/*
- * MMX/3DNow!/SSE/SSE2/SSE3/PNI support
+ * MMX/3DNow!/SSE/SSE2/SSE3/SSSE3/SSE4/PNI support
*
* Copyright (c) 2005 Fabrice Bellard
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* 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
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#if SHIFT == 0
#define Reg MMXReg
-#define XMM_ONLY(x...)
+#define XMM_ONLY(...)
#define B(n) MMX_B(n)
#define W(n) MMX_W(n)
#define L(n) MMX_L(n)
#define SUFFIX _mmx
#else
#define Reg XMMReg
-#define XMM_ONLY(x...) x
+#define XMM_ONLY(...) __VA_ARGS__
#define B(n) XMM_B(n)
#define W(n) XMM_W(n)
#define L(n) XMM_L(n)
d->W(7) >>= shift;
#endif
}
- FORCE_RET();
}
void glue(helper_psraw, SUFFIX)(Reg *d, Reg *s)
d->W(7) <<= shift;
#endif
}
- FORCE_RET();
}
void glue(helper_psrld, SUFFIX)(Reg *d, Reg *s)
d->L(3) >>= shift;
#endif
}
- FORCE_RET();
}
void glue(helper_psrad, SUFFIX)(Reg *d, Reg *s)
d->L(3) <<= shift;
#endif
}
- FORCE_RET();
}
void glue(helper_psrlq, SUFFIX)(Reg *d, Reg *s)
d->Q(1) >>= shift;
#endif
}
- FORCE_RET();
}
void glue(helper_psllq, SUFFIX)(Reg *d, Reg *s)
d->Q(1) <<= shift;
#endif
}
- FORCE_RET();
}
#if SHIFT == 1
d->B(i) = d->B(i + shift);
for(i = 16 - shift; i < 16; i++)
d->B(i) = 0;
- FORCE_RET();
}
void glue(helper_pslldq, SUFFIX)(Reg *d, Reg *s)
d->B(i) = d->B(i - shift);
for(i = 0; i < shift; i++)
d->B(i) = 0;
- FORCE_RET();
}
#endif
d->L(i) = (int16_t)s->W(2*i) * (int16_t)d->W(2*i) +
(int16_t)s->W(2*i+1) * (int16_t)d->W(2*i+1);
}
- FORCE_RET();
}
#if SHIFT == 0
#endif
}
-void glue(helper_maskmov, SUFFIX) (Reg *d, Reg *s)
+void glue(helper_maskmov, SUFFIX) (Reg *d, Reg *s, target_ulong a0)
{
int i;
for(i = 0; i < (8 << SHIFT); i++) {
if (s->B(i) & 0x80)
- stb(A0 + i, d->B(i));
+ stb(a0 + i, d->B(i));
}
- FORCE_RET();
}
void glue(helper_movl_mm_T0, SUFFIX) (Reg *d, uint32_t val)
d->XMM_S(0) = approx_rcp(s->XMM_S(0));
}
+static inline uint64_t helper_extrq(uint64_t src, int shift, int len)
+{
+ uint64_t mask;
+
+ if (len == 0) {
+ mask = ~0LL;
+ } else {
+ mask = (1ULL << len) - 1;
+ }
+ return (src >> shift) & mask;
+}
+
+void helper_extrq_r(XMMReg *d, XMMReg *s)
+{
+ d->XMM_Q(0) = helper_extrq(d->XMM_Q(0), s->XMM_B(1), s->XMM_B(0));
+}
+
+void helper_extrq_i(XMMReg *d, int index, int length)
+{
+ d->XMM_Q(0) = helper_extrq(d->XMM_Q(0), index, length);
+}
+
+static inline uint64_t helper_insertq(uint64_t src, int shift, int len)
+{
+ uint64_t mask;
+
+ if (len == 0) {
+ mask = ~0ULL;
+ } else {
+ mask = (1ULL << len) - 1;
+ }
+ return (src & ~(mask << shift)) | ((src & mask) << shift);
+}
+
+void helper_insertq_r(XMMReg *d, XMMReg *s)
+{
+ d->XMM_Q(0) = helper_insertq(s->XMM_Q(0), s->XMM_B(9), s->XMM_B(8));
+}
+
+void helper_insertq_i(XMMReg *d, int index, int length)
+{
+ d->XMM_Q(0) = helper_insertq(d->XMM_Q(0), index, length);
+}
+
void helper_haddps(XMMReg *d, XMMReg *s)
{
XMMReg r;
SSE_HELPER_CMP(cmpnle, FPU_CMPNLE)
SSE_HELPER_CMP(cmpord, FPU_CMPORD)
-const int comis_eflags[4] = {CC_C, CC_Z, 0, CC_Z | CC_P | CC_C};
+static const int comis_eflags[4] = {CC_C, CC_Z, 0, CC_Z | CC_P | CC_C};
void helper_ucomiss(Reg *d, Reg *s)
{
s1 = s->XMM_S(0);
ret = float32_compare_quiet(s0, s1, &env->sse_status);
