[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [RFC PATCH v4 43/75] target/i386: introduce SSE2 code gener
From: |
Jan Bobek |
Subject: |
[Qemu-devel] [RFC PATCH v4 43/75] target/i386: introduce SSE2 code generators |
Date: |
Wed, 21 Aug 2019 13:29:19 -0400 |
Introduce code generators required by SSE2 instructions.
Signed-off-by: Jan Bobek <address@hidden>
---
target/i386/translate.c | 427 +++++++++++++++++++++++++++++++++++++++-
1 file changed, 425 insertions(+), 2 deletions(-)
diff --git a/target/i386/translate.c b/target/i386/translate.c
index 43917edc76..3445b4cff1 100644
--- a/target/i386/translate.c
+++ b/target/i386/translate.c
@@ -5563,6 +5563,7 @@ INSNOP_LDST(xmm, Mhq)
}
GEN_INSN2(movq, Pq, Eq); /* forward declaration */
+GEN_INSN2(movq, Vdq, Eq); /* forward declaration */
GEN_INSN2(movd, Pq, Ed)
{
const insnop_arg_t(Eq) arg2_r64 = tcg_temp_new_i64();
@@ -5574,6 +5575,17 @@ GEN_INSN2(movd, Ed, Pq)
{
tcg_gen_ld_i32(arg1, cpu_env, arg2 + offsetof(MMXReg, MMX_L(0)));
}
+GEN_INSN2(movd, Vdq, Ed)
+{
+ const insnop_arg_t(Eq) arg2_r64 = tcg_temp_new_i64();
+ tcg_gen_extu_i32_i64(arg2_r64, arg2);
+ gen_insn2(movq, Vdq, Eq)(env, s, arg1, arg2_r64);
+ tcg_temp_free_i64(arg2_r64);
+}
+GEN_INSN2(movd, Ed, Vdq)
+{
+ tcg_gen_ld_i32(arg1, cpu_env, arg2 + offsetof(ZMMReg, ZMM_L(0)));
+}
GEN_INSN2(movq, Pq, Eq)
{
@@ -5583,13 +5595,45 @@ GEN_INSN2(movq, Eq, Pq)
{
tcg_gen_ld_i64(arg1, cpu_env, arg2 + offsetof(MMXReg, MMX_Q(0)));
}
+GEN_INSN2(movq, Vdq, Eq)
+{
+ const TCGv_i64 r64 = tcg_temp_new_i64();
+ tcg_gen_st_i64(arg2, cpu_env, arg1 + offsetof(ZMMReg, ZMM_Q(0)));
+ tcg_gen_movi_i64(r64, 0);
+ tcg_gen_st_i64(r64, cpu_env, arg1 + offsetof(ZMMReg, ZMM_Q(1)));
+ tcg_temp_free_i64(r64);
+}
+GEN_INSN2(movq, Eq, Vdq)
+{
+ tcg_gen_ld_i64(arg1, cpu_env, arg2 + offsetof(ZMMReg, ZMM_Q(0)));
+}
DEF_GEN_INSN2_GVEC(movq, Pq, Qq, mov, MM_OPRSZ, MM_MAXSZ, MO_64)
DEF_GEN_INSN2_GVEC(movq, Qq, Pq, mov, MM_OPRSZ, MM_MAXSZ, MO_64)
+GEN_INSN2(movq, Vdq, Wq)
+{
+ const TCGv_i64 r64 = tcg_temp_new_i64();
+ tcg_gen_ld_i64(r64, cpu_env, arg2 + offsetof(ZMMReg, ZMM_Q(0)));
+ gen_insn2(movq, Vdq, Eq)(env, s, arg1, r64);
+ tcg_temp_free_i64(r64);
+}
+GEN_INSN2(movq, UdqMq, Vq)
+{
+ gen_insn2(movq, Vdq, Wq)(env, s, arg1, arg2);
+}
+
DEF_GEN_INSN2_GVEC(movaps, Vdq, Wdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN2_GVEC(movaps, Wdq, Vdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN2_GVEC(movapd, Vdq, Wdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN2_GVEC(movapd, Wdq, Vdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN2_GVEC(movdqa, Vdq, Wdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN2_GVEC(movdqa, Wdq, Vdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN2_GVEC(movups, Vdq, Wdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN2_GVEC(movups, Wdq, Vdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN2_GVEC(movupd, Vdq, Wdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN2_GVEC(movupd, Wdq, Vdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN2_GVEC(movdqu, Vdq, Wdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN2_GVEC(movdqu, Wdq, Vdq, mov, XMM_OPRSZ, XMM_MAXSZ, MO_64)
GEN_INSN4(movss, Vdq, Vdq, Wd, modrm_mod)
{
@@ -5621,6 +5665,46 @@ GEN_INSN2(movss, Wd, Vd)
gen_insn4(movss, Vdq, Vdq, Wd, modrm_mod)(env, s, arg1, arg1, arg2, 3);
}
+GEN_INSN4(movsd, Vdq, Vdq, Wq, modrm_mod)
+{
+ const TCGv_i64 r64 = tcg_temp_new_i64();
+ tcg_gen_ld_i64(r64, cpu_env, arg3 + offsetof(ZMMReg, ZMM_Q(0)));
+ tcg_gen_st_i64(r64, cpu_env, arg1 + offsetof(ZMMReg, ZMM_Q(0)));
+ if (arg4 == 3) {
+ /* merging movsd */
+ if (arg1 != arg2) {
+ tcg_gen_ld_i64(r64, cpu_env, arg2 + offsetof(ZMMReg, ZMM_Q(1)));
+ tcg_gen_st_i64(r64, cpu_env, arg1 + offsetof(ZMMReg, ZMM_Q(1)));
+ }
+ } else {
+ /* zero-extending movsd */
+ tcg_gen_movi_i64(r64, 0);
