r(pslld, imm, reg)
|
|
||||||
#define pslld_m2r(var, reg) mmx_m2r(pslld, var, reg)
|
|
||||||
#define pslld_r2r(regs, regd) mmx_r2r(pslld, regs, regd)
|
|
||||||
#define pslld(vars, vard) mmx_m2m(pslld, vars, vard)
|
|
||||||
|
|
||||||
#define psllw_i2r(imm, reg) mmx_i2r(psllw, imm, reg)
|
|
||||||
#define psllw_m2r(var, reg) mmx_m2r(psllw, var, reg)
|
|
||||||
#define psllw_r2r(regs, regd) mmx_r2r(psllw, regs, regd)
|
|
||||||
#define psllw(vars, vard) mmx_m2m(psllw, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 1x64, 2x32, and 4x16 Parallel Shift Right Logical
|
|
||||||
*/
|
|
||||||
#define psrlq_i2r(imm, reg) mmx_i2r(psrlq, imm, reg)
|
|
||||||
#define psrlq_m2r(var, reg) mmx_m2r(psrlq, var, reg)
|
|
||||||
#define psrlq_r2r(regs, regd) mmx_r2r(psrlq, regs, regd)
|
|
||||||
#define psrlq(vars, vard) mmx_m2m(psrlq, vars, vard)
|
|
||||||
|
|
||||||
#define psrld_i2r(imm, reg) mmx_i2r(psrld, imm, reg)
|
|
||||||
#define psrld_m2r(var, reg) mmx_m2r(psrld, var, reg)
|
|
||||||
#define psrld_r2r(regs, regd) mmx_r2r(psrld, regs, regd)
|
|
||||||
#define psrld(vars, vard) mmx_m2m(psrld, vars, vard)
|
|
||||||
|
|
||||||
#define psrlw_i2r(imm, reg) mmx_i2r(psrlw, imm, reg)
|
|
||||||
#define psrlw_m2r(var, reg) mmx_m2r(psrlw, var, reg)
|
|
||||||
#define psrlw_r2r(regs, regd) mmx_r2r(psrlw, regs, regd)
|
|
||||||
#define psrlw(vars, vard) mmx_m2m(psrlw, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 2x32 and 4x16 Parallel Shift Right Arithmetic
|
|
||||||
*/
|
|
||||||
#define psrad_i2r(imm, reg) mmx_i2r(psrad, imm, reg)
|
|
||||||
#define psrad_m2r(var, reg) mmx_m2r(psrad, var, reg)
|
|
||||||
#define psrad_r2r(regs, regd) mmx_r2r(psrad, regs, regd)
|
|
||||||
#define psrad(vars, vard) mmx_m2m(psrad, vars, vard)
|
|
||||||
|
|
||||||
#define psraw_i2r(imm, reg) mmx_i2r(psraw, imm, reg)
|
|
||||||
#define psraw_m2r(var, reg) mmx_m2r(psraw, var, reg)
|
|
||||||
#define psraw_r2r(regs, regd) mmx_r2r(psraw, regs, regd)
|
|
||||||
#define psraw(vars, vard) mmx_m2m(psraw, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 2x32->4x16 and 4x16->8x8 PACK and Signed Saturate
|
|
||||||
* (packs source and dest fields into dest in that order)
|
|
||||||
*/
|
|
||||||
#define packssdw_m2r(var, reg) mmx_m2r(packssdw, var, reg)
|
|
||||||
#define packssdw_r2r(regs, regd) mmx_r2r(packssdw, regs, regd)
|
|
||||||
#define packssdw(vars, vard) mmx_m2m(packssdw, vars, vard)
|
|
||||||
|
|
||||||
#define packsswb_m2r(var, reg) mmx_m2r(packsswb, var, reg)
|
|
||||||
#define packsswb_r2r(regs, regd) mmx_r2r(packsswb, regs, regd)
|
|
||||||
#define packsswb(vars, vard) mmx_m2m(packsswb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 4x16->8x8 PACK and Unsigned Saturate
|
|
||||||
* (packs source and dest fields into dest in that order)
