Received: from eggs.gnu.org ([209.51.188.92]:55085) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1hEWse-0003L1-36 for qemu-devel@nongnu.org; Thu, 11 Apr 2019 06:24:31 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hEWdc-0007BD-4P for qemu-devel@nongnu.org; Thu, 11 Apr 2019 06:08:57 -0400 From: David Hildenbrand Date: Thu, 11 Apr 2019 12:08:02 +0200 Message-Id: <20190411100836.646-8-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 07/41] s390x/tcg: Implement VECTOR AVERAGE 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 Handle 32/64-bit elements via gvec expansion and the 8/16 bits via ool helpers. Signed-off-by: David Hildenbrand --- target/s390x/helper.h | 2 ++ target/s390x/insn-data.def | 2 ++ target/s390x/translate_vx.inc.c | 63 +++++++++++++++++++++++++++++++++ target/s390x/vec_int_helper.c | 16 +++++++++ 4 files changed, 83 insertions(+) diff --git a/target/s390x/helper.h b/target/s390x/helper.h index e1847e8877..2b6b716909 100644 --- a/target/s390x/helper.h +++ b/target/s390x/helper.h @@ -148,6 +148,8 @@ DEF_HELPER_FLAGS_4(vstl, TCG_CALL_NO_WG, void, env, c= ptr, i64, i64) /* =3D=3D=3D Vector Integer Instructions =3D=3D=3D */ DEF_HELPER_FLAGS_4(gvec_vacc128, TCG_CALL_NO_RWG, void, ptr, cptr, cptr,= i32) DEF_HELPER_FLAGS_5(gvec_vaccc128, TCG_CALL_NO_RWG, void, ptr, cptr, cptr= , cptr, i32) +DEF_HELPER_FLAGS_4(gvec_vavg8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i= 32) +DEF_HELPER_FLAGS_4(gvec_vavg16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, = i32) =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 456d5597ca..6f8b42e327 100644 --- a/target/s390x/insn-data.def +++ b/target/s390x/insn-data.def @@ -1068,6 +1068,8 @@ F(0xe768, VN, VRR_c, V, 0, 0, 0, 0, vn, 0, IF_VEC) /* VECTOR AND WITH COMPLEMENT */ F(0xe769, VNC, VRR_c, V, 0, 0, 0, 0, vnc, 0, IF_VEC) +/* VECTOR AVERAGE */ + F(0xe7f2, VAVG, VRR_c, V, 0, 0, 0, 0, vavg, 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 aaa247e855..50e03bf151 100644 --- a/target/s390x/translate_vx.inc.c +++ b/target/s390x/translate_vx.inc.c @@ -256,6 +256,17 @@ static void zero_vec(uint8_t reg) tcg_gen_gvec_dup8i(vec_full_reg_offset(reg), 16, 16, 0); } =20 +static void gen_addi2_i64(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 al, TCGv_i6= 4 ah, + uint64_t b) +{ + TCGv_i64 bl =3D tcg_const_i64(b); + TCGv_i64 bh =3D tcg_const_i64(0); + + tcg_gen_add2_i64(dl, dh, al, ah, bl, bh); + tcg_temp_free_i64(bl); + tcg_temp_free_i64(bh); +} + static DisasJumpType op_vge(DisasContext *s, DisasOps *o) { const uint8_t es =3D s->insn->data; @@ -1149,3 +1160,55 @@ static DisasJumpType op_vnc(DisasContext *s, Disas= Ops *o) get_field(s->fields, v2), get_field(s->fields, v3)); return DISAS_NEXT; } + +static void gen_avg_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i64 t0 =3D tcg_temp_new_i64(); + TCGv_i64 t1 =3D tcg_temp_new_i64(); + + tcg_gen_ext_i32_i64(t0, a); + tcg_gen_ext_i32_i64(t1, b); + tcg_gen_add_i64(t0, t0, t1); + tcg_gen_addi_i64(t0, t0, 1); + tcg_gen_shri_i64(t0, t0, 1); + tcg_gen_extrl_i64_i32(d, t0); + + tcg_temp_free(t0); + tcg_temp_free(t1); +} + +static void gen_avg_i64(TCGv_i64 dl, TCGv_i64 al, TCGv_i64 bl) +{ + TCGv_i64 dh =3D tcg_temp_new_i64(); + TCGv_i64 ah =3D tcg_temp_new_i64(); + TCGv_i64 bh =3D tcg_temp_new_i64(); + + /* extending the sign by one bit is sufficient */ + tcg_gen_extract_i64(ah, al, 63, 1); + tcg_gen_extract_i64(bh, bl, 63, 1); + tcg_gen_add2_i64(dl, dh, al, ah, bl, bh); + gen_addi2_i64(dl, dh, dl, dh, 1); + tcg_gen_extract2_i64(dl, dl, dh, 1); + + tcg_temp_free_i64(dh); + tcg_temp_free_i64(ah); + tcg_temp_free_i64(bh); +} +static DisasJumpType op_vavg(DisasContext *s, DisasOps *o) +{ + const uint8_t es =3D get_field(s->fields, m4); + static const GVecGen3 g[4] =3D { + { .fno =3D gen_helper_gvec_vavg8, }, + { .fno =3D gen_helper_gvec_vavg16, }, + { .fni4 =3D gen_avg_i32, }, + { .fni8 =3D gen_avg_i64, }, + }; + + if (es > ES_64) { + gen_program_exception(s, PGM_SPECIFICATION); + return DISAS_NORETURN; + } + gen_gvec_3(get_field(s->fields, v1), get_field(s->fields, v2), + get_field(s->fields, v3), &g[es]); + return DISAS_NEXT; +} diff --git a/target/s390x/vec_int_helper.c b/target/s390x/vec_int_helper.= c index 97fc559da0..149cfaaeae 100644 --- a/target/s390x/vec_int_helper.c +++ b/target/s390x/vec_int_helper.c @@ -61,3 +61,19 @@ void HELPER(gvec_vaccc128)(void *v1, const void *v2, c= onst void *v3, dst->doubleword[0] =3D 0; dst->doubleword[1] =3D carry; } + +#define DEF_VAVG(BITS) = \ +void HELPER(gvec_vavg##BITS)(void *v1, const void *v2, const void *v3, = \ + uint32_t desc) = \ +{ = \ + int i; = \ + = \ + for (i =3D 0; i < (128 / BITS); i++) { = \ + const int32_t a =3D (int##BITS##_t)s390_vec_read_element##BITS(v= 2, i); \ + const int32_t b =3D (int##BITS##_t)s390_vec_read_element##BITS(v= 3, i); \ + = \ + s390_vec_write_element##BITS(v1, i, (a + b + 1) >> 1); = \ + } = \ +} +DEF_VAVG(8) +DEF_VAVG(16) --=20 2.20.1