ops_sse.h revision 178d85b8274f9ac82fb553c80760bbbb4044401c
/*
*
* Copyright (c) 2005 Fabrice Bellard
* Copyright (c) 2008 Intel Corporation <andrew.zaborowski@intel.com>
*
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
/*
* Oracle LGPL Disclaimer: For the avoidance of doubt, except that if any license choice
* other than GPL or LGPL is available it will apply instead, Oracle elects to use only
* the Lesser General Public License version 2.1 (LGPLv2) at this time for any software where
* a choice of LGPL license versions is made available with the language indicating
* that LGPLv2 or any later version may be used, or where a choice of which version
* of the LGPL is applied is otherwise unspecified.
*/
#if SHIFT == 0
#define XMM_ONLY(x...)
#define B(n) MMX_B(n)
#define W(n) MMX_W(n)
#define L(n) MMX_L(n)
#define Q(n) q
#else
#define XMM_ONLY(x...) x
#define B(n) XMM_B(n)
#define W(n) XMM_W(n)
#define L(n) XMM_L(n)
#define Q(n) XMM_Q(n)
#endif
{
int shift;
if (s->Q(0) > 15) {
d->Q(0) = 0;
#if SHIFT == 1
d->Q(1) = 0;
#endif
} else {
shift = s->B(0);
d->W(0) >>= shift;
d->W(1) >>= shift;
d->W(2) >>= shift;
d->W(3) >>= shift;
#if SHIFT == 1
d->W(4) >>= shift;
d->W(5) >>= shift;
d->W(6) >>= shift;
d->W(7) >>= shift;
#endif
}
FORCE_RET();
}
{
int shift;
if (s->Q(0) > 15) {
shift = 15;
} else {
shift = s->B(0);
}
#if SHIFT == 1
#endif
}
{
int shift;
if (s->Q(0) > 15) {
d->Q(0) = 0;
#if SHIFT == 1
d->Q(1) = 0;
#endif
} else {
shift = s->B(0);
d->W(0) <<= shift;
d->W(1) <<= shift;
d->W(2) <<= shift;
d->W(3) <<= shift;
#if SHIFT == 1
d->W(4) <<= shift;
d->W(5) <<= shift;
d->W(6) <<= shift;
d->W(7) <<= shift;
#endif
}
FORCE_RET();
}
{
int shift;
if (s->Q(0) > 31) {
d->Q(0) = 0;
#if SHIFT == 1
d->Q(1) = 0;
#endif
} else {
shift = s->B(0);
d->L(0) >>= shift;
d->L(1) >>= shift;
#if SHIFT == 1
d->L(2) >>= shift;
d->L(3) >>= shift;
#endif
}
FORCE_RET();
}
{
int shift;
if (s->Q(0) > 31) {
shift = 31;
} else {
shift = s->B(0);
}
#if SHIFT == 1
#endif
}
{
int shift;
if (s->Q(0) > 31) {
d->Q(0) = 0;
#if SHIFT == 1
d->Q(1) = 0;
#endif
} else {
shift = s->B(0);
d->L(0) <<= shift;
d->L(1) <<= shift;
#if SHIFT == 1
d->L(2) <<= shift;
d->L(3) <<= shift;
#endif
}
FORCE_RET();
}
{
int shift;
if (s->Q(0) > 63) {
d->Q(0) = 0;
#if SHIFT == 1
d->Q(1) = 0;
#endif
} else {
shift = s->B(0);
d->Q(0) >>= shift;
#if SHIFT == 1
d->Q(1) >>= shift;
#endif
}
FORCE_RET();
}
{
int shift;
if (s->Q(0) > 63) {
d->Q(0) = 0;
#if SHIFT == 1
d->Q(1) = 0;
#endif
} else {
shift = s->B(0);
d->Q(0) <<= shift;
#if SHIFT == 1
d->Q(1) <<= shift;
#endif
}
FORCE_RET();
}
#if SHIFT == 1
{
int shift, i;
shift = s->L(0);
if (shift > 16)
shift = 16;
for(i = 0; i < 16 - shift; i++)
