From nobody Tue Feb 10 07:23:16 2026 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1593624477; cv=none; d=zohomail.com; s=zohoarc; b=bn2nKhohnO761NRq3sHow/Z2+ZKJmCneuvZ4CVSaQfYIUa2hCMWpNmYIO/t7+Z3jnp1hnB6BwBKEmg64pJ5UH9UyJcUc3vXhEAUXXom50MIYbTQq0iVwweXgLU/hfSw2el1rRrNAcw4z/uAzPgG6P9wslzJ85nQUB6inafQpwLg= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1593624477; h=Content-Transfer-Encoding:Cc:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=R0kvBZcbGervu80q3B3YwlVpYEnPD11dYcZjMb3ED9A=; b=nLxNlu5yvMs3kzF7bBBKc/oi3cT9w9nAwnIiS0+tqpVl5ZGrrWJ1bsj7h7sw/h/2ojjZnT+Pb0eM9hNApG68SoAUdmiXjWYioBA4TRPSXzPyMU+QUXWCoc36jpbejAXwnBnV3sveAfvHEY8BWXr9yE6+DqRPDm/l/5aTfBw1mEY= ARC-Authentication-Results: i=1; mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1593624477325632.2752833164134; Wed, 1 Jul 2020 10:27:57 -0700 (PDT) Received: from localhost ([::1]:49144 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jqgWZ-0001sx-2E for importer@patchew.org; Wed, 01 Jul 2020 13:27:55 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:59110) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jqgVn-00012c-VK; Wed, 01 Jul 2020 13:27:08 -0400 Received: from smtp2200-217.mail.aliyun.com ([121.197.200.217]:44273) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jqgVl-0002ZZ-TL; Wed, 01 Jul 2020 13:27:07 -0400 Received: from L-PF1D6DP4-1208.hz.ali.com(mailfrom:zhiwei_liu@c-sky.com fp:SMTPD_---.HvxcqhE_1593624415) by smtp.aliyun-inc.com(10.147.44.118); Thu, 02 Jul 2020 01:26:55 +0800 X-Alimail-AntiSpam: AC=CONTINUE; BC=0.07788349|-1; CH=blue; DM=|OVERLOAD|false|; DS=CONTINUE|ham_system_inform|0.16566-4.44909e-05-0.834296; FP=0|0|0|0|0|-1|-1|-1; HT=e02c03267; MF=zhiwei_liu@c-sky.com; NM=1; PH=DS; RN=8; RT=8; SR=0; TI=SMTPD_---.HvxcqhE_1593624415; From: LIU Zhiwei To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Subject: [PATCH v12 60/61] target/riscv: vector compress instruction Date: Wed, 1 Jul 2020 23:25:48 +0800 Message-Id: <20200701152549.1218-61-zhiwei_liu@c-sky.com> X-Mailer: git-send-email 2.23.0 In-Reply-To: <20200701152549.1218-1-zhiwei_liu@c-sky.com> References: <20200701152549.1218-1-zhiwei_liu@c-sky.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: none client-ip=121.197.200.217; envelope-from=zhiwei_liu@c-sky.com; helo=smtp2200-217.mail.aliyun.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/07/01 11:22:02 X-ACL-Warn: Detected OS = Linux 3.x [generic] [fuzzy] X-Spam_score_int: -18 X-Spam_score: -1.9 X-Spam_bar: - X-Spam_report: (-1.9 / 5.0 requ) BAYES_00=-1.9, SPF_HELO_NONE=0.001, SPF_NONE=0.001, UNPARSEABLE_RELAY=0.001 autolearn=_AUTOLEARN X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: richard.henderson@linaro.org, wxy194768@alibaba-inc.com, wenmeng_zhang@c-sky.com, Alistair.Francis@wdc.com, palmer@dabbelt.com, LIU Zhiwei Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Type: text/plain; charset="utf-8" Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson --- target/riscv/helper.h | 5 ++++ target/riscv/insn32.decode | 1 + target/riscv/insn_trans/trans_rvv.inc.c | 32 +++++++++++++++++++++++++ target/riscv/vector_helper.c | 26 ++++++++++++++++++++ 4 files changed, 64 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index eca1ab541b..acc298219d 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -1145,3 +1145,8 @@ DEF_HELPER_6(vrgather_vx_b, void, ptr, ptr, tl, ptr, = env, i32) DEF_HELPER_6(vrgather_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vrgather_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vrgather_vx_d, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vcompress_vm_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vcompress_vm_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vcompress_vm_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vcompress_vm_d, void, ptr, ptr, ptr, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 80d5ff74a9..bdd8563067 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -577,6 +577,7 @@ vslide1down_vx 001111 . ..... ..... 110 ..... 1010111 = @r_vm vrgather_vv 001100 . ..... ..... 000 ..... 1010111 @r_vm vrgather_vx 001100 . ..... ..... 100 ..... 1010111 @r_vm vrgather_vi 001100 . ..... ..... 011 ..... 1010111 @r_vm +vcompress_vm 010111 - ..... ..... 010 ..... 1010111 @r =20 vsetvli 0 ........... ..... 111 ..... 1010111 @r2_zimm vsetvl 1000000 ..... ..... 111 ..... 1010111 @r diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_tr= ans/trans_rvv.inc.c index c0b7745a63..dc333e6a91 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2854,3 +2854,35 @@ static bool trans_vrgather_vi(DisasContext *s, arg_r= mrr *a) } return true; } + +/* Vector Compress Instruction */ +static bool vcompress_vm_check(DisasContext *s, arg_r *a) +{ + return (vext_check_isa_ill(s) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs1, 1) && + (a->rd !=3D a->rs2)); +} + +static bool trans_vcompress_vm(DisasContext *s, arg_r *a) +{ + if (vcompress_vm_check(s, a)) { + uint32_t data =3D 0; + static gen_helper_gvec_4_ptr * const fns[4] =3D { + gen_helper_vcompress_vm_b, gen_helper_vcompress_vm_h, + gen_helper_vcompress_vm_w, gen_helper_vcompress_vm_d, + }; + TCGLabel *over =3D gen_new_label(); + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); + + data =3D FIELD_DP32(data, VDATA, MLEN, s->mlen); + data =3D FIELD_DP32(data, VDATA, LMUL, s->lmul); + tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), + vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2), + cpu_env, 0, s->vlen / 8, data, fns[s->sew]); + gen_set_label(over); + return true; + } + return false; +} diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 3179b1faef..39f44d1029 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -4871,3 +4871,29 @@ GEN_VEXT_VRGATHER_VX(vrgather_vx_b, uint8_t, H1, cle= arb) GEN_VEXT_VRGATHER_VX(vrgather_vx_h, uint16_t, H2, clearh) GEN_VEXT_VRGATHER_VX(vrgather_vx_w, uint32_t, H4, clearl) GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq) + +/* Vector Compress Instruction */ +#define GEN_VEXT_VCOMPRESS_VM(NAME, ETYPE, H, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2, \ + CPURISCVState *env, uint32_t desc) \ +{ \ + uint32_t mlen =3D vext_mlen(desc); = \ + uint32_t vlmax =3D env_archcpu(env)->cfg.vlen / mlen; = \ + uint32_t vl =3D env->vl; = \ + uint32_t num =3D 0, i; = \ + \ + for (i =3D 0; i < vl; i++) { = \ + if (!vext_elem_mask(vs1, mlen, i)) { \ + continue; \ + } \ + *((ETYPE *)vd + H(num)) =3D *((ETYPE *)vs2 + H(i)); = \ + num++; \ + } \ + CLEAR_FN(vd, num, num * sizeof(ETYPE), vlmax * sizeof(ETYPE)); \ +} + +/* Compress into vd elements of vs2 where vs1 is enabled */ +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_b, uint8_t, H1, clearb) +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_h, uint16_t, H2, clearh) +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_w, uint32_t, H4, clearl) +GEN_VEXT_VCOMPRESS_VM(vcompress_vm_d, uint64_t, H8, clearq) --=20 2.23.0