From nobody Thu Dec 18 22:24:09 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 1530285392656930.2083254227019; Fri, 29 Jun 2018 08:16:32 -0700 (PDT) Received: from localhost ([::1]:42890 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fYv8R-0001VV-Jt for importer@patchew.org; Fri, 29 Jun 2018 11:16:31 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:33949) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fYumr-0007Wh-D5 for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:16 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fYumo-0006sb-U0 for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:13 -0400 Received: from orth.archaic.org.uk ([2001:8b0:1d0::2]:43102) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fYumo-0006kj-Fs for qemu-devel@nongnu.org; Fri, 29 Jun 2018 10:54:10 -0400 Received: from pm215 by orth.archaic.org.uk with local (Exim 4.89) (envelope-from ) id 1fYumm-0004eO-VX for qemu-devel@nongnu.org; Fri, 29 Jun 2018 15:54:08 +0100 From: Peter Maydell To: qemu-devel@nongnu.org Date: Fri, 29 Jun 2018 15:53:16 +0100 Message-Id: <20180629145347.652-25-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 24/55] target/arm: Implement SVE Floating Point Multiply Indexed Group 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: 20180627043328.11531-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 14 +++++++++++ target/arm/translate-sve.c | 50 ++++++++++++++++++++++++++++++++++++++ target/arm/vec_helper.c | 48 ++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 19 +++++++++++++++ 4 files changed, 131 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index 879a7229e99..56439ac1e41 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -620,6 +620,20 @@ DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_ftsmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) =20 +DEF_HELPER_FLAGS_5(gvec_fmul_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 1b467a5ddcd..e90f593f6ca 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -3400,6 +3400,56 @@ DO_ZZI(UMIN, umin) =20 #undef DO_ZZI =20 +/* + *** SVE Floating Point Multiply-Add Indexed Group + */ + +static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a, uint32_t in= sn) +{ + static gen_helper_gvec_4_ptr * const fns[3] =3D { + gen_helper_gvec_fmla_idx_h, + gen_helper_gvec_fmla_idx_s, + gen_helper_gvec_fmla_idx_d, + }; + + 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(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + status, vsz, vsz, (a->index << 1) | a->sub, + fns[a->esz - 1]); + tcg_temp_free_ptr(status); + } + return true; +} + +/* + *** SVE Floating Point Multiply Indexed Group + */ + +static bool trans_FMUL_zzx(DisasContext *s, arg_FMUL_zzx *a, uint32_t insn) +{ + static gen_helper_gvec_3_ptr * const fns[3] =3D { + gen_helper_gvec_fmul_idx_h, + gen_helper_gvec_fmul_idx_s, + gen_helper_gvec_fmul_idx_d, + }; + + 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_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + status, vsz, vsz, a->index, fns[a->esz - 1]); + tcg_temp_free_ptr(status); + } + return true; +} + /* *** SVE Floating Point Accumulating Reduction Group */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index f504dd53c8f..97af75a61b3 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -495,3 +495,51 @@ DO_3OP(gvec_rsqrts_d, helper_rsqrtsf_f64, float64) =20 #endif #undef DO_3OP + +/* For the indexed ops, SVE applies the index per 128-bit vector segment. + * For AdvSIMD, there is of course only one such vector segment. + */ + +#define DO_MUL_IDX(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc)= \ +{ = \ + intptr_t i, j, oprsz =3D simd_oprsz(desc), segment =3D 16 / sizeof(TYP= E); \ + intptr_t idx =3D simd_data(desc); = \ + TYPE *d =3D vd, *n =3D vn, *m =3D vm; = \ + for (i =3D 0; i < oprsz / sizeof(TYPE); i +=3D segment) { = \ + TYPE mm =3D m[H(i + idx)]; = \ + for (j =3D 0; j < segment; j++) { = \ + d[i + j] =3D TYPE##_mul(n[i + j], mm, stat); = \ + } = \ + } = \ +} + +DO_MUL_IDX(gvec_fmul_idx_h, float16, H2) +DO_MUL_IDX(gvec_fmul_idx_s, float32, H4) +DO_MUL_IDX(gvec_fmul_idx_d, float64, ) + +#undef DO_MUL_IDX + +#define DO_FMLA_IDX(NAME, TYPE, H) = \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, = \ + void *stat, uint32_t desc) = \ +{ = \ + intptr_t i, j, oprsz =3D simd_oprsz(desc), segment =3D 16 / sizeof(TYP= E); \ + TYPE op1_neg =3D extract32(desc, SIMD_DATA_SHIFT, 1); = \ + intptr_t idx =3D desc >> (SIMD_DATA_SHIFT + 1); = \ + TYPE *d =3D vd, *n =3D vn, *m =3D vm, *a =3D va; = \ + op1_neg <<=3D (8 * sizeof(TYPE) - 1); = \ + for (i =3D 0; i < oprsz / sizeof(TYPE); i +=3D segment) { = \ + TYPE mm =3D m[H(i + idx)]; = \ + for (j =3D 0; j < segment; j++) { = \ + d[i + j] =3D TYPE##_muladd(n[i + j] ^ op1_neg, = \ + mm, a[i + j], 0, stat); = \ + } = \ + } = \ +} + +DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2) +DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4) +DO_FMLA_IDX(gvec_fmla_idx_d, float64, ) + +#undef DO_FMLA_IDX diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 267eb2dcfc6..15fa790d5b2 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -29,6 +29,7 @@ %imm9_16_10 16:s6 10:3 %size_23 23:2 %dtype_23_13 23:2 13:2 +%index3_22_19 22:1 19:2 =20 # A combination of tsz:imm3 -- extract esize. %tszimm_esz 22:2 5:5 !function=3Dtszimm_esz @@ -716,6 +717,24 @@ UMIN_zzi 00100101 .. 101 011 110 ........ .....= @rdn_i8u # SVE integer multiply immediate (unpredicated) MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s =20 +### SVE FP Multiply-Add Indexed Group + +# SVE floating-point multiply-add (indexed) +FMLA_zzxz 01100100 0.1 .. rm:3 00000 sub:1 rn:5 rd:5 \ + ra=3D%reg_movprfx index=3D%index3_22_19 esz=3D1 +FMLA_zzxz 01100100 101 index:2 rm:3 00000 sub:1 rn:5 rd:5 \ + ra=3D%reg_movprfx esz=3D2 +FMLA_zzxz 01100100 111 index:1 rm:4 00000 sub:1 rn:5 rd:5 \ + ra=3D%reg_movprfx esz=3D3 + +### SVE FP Multiply Indexed Group + +# SVE floating-point multiply (indexed) +FMUL_zzx 01100100 0.1 .. rm:3 001000 rn:5 rd:5 \ + index=3D%index3_22_19 esz=3D1 +FMUL_zzx 01100100 101 index:2 rm:3 001000 rn:5 rd:5 esz=3D2 +FMUL_zzx 01100100 111 index:1 rm:4 001000 rn:5 rd:5 esz=3D3 + ### SVE FP Accumulating Reduction Group =20 # SVE floating-point serial reduction (predicated) --=20 2.17.1