CC_SRC = comis_eflags[ret + 1];
- FORCE_RET();
}
void helper_comiss(Reg *d, Reg *s)
s1 = s->XMM_S(0);
ret = float32_compare(s0, s1, &env->sse_status);
CC_SRC = comis_eflags[ret + 1];
- FORCE_RET();
}
void helper_ucomisd(Reg *d, Reg *s)
d1 = s->XMM_D(0);
ret = float64_compare_quiet(d0, d1, &env->sse_status);
CC_SRC = comis_eflags[ret + 1];
- FORCE_RET();
}
void helper_comisd(Reg *d, Reg *s)
d1 = s->XMM_D(0);
ret = float64_compare(d0, d1, &env->sse_status);
CC_SRC = comis_eflags[ret + 1];
- FORCE_RET();
}
uint32_t helper_movmskps(Reg *s)
{
uint32_t val;
val = 0;
- val |= (s->XMM_B(0) >> 7);
- val |= (s->XMM_B(1) >> 6) & 0x02;
- val |= (s->XMM_B(2) >> 5) & 0x04;
- val |= (s->XMM_B(3) >> 4) & 0x08;
- val |= (s->XMM_B(4) >> 3) & 0x10;
- val |= (s->XMM_B(5) >> 2) & 0x20;
- val |= (s->XMM_B(6) >> 1) & 0x40;
- val |= (s->XMM_B(7)) & 0x80;
+ val |= (s->B(0) >> 7);
+ val |= (s->B(1) >> 6) & 0x02;
+ val |= (s->B(2) >> 5) & 0x04;
+ val |= (s->B(3) >> 4) & 0x08;
+ val |= (s->B(4) >> 3) & 0x10;
+ val |= (s->B(5) >> 2) & 0x20;
+ val |= (s->B(6) >> 1) & 0x40;
+ val |= (s->B(7)) & 0x80;
#if SHIFT == 1
- val |= (s->XMM_B(8) << 1) & 0x0100;
- val |= (s->XMM_B(9) << 2) & 0x0200;
- val |= (s->XMM_B(10) << 3) & 0x0400;
- val |= (s->XMM_B(11) << 4) & 0x0800;
- val |= (s->XMM_B(12) << 5) & 0x1000;
- val |= (s->XMM_B(13) << 6) & 0x2000;
- val |= (s->XMM_B(14) << 7) & 0x4000;
- val |= (s->XMM_B(15) << 8) & 0x8000;
+ val |= (s->B(8) << 1) & 0x0100;
+ val |= (s->B(9) << 2) & 0x0200;
+ val |= (s->B(10) << 3) & 0x0400;
+ val |= (s->B(11) << 4) & 0x0800;
+ val |= (s->B(12) << 5) & 0x1000;
+ val |= (s->B(13) << 6) & 0x2000;
+ val |= (s->B(14) << 7) & 0x4000;
+ val |= (s->B(15) << 8) & 0x8000;
#endif
return val;
}
}
#endif
+/* SSSE3 op helpers */
+void glue(helper_pshufb, SUFFIX) (Reg *d, Reg *s)
+{
+ int i;
+ Reg r;
+
+ for (i = 0; i < (8 << SHIFT); i++)
+ r.B(i) = (s->B(i) & 0x80) ? 0 : (d->B(s->B(i) & ((8 << SHIFT) - 1)));
+
+ *d = r;
+}
+
+void glue(helper_phaddw, SUFFIX) (Reg *d, Reg *s)
+{
+ d->W(0) = (int16_t)d->W(0) + (int16_t)d->W(1);
+ d->W(1) = (int16_t)d->W(2) + (int16_t)d->W(3);
+ XMM_ONLY(d->W(2) = (int16_t)d->W(4) + (int16_t)d->W(5));
+ XMM_ONLY(d->W(3) = (int16_t)d->W(6) + (int16_t)d->W(7));
+ d->W((2 << SHIFT) + 0) = (int16_t)s->W(0) + (int16_t)s->W(1);
+ d->W((2 << SHIFT) + 1) = (int16_t)s->W(2) + (int16_t)s->W(3);
+ XMM_ONLY(d->W(6) = (int16_t)s->W(4) + (int16_t)s->W(5));
+ XMM_ONLY(d->W(7) = (int16_t)s->W(6) + (int16_t)s->W(7));
+}
+
+void glue(helper_phaddd, SUFFIX) (Reg *d, Reg *s)
+{
+ d->L(0) = (int32_t)d->L(0) + (int32_t)d->L(1);
+ XMM_ONLY(d->L(1) = (int32_t)d->L(2) + (int32_t)d->L(3));
+ d->L((1 << SHIFT) + 0) = (int32_t)s->L(0) + (int32_t)s->L(1);
+ XMM_ONLY(d->L(3) = (int32_t)s->L(2) + (int32_t)s->L(3));
+}
+
+void glue(helper_phaddsw, SUFFIX) (Reg *d, Reg *s)
+{
+ d->W(0) = satsw((int16_t)d->W(0) + (int16_t)d->W(1));
+ d->W(1) = satsw((int16_t)d->W(2) + (int16_t)d->W(3));
+ XMM_ONLY(d->W(2) = satsw((int16_t)d->W(4) + (int16_t)d->W(5)));
+ XMM_ONLY(d->W(3) = satsw((int16_t)d->W(6) + (int16_t)d->W(7)));
+ d->W((2 << SHIFT) + 0) = satsw((int16_t)s->W(0) + (int16_t)s->W(1));
+ d->W((2 << SHIFT) + 1) = satsw((int16_t)s->W(2) + (int16_t)s->W(3));