+ tcg_gen_st_i64(r64, cpu_env, arg1 + offsetof(ZMMReg, ZMM_Q(1)));
+ }
+ tcg_temp_free_i64(r64);
+}
+GEN_INSN2(movsd, Wq, Vq)
+{
+ gen_insn4(movsd, Vdq, Vdq, Wq, modrm_mod)(env, s, arg1, arg1, arg2, 3);
+}
+
+GEN_INSN2(movq2dq, Vdq, Nq)
+{
+ const insnop_arg_t(Vdq) dofs = offsetof(ZMMReg, ZMM_Q(0));
+ const insnop_arg_t(Nq) aofs = offsetof(MMXReg, MMX_Q(0));
+ gen_op_movq(s, arg1 + dofs, arg2 + aofs);
+
+ const TCGv_i64 r64z = tcg_const_i64(0);
+ tcg_gen_st_i64(r64z, cpu_env, arg1 + offsetof(ZMMReg, ZMM_Q(1)));
+ tcg_temp_free_i64(r64z);
+}
+GEN_INSN2(movdq2q, Pq, Uq)
+{
+ const insnop_arg_t(Pq) dofs = offsetof(MMXReg, MMX_Q(0));
+ const insnop_arg_t(Uq) aofs = offsetof(ZMMReg, ZMM_Q(0));
+ gen_op_movq(s, arg1 + dofs, arg2 + aofs);
+}
+
GEN_INSN3(movhlps, Vdq, Vdq, UdqMhq)
{
const TCGv_i64 r64 = tcg_temp_new_i64();
@@ -5637,6 +5721,21 @@ GEN_INSN2(movlps, Mq, Vq)
insnop_ldst(xmm, Mq)(env, s, 1, arg2, arg1);
}
+GEN_INSN3(movlpd, Vdq, Vdq, Mq)
+{
+ insnop_ldst(xmm, Mq)(env, s, 0, arg1, arg3);
+ if (arg1 != arg2) {
+ const TCGv_i64 r64 = tcg_temp_new_i64();
+ tcg_gen_ld_i64(r64, cpu_env, arg2 + offsetof(ZMMReg, ZMM_Q(1)));
+ tcg_gen_st_i64(r64, cpu_env, arg1 + offsetof(ZMMReg, ZMM_Q(1)));
+ tcg_temp_free_i64(r64);
+ }
+}
+GEN_INSN2(movlpd, Mq, Vq)
+{
+ insnop_ldst(xmm, Mq)(env, s, 1, arg2, arg1);
+}
+
GEN_INSN3(movlhps, Vdq, Vq, Wq)
{
const TCGv_i64 r64 = tcg_temp_new_i64();
@@ -5653,6 +5752,21 @@ GEN_INSN2(movhps, Mq, Vdq)
insnop_ldst(xmm, Mhq)(env, s, 1, arg2, arg1);
}
+GEN_INSN3(movhpd, Vdq, Vq, Mq)
+{
+ if (arg1 != arg2) {
+ const TCGv_i64 r64 = tcg_temp_new_i64();
+ tcg_gen_ld_i64(r64, cpu_env, arg2 + offsetof(ZMMReg, ZMM_Q(0)));
+ tcg_gen_st_i64(r64, cpu_env, arg1 + offsetof(ZMMReg, ZMM_Q(0)));
+ tcg_temp_free_i64(r64);
+ }
+ insnop_ldst(xmm, Mhq)(env, s, 0, arg1, arg3);
+}
+GEN_INSN2(movhpd, Mq, Vdq)
+{
+ insnop_ldst(xmm, Mhq)(env, s, 1, arg2, arg1);
+}
+
DEF_GEN_INSN2_HELPER_DEP(pmovmskb, pmovmskb_mmx, Gd, Nq)
GEN_INSN2(pmovmskb, Gq, Nq)
{
@@ -5661,6 +5775,14 @@ GEN_INSN2(pmovmskb, Gq, Nq)
tcg_gen_extu_i32_i64(arg1, arg1_r32);
tcg_temp_free_i32(arg1_r32);
}
+DEF_GEN_INSN2_HELPER_DEP(pmovmskb, pmovmskb_xmm, Gd, Udq)
+GEN_INSN2(pmovmskb, Gq, Udq)
+{
+ const TCGv_i32 arg1_r32 = tcg_temp_new_i32();
+ gen_insn2(pmovmskb, Gd, Udq)(env, s, arg1_r32, arg2);
+ tcg_gen_extu_i32_i64(arg1, arg1_r32);
+ tcg_temp_free_i32(arg1_r32);
+}
DEF_GEN_INSN2_HELPER_DEP(movmskps, movmskps, Gd, Udq)
GEN_INSN2(movmskps, Gq, Udq)
@@ -5671,78 +5793,154 @@ GEN_INSN2(movmskps, Gq, Udq)
tcg_temp_free_i32(arg1_r32);
}
+DEF_GEN_INSN2_HELPER_DEP(movmskpd, movmskpd, Gd, Udq)
+GEN_INSN2(movmskpd, Gq, Udq)
+{
+ const TCGv_i32 arg1_r32 = tcg_temp_new_i32();
+ gen_insn2(movmskpd, Gd, Udq)(env, s, arg1_r32, arg2);
+ tcg_gen_extu_i32_i64(arg1, arg1_r32);
+ tcg_temp_free_i32(arg1_r32);
+}
+
DEF_GEN_INSN3_GVEC(paddb, Pq, Pq, Qq, add, MM_OPRSZ, MM_MAXSZ, MO_8)
+DEF_GEN_INSN3_GVEC(paddb, Vdq, Vdq, Wdq, add, XMM_OPRSZ, XMM_MAXSZ, MO_8)
DEF_GEN_INSN3_GVEC(paddw, Pq, Pq, Qq, add, MM_OPRSZ, MM_MAXSZ, MO_16)
+DEF_GEN_INSN3_GVEC(paddw, Vdq, Vdq, Wdq, add, XMM_OPRSZ, XMM_MAXSZ, MO_16)
DEF_GEN_INSN3_GVEC(paddd, Pq, Pq, Qq, add, MM_OPRSZ, MM_MAXSZ, MO_32)
+DEF_GEN_INSN3_GVEC(paddd, Vdq, Vdq, Wdq, add, XMM_OPRSZ, XMM_MAXSZ, MO_32)
+DEF_GEN_INSN3_GVEC(paddq, Pq, Pq, Qq, add, MM_OPRSZ, MM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(paddq, Vdq, Vdq, Wdq, add, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(paddsb, Pq, Pq, Qq, ssadd, MM_OPRSZ, MM_MAXSZ, MO_8)
+DEF_GEN_INSN3_GVEC(paddsb, Vdq, Vdq, Wdq, ssadd, XMM_OPRSZ, XMM_MAXSZ, MO_8)
DEF_GEN_INSN3_GVEC(paddsw, Pq, Pq, Qq, ssadd, MM_OPRSZ, MM_MAXSZ, MO_16)
+DEF_GEN_INSN3_GVEC(paddsw, Vdq, Vdq, Wdq, ssadd, XMM_OPRSZ, XMM_MAXSZ, MO_16)
DEF_GEN_INSN3_GVEC(paddusb, Pq, Pq, Qq, usadd, MM_OPRSZ, MM_MAXSZ, MO_8)
+DEF_GEN_INSN3_GVEC(paddusb, Vdq, Vdq, Wdq, usadd, XMM_OPRSZ, XMM_MAXSZ, MO_8)
