+/* 3DNow! float ops */
+#if SHIFT == 0
+void helper_pi2fd(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_S(0) = int32_to_float32(s->MMX_L(0), &env->mmx_status);
+ d->MMX_S(1) = int32_to_float32(s->MMX_L(1), &env->mmx_status);
+}
+
+void helper_pi2fw(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_S(0) = int32_to_float32((int16_t)s->MMX_W(0), &env->mmx_status);
+ d->MMX_S(1) = int32_to_float32((int16_t)s->MMX_W(2), &env->mmx_status);
+}
+
+void helper_pf2id(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_L(0) = float32_to_int32_round_to_zero(s->MMX_S(0), &env->mmx_status);
+ d->MMX_L(1) = float32_to_int32_round_to_zero(s->MMX_S(1), &env->mmx_status);
+}
+
+void helper_pf2iw(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_L(0) = satsw(float32_to_int32_round_to_zero(s->MMX_S(0),
+ &env->mmx_status));
+ d->MMX_L(1) = satsw(float32_to_int32_round_to_zero(s->MMX_S(1),
+ &env->mmx_status));
+}
+
+void helper_pfacc(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ MMXReg r;
+
+ r.MMX_S(0) = float32_add(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
+ r.MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
+ *d = r;
+}
+
+void helper_pfadd(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_S(0) = float32_add(d->MMX_S(0), s->MMX_S(0), &env->mmx_status);
+ d->MMX_S(1) = float32_add(d->MMX_S(1), s->MMX_S(1), &env->mmx_status);
+}
+
+void helper_pfcmpeq(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_L(0) = float32_eq_quiet(d->MMX_S(0), s->MMX_S(0),
+ &env->mmx_status) ? -1 : 0;
+ d->MMX_L(1) = float32_eq_quiet(d->MMX_S(1), s->MMX_S(1),
+ &env->mmx_status) ? -1 : 0;
+}
+
+void helper_pfcmpge(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_L(0) = float32_le(s->MMX_S(0), d->MMX_S(0),
+ &env->mmx_status) ? -1 : 0;
+ d->MMX_L(1) = float32_le(s->MMX_S(1), d->MMX_S(1),
+ &env->mmx_status) ? -1 : 0;
+}
+
+void helper_pfcmpgt(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_L(0) = float32_lt(s->MMX_S(0), d->MMX_S(0),
+ &env->mmx_status) ? -1 : 0;
+ d->MMX_L(1) = float32_lt(s->MMX_S(1), d->MMX_S(1),
+ &env->mmx_status) ? -1 : 0;
+}
+
+void helper_pfmax(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ if (float32_lt(d->MMX_S(0), s->MMX_S(0), &env->mmx_status)) {
+ d->MMX_S(0) = s->MMX_S(0);
+ }
+ if (float32_lt(d->MMX_S(1), s->MMX_S(1), &env->mmx_status)) {
+ d->MMX_S(1) = s->MMX_S(1);
+ }
+}
+
+void helper_pfmin(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ if (float32_lt(s->MMX_S(0), d->MMX_S(0), &env->mmx_status)) {
+ d->MMX_S(0) = s->MMX_S(0);
+ }
+ if (float32_lt(s->MMX_S(1), d->MMX_S(1), &env->mmx_status)) {
+ d->MMX_S(1) = s->MMX_S(1);
+ }
+}
+
+void helper_pfmul(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_S(0) = float32_mul(d->MMX_S(0), s->MMX_S(0), &env->mmx_status);
+ d->MMX_S(1) = float32_mul(d->MMX_S(1), s->MMX_S(1), &env->mmx_status);
+}
+
+void helper_pfnacc(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ MMXReg r;
+
+ r.MMX_S(0) = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