+ XMM_ONLY(d->W(6) = satsw((int16_t)s->W(4) + (int16_t)s->W(5)));
+ XMM_ONLY(d->W(7) = satsw((int16_t)s->W(6) + (int16_t)s->W(7)));
+}
+
+void glue(helper_pmaddubsw, SUFFIX) (Reg *d, Reg *s)
+{
+ d->W(0) = satsw((int8_t)s->B( 0) * (uint8_t)d->B( 0) +
+ (int8_t)s->B( 1) * (uint8_t)d->B( 1));
+ d->W(1) = satsw((int8_t)s->B( 2) * (uint8_t)d->B( 2) +
+ (int8_t)s->B( 3) * (uint8_t)d->B( 3));
+ d->W(2) = satsw((int8_t)s->B( 4) * (uint8_t)d->B( 4) +
+ (int8_t)s->B( 5) * (uint8_t)d->B( 5));
+ d->W(3) = satsw((int8_t)s->B( 6) * (uint8_t)d->B( 6) +
+ (int8_t)s->B( 7) * (uint8_t)d->B( 7));
+#if SHIFT == 1
+ d->W(4) = satsw((int8_t)s->B( 8) * (uint8_t)d->B( 8) +
+ (int8_t)s->B( 9) * (uint8_t)d->B( 9));
+ d->W(5) = satsw((int8_t)s->B(10) * (uint8_t)d->B(10) +
+ (int8_t)s->B(11) * (uint8_t)d->B(11));
+ d->W(6) = satsw((int8_t)s->B(12) * (uint8_t)d->B(12) +
+ (int8_t)s->B(13) * (uint8_t)d->B(13));
+ d->W(7) = satsw((int8_t)s->B(14) * (uint8_t)d->B(14) +
+ (int8_t)s->B(15) * (uint8_t)d->B(15));
+#endif
+}
+
+void glue(helper_phsubw, SUFFIX) (Reg *d, Reg *s)
+{
+ d->W(0) = (int16_t)d->W(0) - (int16_t)d->W(1);
+ d->W(1) = (int16_t)d->W(2) - (int16_t)d->W(3);
+ XMM_ONLY(d->W(2) = (int16_t)d->W(4) - (int16_t)d->W(5));
+ XMM_ONLY(d->W(3) = (int16_t)d->W(6) - (int16_t)d->W(7));
+ d->W((2 << SHIFT) + 0) = (int16_t)s->W(0) - (int16_t)s->W(1);
+ d->W((2 << SHIFT) + 1) = (int16_t)s->W(2) - (int16_t)s->W(3);
+ XMM_ONLY(d->W(6) = (int16_t)s->W(4) - (int16_t)s->W(5));
+ XMM_ONLY(d->W(7) = (int16_t)s->W(6) - (int16_t)s->W(7));
+}
+
+void glue(helper_phsubd, SUFFIX) (Reg *d, Reg *s)
+{
+ d->L(0) = (int32_t)d->L(0) - (int32_t)d->L(1);
+ XMM_ONLY(d->L(1) = (int32_t)d->L(2) - (int32_t)d->L(3));
+ d->L((1 << SHIFT) + 0) = (int32_t)s->L(0) - (int32_t)s->L(1);
+ XMM_ONLY(d->L(3) = (int32_t)s->L(2) - (int32_t)s->L(3));
+}
+
+void glue(helper_phsubsw, SUFFIX) (Reg *d, Reg *s)
+{
+ d->W(0) = satsw((int16_t)d->W(0) - (int16_t)d->W(1));
+ d->W(1) = satsw((int16_t)d->W(2) - (int16_t)d->W(3));
+ XMM_ONLY(d->W(2) = satsw((int16_t)d->W(4) - (int16_t)d->W(5)));
+ XMM_ONLY(d->W(3) = satsw((int16_t)d->W(6) - (int16_t)d->W(7)));
+ d->W((2 << SHIFT) + 0) = satsw((int16_t)s->W(0) - (int16_t)s->W(1));
+ d->W((2 << SHIFT) + 1) = satsw((int16_t)s->W(2) - (int16_t)s->W(3));
+ XMM_ONLY(d->W(6) = satsw((int16_t)s->W(4) - (int16_t)s->W(5)));
+ XMM_ONLY(d->W(7) = satsw((int16_t)s->W(6) - (int16_t)s->W(7)));
+}
+
+#define FABSB(_, x) x > INT8_MAX ? -(int8_t ) x : x
+#define FABSW(_, x) x > INT16_MAX ? -(int16_t) x : x
+#define FABSL(_, x) x > INT32_MAX ? -(int32_t) x : x
+SSE_HELPER_B(helper_pabsb, FABSB)
+SSE_HELPER_W(helper_pabsw, FABSW)
+SSE_HELPER_L(helper_pabsd, FABSL)
+
+#define FMULHRSW(d, s) ((int16_t) d * (int16_t) s + 0x4000) >> 15
+SSE_HELPER_W(helper_pmulhrsw, FMULHRSW)
+
+#define FSIGNB(d, s) s <= INT8_MAX ? s ? d : 0 : -(int8_t ) d
+#define FSIGNW(d, s) s <= INT16_MAX ? s ? d : 0 : -(int16_t) d
+#define FSIGNL(d, s) s <= INT32_MAX ? s ? d : 0 : -(int32_t) d
+SSE_HELPER_B(helper_psignb, FSIGNB)
+SSE_HELPER_W(helper_psignw, FSIGNW)
+SSE_HELPER_L(helper_psignd, FSIGNL)
+
+void glue(helper_palignr, SUFFIX) (Reg *d, Reg *s, int32_t shift)
+{
+ Reg r;
+