DEF_GEN_INSN3_GVEC(paddusw, Pq, Pq, Qq, usadd, MM_OPRSZ, MM_MAXSZ, MO_16)
+DEF_GEN_INSN3_GVEC(paddusw, Vdq, Vdq, Wdq, usadd, XMM_OPRSZ, XMM_MAXSZ, MO_16)
DEF_GEN_INSN3_HELPER_EPP(addps, addps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(addpd, addpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(addss, addss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(addsd, addsd, Vq, Vq, Wq)
DEF_GEN_INSN3_GVEC(psubb, Pq, Pq, Qq, sub, MM_OPRSZ, MM_MAXSZ, MO_8)
+DEF_GEN_INSN3_GVEC(psubb, Vdq, Vdq, Wdq, sub, XMM_OPRSZ, XMM_MAXSZ, MO_8)
DEF_GEN_INSN3_GVEC(psubw, Pq, Pq, Qq, sub, MM_OPRSZ, MM_MAXSZ, MO_16)
+DEF_GEN_INSN3_GVEC(psubw, Vdq, Vdq, Wdq, sub, XMM_OPRSZ, XMM_MAXSZ, MO_16)
DEF_GEN_INSN3_GVEC(psubd, Pq, Pq, Qq, sub, MM_OPRSZ, MM_MAXSZ, MO_32)
+DEF_GEN_INSN3_GVEC(psubd, Vdq, Vdq, Wdq, sub, XMM_OPRSZ, XMM_MAXSZ, MO_32)
+DEF_GEN_INSN3_GVEC(psubq, Pq, Pq, Qq, sub, MM_OPRSZ, MM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(psubq, Vdq, Vdq, Wdq, sub, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(psubsb, Pq, Pq, Qq, sssub, MM_OPRSZ, MM_MAXSZ, MO_8)
+DEF_GEN_INSN3_GVEC(psubsb, Vdq, Vdq, Wdq, sssub, XMM_OPRSZ, XMM_MAXSZ, MO_8)
DEF_GEN_INSN3_GVEC(psubsw, Pq, Pq, Qq, sssub, MM_OPRSZ, MM_MAXSZ, MO_16)
+DEF_GEN_INSN3_GVEC(psubsw, Vdq, Vdq, Wdq, sssub, XMM_OPRSZ, XMM_MAXSZ, MO_16)
DEF_GEN_INSN3_GVEC(psubusb, Pq, Pq, Qq, ussub, MM_OPRSZ, MM_MAXSZ, MO_8)
+DEF_GEN_INSN3_GVEC(psubusb, Vdq, Vdq, Wdq, ussub, XMM_OPRSZ, XMM_MAXSZ, MO_8)
DEF_GEN_INSN3_GVEC(psubusw, Pq, Pq, Qq, ussub, MM_OPRSZ, MM_MAXSZ, MO_16)
+DEF_GEN_INSN3_GVEC(psubusw, Vdq, Vdq, Wdq, ussub, XMM_OPRSZ, XMM_MAXSZ, MO_16)
DEF_GEN_INSN3_HELPER_EPP(subps, subps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(subpd, subpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(subss, subss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(subsd, subsd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(pmullw, pmullw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(pmullw, pmullw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(pmulhw, pmulhw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(pmulhw, pmulhw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(pmulhuw, pmulhuw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(pmulhuw, pmulhuw_xmm, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(pmuludq, pmuludq_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(pmuludq, pmuludq_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(mulps, mulps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(mulpd, mulpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(mulss, mulss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(mulsd, mulsd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(pmaddwd, pmaddwd_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(pmaddwd, pmaddwd_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(divps, divps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(divpd, divpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(divss, divss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(divsd, divsd, Vq, Vq, Wq)
DEF_GEN_INSN2_HELPER_EPP(rcpps, rcpps, Vdq, Wdq)
DEF_GEN_INSN2_HELPER_EPP(rcpss, rcpss, Vd, Wd)
DEF_GEN_INSN2_HELPER_EPP(sqrtps, sqrtps, Vdq, Wdq)
+DEF_GEN_INSN2_HELPER_EPP(sqrtpd, sqrtpd, Vdq, Wdq)
DEF_GEN_INSN2_HELPER_EPP(sqrtss, sqrtss, Vd, Wd)
+DEF_GEN_INSN2_HELPER_EPP(sqrtsd, sqrtsd, Vq, Wq)
DEF_GEN_INSN2_HELPER_EPP(rsqrtps, rsqrtps, Vdq, Wdq)
DEF_GEN_INSN2_HELPER_EPP(rsqrtss, rsqrtss, Vd, Wd)
DEF_GEN_INSN3_GVEC(pminub, Pq, Pq, Qq, umin, MM_OPRSZ, MM_MAXSZ, MO_8)
+DEF_GEN_INSN3_GVEC(pminub, Vdq, Vdq, Wdq, umin, XMM_OPRSZ, XMM_MAXSZ, MO_8)
DEF_GEN_INSN3_GVEC(pminsw, Pq, Pq, Qq, smin, MM_OPRSZ, MM_MAXSZ, MO_16)
+DEF_GEN_INSN3_GVEC(pminsw, Vdq, Vdq, Wdq, smin, XMM_OPRSZ, XMM_MAXSZ, MO_16)
