---
tcg/tcg-op-gvec.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
qemu was generating buggy tcg for arm64's vectorized absolute value
insn when the machine didn't support avx insns.
Subtracting a mask of -1 for each negative element doesn't
add 1 to each negative element. For example, subtracting a mask of
0xffff_ffff_ffff_ffff only adds one to the low byte because
~0xffff_ffff_ffff_ffff + 1 is just 1, instead of 0x0101_0101_0101_0101.
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 3707c0e..793d4ba 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -2264,12 +2264,13 @@ static void gen_absv_mask(TCGv_i64 d, TCGv_i64 b,
unsigned vece)
tcg_gen_muli_i64(t, t, (1 << nbit) - 1);
/*
- * Invert (via xor -1) and add one (via sub -1).
+ * Invert (via xor -1) and add one.
* Because of the ordering the msb is cleared,
* so we never have carry into the next element.
*/
tcg_gen_xor_i64(d, b, t);
- tcg_gen_sub_i64(d, d, t);
+ tcg_gen_andi_i64(t, t, dup_const(vece, 1));
+ tcg_gen_add_i64(d, d, t);
tcg_temp_free_i64(t);
}
--
1.9.1
