From patchwork Sun Jul 2 15:53:44 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Max Chou X-Patchwork-Id: 13299249 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id E2385EB64DA for ; Sun, 2 Jul 2023 15:58:04 +0000 (UTC) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qFzQ8-0003WW-GF; Sun, 02 Jul 2023 11:55:28 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qFzQ7-0003Jy-0b for qemu-devel@nongnu.org; Sun, 02 Jul 2023 11:55:27 -0400 Received: from mail-pg1-x536.google.com ([2607:f8b0:4864:20::536]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1qFzQ2-000099-H1 for qemu-devel@nongnu.org; Sun, 02 Jul 2023 11:55:26 -0400 Received: by mail-pg1-x536.google.com with SMTP id 41be03b00d2f7-55b5a3915f5so1501723a12.0 for ; Sun, 02 Jul 2023 08:55:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sifive.com; s=google; t=1688313314; x=1690905314; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=PyMD7p7TJbZi4xxjOPLq0g5HXJbgJTY945/N9q5fuNY=; b=AeBVo35zbLjGJ+gRiD8MfGmCdcas8Ud3zaoGXm9HQwKGcBdlPD2e0GdfBZkDYfGZLp 77x4mEhzxZr2Sxm1XW9SNCWUViECOLMqNDxGpj1n/yjgWJdcdl44WQOgWM5nVc6l1Q16 xC4AdkAP9l3BPBi9JqKSECiTKPxwdQ7Yv/6V1AGXrKFA3pAE/OHWgvBZ7nTR/MUHrHu9 p/M7EwBRmA1CNEplCPZOrFqvS0AfKHORuK7EsIDPLNnX8Q8myngO+idrpB9kkd4dwtpQ mVpByQrYOY7fjgOcTDNwv1XuJwicyquDbm+kGScqGDge6i5QM+AWp2HFt6QKGbQY6hAl pWOg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1688313314; x=1690905314; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=PyMD7p7TJbZi4xxjOPLq0g5HXJbgJTY945/N9q5fuNY=; b=NINQF6GbxrzFIYaKUK5VXh5yblNkdnTrL/vH7AJGlFAmVuVp5Sj+IO9MQ9tNzvalwy Uzt8esvCcLYmFSUiRT5/dwcXvpxK0mPwdp0Sj7HDRDDZeuW0fcWE4pRW4Gw+H6rBwo7f /0NaXot++KCfhgEzYSxl5bPoUvQ3v2V5/OS8ChzTeksZFM7RlzI/OiH7m9HgAKgwdD9L /A1kyOQrKvBA+xQlD8cc9px8qsF4SU/SJs+Un/1OYcTIF43KlQn698EfsdCERFJKcpHC zU3FcOBUIcM/V18NReR4kIFPGuvDuW4d/nXVIa3c8MII7HdqeFTP1faAIUtiuDdNaBqu eW4g== X-Gm-Message-State: ABy/qLaCxuE7W7oNLoAoGtAb0OZKpl2DPjky+d9Bls96mpjKWWcPeVA+ 0VOqkeCsMvfEGc7CzBs9yo+2ZwGiic4LENMy+PiXRaHEKhW2HhamEJ1Yu4PCGXTBwH4NagGnw7w lzT+cwbqIFXtd+6LXPwKRd6aHtocVnNrCohWK8SDkEq/c0D7YNtjKeoaAw2LnWth3jR3R3ArX6J hzERU= X-Google-Smtp-Source: APBJJlFa7pYgw5rfULnFUuKK75a2BqicxihoNGd8Wx1LHdqNf+uh3eOdZmJ8eD0SX/AlN16pvishig== X-Received: by 2002:a05:6a20:a10b:b0:12e:641b:454a with SMTP id q11-20020a056a20a10b00b0012e641b454amr955537pzk.30.1688313314093; Sun, 02 Jul 2023 08:55:14 -0700 (PDT) Received: from duncan.localdomain (125-228-20-175.hinet-ip.hinet.net. [125.228.20.175]) by smtp.gmail.com with ESMTPSA id y19-20020aa78553000000b0066f37665a63sm8231969pfn.73.2023.07.02.08.55.11 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 02 Jul 2023 08:55:13 -0700 (PDT) From: Max Chou To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Cc: dbarboza@ventanamicro.com, Kiran Ostrolenk , Nazar Kazakov , Lawrence Hunter , Max Chou , Palmer Dabbelt , Alistair Francis , Bin Meng , Weiwei Li , Liu Zhiwei Subject: [PATCH v7 10/15] target/riscv: Add Zvknh ISA extension support Date: Sun, 2 Jul 2023 23:53:44 +0800 Message-Id: <20230702155354.2478495-11-max.chou@sifive.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230702155354.2478495-1-max.chou@sifive.com> References: <20230702155354.2478495-1-max.chou@sifive.com> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::536; envelope-from=max.chou@sifive.com; helo=mail-pg1-x536.