DEF_GEN_INSN3_HELPER_EPP(minps, minps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(minpd, minpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(minss, minss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(minsd, minsd, Vq, Vq, Wq)
DEF_GEN_INSN3_GVEC(pmaxub, Pq, Pq, Qq, umax, MM_OPRSZ, MM_MAXSZ, MO_8)
+DEF_GEN_INSN3_GVEC(pmaxub, Vdq, Vdq, Wdq, umax, XMM_OPRSZ, XMM_MAXSZ, MO_8)
DEF_GEN_INSN3_GVEC(pmaxsw, Pq, Pq, Qq, smax, MM_OPRSZ, MM_MAXSZ, MO_16)
+DEF_GEN_INSN3_GVEC(pmaxsw, Vdq, Vdq, Wdq, smax, XMM_OPRSZ, XMM_MAXSZ, MO_16)
DEF_GEN_INSN3_HELPER_EPP(maxps, maxps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(maxpd, maxpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(maxss, maxss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(maxsd, maxsd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(pavgb, pavgb_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(pavgb, pavgb_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(pavgw, pavgw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(pavgw, pavgw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(psadbw, psadbw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(psadbw, psadbw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_GVEC(pcmpeqb, Pq, Pq, Qq, cmp, MM_OPRSZ, MM_MAXSZ, MO_8,
TCG_COND_EQ)
+DEF_GEN_INSN3_GVEC(pcmpeqb, Vdq, Vdq, Wdq, cmp, XMM_OPRSZ, XMM_MAXSZ, MO_8,
TCG_COND_EQ)
DEF_GEN_INSN3_GVEC(pcmpeqw, Pq, Pq, Qq, cmp, MM_OPRSZ, MM_MAXSZ, MO_16,
TCG_COND_EQ)
+DEF_GEN_INSN3_GVEC(pcmpeqw, Vdq, Vdq, Wdq, cmp, XMM_OPRSZ, XMM_MAXSZ, MO_16,
TCG_COND_EQ)
DEF_GEN_INSN3_GVEC(pcmpeqd, Pq, Pq, Qq, cmp, MM_OPRSZ, MM_MAXSZ, MO_32,
TCG_COND_EQ)
+DEF_GEN_INSN3_GVEC(pcmpeqd, Vdq, Vdq, Wdq, cmp, XMM_OPRSZ, XMM_MAXSZ, MO_32,
TCG_COND_EQ)
DEF_GEN_INSN3_GVEC(pcmpgtb, Pq, Pq, Qq, cmp, MM_OPRSZ, MM_MAXSZ, MO_8,
TCG_COND_GT)
+DEF_GEN_INSN3_GVEC(pcmpgtb, Vdq, Vdq, Wdq, cmp, XMM_OPRSZ, XMM_MAXSZ, MO_8,
TCG_COND_GT)
DEF_GEN_INSN3_GVEC(pcmpgtw, Pq, Pq, Qq, cmp, MM_OPRSZ, MM_MAXSZ, MO_16,
TCG_COND_GT)
+DEF_GEN_INSN3_GVEC(pcmpgtw, Vdq, Vdq, Wdq, cmp, XMM_OPRSZ, XMM_MAXSZ, MO_16,
TCG_COND_GT)
DEF_GEN_INSN3_GVEC(pcmpgtd, Pq, Pq, Qq, cmp, MM_OPRSZ, MM_MAXSZ, MO_32,
TCG_COND_GT)
+DEF_GEN_INSN3_GVEC(pcmpgtd, Vdq, Vdq, Wdq, cmp, XMM_OPRSZ, XMM_MAXSZ, MO_32,
TCG_COND_GT)
DEF_GEN_INSN3_HELPER_EPP(cmpeqps, cmpeqps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(cmpeqpd, cmpeqpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(cmpeqss, cmpeqss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(cmpeqsd, cmpeqsd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(cmpltps, cmpltps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(cmpltpd, cmpltpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(cmpltss, cmpltss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(cmpltsd, cmpltsd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(cmpleps, cmpleps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(cmplepd, cmplepd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(cmpless, cmpless, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(cmplesd, cmplesd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(cmpunordps, cmpunordps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(cmpunordpd, cmpunordpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(cmpunordss, cmpunordss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(cmpunordsd, cmpunordsd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(cmpneqps, cmpneqps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(cmpneqpd, cmpneqpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(cmpneqss, cmpneqss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(cmpneqsd, cmpneqsd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(cmpnltps, cmpnltps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(cmpnltpd, cmpnltpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(cmpnltss, cmpnltss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(cmpnltsd, cmpnltsd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(cmpnleps, cmpnleps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(cmpnlepd, cmpnlepd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(cmpnless, cmpnless, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(cmpnlesd, cmpnlesd, Vq, Vq, Wq)