+ r.MMX_S(1) = float32_sub(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
+ *d = r;
+}
+
+void helper_pfpnacc(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ MMXReg r;
+
+ r.MMX_S(0) = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status);
+ r.MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status);
+ *d = r;
+}
+
+void helper_pfrcp(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_S(0) = float32_div(float32_one, s->MMX_S(0), &env->mmx_status);
+ d->MMX_S(1) = d->MMX_S(0);
+}
+
+void helper_pfrsqrt(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_L(1) = s->MMX_L(0) & 0x7fffffff;
+ d->MMX_S(1) = float32_div(float32_one,
+ float32_sqrt(d->MMX_S(1), &env->mmx_status),
+ &env->mmx_status);
+ d->MMX_L(1) |= s->MMX_L(0) & 0x80000000;
+ d->MMX_L(0) = d->MMX_L(1);
+}
+
+void helper_pfsub(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_S(0) = float32_sub(d->MMX_S(0), s->MMX_S(0), &env->mmx_status);
+ d->MMX_S(1) = float32_sub(d->MMX_S(1), s->MMX_S(1), &env->mmx_status);
+}
+
+void helper_pfsubr(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ d->MMX_S(0) = float32_sub(s->MMX_S(0), d->MMX_S(0), &env->mmx_status);
+ d->MMX_S(1) = float32_sub(s->MMX_S(1), d->MMX_S(1), &env->mmx_status);
+}
+
+void helper_pswapd(CPUX86State *env, MMXReg *d, MMXReg *s)
+{
+ MMXReg r;
+
+ r.MMX_L(0) = s->MMX_L(1);
+ r.MMX_L(1) = s->MMX_L(0);
+ *d = r;
+}
+#endif
+
+/* SSSE3 op helpers */
+void glue(helper_pshufb, SUFFIX)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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)(CPUX86State *env, 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->XMM_S(0) = float32_round_to_int(s->XMM_S(0), &env->sse_status);
+ d->XMM_S(1) = float32_round_to_int(s->XMM_S(1), &env->sse_status);
+ d->XMM_S(2) = float32_round_to_int(s->XMM_S(2), &env->sse_status);
+ d->XMM_S(3) = float32_round_to_int(s->XMM_S(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)(CPUX86State *env, 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->XMM_D(0) = float64_round_to_int(s->XMM_D(0), &env->sse_status);
+ d->XMM_D(1) = float64_round_to_int(s->XMM_D(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)(CPUX86State *env, 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->XMM_S(0) = float32_round_to_int(s->XMM_S(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)(CPUX86State *env, 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->XMM_D(0) = float64_round_to_int(s->XMM_D(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)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
+{
+ float32 iresult = float32_zero;
+
+ if (mask & (1 << 4)) {
+ iresult = float32_add(iresult,
+ float32_mul(d->XMM_S(0), s->XMM_S(0),
+ &env->sse_status),
+ &env->sse_status);
+ }
+ if (mask & (1 << 5)) {
+ iresult = float32_add(iresult,
+ float32_mul(d->XMM_S(1), s->XMM_S(1),
+ &env->sse_status),
+ &env->sse_status);
+ }
+ if (mask & (1 << 6)) {
+ iresult = float32_add(iresult,
+ float32_mul(d->XMM_S(2), s->XMM_S(2),