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org From: Kiran Ostrolenk This commit adds support for the Zvknh vector-crypto extension, which consists of the following instructions: * vsha2ms.vv * vsha2c[hl].vv Translation functions are defined in `target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in `target/riscv/vcrypto_helper.c`. Co-authored-by: Nazar Kazakov Co-authored-by: Lawrence Hunter [max.chou@sifive.com: Replaced vstart checking by TCG op] Signed-off-by: Nazar Kazakov Signed-off-by: Lawrence Hunter Signed-off-by: Kiran Ostrolenk Signed-off-by: Max Chou Reviewed-by: Daniel Henrique Barboza [max.chou@sifive.com: Exposed x-zvknha & x-zvknhb properties] [max.chou@sifive.com: Replaced SEW selection to happened during translation] --- target/riscv/cpu.c | 13 +- target/riscv/cpu_cfg.h | 2 + target/riscv/helper.h | 6 + target/riscv/insn32.decode | 5 + target/riscv/insn_trans/trans_rvvk.c.inc | 129 ++++++++++++ target/riscv/vcrypto_helper.c | 238 +++++++++++++++++++++++ 6 files changed, 390 insertions(+), 3 deletions(-) diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index 9b754122ac..3ca5ac209a 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -119,6 +119,8 @@ static const struct isa_ext_data isa_edata_arr[] = { ISA_EXT_DATA_ENTRY(zvfh, PRIV_VERSION_1_12_0, ext_zvfh), ISA_EXT_DATA_ENTRY(zvfhmin, PRIV_VERSION_1_12_0, ext_zvfhmin), ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned), + ISA_EXT_DATA_ENTRY(zvknha, PRIV_VERSION_1_12_0, ext_zvknha), + ISA_EXT_DATA_ENTRY(zvknhb, PRIV_VERSION_1_12_0, ext_zvknhb), ISA_EXT_DATA_ENTRY(zhinx, PRIV_VERSION_1_12_0, ext_zhinx), ISA_EXT_DATA_ENTRY(zhinxmin, PRIV_VERSION_1_12_0, ext_zhinxmin), ISA_EXT_DATA_ENTRY(smaia, PRIV_VERSION_1_12_0, ext_smaia), @@ -1191,14 +1193,17 @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp) * In principle Zve*x would also suffice here, were they supported * in qemu */ - if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned) && !cpu->cfg.ext_zve32f) { + if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned || cpu->cfg.ext_zvknha) && + !cpu->cfg.ext_zve32f) { error_setg(errp, "Vector crypto extensions require V or Zve* extensions"); return; } - if (cpu->cfg.ext_zvbc && !cpu->cfg.ext_zve64f) { - error_setg(errp, "Zvbc extension requires V or Zve64{f,d} extensions"); + if ((cpu->cfg.ext_zvbc || cpu->cfg.ext_zvknhb) && !cpu->cfg.ext_zve64f) { + error_setg( + errp, + "Zvbc and Zvknhb extensions require V or Zve64{f,d} extensions"); return; } @@ -1705,6 +1710,8 @@ static Property riscv_cpu_extensions[] = { DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false), DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false), DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false), + DEFINE_PROP_BOOL("x-zvknha", RISCVCPU, cfg.ext_zvknha, false), + DEFINE_PROP_BOOL("x-zvknhb", RISCVCPU, cfg.ext_zvknhb, false), DEFINE_PROP_END_OF_LIST(), }; diff --git a/target/riscv/cpu_cfg.h b/target/riscv/cpu_cfg.h index 13dbc11e90..7144bfd228 100644 --- a/target/riscv/cpu_cfg.h +++ b/target/riscv/cpu_cfg.h @@ -86,6 +86,8 @@ struct RISCVCPUConfig { bool ext_zvbb; bool ext_zvbc; bool ext_zvkned; + bool ext_zvknha; + bool ext_zvknhb; bool ext_zmmul; bool ext_zvfh; bool ext_zvfhmin; diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 24b434c8a2..66929b88cb 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -1235,3 +1235,9 @@ DEF_HELPER_4(vaesdm_vs, void, ptr, ptr, env, i32) DEF_HELPER_4(vaesz_vs, void, ptr, ptr, env, i32) DEF_HELPER_5(vaeskf1_vi, void, ptr, ptr, i32, env, i32) DEF_HELPER_5(vaeskf2_vi, void, ptr, ptr, i32, env, i32) + +DEF_HELPER_5(vsha2ms_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsha2ch32_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsha2ch64_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsha2cl32_vv, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vsha2cl64_vv, void, ptr, ptr, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 7e0295d493..d2cfb2729c 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -948,3 +948,8 @@ vaesdm_vs 101001 1 ..... 