DEF_GEN_INSN3_HELPER_EPP(cmpordps, cmpordps, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(cmpordpd, cmpordpd, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(cmpordss, cmpordss, Vd, Vd, Wd)
+DEF_GEN_INSN3_HELPER_EPP(cmpordsd, cmpordsd, Vq, Vq, Wq)
GEN_INSN4(cmpps, Vdq, Vdq, Wdq, Ib)
{
@@ -5776,6 +5974,38 @@ GEN_INSN4(cmpps, Vdq, Vdq, Wdq, Ib)
g_assert_not_reached();
}
+GEN_INSN4(cmppd, Vdq, Vdq, Wdq, Ib)
+{
+ switch (arg4 & 7) {
+ case 0:
+ gen_insn3(cmpeqpd, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3);
+ return;
+ case 1:
+ gen_insn3(cmpltpd, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3);
+ return;
+ case 2:
+ gen_insn3(cmplepd, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3);
+ return;
+ case 3:
+ gen_insn3(cmpunordpd, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3);
+ return;
+ case 4:
+ gen_insn3(cmpneqpd, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3);
+ return;
+ case 5:
+ gen_insn3(cmpnltpd, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3);
+ return;
+ case 6:
+ gen_insn3(cmpnlepd, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3);
+ return;
+ case 7:
+ gen_insn3(cmpordpd, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3);
+ return;
+ }
+
+ g_assert_not_reached();
+}
+
GEN_INSN4(cmpss, Vd, Vd, Wd, Ib)
{
switch (arg4 & 7) {
@@ -5808,26 +6038,78 @@ GEN_INSN4(cmpss, Vd, Vd, Wd, Ib)
g_assert_not_reached();
}
+GEN_INSN4(cmpsd, Vq, Vq, Wq, Ib)
+{
+ switch (arg4 & 7) {
+ case 0:
+ gen_insn3(cmpeqsd, Vq, Vq, Wq)(env, s, arg1, arg2, arg3);
+ return;
+ case 1:
+ gen_insn3(cmpltsd, Vq, Vq, Wq)(env, s, arg1, arg2, arg3);
+ return;
+ case 2:
+ gen_insn3(cmplesd, Vq, Vq, Wq)(env, s, arg1, arg2, arg3);
+ return;
+ case 3:
+ gen_insn3(cmpunordsd, Vq, Vq, Wq)(env, s, arg1, arg2, arg3);
+ return;
+ case 4:
+ gen_insn3(cmpneqsd, Vq, Vq, Wq)(env, s, arg1, arg2, arg3);
+ return;
+ case 5:
+ gen_insn3(cmpnltsd, Vq, Vq, Wq)(env, s, arg1, arg2, arg3);
+ return;
+ case 6:
+ gen_insn3(cmpnlesd, Vq, Vq, Wq)(env, s, arg1, arg2, arg3);
+ return;
+ case 7:
+ gen_insn3(cmpordsd, Vq, Vq, Wq)(env, s, arg1, arg2, arg3);
+ return;
+ }
+
+ g_assert_not_reached();
+}
+
DEF_GEN_INSN2_HELPER_EPP(comiss, comiss, Vd, Wd)
+DEF_GEN_INSN2_HELPER_EPP(comisd, comisd, Vq, Wq)
DEF_GEN_INSN2_HELPER_EPP(ucomiss, ucomiss, Vd, Wd)
+DEF_GEN_INSN2_HELPER_EPP(ucomisd, ucomisd, Vq, Wq)
DEF_GEN_INSN3_GVEC(pand, Pq, Pq, Qq, and, MM_OPRSZ, MM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(pand, Vdq, Vdq, Wdq, and, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(andps, Vdq, Vdq, Wdq, and, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(andpd, Vdq, Vdq, Wdq, and, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(pandn, Pq, Pq, Qq, andn, MM_OPRSZ, MM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(pandn, Vdq, Vdq, Wdq, andn, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(andnps, Vdq, Vdq, Wdq, andn, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(andnpd, Vdq, Vdq, Wdq, andn, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(por, Pq, Pq, Qq, or, MM_OPRSZ, MM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(por, Vdq, Vdq, Wdq, or, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(orps, Vdq, Vdq, Wdq, or, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(orpd, Vdq, Vdq, Wdq, or, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(pxor, Pq, Pq, Qq, xor, MM_OPRSZ, MM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(pxor, Vdq, Vdq, Wdq, xor, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_GVEC(xorps, Vdq, Vdq, Wdq, xor, XMM_OPRSZ, XMM_MAXSZ, MO_64)
