Received: from eggs.gnu.org ([209.51.188.92]:54395) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1hEWsJ-0002Xe-FI for qemu-devel@nongnu.org; Thu, 11 Apr 2019 06:24:08 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hEWeU-0007Zq-Gs for qemu-devel@nongnu.org; Thu, 11 Apr 2019 06:09:51 -0400 From: David Hildenbrand Date: Thu, 11 Apr 2019 12:08:26 +0200 Message-Id: <20190411100836.646-32-david@redhat.com> In-Reply-To: <20190411100836.646-1-david@redhat.com> References: <20190411100836.646-1-david@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Subject: [Qemu-devel] [PATCH v1 31/41] s390x/tcg: Implement VECTOR SHIFT LEFT DOUBLE BY BYTE List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: qemu-s390x@nongnu.org, Thomas Huth , Cornelia Huck , Richard Henderson , David Hildenbrand Implement it via an ool helper. reusing the existing shift helpers. In case the starting index is 0, it is basically a copy of v2 to v1. Signed-off-by: David Hildenbrand --- target/s390x/helper.h | 1 + target/s390x/insn-data.def | 2 ++ target/s390x/translate_vx.inc.c | 15 +++++++++++++++ target/s390x/vec_int_helper.c | 20 ++++++++++++++++++++ 4 files changed, 38 insertions(+) diff --git a/target/s390x/helper.h b/target/s390x/helper.h index 67037f6de6..a433f57009 100644 --- a/target/s390x/helper.h +++ b/target/s390x/helper.h @@ -227,6 +227,7 @@ DEF_HELPER_FLAGS_4(gvec_vesra16, TCG_CALL_NO_RWG, voi= d, ptr, cptr, i64, i32) DEF_HELPER_FLAGS_4(gvec_vesrl8, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i= 32) DEF_HELPER_FLAGS_4(gvec_vesrl16, TCG_CALL_NO_RWG, void, ptr, cptr, i64, = i32) DEF_HELPER_FLAGS_4(gvec_vsl, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_vsldb, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i= 32) =20 #ifndef CONFIG_USER_ONLY DEF_HELPER_3(servc, i32, env, i64, i64) diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def index 2621e433cd..76aec5a21f 100644 --- a/target/s390x/insn-data.def +++ b/target/s390x/insn-data.def @@ -1164,6 +1164,8 @@ F(0xe774, VSL, VRR_c, V, 0, 0, 0, 0, vsl, 0, IF_VEC) /* VECTOR SHIFT LEFT BY BYTE */ F(0xe775, VSLB, VRR_c, V, 0, 0, 0, 0, vsl, 0, IF_VEC) +/* VECTOR SHIFT LEFT DOUBLE BY BYTE */ + F(0xe777, VSLDB, VRI_d, V, 0, 0, 0, 0, vsldb, 0, IF_VEC) =20 #ifndef CONFIG_USER_ONLY /* COMPARE AND SWAP AND PURGE */ diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.= inc.c index c08710fd45..221b729ee0 100644 --- a/target/s390x/translate_vx.inc.c +++ b/target/s390x/translate_vx.inc.c @@ -2089,3 +2089,18 @@ static DisasJumpType op_vsl(DisasContext *s, Disas= Ops *o) tcg_temp_free_i64(shift); return DISAS_NEXT; } + +static DisasJumpType op_vsldb(DisasContext *s, DisasOps *o) +{ + int src_idx =3D get_field(s->fields, i4) & 0xf; + + if (src_idx =3D=3D 0) { + gen_gvec_mov(get_field(s->fields, v1), get_field(s->fields, v2))= ; + } else { + gen_gvec_3_ool(get_field(s->fields, v1), get_field(s->fields, v2= ), + get_field(s->fields, v3), src_idx, + gen_helper_gvec_vsldb); + return DISAS_NEXT; + } + return DISAS_NEXT; +} diff --git a/target/s390x/vec_int_helper.c b/target/s390x/vec_int_helper.= c index b1a3a25f9f..8b922e717f 100644 --- a/target/s390x/vec_int_helper.c +++ b/target/s390x/vec_int_helper.c @@ -43,6 +43,13 @@ static bool s390_vec_is_zero(const S390Vector *v) return !v->doubleword[0] && !v->doubleword[1]; } =20 +static void s390_vec_or(S390Vector *res, const S390Vector *a, + const S390Vector *b) +{ + res->doubleword[0] =3D a->doubleword[0] | b->doubleword[0]; + res->doubleword[1] =3D a->doubleword[1] | b->doubleword[1]; +} + static void s390_vec_xor(S390Vector *res, const S390Vector *a, const S390Vector *b) { @@ -704,3 +711,16 @@ void HELPER(gvec_vsl)(void *v1, const void *v2, uint= 64_t count, { s390_vec_shl(v1, v2, count); } + +void HELPER(gvec_vsldb)(void *v1, const void *v2, const void *v3, + uint32_t desc) +{ + const uint8_t src_idx =3D simd_data(desc); + S390Vector t0; + S390Vector t1; + + g_assert(src_idx > 0 && src_idx < 16); + s390_vec_shl(&t0, v2, src_idx * 8); + s390_vec_shr(&t1, v3, 128 - src_idx * 8); + s390_vec_or(v1, &t0, &t1); +} --=20 2.20.1