d->B(i) = d->B(i + shift);
d->B(i) = 0;
FORCE_RET();
}
{
int shift, i;
shift = s->L(0);
if (shift > 16)
shift = 16;
for(i = 15; i >= shift; i--)
d->B(i) = d->B(i - shift);
for(i = 0; i < shift; i++)
d->B(i) = 0;
FORCE_RET();
}
#endif
#define SSE_HELPER_B(name, F)\
{\
d->B(0) = F(d->B(0), s->B(0));\
d->B(1) = F(d->B(1), s->B(1));\
d->B(2) = F(d->B(2), s->B(2));\
d->B(3) = F(d->B(3), s->B(3));\
d->B(4) = F(d->B(4), s->B(4));\
d->B(5) = F(d->B(5), s->B(5));\
d->B(6) = F(d->B(6), s->B(6));\
d->B(7) = F(d->B(7), s->B(7));\
XMM_ONLY(\
d->B(8) = F(d->B(8), s->B(8));\
d->B(9) = F(d->B(9), s->B(9));\
d->B(10) = F(d->B(10), s->B(10));\
d->B(11) = F(d->B(11), s->B(11));\
d->B(12) = F(d->B(12), s->B(12));\
d->B(13) = F(d->B(13), s->B(13));\
d->B(14) = F(d->B(14), s->B(14));\
d->B(15) = F(d->B(15), s->B(15));\
)\
}
#define SSE_HELPER_W(name, F)\
{\
d->W(0) = F(d->W(0), s->W(0));\
d->W(1) = F(d->W(1), s->W(1));\
d->W(2) = F(d->W(2), s->W(2));\
d->W(3) = F(d->W(3), s->W(3));\
XMM_ONLY(\
d->W(4) = F(d->W(4), s->W(4));\
d->W(5) = F(d->W(5), s->W(5));\
d->W(6) = F(d->W(6), s->W(6));\
d->W(7) = F(d->W(7), s->W(7));\
)\
}
#define SSE_HELPER_L(name, F)\
{\
d->L(0) = F(d->L(0), s->L(0));\
d->L(1) = F(d->L(1), s->L(1));\
XMM_ONLY(\
d->L(2) = F(d->L(2), s->L(2));\
d->L(3) = F(d->L(3), s->L(3));\
)\
}
#define SSE_HELPER_Q(name, F)\
{\
d->Q(0) = F(d->Q(0), s->Q(0));\
XMM_ONLY(\
d->Q(1) = F(d->Q(1), s->Q(1));\
)\
}
#if SHIFT == 0
static inline int satub(int x)
{
if (x < 0)
return 0;
else if (x > 255)
return 255;
else
return x;
}
static inline int satuw(int x)
{
if (x < 0)
return 0;
else if (x > 65535)
return 65535;
else
return x;
}
static inline int satsb(int x)
{
if (x < -128)
return -128;
else if (x > 127)
return 127;
else
return x;
}
static inline int satsw(int x)
{
if (x < -32768)
return -32768;
else if (x > 32767)
return 32767;
else
return x;
}
#define FADD(a, b) ((a) + (b))
#define FSUB(a, b) ((a) - (b))
#define FMINUB(a, b) ((a) < (b)) ? (a) : (b)
#define FMAXUB(a, b) ((a) > (b)) ? (a) : (b)
#define FAND(a, b) (a) & (b)
#define FANDN(a, b) ((~(a)) & (b))
#define FOR(a, b) (a) | (b)
#define FXOR(a, b) (a) ^ (b)
#define FCMPEQ(a, b) (a) == (b) ? -1 : 0
#define FMULLW(a, b) (a) * (b)
#define FMULHUW(a, b) (a) * (b) >> 16
#endif
#if SHIFT == 0
#endif
{
#if SHIFT == 1
#endif
}
{
int i;
for(i = 0; i < (2 << SHIFT); i++) {
}
FORCE_RET();
}
#if SHIFT == 0
static inline int abs1(int a)
{
if (a < 0)
return -a;
else
return a;
}
#endif
{
unsigned int val;
val = 0;
d->Q(0) = val;
#if SHIFT == 1
val = 0;
d->Q(1) = val;
#endif
}
{
int i;
for(i = 0; i < (8 << SHIFT); i++) {
if (s->B(i) & 0x80)
}
FORCE_RET();
}
{
d->L(0) = val;
d->L(1) = 0;
#if SHIFT == 1
d->Q(1) = 0;
#endif
}
