Skip to content

Q
qemu

openeuler / qemu

通知 10
Star 0
Fork 0
Q
qemu
提交 b357f902 编写于 作者: R Richard Henderson
浏览文件
操作

tcg-sparc: Hoist common argument loads in tcg_out_op 

Signed-off-by: NRichard Henderson <rth@twiddle.net>
上级 98b90bab
隐藏空白更改
内联 并排
Showing with 60 addition and 63 deletion
tcg/sparc/tcg-target.c
浏览文件 @ b357f902
......@@ -1142,49 +1142,56 @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data, TCGReg addr,
#endif /* CONFIG_SOFTMMU */
}
static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
const int *const_args)
static void tcg_out_op(TCGContext *s, TCGOpcode opc,
const TCGArg args[TCG_MAX_OP_ARGS],
const int const_args[TCG_MAX_OP_ARGS])
{
int c;
TCGArg a0, a1, a2;
int c, c2;
/* Hoist the loads of the most common arguments. */
a0 = args[0];
a1 = args[1];
a2 = args[2];
c2 = const_args[2];
switch (opc) {
case INDEX_op_exit_tb:
if (check_fit_ptr(args[0], 13)) {
if (check_fit_ptr(a0, 13)) {
tcg_out_arithi(s, TCG_REG_G0, TCG_REG_I7, 8, RETURN);
tcg_out_movi_imm13(s, TCG_REG_O0, args[0]);
tcg_out_movi_imm13(s, TCG_REG_O0, a0);
} else {
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_I0, args[0] & ~0x3ff);
tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_I0, a0 & ~0x3ff);
tcg_out_arithi(s, TCG_REG_G0, TCG_REG_I7, 8, RETURN);
tcg_out_arithi(s, TCG_REG_O0, TCG_REG_O0,
args[0] & 0x3ff, ARITH_OR);
tcg_out_arithi(s, TCG_REG_O0, TCG_REG_O0, a0 & 0x3ff, ARITH_OR);
}
break;
case INDEX_op_goto_tb:
if (s->tb_jmp_offset) {
/* direct jump method */
uint32_t old_insn = *(uint32_t *)s->code_ptr;
s->tb_jmp_offset[args[0]] = s->code_ptr - s->code_buf;
s->tb_jmp_offset[a0] = s->code_ptr - s->code_buf;
/* Make sure to preserve links during retranslation. */
tcg_out32(s, CALL | (old_insn & ~INSN_OP(-1)));
} else {
/* indirect jump method */
tcg_out_ld_ptr(s, TCG_REG_T1, (uintptr_t)(s->tb_next + args[0]));
tcg_out_ld_ptr(s, TCG_REG_T1, (uintptr_t)(s->tb_next + a0));
tcg_out_arithi(s, TCG_REG_G0, TCG_REG_T1, 0, JMPL);
}
tcg_out_nop(s);
s->tb_next_offset[args[0]] = s->code_ptr - s->code_buf;
s->tb_next_offset[a0] = s->code_ptr - s->code_buf;
break;
case INDEX_op_call:
if (const_args[0]) {
tcg_out_calli(s, args[0]);
tcg_out_calli(s, a0);
} else {
tcg_out_arithi(s, TCG_REG_O7, args[0], 0, JMPL);
tcg_out_arithi(s, TCG_REG_O7, a0, 0, JMPL);
}
/* delay slot */
tcg_out_nop(s);
break;
case INDEX_op_br:
tcg_out_bpcc(s, COND_A, BPCC_PT, args[0]);
tcg_out_bpcc(s, COND_A, BPCC_PT, a0);
tcg_out_nop(s);
break;
......@@ -1193,30 +1200,30 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
glue(glue(case INDEX_op_, x), _i64)
OP_32_64(ld8u):
tcg_out_ldst(s, args[0], args[1], args[2], LDUB);
tcg_out_ldst(s, a0, a1, a2, LDUB);
break;
OP_32_64(ld8s):
tcg_out_ldst(s, args[0], args[1], args[2], LDSB);
tcg_out_ldst(s, a0, a1, a2, LDSB);
break;
OP_32_64(ld16u):
tcg_out_ldst(s, args[0], args[1], args[2], LDUH);
