[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v2 08/42] i386: Add ZMM_OFFSET macro
|
From: |
Paul Brook |
|
Subject: |
[PATCH v2 08/42] i386: Add ZMM_OFFSET macro |
|
Date: |
Sun, 24 Apr 2022 23:01:30 +0100 |
Add a convenience macro to get the address of an xmm_regs element within
CPUX86State.
This was originally going to be the basis of an implementation that broke
operations into 128 bit chunks. I scrapped that idea, so this is now a purely
cosmetic change. But I think a worthwhile one - it reduces the number of
function calls that need to be split over multiple lines.
No functional changes.
Signed-off-by: Paul Brook <paul@nowt.org>
---
target/i386/tcg/translate.c | 60 +++++++++++++++++--------------------
1 file changed, 27 insertions(+), 33 deletions(-)
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index 2f5cc24e0c..e9e6062b7f 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -2777,6 +2777,8 @@ static inline void gen_op_movq_env_0(DisasContext *s, int
d_offset)
tcg_gen_st_i64(s->tmp1_i64, cpu_env, d_offset);
}
+#define ZMM_OFFSET(reg) offsetof(CPUX86State, xmm_regs[reg])
+
typedef void (*SSEFunc_i_ep)(TCGv_i32 val, TCGv_ptr env, TCGv_ptr reg);
typedef void (*SSEFunc_l_ep)(TCGv_i64 val, TCGv_ptr env, TCGv_ptr reg);
typedef void (*SSEFunc_0_epi)(TCGv_ptr env, TCGv_ptr reg, TCGv_i32 val);
@@ -3329,14 +3331,14 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
if (mod == 3)
goto illegal_op;
gen_lea_modrm(env, s, modrm);
- gen_sto_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
+ gen_sto_env_A0(s, ZMM_OFFSET(reg));
break;
case 0x3f0: /* lddqu */
CHECK_AVX_V0(s);
if (mod == 3)
goto illegal_op;
gen_lea_modrm(env, s, modrm);
- gen_ldo_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
+ gen_ldo_env_A0(s, ZMM_OFFSET(reg));
break;
case 0x22b: /* movntss */
case 0x32b: /* movntsd */
@@ -3375,15 +3377,13 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
#ifdef TARGET_X86_64
if (s->dflag == MO_64) {
gen_ldst_modrm(env, s, modrm, MO_64, OR_TMP0, 0);
- tcg_gen_addi_ptr(s->ptr0, cpu_env,
- offsetof(CPUX86State,xmm_regs[reg]));
+ tcg_gen_addi_ptr(s->ptr0, cpu_env, ZMM_OFFSET(reg));
gen_helper_movq_mm_T0_xmm(s->ptr0, s->T0);
} else
#endif
{
gen_ldst_modrm(env, s, modrm, MO_32, OR_TMP0, 0);
- tcg_gen_addi_ptr(s->ptr0, cpu_env,
- offsetof(CPUX86State,xmm_regs[reg]));
+ tcg_gen_addi_ptr(s->ptr0, cpu_env, ZMM_OFFSET(reg));
tcg_gen_trunc_tl_i32(s->tmp2_i32, s->T0);
gen_helper_movl_mm_T0_xmm(s->ptr0, s->tmp2_i32);
}
@@ -3410,11 +3410,10 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
CHECK_AVX_V0(s);
if (mod != 3) {
gen_lea_modrm(env, s, modrm);
- gen_ldo_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
+ gen_ldo_env_A0(s, ZMM_OFFSET(reg));
} else {
rm = (modrm & 7) | REX_B(s);
- gen_op_movo(s, offsetof(CPUX86State, xmm_regs[reg]),
- offsetof(CPUX86State,xmm_regs[rm]));
+ gen_op_movo(s, ZMM_OFFSET(reg), ZMM_OFFSET(rm));
}
break;
case 0x210: /* movss xmm, ea */
@@ -3474,7 +3473,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
CHECK_AVX_V0(s);
if (mod != 3) {
gen_lea_modrm(env, s, modrm);