#ifdef TARGET_X86_64
{
d->Q(0) = val;
#if SHIFT == 1
d->Q(1) = 0;
#endif
}
#endif
#if SHIFT == 0
{
Reg r;
r.W(0) = s->W(order & 3);
*d = r;
}
#else
{
Reg r;
r.L(0) = d->L(order & 3);
*d = r;
}
{
Reg r;
r.Q(0) = d->Q(order & 1);
*d = r;
}
{
Reg r;
r.L(0) = s->L(order & 3);
*d = r;
}
{
Reg r;
r.W(0) = s->W(order & 3);
r.Q(1) = s->Q(1);
*d = r;
}
{
Reg r;
r.Q(0) = s->Q(0);
*d = r;
}
#endif
#if SHIFT == 1
/* FPU ops */
/* XXX: not accurate */
#define SSE_HELPER_S(name, F)\
{\
}\
\
{\
}\
{\
}\
\
{\
}
/* float to float conversions */
{
}
{
d->Q(1) = 0;
}
{
}
{
}
/* integer to float */
{
}
{
}
{
}
{
}
{
}
{
}
#ifdef TARGET_X86_64
{
}
{
}
#endif
/* float to integer */
{
}
{
d->XMM_Q(1) = 0;
}
{
}
{
}
{
}
{
}
#ifdef TARGET_X86_64
{
}
{
}
#endif
/* float to integer truncated */
{
}
{
d->XMM_Q(1) = 0;
}
{
}
{
}
{
}
{
}
#ifdef TARGET_X86_64
{
}
{
}
#endif
{
}
{
}
{
}
{
}
{
XMMReg r;
*d = r;
}
{
XMMReg r;
*d = r;
}
{
XMMReg r;
*d = r;
}
{
XMMReg r;
*d = r;
}
{
}
{
}
/* XXX: unordered */
#define SSE_HELPER_CMP(name, F)\
{\
}\
\
{\
}\
{\
}\
\
{\
}
{
int ret;
FORCE_RET();
}
{
int ret;
FORCE_RET();
}
{
int ret;
FORCE_RET();
}
{
int ret;
FORCE_RET();
}
{
}
{
}
#endif
{
val = 0;
#if SHIFT == 1
#endif
return val;
}
{
Reg r;
#if SHIFT == 1
#endif
#if SHIFT == 1
#endif
*d = r;
}
{
Reg r;
#if SHIFT == 1
#endif
#if SHIFT == 1
#endif
*d = r;
}
{
Reg r;
r.W(0) = satsw(d->L(0));
#if SHIFT == 1
#endif
#if SHIFT == 1
#endif
*d = r;
}
\
{ \
Reg r; \
\
XMM_ONLY( \
) \
*d = r; \
} \
\
{ \
Reg r; \
\
XMM_ONLY( \
) \
*d = r; \
} \
\
{ \
Reg r; \
\
XMM_ONLY( \
) \
*d = r; \
} \
\
XMM_ONLY( \
{ \
Reg r; \
\
r.Q(0) = d->Q(base); \
r.Q(1) = s->Q(base); \
*d = r; \
} \
)
UNPCK_OP(l, 0)
UNPCK_OP(h, 1)
/* 3DNow! float ops */
#if SHIFT == 0
{
}
{
}
{
}
{
}
{
MMXReg r;
*d = r;
}
{
}
{
}
{
}
{
}
{
}
{
}
{
}
{
MMXReg r;
*d = r;
}
{
MMXReg r;
*d = r;
}
{
}
{
}
{
}
{
}
{
MMXReg r;
*d = r;
}
#endif
/* SSSE3 op helpers */
{
int i;
Reg r;
for (i = 0; i < (8 << SHIFT); i++)
*d = r;
}
{
}
{
}
{
}
{
#if SHIFT == 1
#endif
}
{
}
{
}
{
}
{
Reg r;
/* XXX could be checked during translation */
r.Q(0) = 0;
XMM_ONLY(r.Q(1) = 0);
} else {
shift <<= 3;
#if SHIFT == 0
#else
#endif
}
*d = r;
}
#if SHIFT == 1
{\
if (num > 2) {\
if (num > 4) {\
if (num > 8) {\
}\
}\
}\
}
{\
if (num > 2) {\
if (num > 4) {\
if (num > 8) {\
}\
}\
}\
}
/* SSE4.1 op helpers */
#define FBLENDVB(d, s, m) (m & 0x80) ? s : d
#define FBLENDVPS(d, s, m) (m & 0x80000000) ? s : d
#define FBLENDVPD(d, s, m) (m & 0x8000000000000000LL) ? s : d
{
}
{\
d->elem(0) = F(0);\
if (num > 3) {\
if (num > 5) {\
}\
}\
}
{
}
#define FCMPEQQ(d, s) d == s ? -1 : 0
{
}
{
int idx = 0;
if (s->W(1) < s->W(idx))
idx = 1;
if (s->W(2) < s->W(idx))
idx = 2;