+DEF_GEN_INSN3_GVEC(xorpd, Vdq, Vdq, Wdq, xor, XMM_OPRSZ, XMM_MAXSZ, MO_64)
DEF_GEN_INSN3_HELPER_EPP(psllw, psllw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(psllw, psllw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(pslld, pslld_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(pslld, pslld_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(psllq, psllq_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(psllq, psllq_xmm, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(pslldq, pslldq_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(psrlw, psrlw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(psrlw, psrlw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(psrld, psrld_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(psrld, psrld_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(psrlq, psrlq_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(psrlq, psrlq_xmm, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(psrldq, psrldq_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(psraw, psraw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(psraw, psraw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(psrad, psrad_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(psrad, psrad_xmm, Vdq, Vdq, Wdq)
#define DEF_GEN_PSHIFT_IMM_MM(mnem, opT1, opT2) \
GEN_INSN3(mnem, opT1, opT2, Ib) \
@@ -5841,31 +6123,70 @@ DEF_GEN_INSN3_HELPER_EPP(psrad, psrad_mmx, Pq, Pq, Qq)
gen_insn2(movq, Pq, Eq)(env, s, arg3_mm, arg3_r64); \
gen_insn3(mnem, Pq, Pq, Qq)(env, s, arg1, arg2, arg3_mm); \
}
+#define DEF_GEN_PSHIFT_IMM_XMM(mnem, opT1, opT2) \
+ GEN_INSN3(mnem, opT1, opT2, Ib) \
+ { \
+ const uint64_t arg3_ui64 = (uint8_t)arg3; \
+ const insnop_arg_t(Eq) arg3_r64 = s->tmp1_i64; \
+ const insnop_arg_t(Wdq) arg3_xmm = \
+ offsetof(CPUX86State, xmm_t0.ZMM_Q(0)); \
+ \
+ tcg_gen_movi_i64(arg3_r64, arg3_ui64); \
+ gen_insn2(movq, Vdq, Eq)(env, s, arg3_xmm, arg3_r64); \
+ gen_insn3(mnem, Vdq, Vdq, Wdq)(env, s, arg1, arg2, arg3_xmm); \
+ }
DEF_GEN_PSHIFT_IMM_MM(psllw, Nq, Nq)
+DEF_GEN_PSHIFT_IMM_XMM(psllw, Udq, Udq)
DEF_GEN_PSHIFT_IMM_MM(pslld, Nq, Nq)
+DEF_GEN_PSHIFT_IMM_XMM(pslld, Udq, Udq)
DEF_GEN_PSHIFT_IMM_MM(psllq, Nq, Nq)
+DEF_GEN_PSHIFT_IMM_XMM(psllq, Udq, Udq)
+DEF_GEN_PSHIFT_IMM_XMM(pslldq, Udq, Udq)
DEF_GEN_PSHIFT_IMM_MM(psrlw, Nq, Nq)
+DEF_GEN_PSHIFT_IMM_XMM(psrlw, Udq, Udq)
DEF_GEN_PSHIFT_IMM_MM(psrld, Nq, Nq)
+DEF_GEN_PSHIFT_IMM_XMM(psrld, Udq, Udq)
DEF_GEN_PSHIFT_IMM_MM(psrlq, Nq, Nq)
+DEF_GEN_PSHIFT_IMM_XMM(psrlq, Udq, Udq)
+DEF_GEN_PSHIFT_IMM_XMM(psrldq, Udq, Udq)
DEF_GEN_PSHIFT_IMM_MM(psraw, Nq, Nq)
+DEF_GEN_PSHIFT_IMM_XMM(psraw, Udq, Udq)
DEF_GEN_PSHIFT_IMM_MM(psrad, Nq, Nq)
+DEF_GEN_PSHIFT_IMM_XMM(psrad, Udq, Udq)
DEF_GEN_INSN3_HELPER_EPP(packsswb, packsswb_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(packsswb, packsswb_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(packssdw, packssdw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(packssdw, packssdw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(packuswb, packuswb_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(packuswb, packuswb_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(punpcklbw, punpcklbw_mmx, Pq, Pq, Qd)
+DEF_GEN_INSN3_HELPER_EPP(punpcklbw, punpcklbw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(punpcklwd, punpcklwd_mmx, Pq, Pq, Qd)
+DEF_GEN_INSN3_HELPER_EPP(punpcklwd, punpcklwd_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(punpckldq, punpckldq_mmx, Pq, Pq, Qd)
