@@ -3332,13 +3332,22 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
static void expand_vec_shi(TCGType type, unsigned vece, TCGv_vec v0,
TCGv_vec v1, TCGArg imm, TCGOpcode opci)
{
- TCGv_vec t1 = tcg_temp_new_vec(type);
+ TCGv_vec t1;
- /* Splat w/bytes for xxspltib. */
- tcg_gen_dupi_vec(MO_8, t1, imm & ((8 << vece) - 1));
+ if (vece == MO_32) {
+ /*
+ * Only 5 bits are significant, and VSPLTISB can represent -16..15.
+ * So using negative numbers gets us the 4th bit easily.
+ */
+ imm = sextract32(imm, 0, 5);
+ } else {
+ imm &= (8 << vece) - 1;
+ }
+
+ /* Splat w/bytes for xxspltib when 2.07 allows MO_64. */
+ t1 = tcg_constant_vec(type, MO_8, imm);
vec_gen_3(opci, type, vece, tcgv_vec_arg(v0),
tcgv_vec_arg(v1), tcgv_vec_arg(t1));
- tcg_temp_free_vec(t1);
}
static void expand_vec_cmp(TCGType type, unsigned vece, TCGv_vec v0,
@@ -3396,7 +3405,7 @@ static void expand_vec_mul(TCGType type, unsigned vece, TCGv_vec v0,
{
TCGv_vec t1 = tcg_temp_new_vec(type);
TCGv_vec t2 = tcg_temp_new_vec(type);
- TCGv_vec t3, t4;
+ TCGv_vec c0, c16;
switch (vece) {
case MO_8:
@@ -3415,21 +3424,22 @@ static void expand_vec_mul(TCGType type, unsigned vece, TCGv_vec v0,
case MO_32:
tcg_debug_assert(!have_isa_2_07);
- t3 = tcg_temp_new_vec(type);
- t4 = tcg_temp_new_vec(type);
- tcg_gen_dupi_vec(MO_8, t4, -16);
+ /*
+ * Only 5 bits are significant, and VSPLTISB can represent -16..15.
+ * So using -16 is a quick way to represent 16.
+ */
+ c16 = tcg_constant_vec(type, MO_8, -16);
+ c0 = tcg_constant_vec(type, MO_8, 0);
+
vec_gen_3(INDEX_op_rotlv_vec, type, MO_32, tcgv_vec_arg(t1),
- tcgv_vec_arg(v2), tcgv_vec_arg(t4));
+ tcgv_vec_arg(v2), tcgv_vec_arg(c16));
vec_gen_3(INDEX_op_ppc_mulou_vec, type, MO_16, tcgv_vec_arg(t2),
tcgv_vec_arg(v1), tcgv_vec_arg(v2));
- tcg_gen_dupi_vec(MO_8, t3, 0);
- vec_gen_4(INDEX_op_ppc_msum_vec, type, MO_16, tcgv_vec_arg(t3),
- tcgv_vec_arg(v1), tcgv_vec_arg(t1), tcgv_vec_arg(t3));
- vec_gen_3(INDEX_op_shlv_vec, type, MO_32, tcgv_vec_arg(t3),
- tcgv_vec_arg(t3), tcgv_vec_arg(t4));
- tcg_gen_add_vec(MO_32, v0, t2, t3);
- tcg_temp_free_vec(t3);
- tcg_temp_free_vec(t4);
+ vec_gen_4(INDEX_op_ppc_msum_vec, type, MO_16, tcgv_vec_arg(t1),
+ tcgv_vec_arg(v1), tcgv_vec_arg(t1), tcgv_vec_arg(c0));
+ vec_gen_3(INDEX_op_shlv_vec, type, MO_32, tcgv_vec_arg(t1),
+ tcgv_vec_arg(t1), tcgv_vec_arg(c16));
+ tcg_gen_add_vec(MO_32, v0, t1, t2);
break;
default:
Improve expand_vec_shi to use sign-extraction for MO_32. This allows a single VSPLTISB instruction to load all of the valid shift constants. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/ppc/tcg-target.c.inc | 44 ++++++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 17 deletions(-) -- 2.25.1