tcg_out_ldst(s, a0, a1, a2, LDUH);
break;
OP_32_64(ld16s):
tcg_out_ldst(s, args[0], args[1], args[2], LDSH);
tcg_out_ldst(s, a0, a1, a2, LDSH);
break;
case INDEX_op_ld_i32:
case INDEX_op_ld32u_i64:
tcg_out_ldst(s, args[0], args[1], args[2], LDUW);
tcg_out_ldst(s, a0, a1, a2, LDUW);
break;
OP_32_64(st8):
tcg_out_ldst(s, args[0], args[1], args[2], STB);
tcg_out_ldst(s, a0, a1, a2, STB);
break;
OP_32_64(st16):
tcg_out_ldst(s, args[0], args[1], args[2], STH);
tcg_out_ldst(s, a0, a1, a2, STH);
break;
case INDEX_op_st_i32:
case INDEX_op_st32_i64:
tcg_out_ldst(s, args[0], args[1], args[2], STW);
tcg_out_ldst(s, a0, a1, a2, STW);
break;
OP_32_64(add):
c = ARITH_ADD;
......@@ -1243,7 +1250,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
c = SHIFT_SLL;
do_shift32:
/* Limit immediate shift count lest we create an illegal insn. */
tcg_out_arithc(s, args[0], args[1], args[2] & 31, const_args[2], c);
tcg_out_arithc(s, a0, a1, a2 & 31, c2, c);
break;
case INDEX_op_shr_i32:
c = SHIFT_SRL;
......@@ -1263,34 +1270,29 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
goto gen_arith1;
case INDEX_op_div_i32:
tcg_out_div32(s, args[0], args[1], args[2], const_args[2], 0);
tcg_out_div32(s, a0, a1, a2, c2, 0);
break;
case INDEX_op_divu_i32:
tcg_out_div32(s, args[0], args[1], args[2], const_args[2], 1);
tcg_out_div32(s, a0, a1, a2, c2, 1);
break;
case INDEX_op_brcond_i32:
tcg_out_brcond_i32(s, args[2], args[0], args[1], const_args[1],
args[3]);
tcg_out_brcond_i32(s, a2, a0, a1, const_args[1], args[3]);
break;
case INDEX_op_setcond_i32:
tcg_out_setcond_i32(s, args[3], args[0], args[1],
args[2], const_args[2]);
tcg_out_setcond_i32(s, args[3], a0, a1, a2, c2);
break;
case INDEX_op_movcond_i32:
tcg_out_movcond_i32(s, args[5], args[0], args[1],
args[2], const_args[2], args[3], const_args[3]);
tcg_out_movcond_i32(s, args[5], a0, a1, a2, c2, args[3], const_args[3]);
break;
case INDEX_op_add2_i32:
tcg_out_addsub2(s, args[0], args[1], args[2], args[3],
args[4], const_args[4], args[5], const_args[5],
ARITH_ADDCC, ARITH_ADDX);
tcg_out_addsub2(s, a0, a1, a2, args[3], args[4], const_args[4],
args[5], const_args[5], ARITH_ADDCC, ARITH_ADDX);
break;
case INDEX_op_sub2_i32:
tcg_out_addsub2(s, args[0], args[1], args[2], args[3],
args[4], const_args[4], args[5], const_args[5],
ARITH_SUBCC, ARITH_SUBX);
tcg_out_addsub2(s, a0, a1, a2, args[3], args[4], const_args[4],
args[5], const_args[5], ARITH_SUBCC, ARITH_SUBX);
break;
case INDEX_op_mulu2_i32:
c = ARITH_UMUL;
......@@ -1300,41 +1302,39 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
do_mul2:
/* The 32-bit multiply insns produce a full 64-bit result. If the
destination register can hold it, we can avoid the slower RDY. */
tcg_out_arithc(s, args[0], args[2], args[3], const_args[3], c);
if (SPARC64 || args[0] <= TCG_REG_O7) {
tcg_out_arithi(s, args[1], args[0], 32, SHIFT_SRLX);