+ &env->sse_status),
+ &env->sse_status);
+ }
+ if (mask & (1 << 7)) {
+ iresult = float32_add(iresult,
+ float32_mul(d->XMM_S(3), s->XMM_S(3),
+ &env->sse_status),
+ &env->sse_status);
+ }
+ d->XMM_S(0) = (mask & (1 << 0)) ? iresult : float32_zero;
+ d->XMM_S(1) = (mask & (1 << 1)) ? iresult : float32_zero;
+ d->XMM_S(2) = (mask & (1 << 2)) ? iresult : float32_zero;
+ d->XMM_S(3) = (mask & (1 << 3)) ? iresult : float32_zero;
+}
+
+void glue(helper_dppd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, uint32_t mask)
+{
+ float64 iresult = float64_zero;
+
+ if (mask & (1 << 4)) {
+ iresult = float64_add(iresult,
+ float64_mul(d->XMM_D(0), s->XMM_D(0),
+ &env->sse_status),
+ &env->sse_status);
+ }
+ if (mask & (1 << 5)) {
+ iresult = float64_add(iresult,
+ float64_mul(d->XMM_D(1), s->XMM_D(1),
+ &env->sse_status),
+ &env->sse_status);
+ }
+ d->XMM_D(0) = (mask & (1 << 0)) ? iresult : float64_zero;
+ d->XMM_D(1) = (mask & (1 << 1)) ? iresult : float64_zero;
+}
+
+void glue(helper_mpsadbw, SUFFIX)(CPUX86State *env, 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 */
+#define FCMPGTQ(d, s) ((int64_t)d > (int64_t)s ? -1 : 0)
+SSE_HELPER_Q(helper_pcmpgtq, FCMPGTQ)
+
+static inline int pcmp_elen(CPUX86State *env, 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(CPUX86State *env, 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 = (1 << (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;
+ v = 1;
+ for (i = MIN(upper - j, validd); i >= 0; i--) {
+ v &= (pcmp_val(s, ctrl, i + j) == pcmp_val(d, ctrl, i));
+ }
+ res |= v;
+ }
+ break;
+ }
+
+ switch ((ctrl >> 4) & 3) {
+ case 1:
+ res ^= (2 << upper) - 1;
+ break;
+ case 3:
+ res ^= (1 << (valids + 1)) - 1;
+ break;
+ }
+
+ if (res) {
+ CC_SRC |= CC_C;
+ }
+ if (res & 1) {
+ CC_SRC |= CC_O;
+ }
+
+ return res;
+}
+
+void glue(helper_pcmpestri, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+ uint32_t ctrl)
+{
+ unsigned int res = pcmpxstrx(env, d, s, ctrl,
+ pcmp_elen(env, R_EDX, ctrl),
+ pcmp_elen(env, R_EAX, ctrl));
+
+ if (res) {
+ env->regs[R_ECX] = (ctrl & (1 << 6)) ? 31 - clz32(res) : ctz32(res);
+ } else {
+ env->regs[R_ECX] = 16 >> (ctrl & (1 << 0));
+ }
+}
+
+void glue(helper_pcmpestrm, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+ uint32_t ctrl)
+{
+ int i;
+ unsigned int res = pcmpxstrx(env, d, s, ctrl,
+ pcmp_elen(env, R_EDX, ctrl),
+ pcmp_elen(env, R_EAX, ctrl));
+
+ if ((ctrl >> 6) & 1) {
+ if (ctrl & 1) {
+ for (i = 0; i < 8; i++, res >>= 1) {
+ env->xmm_regs[0].W(i) = (res & 1) ? ~0 : 0;
+ }
+ } else {
+ for (i = 0; i < 16; i++, res >>= 1) {
+ env->xmm_regs[0].B(i) = (res & 1) ? ~0 : 0;
+ }
+ }
+ } else {
+ env->xmm_regs[0].Q(1) = 0;
+ env->xmm_regs[0].Q(0) = res;
+ }
+}
+
+void glue(helper_pcmpistri, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+ uint32_t ctrl)
+{
+ unsigned int res = pcmpxstrx(env, d, s, ctrl,
+ pcmp_ilen(s, ctrl),
+ pcmp_ilen(d, ctrl));
+
+ if (res) {
+ env->regs[R_ECX] = (ctrl & (1 << 6)) ? 31 - clz32(res) : ctz32(res);
+ } else {