+ /* XXX could be checked during translation */
+ if (shift >= (16 << SHIFT)) {
+ r.Q(0) = 0;
+ XMM_ONLY(r.Q(1) = 0);
+ } else {
+ shift <<= 3;
+#define SHR(v, i) (i < 64 && i > -64 ? i > 0 ? v >> (i) : (v << -(i)) : 0)
+#if SHIFT == 0
+ r.Q(0) = SHR(s->Q(0), shift - 0) |
+ SHR(d->Q(0), shift - 64);
+#else
+ r.Q(0) = SHR(s->Q(0), shift - 0) |
+ SHR(s->Q(1), shift - 64) |
+ SHR(d->Q(0), shift - 128) |
+ SHR(d->Q(1), shift - 192);
+ r.Q(1) = SHR(s->Q(0), shift + 64) |
+ SHR(s->Q(1), shift - 0) |
+ SHR(d->Q(0), shift - 64) |
+ SHR(d->Q(1), shift - 128);
+#endif
+#undef SHR
+ }
+
+ *d = r;
+}
+
+#define XMM0 env->xmm_regs[0]
+
+#if SHIFT == 1
+#define SSE_HELPER_V(name, elem, num, F)\
+void glue(name, SUFFIX) (Reg *d, Reg *s)\
+{\
+ d->elem(0) = F(d->elem(0), s->elem(0), XMM0.elem(0));\
+ d->elem(1) = F(d->elem(1), s->elem(1), XMM0.elem(1));\
+ if (num > 2) {\
+ d->elem(2) = F(d->elem(2), s->elem(2), XMM0.elem(2));\
+ d->elem(3) = F(d->elem(3), s->elem(3), XMM0.elem(3));\
+ if (num > 4) {\
+ d->elem(4) = F(d->elem(4), s->elem(4), XMM0.elem(4));\
+ d->elem(5) = F(d->elem(5), s->elem(5), XMM0.elem(5));\
+ d->elem(6) = F(d->elem(6), s->elem(6), XMM0.elem(6));\
+ d->elem(7) = F(d->elem(7), s->elem(7), XMM0.elem(7));\
+ if (num > 8) {\
+ d->elem(8) = F(d->elem(8), s->elem(8), XMM0.elem(8));\
+ d->elem(9) = F(d->elem(9), s->elem(9), XMM0.elem(9));\
+ d->elem(10) = F(d->elem(10), s->elem(10), XMM0.elem(10));\
+ d->elem(11) = F(d->elem(11), s->elem(11), XMM0.elem(11));\
+ d->elem(12) = F(d->elem(12), s->elem(12), XMM0.elem(12));\
+ d->elem(13) = F(d->elem(13), s->elem(13), XMM0.elem(13));\
+ d->elem(14) = F(d->elem(14), s->elem(14), XMM0.elem(14));\
+ d->elem(15) = F(d->elem(15), s->elem(15), XMM0.elem(15));\
+ }\
+ }\
+ }\
+}
+
+#define SSE_HELPER_I(name, elem, num, F)\
+void glue(name, SUFFIX) (Reg *d, Reg *s, uint32_t imm)\
+{\
+ d->elem(0) = F(d->elem(0), s->elem(0), ((imm >> 0) & 1));\
+ d->elem(1) = F(d->elem(1), s->elem(1), ((imm >> 1) & 1));\
+ if (num > 2) {\
+ d->elem(2) = F(d->elem(2), s->elem(2), ((imm >> 2) & 1));\
+ d->elem(3) = F(d->elem(3), s->elem(3), ((imm >> 3) & 1));\
+ if (num > 4) {\
+ d->elem(4) = F(d->elem(4), s->elem(4), ((imm >> 4) & 1));\
+ d->elem(5) = F(d->elem(5), s->elem(5), ((imm >> 5) & 1));\
+ d->elem(6) = F(d->elem(6), s->elem(6), ((imm >> 6) & 1));\
+ d->elem(7) = F(d->elem(7), s->elem(7), ((imm >> 7) & 1));\
+ if (num > 8) {\
+ d->elem(8) = F(d->elem(8), s->elem(8), ((imm >> 8) & 1));\
+ d->elem(9) = F(d->elem(9), s->elem(9), ((imm >> 9) & 1));\
+ d->elem(10) = F(d->elem(10), s->elem(10), ((imm >> 10) & 1));\
+ d->elem(11) = F(d->elem(11), s->elem(11), ((imm >> 11) & 1));\
+ d->elem(12) = F(d->elem(12), s->elem(12), ((imm >> 12) & 1));\
+ d->elem(13) = F(d->elem(13), s->elem(13), ((imm >> 13) & 1));\
+ d->elem(14) = F(d->elem(14), s->elem(14), ((imm >> 14) & 1));\
+ d->elem(15) = F(d->elem(15), s->elem(15), ((imm >> 15) & 1));\
+ }\
+ }\
+ }\
+}
+
+/* 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
+SSE_HELPER_V(helper_pblendvb, B, 16, FBLENDVB)
+SSE_HELPER_V(helper_blendvps, L, 4, FBLENDVPS)
+SSE_HELPER_V(helper_blendvpd, Q, 2, FBLENDVPD)
+
+void glue(helper_ptest, SUFFIX) (Reg *d, Reg *s)
+{