- gen_ldo_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
+ gen_ldo_env_A0(s, ZMM_OFFSET(reg));
} else {
rm = (modrm & 7) | REX_B(s);
gen_op_movl(s, offsetof(CPUX86State, xmm_regs[reg].ZMM_L(0)),
@@ -3519,7 +3518,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
CHECK_AVX_V0(s);
if (mod != 3) {
gen_lea_modrm(env, s, modrm);
- gen_ldo_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
+ gen_ldo_env_A0(s, ZMM_OFFSET(reg));
} else {
rm = (modrm & 7) | REX_B(s);
gen_op_movl(s, offsetof(CPUX86State, xmm_regs[reg].ZMM_L(1)),
@@ -3542,8 +3541,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
goto illegal_op;
field_length = x86_ldub_code(env, s) & 0x3F;
bit_index = x86_ldub_code(env, s) & 0x3F;
- tcg_gen_addi_ptr(s->ptr0, cpu_env,
- offsetof(CPUX86State,xmm_regs[reg]));
+ tcg_gen_addi_ptr(s->ptr0, cpu_env, ZMM_OFFSET(reg));
if (b1 == 1)
gen_helper_extrq_i(cpu_env, s->ptr0,
tcg_const_i32(bit_index),
@@ -3617,11 +3615,10 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
CHECK_AVX_V0(s);
if (mod != 3) {
gen_lea_modrm(env, s, modrm);
- gen_sto_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
+ gen_sto_env_A0(s, ZMM_OFFSET(reg));
} else {
rm = (modrm & 7) | REX_B(s);
- gen_op_movo(s, offsetof(CPUX86State, xmm_regs[rm]),
- offsetof(CPUX86State,xmm_regs[reg]));
+ gen_op_movo(s, ZMM_OFFSET(rm), ZMM_OFFSET(reg));
}
break;
case 0x211: /* movss ea, xmm */
@@ -3708,7 +3705,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
}
if (is_xmm) {
rm = (modrm & 7) | REX_B(s);
- op2_offset = offsetof(CPUX86State,xmm_regs[rm]);
+ op2_offset = ZMM_OFFSET(rm);
} else {
rm = (modrm & 7);
op2_offset = offsetof(CPUX86State,fpregs[rm].mmx);
@@ -3720,16 +3717,14 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
case 0x050: /* movmskps */
CHECK_AVX_V0(s);
rm = (modrm & 7) | REX_B(s);
- tcg_gen_addi_ptr(s->ptr0, cpu_env,
- offsetof(CPUX86State,xmm_regs[rm]));
+ tcg_gen_addi_ptr(s->ptr0, cpu_env, ZMM_OFFSET(rm));
gen_helper_movmskps(s->tmp2_i32, cpu_env, s->ptr0);
tcg_gen_extu_i32_tl(cpu_regs[reg], s->tmp2_i32);
break;
case 0x150: /* movmskpd */
CHECK_AVX_V0(s);
rm = (modrm & 7) | REX_B(s);
- tcg_gen_addi_ptr(s->ptr0, cpu_env,
- offsetof(CPUX86State,xmm_regs[rm]));
+ tcg_gen_addi_ptr(s->ptr0, cpu_env, ZMM_OFFSET(rm));
gen_helper_movmskpd(s->tmp2_i32, cpu_env, s->ptr0);
tcg_gen_extu_i32_tl(cpu_regs[reg], s->tmp2_i32);
break;
@@ -3745,7 +3740,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
rm = (modrm & 7);
op2_offset = offsetof(CPUX86State,fpregs[rm].mmx);
}
- op1_offset = offsetof(CPUX86State,xmm_regs[reg]);
+ op1_offset = ZMM_OFFSET(reg);
tcg_gen_addi_ptr(s->ptr0, cpu_env, op1_offset);
tcg_gen_addi_ptr(s->ptr1, cpu_env, op2_offset);
switch(b >> 8) {
@@ -3763,7 +3758,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
CHECK_AVX(s);
ot = mo_64_32(s->dflag);
gen_ldst_modrm(env, s, modrm, ot, OR_TMP0, 0);
- op1_offset = offsetof(CPUX86State,xmm_regs[reg]);
+ op1_offset = ZMM_OFFSET(reg);
tcg_gen_addi_ptr(s->ptr0, cpu_env, op1_offset);
if (ot == MO_32) {
SSEFunc_0_epi sse_fn_epi = sse_op_table3ai[(b >> 8) & 1];
@@ -3790,7 +3785,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