if (s->W(3) < s->W(idx))
idx = 3;
if (s->W(4) < s->W(idx))
idx = 4;
if (s->W(5) < s->W(idx))
idx = 5;
if (s->W(6) < s->W(idx))
idx = 6;
if (s->W(7) < s->W(idx))
idx = 7;
d->Q(1) = 0;
d->L(1) = 0;
d->W(1) = idx;
d->W(0) = s->W(idx);
}
{
signed char prev_rounding_mode;
switch (mode & 3) {
case 0:
break;
case 1:
break;
case 2:
break;
case 3:
break;
}
#if 0 /* TODO */
&env->sse_status);
#endif
}
{
signed char prev_rounding_mode;
switch (mode & 3) {
case 0:
break;
case 1:
break;
case 2:
break;
case 3:
break;
}
#if 0 /* TODO */
&env->sse_status);
#endif
}
{
signed char prev_rounding_mode;
switch (mode & 3) {
case 0:
break;
case 1:
break;
case 2:
break;
case 3:
break;
}
#if 0 /* TODO */
&env->sse_status);
#endif
}
{
signed char prev_rounding_mode;
switch (mode & 3) {
case 0:
break;
case 1:
break;
case 2:
break;
case 3:
break;
}
#if 0 /* TODO */
&env->sse_status);
#endif
}
#define FBLENDP(d, s, m) m ? s : d
{
&env->sse_status);
&env->sse_status);
&env->sse_status);
&env->sse_status);
}
{
&env->sse_status);
&env->sse_status);
}
{
int i;
Reg r;
for (i = 0; i < 8; i++, d0++) {
r.W(i) = 0;
}
*d = r;
}
/* SSE4.2 op helpers */
/* it's unclear whether signed or unsigned */
#define FCMPGTQ(d, s) d > s ? -1 : 0
{
int val;
/* Presence of REX.W is indicated by a bit higher than 7 set */
if (ctrl >> 8)
else
if (ctrl & 1) {
if (val > 8)
return 8;
} else
if (val > 16)
return 16;
return val;
}
{
int val = 0;
if (ctrl & 1) {
val++;
} else
val++;
return val;
}
{
switch ((ctrl >> 0) & 3) {
case 0:
return r->B(i);
case 1:
return r->W(i);
case 2:
return (int8_t) r->B(i);
case 3:
default:
return (int16_t) r->W(i);
}
}
{
unsigned int res = 0;
int v;
int j, i;
valids--;
validd--;
case 0:
for (j = valids; j >= 0; j--) {
res <<= 1;
for (i = validd; i >= 0; i--)
}
break;
case 1:
for (j = valids; j >= 0; j--) {
res <<= 1;
}
break;
case 2:
res <<= 1;
}
break;
case 3:
res <<= 1;
res |= 1;
}
break;
}
case 1:
break;
case 3:
break;
}
if (res)
if (res & 1)
return res;
}
{
}
return ret;
}
{
}
return ret;
}
{
if (res)
#ifndef VBOX
#else
#endif
else
}
{
int i;
if (ctrl & 1)
d->W(i) = (res & 1) ? ~0 : 0;
else
d->B(i) = (res & 1) ? ~0 : 0;
} else {
d->Q(1) = 0;
d->Q(0) = res;
}
}
{
if (res)
else
}
{
int i;
if (ctrl & 1)
d->W(i) = (res & 1) ? ~0 : 0;
else
d->B(i) = (res & 1) ? ~0 : 0;
} else {
d->Q(1) = 0;
d->Q(0) = res;
}
}
#define CRCPOLY 0x1edc6f41
#define CRCPOLY_BITREV 0x82f63b78
{
while (len--)
return crc;
}
{
n = POPCOUNT(n, 0);
n = POPCOUNT(n, 1);
n = POPCOUNT(n, 2);
n = POPCOUNT(n, 3);
if (type == 1)
return n & 0xff;
n = POPCOUNT(n, 4);
#ifndef TARGET_X86_64
return n;
#else
if (type == 2)
return n & 0xff;
return POPCOUNT(n, 5);
#endif
}
#endif
#undef B
#undef W
#undef L
#undef Q