+DEF_GEN_INSN3_HELPER_EPP(punpckldq, punpckldq_xmm, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(punpcklqdq, punpcklqdq_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(punpckhbw, punpckhbw_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(punpckhbw, punpckhbw_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(punpckhwd, punpckhwd_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(punpckhwd, punpckhwd_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(punpckhdq, punpckhdq_mmx, Pq, Pq, Qq)
+DEF_GEN_INSN3_HELPER_EPP(punpckhdq, punpckhdq_xmm, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(punpckhqdq, punpckhqdq_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(unpcklps, punpckldq_xmm, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(unpcklpd, punpcklqdq_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_EPP(unpckhps, punpckhdq_xmm, Vdq, Vdq, Wdq)
+DEF_GEN_INSN3_HELPER_EPP(unpckhpd, punpckhqdq_xmm, Vdq, Vdq, Wdq)
DEF_GEN_INSN3_HELPER_PPI(pshufw, pshufw_mmx, Pq, Qq, Ib)
+DEF_GEN_INSN3_HELPER_PPI(pshuflw, pshuflw_xmm, Vdq, Wdq, Ib)
+DEF_GEN_INSN3_HELPER_PPI(pshufhw, pshufhw_xmm, Vdq, Wdq, Ib)
+DEF_GEN_INSN3_HELPER_PPI(pshufd, pshufd_xmm, Vdq, Wdq, Ib)
DEF_GEN_INSN4_HELPER_PPI(shufps, shufps, Vdq, Vdq, Wdq, Ib)
+DEF_GEN_INSN4_HELPER_PPI(shufpd, shufpd, Vdq, Vdq, Wdq, Ib)
GEN_INSN4(pinsrw, Pq, Pq, RdMw, Ib)
{
@@ -5874,6 +6195,13 @@ GEN_INSN4(pinsrw, Pq, Pq, RdMw, Ib)
const size_t ofs = offsetof(MMXReg, MMX_W(arg4 & 3));
tcg_gen_st16_i32(arg3, cpu_env, arg1 + ofs);
}
+GEN_INSN4(pinsrw, Vdq, Vdq, RdMw, Ib)
+{
+ assert(arg1 == arg2);
+
+ const size_t ofs = offsetof(ZMMReg, ZMM_W(arg4 & 7));
+ tcg_gen_st16_i32(arg3, cpu_env, arg1 + ofs);
+}
GEN_INSN3(pextrw, Gd, Nq, Ib)
{
@@ -5885,16 +6213,46 @@ GEN_INSN3(pextrw, Gq, Nq, Ib)
const size_t ofs = offsetof(MMXReg, MMX_W(arg3 & 3));
tcg_gen_ld16u_i64(arg1, cpu_env, arg2 + ofs);
}
+GEN_INSN3(pextrw, Gd, Udq, Ib)
+{
+ const size_t ofs = offsetof(ZMMReg, ZMM_W(arg3 & 7));
+ tcg_gen_ld16u_i32(arg1, cpu_env, arg2 + ofs);
+}
+GEN_INSN3(pextrw, Gq, Udq, Ib)
+{
+ const size_t ofs = offsetof(ZMMReg, ZMM_W(arg3 & 7));
+ tcg_gen_ld16u_i64(arg1, cpu_env, arg2 + ofs);
+}
DEF_GEN_INSN2_HELPER_EPP(cvtpi2ps, cvtpi2ps, Vdq, Qq)
DEF_GEN_INSN2_HELPER_EPD(cvtsi2ss, cvtsi2ss, Vd, Ed)
DEF_GEN_INSN2_HELPER_EPQ(cvtsi2ss, cvtsq2ss, Vd, Eq)
+DEF_GEN_INSN2_HELPER_EPP(cvtpi2pd, cvtpi2pd, Vdq, Qq)
+DEF_GEN_INSN2_HELPER_EPD(cvtsi2sd, cvtsi2sd, Vq, Ed)
+DEF_GEN_INSN2_HELPER_EPQ(cvtsi2sd, cvtsq2sd, Vq, Eq)
DEF_GEN_INSN2_HELPER_EPP(cvtps2pi, cvtps2pi, Pq, Wq)
DEF_GEN_INSN2_HELPER_DEP(cvtss2si, cvtss2si, Gd, Wd)
DEF_GEN_INSN2_HELPER_QEP(cvtss2si, cvtss2sq, Gq, Wd)
+DEF_GEN_INSN2_HELPER_EPP(cvtpd2pi, cvtpd2pi, Pq, Wdq)
+DEF_GEN_INSN2_HELPER_DEP(cvtsd2si, cvtsd2si, Gd, Wq)
+DEF_GEN_INSN2_HELPER_QEP(cvtsd2si, cvtsd2sq, Gq, Wq)
DEF_GEN_INSN2_HELPER_EPP(cvttps2pi, cvttps2pi, Pq, Wq)
DEF_GEN_INSN2_HELPER_DEP(cvttss2si, cvttss2si, Gd, Wd)
DEF_GEN_INSN2_HELPER_QEP(cvttss2si, cvttss2sq, Gq, Wd)
+DEF_GEN_INSN2_HELPER_EPP(cvttpd2pi, cvttpd2pi, Pq, Wdq)
+DEF_GEN_INSN2_HELPER_DEP(cvttsd2si, cvttsd2si, Gd, Wq)
+DEF_GEN_INSN2_HELPER_QEP(cvttsd2si, cvttsd2sq, Gq, Wq)
+
+DEF_GEN_INSN2_HELPER_EPP(cvtpd2dq, cvtpd2dq, Vdq, Wdq)
+DEF_GEN_INSN2_HELPER_EPP(cvttpd2dq, cvttpd2dq, Vdq, Wdq)
+DEF_GEN_INSN2_HELPER_EPP(cvtdq2pd, cvtdq2pd, Vdq, Wq)
+DEF_GEN_INSN2_HELPER_EPP(cvtps2pd, cvtps2pd, Vdq, Wq)
+DEF_GEN_INSN2_HELPER_EPP(cvtpd2ps, cvtpd2ps, Vdq, Wdq)
+DEF_GEN_INSN2_HELPER_EPP(cvtss2sd, cvtss2sd, Vq, Wd)
+DEF_GEN_INSN2_HELPER_EPP(cvtsd2ss, cvtsd2ss, Vd, Wq)
+DEF_GEN_INSN2_HELPER_EPP(cvtdq2ps, cvtdq2ps, Vdq, Wdq)
+DEF_GEN_INSN2_HELPER_EPP(cvtps2dq, cvtps2dq, Vdq, Wdq)
+DEF_GEN_INSN2_HELPER_EPP(cvttps2dq, cvttps2dq, Vdq, Wdq)
GEN_INSN2(maskmovq, Pq, Nq)
{
@@ -5912,25 +6270,90 @@ GEN_INSN2(maskmovq, Pq, Nq)
tcg_temp_free_ptr(arg1_ptr);
tcg_temp_free_ptr(arg2_ptr);
}
+GEN_INSN2(maskmovdqu, Vdq, Udq)
+{
+ const TCGv_ptr arg1_ptr = tcg_temp_new_ptr();
+ const TCGv_ptr arg2_ptr = tcg_temp_new_ptr();
+
+ tcg_gen_mov_tl(s->A0, cpu_regs[R_EDI]);