+ uint64_t zf = (s->Q(0) & d->Q(0)) | (s->Q(1) & d->Q(1));
+ uint64_t cf = (s->Q(0) & ~d->Q(0)) | (s->Q(1) & ~d->Q(1));
+
+ CC_SRC = (zf ? 0 : CC_Z) | (cf ? 0 : CC_C);
+}
+
+#define SSE_HELPER_F(name, elem, num, F)\
+void glue(name, SUFFIX) (Reg *d, Reg *s)\
+{\
+ d->elem(0) = F(0);\
+ d->elem(1) = F(1);\
+ if (num > 2) {\
+ d->elem(2) = F(2);\
+ d->elem(3) = F(3);\
+ if (num > 4) {\
+ d->elem(4) = F(4);\
+ d->elem(5) = F(5);\
+ d->elem(6) = F(6);\
+ d->elem(7) = F(7);\
+ }\
+ }\
+}
+
+SSE_HELPER_F(helper_pmovsxbw, W, 8, (int8_t) s->B)
+SSE_HELPER_F(helper_pmovsxbd, L, 4, (int8_t) s->B)
+SSE_HELPER_F(helper_pmovsxbq, Q, 2, (int8_t) s->B)
+SSE_HELPER_F(helper_pmovsxwd, L, 4, (int16_t) s->W)
+SSE_HELPER_F(helper_pmovsxwq, Q, 2, (int16_t) s->W)
+SSE_HELPER_F(helper_pmovsxdq, Q, 2, (int32_t) s->L)
+SSE_HELPER_F(helper_pmovzxbw, W, 8, s->B)
+SSE_HELPER_F(helper_pmovzxbd, L, 4, s->B)
+SSE_HELPER_F(helper_pmovzxbq, Q, 2, s->B)
+SSE_HELPER_F(helper_pmovzxwd, L, 4, s->W)
+SSE_HELPER_F(helper_pmovzxwq, Q, 2, s->W)
+SSE_HELPER_F(helper_pmovzxdq, Q, 2, s->L)
+
+void glue(helper_pmuldq, SUFFIX) (Reg *d, Reg *s)
+{
+ d->Q(0) = (int64_t) (int32_t) d->L(0) * (int32_t) s->L(0);
+ d->Q(1) = (int64_t) (int32_t) d->L(2) * (int32_t) s->L(2);
+}
+
+#define FCMPEQQ(d, s) d == s ? -1 : 0
+SSE_HELPER_Q(helper_pcmpeqq, FCMPEQQ)
+
+void glue(helper_packusdw, SUFFIX) (Reg *d, Reg *s)
+{
+ d->W(0) = satuw((int32_t) d->L(0));
+ d->W(1) = satuw((int32_t) d->L(1));
+ d->W(2) = satuw((int32_t) d->L(2));
+ d->W(3) = satuw((int32_t) d->L(3));
+ d->W(4) = satuw((int32_t) s->L(0));
+ d->W(5) = satuw((int32_t) s->L(1));
+ d->W(6) = satuw((int32_t) s->L(2));
+ d->W(7) = satuw((int32_t) s->L(3));
+}
+
+#define FMINSB(d, s) MIN((int8_t) d, (int8_t) s)
+#define FMINSD(d, s) MIN((int32_t) d, (int32_t) s)
+#define FMAXSB(d, s) MAX((int8_t) d, (int8_t) s)
+#define FMAXSD(d, s) MAX((int32_t) d, (int32_t) s)
+SSE_HELPER_B(helper_pminsb, FMINSB)
+SSE_HELPER_L(helper_pminsd, FMINSD)
+SSE_HELPER_W(helper_pminuw, MIN)
+SSE_HELPER_L(helper_pminud, MIN)
+SSE_HELPER_B(helper_pmaxsb, FMAXSB)
+SSE_HELPER_L(helper_pmaxsd, FMAXSD)
+SSE_HELPER_W(helper_pmaxuw, MAX)
+SSE_HELPER_L(helper_pmaxud, MAX)
+
+#define FMULLD(d, s) (int32_t) d * (int32_t) s
+SSE_HELPER_L(helper_pmulld, FMULLD)
+
+void glue(helper_phminposuw, SUFFIX) (Reg *d, Reg *s)
+{
+ 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);
+}
+
+void glue(helper_roundps, SUFFIX) (Reg *d, Reg *s, uint32_t mode)
+{
+ signed char prev_rounding_mode;
+
+ prev_rounding_mode = env->sse_status.float_rounding_mode;
+ if (!(mode & (1 << 2)))
+ switch (mode & 3) {
+ case 0:
+ set_float_rounding_mode(float_round_nearest_even, &env->sse_status);
+ break;
+ case 1:
+ set_float_rounding_mode(float_round_down, &env->sse_status);
+ break;
+ case 2:
+ set_float_rounding_mode(float_round_up, &env->sse_status);
+ break;
+ case 3:
+ set_float_rounding_mode(float_round_to_zero, &env->sse_status);
+ break;
+ }
+
+ d->L(0) = float64_round_to_int(s->L(0), &env->sse_status);
+ d->L(1) = float64_round_to_int(s->L(1), &env->sse_status);
+ d->L(2) = float64_round_to_int(s->L(2), &env->sse_status);
+ d->L(3) = float64_round_to_int(s->L(3), &env->sse_status);