|
|
||||||
*/
|
|
||||||
#define packuswb_m2r(var, reg) mmx_m2r(packuswb, var, reg)
|
|
||||||
#define packuswb_r2r(regs, regd) mmx_r2r(packuswb, regs, regd)
|
|
||||||
#define packuswb(vars, vard) mmx_m2m(packuswb, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 2x32->1x64, 4x16->2x32, and 8x8->4x16 UNPaCK Low
|
|
||||||
* (interleaves low half of dest with low half of source
|
|
||||||
* as padding in each result field)
|
|
||||||
*/
|
|
||||||
#define punpckldq_m2r(var, reg) mmx_m2r(punpckldq, var, reg)
|
|
||||||
#define punpckldq_r2r(regs, regd) mmx_r2r(punpckldq, regs, regd)
|
|
||||||
#define punpckldq(vars, vard) mmx_m2m(punpckldq, vars, vard)
|
|
||||||
|
|
||||||
#define punpcklwd_m2r(var, reg) mmx_m2r(punpcklwd, var, reg)
|
|
||||||
#define punpcklwd_r2r(regs, regd) mmx_r2r(punpcklwd, regs, regd)
|
|
||||||
#define punpcklwd(vars, vard) mmx_m2m(punpcklwd, vars, vard)
|
|
||||||
|
|
||||||
#define punpcklbw_m2r(var, reg) mmx_m2r(punpcklbw, var, reg)
|
|
||||||
#define punpcklbw_r2r(regs, regd) mmx_r2r(punpcklbw, regs, regd)
|
|
||||||
#define punpcklbw(vars, vard) mmx_m2m(punpcklbw, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* 2x32->1x64, 4x16->2x32, and 8x8->4x16 UNPaCK High
|
|
||||||
* (interleaves high half of dest with high half of source
|
|
||||||
* as padding in each result field)
|
|
||||||
*/
|
|
||||||
#define punpckhdq_m2r(var, reg) mmx_m2r(punpckhdq, var, reg)
|
|
||||||
#define punpckhdq_r2r(regs, regd) mmx_r2r(punpckhdq, regs, regd)
|
|
||||||
#define punpckhdq(vars, vard) mmx_m2m(punpckhdq, vars, vard)
|
|
||||||
|
|
||||||
#define punpckhwd_m2r(var, reg) mmx_m2r(punpckhwd, var, reg)
|
|
||||||
#define punpckhwd_r2r(regs, regd) mmx_r2r(punpckhwd, regs, regd)
|
|
||||||
#define punpckhwd(vars, vard) mmx_m2m(punpckhwd, vars, vard)
|
|
||||||
|
|
||||||
#define punpckhbw_m2r(var, reg) mmx_m2r(punpckhbw, var, reg)
|
|
||||||
#define punpckhbw_r2r(regs, regd) mmx_r2r(punpckhbw, regs, regd)
|
|
||||||
#define punpckhbw(vars, vard) mmx_m2m(punpckhbw, vars, vard)
|
|
||||||
|
|
||||||
|
|
||||||
/* Empty MMx State
|
|
||||||
* (used to clean-up when going from mmx to float use
|
|
||||||
* of the registers that are shared by both; note that
|
|
||||||
* there is no float-to-mmx operation needed, because
|
|
||||||
* only the float tag word info is corruptible)
|
|
||||||
*/
|
|
||||||
#ifdef MMX_TRACE
|
|
||||||
|
|
||||||
#define emms() \
|
|
||||||
{ \
|
|
||||||
printf("emms()\n"); \
|
|
||||||
__asm__ __volatile__ ("emms"); \
|
|
||||||
}
|
|
||||||
|
|
||||||
#else
|
|
||||||
|
|
||||||
#define emms() __asm__ __volatile__ ("emms")
|
|
||||||
|
|
||||||
#endif
|
|
||||||
|
|
||||||
|
|
||||||
#endif /* _MMX_H_ */
|
|
||||||
Loading…
Reference in New Issue