+ gen_extu(s->aflag, s->A0);
+ gen_add_A0_ds_seg(s);
+
+ tcg_gen_addi_ptr(arg1_ptr, cpu_env, arg1);
+ tcg_gen_addi_ptr(arg2_ptr, cpu_env, arg2);
+ gen_helper_maskmov_xmm(cpu_env, arg1_ptr, arg2_ptr, s->A0);
+
+ tcg_temp_free_ptr(arg1_ptr);
+ tcg_temp_free_ptr(arg2_ptr);
+}
GEN_INSN2(movntps, Mdq, Vdq)
{
insnop_ldst(xmm, Mdq)(env, s, 1, arg2, arg1);
}
+GEN_INSN2(movntpd, Mdq, Vdq)
+{
+ insnop_ldst(xmm, Mdq)(env, s, 1, arg2, arg1);
+}
+
+GEN_INSN2(movnti, Md, Gd)
+{
+ insnop_ldst(tcg_i32, Md)(env, s, 1, arg2, arg1);
+}
+GEN_INSN2(movnti, Mq, Gq)
+{
+ insnop_ldst(tcg_i64, Mq)(env, s, 1, arg2, arg1);
+}
GEN_INSN2(movntq, Mq, Pq)
{
insnop_ldst(mm, Mq)(env, s, 1, arg2, arg1);
}
+GEN_INSN2(movntdq, Mdq, Vdq)
+{
+ insnop_ldst(xmm, Mdq)(env, s, 1, arg2, arg1);
+}
+
+GEN_INSN0(pause)
+{
+ /* handled in disas_insn at the moment */
+ g_assert_not_reached();
+}
DEF_GEN_INSN0_HELPER(emms, emms)
-GEN_INSN0(sfence)
+GEN_INSN2(sfence_clflush, modrm_mod, modrm)
+{
+ if (arg1 == 3) {
+ /* sfence */
+ if (s->prefix & PREFIX_LOCK) {
+ gen_illegal_opcode(s);
+ } else {
+ tcg_gen_mb(TCG_MO_ST_ST | TCG_BAR_SC);
+ }
+ } else {
+ /* clflush */
+ if (!check_cpuid(env, s, CHECK_CPUID_CLFLUSH)) {
+ gen_illegal_opcode(s);
+ } else {
+ gen_nop_modrm(env, s, arg2);
+ }
+ }
+}
+GEN_INSN0(lfence)
+{
+ if (s->prefix & PREFIX_LOCK) {
+ gen_illegal_opcode(s);
+ } else {
+ tcg_gen_mb(TCG_MO_LD_LD | TCG_BAR_SC);
+ }
+}
+GEN_INSN0(mfence)
{
if (s->prefix & PREFIX_LOCK) {
gen_illegal_opcode(s);
} else {
- tcg_gen_mb(TCG_MO_ST_ST | TCG_BAR_SC);
+ tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC);
}
}
--
2.20.1
- [Qemu-devel] [RFC PATCH v4 48/75] target/i386: introduce SSSE3 translators, (continued)
- [Qemu-devel] [RFC PATCH v4 48/75] target/i386: introduce SSSE3 translators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 44/75] target/i386: introduce SSE2 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 62/75] target/i386: introduce AVX2 translators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 53/75] target/i386: introduce SSE4.1 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 59/75] target/i386: introduce AVX translators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 47/75] target/i386: introduce SSE3 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 51/75] target/i386: introduce SSE4.1 translators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 66/75] target/i386: cleanup leftovers in ops_sse_header.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 67/75] target/i386: introduce aliases for helper-based tcg_gen_gvec_* functions, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 69/75] target/i386: convert pmullw/pmulhw/pmulhuw helpers to gvec style, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 43/75] target/i386: introduce SSE2 code generators,
Jan Bobek <=
- [Qemu-devel] [RFC PATCH v4 50/75] target/i386: introduce SSSE3 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 55/75] target/i386: introduce SSE4.2 vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 57/75] target/i386: introduce AES and PCLMULQDQ code generators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 58/75] target/i386: introduce AES and PCLMULQDQ vector instructions to sse-opcode.inc.h, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 65/75] target/i386: remove obsoleted helpers, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 49/75] target/i386: introduce SSSE3 code generators, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 70/75] target/i386: convert pavgb/pavgw helpers to gvec style, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 71/75] target/i386: convert pmuludq/pmaddwd helpers to gvec style, Jan Bobek, 2019/08/21
- [Qemu-devel] [RFC PATCH v4 73/75] target/i386: remove obsoleted helper_mov(l, q)_mm_T0, Jan Bobek, 2019/08/21