diff options
| -rw-r--r-- | include/tcg/tcg.h | 4 | ||||
| -rw-r--r-- | tcg/i386/tcg-target.c.inc | 9 | ||||
| -rw-r--r-- | tcg/tcg-op-vec.c | 34 |
3 files changed, 6 insertions, 41 deletions
diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index 00c4fbe..d620012 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -999,10 +999,6 @@ void tcg_optimize(TCGContext *s); /* Allocate a new temporary and initialize it with a constant. */ TCGv_i32 tcg_const_i32(int32_t val); TCGv_i64 tcg_const_i64(int64_t val); -TCGv_vec tcg_const_zeros_vec(TCGType); -TCGv_vec tcg_const_ones_vec(TCGType); -TCGv_vec tcg_const_zeros_vec_matching(TCGv_vec); -TCGv_vec tcg_const_ones_vec_matching(TCGv_vec); /* * Locate or create a read-only temporary that is a constant. diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index 4060a35..4444eb9 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -3651,6 +3651,7 @@ static void expand_vec_sari(TCGType type, unsigned vece, break; case MO_64: + t1 = tcg_temp_new_vec(type); if (imm <= 32) { /* * We can emulate a small sign extend by performing an arithmetic @@ -3659,24 +3660,22 @@ static void expand_vec_sari(TCGType type, unsigned vece, * does not, so we have to bound the smaller shift -- we get the * same result in the high half either way. */ - t1 = tcg_temp_new_vec(type); tcg_gen_sari_vec(MO_32, t1, v1, MIN(imm, 31)); tcg_gen_shri_vec(MO_64, v0, v1, imm); vec_gen_4(INDEX_op_x86_blend_vec, type, MO_32, tcgv_vec_arg(v0), tcgv_vec_arg(v0), tcgv_vec_arg(t1), 0xaa); - tcg_temp_free_vec(t1); } else { /* Otherwise we will need to use a compare vs 0 to produce * the sign-extend, shift and merge. */ - t1 = tcg_const_zeros_vec(type); - tcg_gen_cmp_vec(TCG_COND_GT, MO_64, t1, t1, v1); + tcg_gen_cmp_vec(TCG_COND_GT, MO_64, t1, + tcg_constant_vec(type, MO_64, 0), v1); tcg_gen_shri_vec(MO_64, v0, v1, imm); tcg_gen_shli_vec(MO_64, t1, t1, 64 - imm); tcg_gen_or_vec(MO_64, v0, v0, t1); - tcg_temp_free_vec(t1); } + tcg_temp_free_vec(t1); break; default: diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c index 0f023f4..aeeb243 100644 --- a/tcg/tcg-op-vec.c +++ b/tcg/tcg-op-vec.c @@ -229,32 +229,6 @@ void tcg_gen_mov_vec(TCGv_vec r, TCGv_vec a) } } -TCGv_vec tcg_const_zeros_vec(TCGType type) -{ - TCGv_vec ret = tcg_temp_new_vec(type); - tcg_gen_dupi_vec(MO_64, ret, 0); - return ret; -} - -TCGv_vec tcg_const_ones_vec(TCGType type) -{ - TCGv_vec ret = tcg_temp_new_vec(type); - tcg_gen_dupi_vec(MO_64, ret, -1); - return ret; -} - -TCGv_vec tcg_const_zeros_vec_matching(TCGv_vec m) -{ - TCGTemp *t = tcgv_vec_temp(m); - return tcg_const_zeros_vec(t->base_type); -} - -TCGv_vec tcg_const_ones_vec_matching(TCGv_vec m) -{ - TCGTemp *t = tcgv_vec_temp(m); - return tcg_const_ones_vec(t->base_type); -} - void tcg_gen_dupi_vec(unsigned vece, TCGv_vec r, uint64_t a) { TCGTemp *rt = tcgv_vec_temp(r); @@ -431,9 +405,7 @@ void tcg_gen_not_vec(unsigned vece, TCGv_vec r, TCGv_vec a) const TCGOpcode *hold_list = tcg_swap_vecop_list(NULL); if (!TCG_TARGET_HAS_not_vec || !do_op2(vece, r, a, INDEX_op_not_vec)) { - TCGv_vec t = tcg_const_ones_vec_matching(r); - tcg_gen_xor_vec(0, r, a, t); - tcg_temp_free_vec(t); + tcg_gen_xor_vec(0, r, a, tcg_constant_vec_matching(r, 0, -1)); } tcg_swap_vecop_list(hold_list); } @@ -446,9 +418,7 @@ void tcg_gen_neg_vec(unsigned vece, TCGv_vec r, TCGv_vec a) hold_list = tcg_swap_vecop_list(NULL); if (!TCG_TARGET_HAS_neg_vec || !do_op2(vece, r, a, INDEX_op_neg_vec)) { - TCGv_vec t = tcg_const_zeros_vec_matching(r); - tcg_gen_sub_vec(vece, r, t, a); - tcg_temp_free_vec(t); + tcg_gen_sub_vec(vece, r, tcg_constant_vec_matching(r, vece, 0), a); } tcg_swap_vecop_list(hold_list); } |