+
+#if 0 /* TODO */
+ if (mode & (1 << 3))
+ set_float_exception_flags(
+ get_float_exception_flags(&env->sse_status) &
+ ~float_flag_inexact,
+ &env->sse_status);
+#endif
+ env->sse_status.float_rounding_mode = prev_rounding_mode;
+}
+
+void glue(helper_roundpd, SUFFIX) (Reg *d, Reg *s, uint32_t mode)
+{
+ signed char prev_rounding_mode;
+
+ prev_rounding_mode = env->sse_status.float_rounding_mode;
+ if (!(mode & (1 << 2)))
+ switch (mode & 3) {
+ case 0:
+ set_float_rounding_mode(float_round_nearest_even, &env->sse_status);
+ break;
+ case 1:
+ set_float_rounding_mode(float_round_down, &env->sse_status);
+ break;
+ case 2:
+ set_float_rounding_mode(float_round_up, &env->sse_status);
+ break;
+ case 3:
+ set_float_rounding_mode(float_round_to_zero, &env->sse_status);
+ break;
+ }
+
+ d->Q(0) = float64_round_to_int(s->Q(0), &env->sse_status);
+ d->Q(1) = float64_round_to_int(s->Q(1), &env->sse_status);
+
+#if 0 /* TODO */
+ if (mode & (1 << 3))
+ set_float_exception_flags(
+ get_float_exception_flags(&env->sse_status) &
+ ~float_flag_inexact,
+ &env->sse_status);
+#endif
+ env->sse_status.float_rounding_mode = prev_rounding_mode;
+}
+
+void glue(helper_roundss, SUFFIX) (Reg *d, Reg *s, uint32_t mode)
+{
+ signed char prev_rounding_mode;
+
+ prev_rounding_mode = env->sse_status.float_rounding_mode;
+ if (!(mode & (1 << 2)))
+ switch (mode & 3) {
+ case 0:
+ set_float_rounding_mode(float_round_nearest_even, &env->sse_status);
+ break;
+ case 1:
+ set_float_rounding_mode(float_round_down, &env->sse_status);
+ break;
+ case 2:
+ set_float_rounding_mode(float_round_up, &env->sse_status);
+ break;
+ case 3:
+ set_float_rounding_mode(float_round_to_zero, &env->sse_status);
+ break;
+ }
+
+ d->L(0) = float64_round_to_int(s->L(0), &env->sse_status);
+
+#if 0 /* TODO */
+ if (mode & (1 << 3))
+ set_float_exception_flags(
+ get_float_exception_flags(&env->sse_status) &
+ ~float_flag_inexact,
+ &env->sse_status);
+#endif
+ env->sse_status.float_rounding_mode = prev_rounding_mode;
+}
+
+void glue(helper_roundsd, SUFFIX) (Reg *d, Reg *s, uint32_t mode)
+{
+ signed char prev_rounding_mode;
+
+ prev_rounding_mode = env->sse_status.float_rounding_mode;
+ if (!(mode & (1 << 2)))
+ switch (mode & 3) {
+ case 0:
+ set_float_rounding_mode(float_round_nearest_even, &env->sse_status);
+ break;
+ case 1:
+ set_float_rounding_mode(float_round_down, &env->sse_status);
+ break;
+ case 2:
+ set_float_rounding_mode(float_round_up, &env->sse_status);
+ break;
+ case 3:
+ set_float_rounding_mode(float_round_to_zero, &env->sse_status);
+ break;
+ }
+
+ d->Q(0) = float64_round_to_int(s->Q(0), &env->sse_status);
+
+#if 0 /* TODO */
+ if (mode & (1 << 3))
+ set_float_exception_flags(
+ get_float_exception_flags(&env->sse_status) &
+ ~float_flag_inexact,
+ &env->sse_status);
+#endif
+ env->sse_status.float_rounding_mode = prev_rounding_mode;
+}
+
+#define FBLENDP(d, s, m) m ? s : d
+SSE_HELPER_I(helper_blendps, L, 4, FBLENDP)
+SSE_HELPER_I(helper_blendpd, Q, 2, FBLENDP)
+SSE_HELPER_I(helper_pblendw, W, 8, FBLENDP)
+
+void glue(helper_dpps, SUFFIX) (Reg *d, Reg *s, uint32_t mask)
+{
+ float32 iresult = 0 /*float32_zero*/;
+
+ if (mask & (1 << 4))