gen_ldo_env_A0(s, op2_offset);
} else {
rm = (modrm & 7) | REX_B(s);
- op2_offset = offsetof(CPUX86State,xmm_regs[rm]);
+ op2_offset = ZMM_OFFSET(rm);
}
op1_offset = offsetof(CPUX86State,fpregs[reg & 7].mmx);
tcg_gen_addi_ptr(s->ptr0, cpu_env, op1_offset);
@@ -3828,7 +3823,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
op2_offset = offsetof(CPUX86State,xmm_t0);
} else {
rm = (modrm & 7) | REX_B(s);
- op2_offset = offsetof(CPUX86State,xmm_regs[rm]);
+ op2_offset = ZMM_OFFSET(rm);
}
tcg_gen_addi_ptr(s->ptr0, cpu_env, op2_offset);
if (ot == MO_32) {
@@ -3921,8 +3916,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
if (b1) {
CHECK_AVX_V0(s);
rm = (modrm & 7) | REX_B(s);
- tcg_gen_addi_ptr(s->ptr0, cpu_env,
- offsetof(CPUX86State, xmm_regs[rm]));
+ tcg_gen_addi_ptr(s->ptr0, cpu_env, ZMM_OFFSET(rm));
gen_helper_pmovmskb_xmm(s->tmp2_i32, cpu_env, s->ptr0);
} else {
CHECK_NO_VEX(s);
@@ -3969,7 +3963,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
} else {
CHECK_AVX(s);
}
- op1_offset = offsetof(CPUX86State,xmm_regs[reg]);
+ op1_offset = ZMM_OFFSET(reg);
if (op6.flags & SSE_OPF_MMX) {
CHECK_AVX2_256(s);
@@ -3983,7 +3977,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
}
if (mod == 3) {
- op2_offset = offsetof(CPUX86State,xmm_regs[rm | REX_B(s)]);
+ op2_offset = ZMM_OFFSET(rm | REX_B(s));
} else {
op2_offset = offsetof(CPUX86State,xmm_t0);
gen_lea_modrm(env, s, modrm);
@@ -4580,9 +4574,9 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
}
if (b1) {
- op1_offset = offsetof(CPUX86State,xmm_regs[reg]);
+ op1_offset = ZMM_OFFSET(reg);
if (mod == 3) {
- op2_offset = offsetof(CPUX86State,xmm_regs[rm | REX_B(s)]);
+ op2_offset = ZMM_OFFSET(rm | REX_B(s));
} else {
op2_offset = offsetof(CPUX86State,xmm_t0);
gen_lea_modrm(env, s, modrm);
@@ -4679,7 +4673,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
if (sse_op.flags & SSE_OPF_MMX) {
CHECK_AVX2_256(s);
}
- op1_offset = offsetof(CPUX86State,xmm_regs[reg]);
+ op1_offset = ZMM_OFFSET(reg);
if (mod != 3) {
int sz = 4;
@@ -4726,7 +4720,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s,
int b,
}
} else {
rm = (modrm & 7) | REX_B(s);
- op2_offset = offsetof(CPUX86State,xmm_regs[rm]);
+ op2_offset = ZMM_OFFSET(rm);
}
} else {
CHECK_NO_VEX(s);
--
2.36.0
- [PATCH v2 06/42] i386: Add CHECK_NO_VEX, (continued)
- [PATCH v2 06/42] i386: Add CHECK_NO_VEX, Paul Brook, 2022/04/24
- [PATCH v2 02/42] i386: DPPS rounding fix, Paul Brook, 2022/04/24
- [PATCH v2 09/42] i386: Helper macro for 256 bit AVX helpers, Paul Brook, 2022/04/24
- [PATCH v2 07/42] Enforce VEX encoding restrictions, Paul Brook, 2022/04/24
- [PATCH v2 08/42] i386: Add ZMM_OFFSET macro,
Paul Brook <=
- [PATCH v2 04/42] i386: Rework sse_op_table1, Paul Brook, 2022/04/24
- [PATCH v2 05/42] i386: Rework sse_op_table6/7, Paul Brook, 2022/04/24
- [PATCH v2 03/42] Add AVX_EN hflag, Paul Brook, 2022/04/24
- [PATCH v2 10/42] i386: Rewrite vector shift helper, Paul Brook, 2022/04/24
- [PATCH v2 17/42] i386: Destructive FP helpers for AVX, Paul Brook, 2022/04/24
- [PATCH v2 30/42] i386: Implement VPERMIL, Paul Brook, 2022/04/24