On 2024/9/5 3:05, Richard Henderson wrote:
On 9/4/24 08:25, LIU Zhiwei wrote:
I'm trying to work out how much benefit there is here of expanding
these early, as opposed to simply using TCG_REG_TMP0 when the
immediate doesn't fit,
We find for rotli, it just copied code from the implementati
On 9/4/24 08:25, LIU Zhiwei wrote:
I'm trying to work out how much benefit there is here of expanding these early, as
opposed to simply using TCG_REG_TMP0 when the immediate doesn't fit,
We find for rotli, it just copied code from the implementation of INDEX_op_shli_vec and
INDEX_op_shri_vec
On 2024/9/3 23:15, Richard Henderson wrote:
On 8/29/24 23:16, LIU Zhiwei wrote:
@@ -2589,6 +2605,69 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType
type, unsigned vece,
}
}
break;
+ case INDEX_op_shli_vec:
+ if (a2 > 31) {
+ tcg_gen_shls_
On 8/29/24 23:16, LIU Zhiwei wrote:
@@ -2589,6 +2605,69 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType type,
unsigned vece,
}
}
break;
+case INDEX_op_shli_vec:
+if (a2 > 31) {
+tcg_gen_shls_vec(vece, v0, v1, tcg_constant_i32(a2));
+
