target-sh4: improve cmp/str instruction

Instead of testing bytes one by one, we can use the following trick
from https://graphics.stanford.edu/~seander/bithacks.html:

  haszero(v) = (v - 0x01010101) & ~v & 0x80808080

The subexpression v - 0x01010101, evaluates to a high bit set in any
byte whenever the corresponding byte in v is zero or greater than 0x80.
The sub-expression ~v & 0x80808080 evaluates to high bits set in bytes
where the byte of v doesn't have its high bit set (so the byte was less
than 0x80). Finally, by ANDing these two sub-expressions the result is
the high bits set where the bytes in v were zero, since the high bits
set due to a value greater than 0x80 in the first sub-expression are
masked off by the second.

Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>

diff --git a/target-sh4/translate.c b/target-sh4/translate.c
index 50043cf..ca6ef5a 100644 (file)
--- a/target-sh4/translate.c
+++ b/target-sh4/translate.c
@@ -688,18 +688,11 @@ static void _decode_opc(DisasContext * ctx)
        {
            TCGv cmp1 = tcg_temp_new();
            TCGv cmp2 = tcg_temp_new();
-           tcg_gen_xor_i32(cmp1, REG(B7_4), REG(B11_8));
-           tcg_gen_andi_i32(cmp2, cmp1, 0xff000000);
-            tcg_gen_setcondi_i32(TCG_COND_EQ, cpu_sr_t, cmp2, 0);
-           tcg_gen_andi_i32(cmp2, cmp1, 0x00ff0000);
-           tcg_gen_setcondi_i32(TCG_COND_EQ, cmp2, cmp2, 0);
-            tcg_gen_or_i32(cpu_sr_t, cpu_sr_t, cmp2);
-           tcg_gen_andi_i32(cmp2, cmp1, 0x0000ff00);
-           tcg_gen_setcondi_i32(TCG_COND_EQ, cmp2, cmp2, 0);
-            tcg_gen_or_i32(cpu_sr_t, cpu_sr_t, cmp2);
-           tcg_gen_andi_i32(cmp2, cmp1, 0x000000ff);
-           tcg_gen_setcondi_i32(TCG_COND_EQ, cmp2, cmp2, 0);
-            tcg_gen_or_i32(cpu_sr_t, cpu_sr_t, cmp2);
+            tcg_gen_xor_i32(cmp2, REG(B7_4), REG(B11_8));
+            tcg_gen_subi_i32(cmp1, cmp2, 0x01010101);
+            tcg_gen_andc_i32(cmp1, cmp1, cmp2);
+            tcg_gen_andi_i32(cmp1, cmp1, 0x80808080);
+            tcg_gen_setcondi_i32(TCG_COND_NE, cpu_sr_t, cmp1, 0);
            tcg_temp_free(cmp2);
            tcg_temp_free(cmp1);
        }