From nobody Thu Dec 18 19:36:22 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1530285882493914.3786876232383; Fri, 29 Jun 2018 08:24:42 -0700 (PDT) Received: from localhost ([::1]:42929 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fYvGL-0008CE-L6 for importer@patchew.org; Fri, 29 Jun 2018 11:24:41 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:33934) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fYumq-0007VN-Fg for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:15 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fYumn-0006nD-B0 for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:12 -0400 Received: from orth.archaic.org.uk ([2001:8b0:1d0::2]:43098) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fYumm-0006YJ-PH for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:09 -0400 Received: from pm215 by orth.archaic.org.uk with local (Exim 4.89) (envelope-from ) id 1fYuml-0004dV-9h for qemu-devel@nongnu.org; Fri, 29 Jun 2018 15:54:07 +0100 From: Peter Maydell To: qemu-devel@nongnu.org Date: Fri, 29 Jun 2018 15:53:14 +0100 Message-Id: <20180629145347.652-23-peter.maydell@linaro.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20180629145347.652-1-peter.maydell@linaro.org> References: <20180629145347.652-1-peter.maydell@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2001:8b0:1d0::2 Subject: [Qemu-devel] [PULL 22/55] target/arm: Implement SVE floating-point compare vectors X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" From: Richard Henderson Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20180627043328.11531-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper-sve.h | 49 ++++++++++++++++++++++++++++++ target/arm/sve_helper.c | 62 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 40 ++++++++++++++++++++++++ target/arm/sve.decode | 11 +++++++ 4 files changed, 162 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 55e8a908d4c..6089b3a53fd 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -839,6 +839,55 @@ DEF_HELPER_FLAGS_5(sve_ucvt_ds, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_ucvt_dd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) =20 +DEF_HELPER_FLAGS_6(sve_fcmge_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmge_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmge_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fcmgt_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmgt_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmgt_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fcmeq_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmeq_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmeq_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fcmne_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmne_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmne_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fcmuo_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmuo_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmuo_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_facge_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_facge_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_facge_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_facgt_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_facgt_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_facgt_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index 81fc9680870..41d8ce6b54d 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -3193,6 +3193,68 @@ void HELPER(sve_fnmls_zpzzz_d)(CPUARMState *env, voi= d *vg, uint32_t desc) do_fmla_zpzzz_d(env, vg, desc, 0, INT64_MIN); } =20 +/* Two operand floating-point comparison controlled by a predicate. + * Unlike the integer version, we are not allowed to optimistically + * compare operands, since the comparison may have side effects wrt + * the FPSR. + */ +#define DO_FPCMP_PPZZ(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ + void *status, uint32_t desc) \ +{ \ + intptr_t i =3D simd_oprsz(desc), j =3D (i - 1) >> 6; = \ + uint64_t *d =3D vd, *g =3D vg; = \ + do { \ + uint64_t out =3D 0, pg =3D g[j]; = \ + do { \ + i -=3D sizeof(TYPE), out <<=3D sizeof(TYPE); = \ + if (likely((pg >> (i & 63)) & 1)) { \ + TYPE nn =3D *(TYPE *)(vn + H(i)); \ + TYPE mm =3D *(TYPE *)(vm + H(i)); \ + out |=3D OP(TYPE, nn, mm, status); \ + } \ + } while (i & 63); \ + d[j--] =3D out; \ + } while (i > 0); \ +} + +#define DO_FPCMP_PPZZ_H(NAME, OP) \ + DO_FPCMP_PPZZ(NAME##_h, float16, H1_2, OP) +#define DO_FPCMP_PPZZ_S(NAME, OP) \ + DO_FPCMP_PPZZ(NAME##_s, float32, H1_4, OP) +#define DO_FPCMP_PPZZ_D(NAME, OP) \ + DO_FPCMP_PPZZ(NAME##_d, float64, , OP) + +#define DO_FPCMP_PPZZ_ALL(NAME, OP) \ + DO_FPCMP_PPZZ_H(NAME, OP) \ + DO_FPCMP_PPZZ_S(NAME, OP) \ + DO_FPCMP_PPZZ_D(NAME, OP) + +#define DO_FCMGE(TYPE, X, Y, ST) TYPE##_compare(Y, X, ST) <=3D 0 +#define DO_FCMGT(TYPE, X, Y, ST) TYPE##_compare(Y, X, ST) < 0 +#define DO_FCMEQ(TYPE, X, Y, ST) TYPE##_compare_quiet(X, Y, ST) =3D=3D 0 +#define DO_FCMNE(TYPE, X, Y, ST) TYPE##_compare_quiet(X, Y, ST) !=3D 0 +#define DO_FCMUO(TYPE, X, Y, ST) \ + TYPE##_compare_quiet(X, Y, ST) =3D=3D float_relation_unordered +#define DO_FACGE(TYPE, X, Y, ST) \ + TYPE##_compare(TYPE##_abs(Y), TYPE##_abs(X), ST) <=3D 0 +#define DO_FACGT(TYPE, X, Y, ST) \ + TYPE##_compare(TYPE##_abs(Y), TYPE##_abs(X), ST) < 0 + +DO_FPCMP_PPZZ_ALL(sve_fcmge, DO_FCMGE) +DO_FPCMP_PPZZ_ALL(sve_fcmgt, DO_FCMGT) +DO_FPCMP_PPZZ_ALL(sve_fcmeq, DO_FCMEQ) +DO_FPCMP_PPZZ_ALL(sve_fcmne, DO_FCMNE) +DO_FPCMP_PPZZ_ALL(sve_fcmuo, DO_FCMUO) +DO_FPCMP_PPZZ_ALL(sve_facge, DO_FACGE) +DO_FPCMP_PPZZ_ALL(sve_facgt, DO_FACGT) + +#undef DO_FPCMP_PPZZ_ALL +#undef DO_FPCMP_PPZZ_D +#undef DO_FPCMP_PPZZ_S +#undef DO_FPCMP_PPZZ_H +#undef DO_FPCMP_PPZZ + /* * Load contiguous data, protected by a governing predicate. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 75913585399..0397109778b 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -3533,6 +3533,46 @@ DO_FP3(FMULX, fmulx) =20 #undef DO_FP3 =20 +static bool do_fp_cmp(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_4_ptr *fn) +{ + if (fn =3D=3D NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz =3D vec_full_reg_size(s); + TCGv_ptr status =3D get_fpstatus_ptr(a->esz =3D=3D MO_16); + tcg_gen_gvec_4_ptr(pred_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + pred_full_reg_offset(s, a->pg), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); + } + return true; +} + +#define DO_FPCMP(NAME, name) \ +static bool trans_##NAME##_ppzz(DisasContext *s, arg_rprr_esz *a, \ + uint32_t insn) \ +{ \ + static gen_helper_gvec_4_ptr * const fns[4] =3D { \ + NULL, gen_helper_sve_##name##_h, \ + gen_helper_sve_##name##_s, gen_helper_sve_##name##_d \ + }; \ + return do_fp_cmp(s, a, fns[a->esz]); \ +} + +DO_FPCMP(FCMGE, fcmge) +DO_FPCMP(FCMGT, fcmgt) +DO_FPCMP(FCMEQ, fcmeq) +DO_FPCMP(FCMNE, fcmne) +DO_FPCMP(FCMUO, fcmuo) +DO_FPCMP(FACGE, facge) +DO_FPCMP(FACGT, facgt) + +#undef DO_FPCMP + typedef void gen_helper_sve_fmla(TCGv_env, TCGv_ptr, TCGv_i32); =20 static bool do_fmla(DisasContext *s, arg_rprrr_esz *a, gen_helper_sve_fmla= *fn) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 75133ce6596..a1bc6cb395c 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -324,6 +324,17 @@ UXTH 00000100 .. 010 011 101 ... ..... ....= . @rd_pg_rn SXTW 00000100 .. 010 100 101 ... ..... ..... @rd_pg_rn UXTW 00000100 .. 010 101 101 ... ..... ..... @rd_pg_rn =20 +### SVE Floating Point Compare - Vectors Group + +# SVE floating-point compare vectors +FCMGE_ppzz 01100101 .. 0 ..... 010 ... ..... 0 .... @pd_pg_rn_= rm +FCMGT_ppzz 01100101 .. 0 ..... 010 ... ..... 1 .... @pd_pg_rn_= rm +FCMEQ_ppzz 01100101 .. 0 ..... 011 ... ..... 0 .... @pd_pg_rn_= rm +FCMNE_ppzz 01100101 .. 0 ..... 011 ... ..... 1 .... @pd_pg_rn_= rm +FCMUO_ppzz 01100101 .. 0 ..... 110 ... ..... 0 .... @pd_pg_rn_= rm +FACGE_ppzz 01100101 .. 0 ..... 110 ... ..... 1 .... @pd_pg_rn_= rm +FACGT_ppzz 01100101 .. 0 ..... 111 ... ..... 1 .... @pd_pg_rn_= rm + ### SVE Integer Multiply-Add Group =20 # SVE integer multiply-add writing addend (predicated) --=20 2.17.1