target/i386: reimplement 0x0f 0x60-0x6f, add AVX

These are both MMX and SSE/AVX instructions, except for vmovdqu.  In both
cases the inputs and output is in s->ptr{0,1,2}, so the only difference
between MMX, SSE, and AVX is which helper to call.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Paolo Bonzini 2022-09-20 05:42:45 -04:00
parent b98f886c8f
commit 92ec056a6b
3 changed files with 262 additions and 1 deletions

View file

@ -135,6 +135,19 @@ static uint8_t get_modrm(DisasContext *s, CPUX86State *env)
return s->modrm;
}
static inline const X86OpEntry *decode_by_prefix(DisasContext *s, const X86OpEntry entries[4])
{
if (s->prefix & PREFIX_REPNZ) {
return &entries[3];
} else if (s->prefix & PREFIX_REPZ) {
return &entries[2];
} else if (s->prefix & PREFIX_DATA) {
return &entries[1];
} else {
return &entries[0];
}
}
static void decode_group17(DisasContext *s, CPUX86State *env, X86OpEntry *entry, uint8_t *b)
{
static const X86GenFunc group17_gen[8] = {
@ -144,6 +157,17 @@ static void decode_group17(DisasContext *s, CPUX86State *env, X86OpEntry *entry,
entry->gen = group17_gen[op];
}
static void decode_0F6F(DisasContext *s, CPUX86State *env, X86OpEntry *entry, uint8_t *b)
{
static const X86OpEntry opcodes_0F6F[4] = {
X86_OP_ENTRY3(MOVDQ, P,q, None,None, Q,q, vex1 mmx), /* movq */
X86_OP_ENTRY3(MOVDQ, V,x, None,None, W,x, vex1), /* movdqa */
X86_OP_ENTRY3(MOVDQ, V,x, None,None, W,x, vex4_unal), /* movdqu */
{},
};
*entry = *decode_by_prefix(s, opcodes_0F6F);
}
static const X86OpEntry opcodes_0F38_00toEF[240] = {
};
@ -229,8 +253,26 @@ static void decode_0F3A(DisasContext *s, CPUX86State *env, X86OpEntry *entry, ui
}
static const X86OpEntry opcodes_0F[256] = {
[0x60] = X86_OP_ENTRY3(PUNPCKLBW, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x61] = X86_OP_ENTRY3(PUNPCKLWD, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x62] = X86_OP_ENTRY3(PUNPCKLDQ, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x63] = X86_OP_ENTRY3(PACKSSWB, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x64] = X86_OP_ENTRY3(PCMPGTB, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x65] = X86_OP_ENTRY3(PCMPGTW, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x66] = X86_OP_ENTRY3(PCMPGTD, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x67] = X86_OP_ENTRY3(PACKUSWB, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x38] = X86_OP_GROUP0(0F38),
[0x3a] = X86_OP_GROUP0(0F3A),
[0x68] = X86_OP_ENTRY3(PUNPCKHBW, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x69] = X86_OP_ENTRY3(PUNPCKHWD, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x6a] = X86_OP_ENTRY3(PUNPCKHDQ, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x6b] = X86_OP_ENTRY3(PACKSSDW, V,x, H,x, W,x, vex4 mmx avx2_256 p_00_66),
[0x6c] = X86_OP_ENTRY3(PUNPCKLQDQ, V,x, H,x, W,x, vex4 p_66 avx2_256),
[0x6d] = X86_OP_ENTRY3(PUNPCKHQDQ, V,x, H,x, W,x, vex4 p_66 avx2_256),
[0x6e] = X86_OP_ENTRY3(MOVD_to, V,x, None,None, E,y, vex5 mmx p_00_66), /* wrong dest Vy on SDM! */
[0x6f] = X86_OP_GROUP0(0F6F),
};
static void do_decode_0F(DisasContext *s, CPUX86State *env, X86OpEntry *entry, uint8_t *b)