tcg_out_arithc(s, a0, a2, args[3], const_args[3], c);
if (SPARC64 || a0 <= TCG_REG_O7) {
tcg_out_arithi(s, a1, a0, 32, SHIFT_SRLX);
} else {
tcg_out_rdy(s, args[1]);
tcg_out_rdy(s, a1);
}
break;
case INDEX_op_qemu_ld_i32:
tcg_out_qemu_ld(s, args[0], args[1], args[2], args[3], false);
tcg_out_qemu_ld(s, a0, a1, a2, args[3], false);
break;
case INDEX_op_qemu_ld_i64:
tcg_out_qemu_ld(s, args[0], args[1], args[2], args[3], true);
tcg_out_qemu_ld(s, a0, a1, a2, args[3], true);
break;
case INDEX_op_qemu_st_i32:
tcg_out_qemu_st(s, args[0], args[1], args[2], args[3]);
break;
case INDEX_op_qemu_st_i64:
tcg_out_qemu_st(s, args[0], args[1], args[2], args[3]);
tcg_out_qemu_st(s, a0, a1, a2, args[3]);
break;
case INDEX_op_ld32s_i64:
tcg_out_ldst(s, args[0], args[1], args[2], LDSW);
tcg_out_ldst(s, a0, a1, a2, LDSW);
break;
case INDEX_op_ld_i64:
tcg_out_ldst(s, args[0], args[1], args[2], LDX);
tcg_out_ldst(s, a0, a1, a2, LDX);
break;
case INDEX_op_st_i64:
tcg_out_ldst(s, args[0], args[1], args[2], STX);
tcg_out_ldst(s, a0, a1, a2, STX);
break;
case INDEX_op_shl_i64:
c = SHIFT_SLLX;
do_shift64:
/* Limit immediate shift count lest we create an illegal insn. */
tcg_out_arithc(s, args[0], args[1], args[2] & 63, const_args[2], c);
tcg_out_arithc(s, a0, a1, a2 & 63, c2, c);
break;
case INDEX_op_shr_i64:
c = SHIFT_SRLX;
......@@ -1352,38 +1352,35 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
c = ARITH_UDIVX;
goto gen_arith;
case INDEX_op_ext32s_i64:
tcg_out_arithi(s, args[0], args[1], 0, SHIFT_SRA);
tcg_out_arithi(s, a0, a1, 0, SHIFT_SRA);
break;
case INDEX_op_ext32u_i64:
tcg_out_arithi(s, args[0], args[1], 0, SHIFT_SRL);
tcg_out_arithi(s, a0, a1, 0, SHIFT_SRL);
break;
case INDEX_op_trunc_shr_i32:
if (args[2] == 0) {
tcg_out_mov(s, TCG_TYPE_I32, args[0], args[1]);
if (a2 == 0) {
tcg_out_mov(s, TCG_TYPE_I32, a0, a1);
} else {
tcg_out_arithi(s, args[0], args[1], args[2], SHIFT_SRLX);
tcg_out_arithi(s, a0, a1, a2, SHIFT_SRLX);
}
break;
case INDEX_op_brcond_i64:
tcg_out_brcond_i64(s, args[2], args[0], args[1], const_args[1],
args[3]);
tcg_out_brcond_i64(s, a2, a0, a1, const_args[1], args[3]);
break;
case INDEX_op_setcond_i64:
tcg_out_setcond_i64(s, args[3], args[0], args[1],
args[2], const_args[2]);
tcg_out_setcond_i64(s, args[3], a0, a1, a2, c2);
break;
case INDEX_op_movcond_i64:
tcg_out_movcond_i64(s, args[5], args[0], args[1],
args[2], const_args[2], args[3], const_args[3]);
tcg_out_movcond_i64(s, args[5], a0, a1, a2, c2, args[3], const_args[3]);
break;
gen_arith:
tcg_out_arithc(s, args[0], args[1], args[2], const_args[2], c);
tcg_out_arithc(s, a0, a1, a2, c2, c);
break;
gen_arith1:
tcg_out_arithc(s, args[0], TCG_REG_G0, args[1], const_args[1], c);
tcg_out_arithc(s, a0, TCG_REG_G0, a1, const_args[1], c);
break;
case INDEX_op_mov_i64:
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或