| Message ID | 4bba2d47c5a2b61e2e68b0546f27183b7277a5d4.1272479073.git.rth@twiddle.net |
|---|---|
| State | New |
| Headers | show |
On Wed, Apr 14, 2010 at 01:29:27PM -0700, Richard Henderson wrote: > The result is shorter than the mov+add that TCG would > otherwise generate for us. > > Signed-off-by: Richard Henderson <rth@twiddle.net> Acked-by: Aurelien Jarno <aurelien@aurel32.net> > --- > tcg/i386/tcg-target.c | 23 ++++++++++++++++++++--- > 1 files changed, 20 insertions(+), 3 deletions(-) > > diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c > index 755d46d..646a7b6 100644 > --- a/tcg/i386/tcg-target.c > +++ b/tcg/i386/tcg-target.c > @@ -1186,6 +1186,25 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, > case INDEX_op_st_i32: > tcg_out_st(s, TCG_TYPE_I32, args[0], args[1], args[2]); > break; > + case INDEX_op_add_i32: > + /* For 3-operand addition, use LEA. */ > + if (args[0] != args[1]) { > + TCGArg a0 = args[0], a1 = args[1], a2 = args[2], c3 = 0; > + > + if (const_args[2]) { > + c3 = a2, a2 = -1; > + } else if (a0 == a2) { > + /* Watch out for dest = src + dest, since we've removed > + the matching constraint on the add. */ > + tgen_arithr(s, ARITH_ADD, a0, a1); > + break; > + } > + > + tcg_out_modrm_sib_offset(s, OPC_LEA, a0, a1, a2, 0, c3); > + break; > + } > + c = ARITH_ADD; > + goto gen_arith; > case INDEX_op_sub_i32: > c = ARITH_SUB; > goto gen_arith; > @@ -1198,8 +1217,6 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, > case INDEX_op_xor_i32: > c = ARITH_XOR; > goto gen_arith; > - case INDEX_op_add_i32: > - c = ARITH_ADD; > gen_arith: > if (const_args[2]) { > tgen_arithi(s, c, args[0], args[2], 0); > @@ -1374,7 +1391,7 @@ static const TCGTargetOpDef x86_op_defs[] = { > { INDEX_op_st16_i32, { "r", "r" } }, > { INDEX_op_st_i32, { "r", "r" } }, > > - { INDEX_op_add_i32, { "r", "0", "ri" } }, > + { INDEX_op_add_i32, { "r", "r", "ri" } }, > { INDEX_op_sub_i32, { "r", "0", "ri" } }, > { INDEX_op_mul_i32, { "r", "0", "ri" } }, > { INDEX_op_mulu2_i32, { "a", "d", "a", "r" } }, > -- > 1.6.6.1 > > > >
diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c index 755d46d..646a7b6 100644 --- a/tcg/i386/tcg-target.c +++ b/tcg/i386/tcg-target.c @@ -1186,6 +1186,25 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, case INDEX_op_st_i32: tcg_out_st(s, TCG_TYPE_I32, args[0], args[1], args[2]); break; + case INDEX_op_add_i32: + /* For 3-operand addition, use LEA. */ + if (args[0] != args[1]) { + TCGArg a0 = args[0], a1 = args[1], a2 = args[2], c3 = 0; + + if (const_args[2]) { + c3 = a2, a2 = -1; + } else if (a0 == a2) { + /* Watch out for dest = src + dest, since we've removed + the matching constraint on the add. */ + tgen_arithr(s, ARITH_ADD, a0, a1); + break; + } + + tcg_out_modrm_sib_offset(s, OPC_LEA, a0, a1, a2, 0, c3); + break; + } + c = ARITH_ADD; + goto gen_arith; case INDEX_op_sub_i32: c = ARITH_SUB; goto gen_arith; @@ -1198,8 +1217,6 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, case INDEX_op_xor_i32: c = ARITH_XOR; goto gen_arith; - case INDEX_op_add_i32: - c = ARITH_ADD; gen_arith: if (const_args[2]) { tgen_arithi(s, c, args[0], args[2], 0); @@ -1374,7 +1391,7 @@ static const TCGTargetOpDef x86_op_defs[] = { { INDEX_op_st16_i32, { "r", "r" } }, { INDEX_op_st_i32, { "r", "r" } }, - { INDEX_op_add_i32, { "r", "0", "ri" } }, + { INDEX_op_add_i32, { "r", "r", "ri" } }, { INDEX_op_sub_i32, { "r", "0", "ri" } }, { INDEX_op_mul_i32, { "r", "0", "ri" } }, { INDEX_op_mulu2_i32, { "a", "d", "a", "r" } },
The result is shorter than the mov+add that TCG would otherwise generate for us. Signed-off-by: Richard Henderson <rth@twiddle.net> --- tcg/i386/tcg-target.c | 23 ++++++++++++++++++++--- 1 files changed, 20 insertions(+), 3 deletions(-)