From e7e8f33fb603c3bfa0479d7d924f2ad676a84317 Mon Sep 17 00:00:00 2001 From: Stephen Long Date: Thu, 13 Aug 2020 09:18:18 -0700 Subject: [PATCH] tcg: Fix tcg gen for vectorized absolute value The fallback inline expansion for vectorized absolute value, when the host doesn't support such an insn was flawed. E.g. when a vector of bytes has all elements negative, mask will be 0xffff_ffff_ffff_ffff. Subtracting mask only adds 1 to the low element instead of all elements becase -mask is 1 and not 0x0101_0101_0101_0101. Signed-off-by: Stephen Long Message-Id: <20200813161818.190-1-steplong@quicinc.com> Signed-off-by: Richard Henderson --- tcg/tcg-op-gvec.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index 3707c0effb..793d4ba64c 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); }