+ env->regs[R_ECX] = 16 >> (ctrl & (1 << 0));
+ }
+}
+
+void glue(helper_pcmpistrm, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+ uint32_t ctrl)
+{
+ int i;
+ unsigned int res = pcmpxstrx(env, 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) {
+ env->xmm_regs[0].W(i) = (res & 1) ? ~0 : 0;
+ }
+ } else {
+ for (i = 0; i < 16; i++, res >>= 1) {
+ env->xmm_regs[0].B(i) = (res & 1) ? ~0 : 0;
+ }
+ }
+ } else {
+ env->xmm_regs[0].Q(1) = 0;
+ env->xmm_regs[0].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(CPUX86State *env, 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
+}
+
+void glue(helper_pclmulqdq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+ uint32_t ctrl)
+{
+ uint64_t ah, al, b, resh, resl;
+
+ ah = 0;
+ al = d->Q((ctrl & 1) != 0);
+ b = s->Q((ctrl & 16) != 0);
+ resh = resl = 0;
+
+ while (b) {
+ if (b & 1) {
+ resl ^= al;
+ resh ^= ah;
+ }
+ ah = (ah << 1) | (al >> 63);
+ al <<= 1;
+ b >>= 1;
+ }
+
+ d->Q(0) = resl;
+ d->Q(1) = resh;
+}
+
+/* AES-NI op helpers */
+static const uint8_t aes_shifts[16] = {
+ 0, 5, 10, 15, 4, 9, 14, 3, 8, 13, 2, 7, 12, 1, 6, 11
+};
+
+static const uint8_t aes_ishifts[16] = {
+ 0, 13, 10, 7, 4, 1, 14, 11, 8, 5, 2, 15, 12, 9, 6, 3
+};
+
+void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ Reg st = *d;
+ Reg rk = *s;
+
+ for (i = 0 ; i < 4 ; i++) {
+ d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(aes_ishifts[4*i+0])] ^
+ AES_Td1[st.B(aes_ishifts[4*i+1])] ^
+ AES_Td2[st.B(aes_ishifts[4*i+2])] ^
+ AES_Td3[st.B(aes_ishifts[4*i+3])]);
+ }
+}
+
+void glue(helper_aesdeclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ Reg st = *d;
+ Reg rk = *s;
+
+ for (i = 0; i < 16; i++) {
+ d->B(i) = rk.B(i) ^ (AES_Td4[st.B(aes_ishifts[i])] & 0xff);
+ }
+}
+
+void glue(helper_aesenc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ Reg st = *d;
+ Reg rk = *s;
+
+ for (i = 0 ; i < 4 ; i++) {
+ d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(aes_shifts[4*i+0])] ^
+ AES_Te1[st.B(aes_shifts[4*i+1])] ^
+ AES_Te2[st.B(aes_shifts[4*i+2])] ^
+ AES_Te3[st.B(aes_shifts[4*i+3])]);
+ }
+}
+
+void glue(helper_aesenclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ Reg st = *d;
+ Reg rk = *s;
+
+ for (i = 0; i < 16; i++) {
+ d->B(i) = rk.B(i) ^ (AES_Te4[st.B(aes_shifts[i])] & 0xff);
+ }
+
+}
+
+void glue(helper_aesimc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+{
+ int i;
+ Reg tmp = *s;
+
+ for (i = 0 ; i < 4 ; i++) {
+ d->L(i) = bswap32(AES_Td0[AES_Te4[tmp.B(4*i+0)] & 0xff] ^
+ AES_Td1[AES_Te4[tmp.B(4*i+1)] & 0xff] ^
+ AES_Td2[AES_Te4[tmp.B(4*i+2)] & 0xff] ^
+ AES_Td3[AES_Te4[tmp.B(4*i+3)] & 0xff]);
+ }
+}
+
+void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
+ uint32_t ctrl)
+{
+ int i;
+ Reg tmp = *s;
+
+ for (i = 0 ; i < 4 ; i++) {
+ d->B(i) = AES_Te4[tmp.B(i + 4)] & 0xff;
+ d->B(i + 8) = AES_Te4[tmp.B(i + 12)] & 0xff;
+ }
+ d->L(1) = (d->L(0) << 24 | d->L(0) >> 8) ^ ctrl;
+ d->L(3) = (d->L(2) << 24 | d->L(2) >> 8) ^ ctrl;
+}
+#endif
+
projects / qemu.git / blobdiff