+ iresult = float32_add(iresult,
+ float32_mul(d->L(0), s->L(0), &env->sse_status),
+ &env->sse_status);
+ if (mask & (1 << 5))
+ iresult = float32_add(iresult,
+ float32_mul(d->L(1), s->L(1), &env->sse_status),
+ &env->sse_status);
+ if (mask & (1 << 6))
+ iresult = float32_add(iresult,
+ float32_mul(d->L(2), s->L(2), &env->sse_status),
+ &env->sse_status);
+ if (mask & (1 << 7))
+ iresult = float32_add(iresult,
+ float32_mul(d->L(3), s->L(3), &env->sse_status),
+ &env->sse_status);
+ d->L(0) = (mask & (1 << 0)) ? iresult : 0 /*float32_zero*/;
+ d->L(1) = (mask & (1 << 1)) ? iresult : 0 /*float32_zero*/;
+ d->L(2) = (mask & (1 << 2)) ? iresult : 0 /*float32_zero*/;
+ d->L(3) = (mask & (1 << 3)) ? iresult : 0 /*float32_zero*/;
+}
+
+void glue(helper_dppd, SUFFIX) (Reg *d, Reg *s, uint32_t mask)
+{
+ float64 iresult = 0 /*float64_zero*/;
+
+ if (mask & (1 << 4))
+ iresult = float64_add(iresult,
+ float64_mul(d->Q(0), s->Q(0), &env->sse_status),
+ &env->sse_status);
+ if (mask & (1 << 5))
+ iresult = float64_add(iresult,
+ float64_mul(d->Q(1), s->Q(1), &env->sse_status),
+ &env->sse_status);
+ d->Q(0) = (mask & (1 << 0)) ? iresult : 0 /*float64_zero*/;
+ d->Q(1) = (mask & (1 << 1)) ? iresult : 0 /*float64_zero*/;
+}
+
+void glue(helper_mpsadbw, SUFFIX) (Reg *d, Reg *s, uint32_t offset)
+{
+ int s0 = (offset & 3) << 2;
+ int d0 = (offset & 4) << 0;
+ int i;
+ Reg r;
+
+ for (i = 0; i < 8; i++, d0++) {
+ r.W(i) = 0;
+ r.W(i) += abs1(d->B(d0 + 0) - s->B(s0 + 0));
+ r.W(i) += abs1(d->B(d0 + 1) - s->B(s0 + 1));
+ r.W(i) += abs1(d->B(d0 + 2) - s->B(s0 + 2));
+ r.W(i) += abs1(d->B(d0 + 3) - s->B(s0 + 3));
+ }
+
+ *d = r;
+}
+
+/* SSE4.2 op helpers */
+/* it's unclear whether signed or unsigned */
+#define FCMPGTQ(d, s) d > s ? -1 : 0
+SSE_HELPER_Q(helper_pcmpgtq, FCMPGTQ)
+
+static inline int pcmp_elen(int reg, uint32_t ctrl)
+{
+ int val;
+
+ /* Presence of REX.W is indicated by a bit higher than 7 set */
+ if (ctrl >> 8)
+ val = abs1((int64_t) env->regs[reg]);
+ else
+ val = abs1((int32_t) env->regs[reg]);
+
+ if (ctrl & 1) {
+ if (val > 8)
+ return 8;
+ } else
+ if (val > 16)
+ return 16;
+
+ return val;
+}
+
+static inline int pcmp_ilen(Reg *r, uint8_t ctrl)
+{
+ int val = 0;
+
+ if (ctrl & 1) {
+ while (val < 8 && r->W(val))
+ val++;
+ } else
+ while (val < 16 && r->B(val))
+ val++;
+
+ return val;
+}
+
+static inline int pcmp_val(Reg *r, uint8_t ctrl, int i)
+{
+ 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);
+ }
+}
+
+static inline unsigned pcmpxstrx(Reg *d, Reg *s,
+ int8_t ctrl, int valids, int validd)
+{
+ unsigned int res = 0;
+ int v;
+ int j, i;
+ int upper = (ctrl & 1) ? 7 : 15;
+
+ valids--;
+ validd--;
+
+ CC_SRC = (valids < upper ? CC_Z : 0) | (validd < upper ? CC_S : 0);
+
+ switch ((ctrl >> 2) & 3) {
+ case 0:
+ for (j = valids; j >= 0; j--) {
+ res <<= 1;
+ v = pcmp_val(s, ctrl, j);
+ for (i = validd; i >= 0; i--)
+ res |= (v == pcmp_val(d, ctrl, i));
+ }
+ break;
+ case 1:
+ for (j = valids; j >= 0; j--) {
+ res <<= 1;
+ v = pcmp_val(s, ctrl, j);
+ for (i = ((validd - 1) | 1); i >= 0; i -= 2)
+ res |= (pcmp_val(d, ctrl, i - 0) <= v &&
+ pcmp_val(d, ctrl, i - 1) >= v);
+ }
+ break;
+ case 2:
+ res = (2 << (upper - MAX(valids, validd))) - 1;
+ res <<= MAX(valids, validd) - MIN(valids, validd);
+ for (i = MIN(valids, validd); i >= 0; i--) {
+ res <<= 1;
+ v = pcmp_val(s, ctrl, i);
+ res |= (v == pcmp_val(d, ctrl, i));
+ }
+ break;
+ case 3:
+ for (j = valids - validd; j >= 0; j--) {
+ res <<= 1;
+ res |= 1;
+ for (i = MIN(upper - j, validd); i >= 0; i--)
+ res &= (pcmp_val(s, ctrl, i + j) == pcmp_val(d, ctrl, i));
+ }
+ break;
+ }
+
+ switch ((ctrl >> 4) & 3) {
+ case 1:
+ res ^= (2 << upper) - 1;
+ break;
+ case 3:
+ res ^= (2 << valids) - 1;
+ break;
+ }
+
+ if (res)
+ CC_SRC |= CC_C;
+ if (res & 1)
+ CC_SRC |= CC_O;
+
+ return res;
+}
+
+static inline int rffs1(unsigned int val)
+{
+ int ret = 1, hi;
+
+ for (hi = sizeof(val) * 4; hi; hi /= 2)
+ if (val >> hi) {
+ val >>= hi;
+ ret += hi;
+ }
+
+ return ret;
+}
+
+static inline int ffs1(unsigned int val)
+{
+ int ret = 1, hi;
+
+ for (hi = sizeof(val) * 4; hi; hi /= 2)
+ if (val << hi) {
+ val <<= hi;
+ ret += hi;
+ }
+
+ return ret;
+}
+
+void glue(helper_pcmpestri, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl)
+{
+ unsigned int res = pcmpxstrx(d, s, ctrl,
+ pcmp_elen(R_EDX, ctrl),
+ pcmp_elen(R_EAX, ctrl));
+
+ if (res)
+ env->regs[R_ECX] = ((ctrl & (1 << 6)) ? rffs1 : ffs1)(res) - 1;
+ else
+ env->regs[R_ECX] = 16 >> (ctrl & (1 << 0));
+}
+
+void glue(helper_pcmpestrm, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl)
+{
+ int i;
+ unsigned int res = pcmpxstrx(d, s, ctrl,
+ pcmp_elen(R_EDX, ctrl),
+ pcmp_elen(R_EAX, ctrl));
+
+ if ((ctrl >> 6) & 1) {
+ if (ctrl & 1)
+ for (i = 0; i <= 8; i--, res >>= 1)
+ d->W(i) = (res & 1) ? ~0 : 0;
+ else
+ for (i = 0; i <= 16; i--, res >>= 1)
+ d->B(i) = (res & 1) ? ~0 : 0;
+ } else {
+ d->Q(1) = 0;
+ d->Q(0) = res;
+ }
+}
+
+void glue(helper_pcmpistri, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl)
+{
+ unsigned int res = pcmpxstrx(d, s, ctrl,
+ pcmp_ilen(s, ctrl),
+ pcmp_ilen(d, ctrl));
+
+ if (res)
+ env->regs[R_ECX] = ((ctrl & (1 << 6)) ? rffs1 : ffs1)(res) - 1;
+ else
+ env->regs[R_ECX] = 16 >> (ctrl & (1 << 0));
+}
+
+void glue(helper_pcmpistrm, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl)
+{
+ int i;
+ unsigned int res = pcmpxstrx(d, s, ctrl,
+ pcmp_ilen(s, ctrl),
+ pcmp_ilen(d, ctrl));
+
+ if ((ctrl >> 6) & 1) {
+ if (ctrl & 1)
+ for (i = 0; i <= 8; i--, res >>= 1)
+ d->W(i) = (res & 1) ? ~0 : 0;
+ else
+ for (i = 0; i <= 16; i--, res >>= 1)
+ d->B(i) = (res & 1) ? ~0 : 0;
+ } else {
+ d->Q(1) = 0;
+ d->Q(0) = res;
+ }
+}
+
+#define CRCPOLY 0x1edc6f41
+#define CRCPOLY_BITREV 0x82f63b78
+target_ulong helper_crc32(uint32_t crc1, target_ulong msg, uint32_t len)
+{
+ target_ulong crc = (msg & ((target_ulong) -1 >>
+ (TARGET_LONG_BITS - len))) ^ crc1;
+
+ while (len--)
+ crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_BITREV : 0);
+
+ return crc;
+}
+
+#define POPMASK(i) ((target_ulong) -1 / ((1LL << (1 << i)) + 1))
+#define POPCOUNT(n, i) (n & POPMASK(i)) + ((n >> (1 << i)) & POPMASK(i))
+target_ulong helper_popcnt(target_ulong n, uint32_t type)
+{
+ CC_SRC = n ? 0 : CC_Z;
+
+ 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 SHIFT
#undef XMM_ONLY
#undef Reg
projects / qemu.git / blobdiff