00000 010 ..... 1110111 @r2_vm_1 vaesz_vs 101001 1 ..... 00111 010 ..... 1110111 @r2_vm_1 vaeskf1_vi 100010 1 ..... ..... 010 ..... 1110111 @r_vm_1 vaeskf2_vi 101010 1 ..... ..... 010 ..... 1110111 @r_vm_1 + +# *** Zvknh vector crypto extension *** +vsha2ms_vv 101101 1 ..... ..... 010 ..... 1110111 @r_vm_1 +vsha2ch_vv 101110 1 ..... ..... 010 ..... 1110111 @r_vm_1 +vsha2cl_vv 101111 1 ..... ..... 010 ..... 1110111 @r_vm_1 diff --git a/target/riscv/insn_trans/trans_rvvk.c.inc b/target/riscv/insn_trans/trans_rvvk.c.inc index 817353f4d3..a35be11b95 100644 --- a/target/riscv/insn_trans/trans_rvvk.c.inc +++ b/target/riscv/insn_trans/trans_rvvk.c.inc @@ -371,3 +371,132 @@ static bool vaeskf2_check(DisasContext *s, arg_vaeskf2_vi *a) GEN_VI_UNMASKED_TRANS(vaeskf1_vi, vaeskf1_check, ZVKNED_EGS) GEN_VI_UNMASKED_TRANS(vaeskf2_vi, vaeskf2_check, ZVKNED_EGS) + +/* + * Zvknh + */ + +#define ZVKNH_EGS 4 + +#define GEN_VV_UNMASKED_TRANS(NAME, CHECK, EGS) \ + static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ + { \ + if (CHECK(s, a)) { \ + uint32_t data = 0; \ + TCGLabel *over = gen_new_label(); \ + TCGv_i32 egs; \ + \ + if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { \ + /* save opcode for unwinding in case we throw an exception */ \ + decode_save_opc(s); \ + egs = tcg_constant_i32(EGS); \ + gen_helper_egs_check(egs, cpu_env); \ + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \ + } \ + \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + data = FIELD_DP32(data, VDATA, VTA, s->vta); \ + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \ + data = FIELD_DP32(data, VDATA, VMA, s->vma); \ + \ + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), \ + vreg_ofs(s, a->rs2), cpu_env, \ + s->cfg_ptr->vlen / 8, s->cfg_ptr->vlen / 8, \ + data, gen_helper_##NAME); \ + \ + mark_vs_dirty(s); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ + } + +static bool vsha_check_sew(DisasContext *s) +{ + return (s->cfg_ptr->ext_zvknha == true && s->sew == MO_32) || + (s->cfg_ptr->ext_zvknhb == true && + (s->sew == MO_32 || s->sew == MO_64)); +} + +static bool vsha_check(DisasContext *s, arg_rmrr *a) +{ + int egw_bytes = ZVKNH_EGS << s->sew; + int mult = 1 << MAX(s->lmul, 0); + return opivv_check(s, a) && + vsha_check_sew(s) && + MAXSZ(s) >= egw_bytes && + !is_overlapped(a->rd, mult, a->rs1, mult) && + !is_overlapped(a->rd, mult, a->rs2, mult) && + s->lmul >= 0; +} + +GEN_VV_UNMASKED_TRANS(vsha2ms_vv, vsha_check, ZVKNH_EGS) + +static bool trans_vsha2cl_vv(DisasContext *s, arg_rmrr *a) +{ + if (vsha_check(s, a)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + TCGv_i32 egs; + + if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { + /* save opcode for unwinding in case we throw an exception */ + decode_save_opc(s); + egs = tcg_constant_i32(ZVKNH_EGS); + gen_helper_egs_check(egs, cpu_env); + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); + } + + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); + data = FIELD_DP32(data, VDATA, VMA, s->vma); + + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), + vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8, + s->cfg_ptr->vlen / 8, data, + s->sew == MO_32 ? + gen_helper_vsha2cl32_vv : gen_helper_vsha2cl64_vv); + + mark_vs_dirty(s); + gen_set_label(over); + return true; + } + return false; +} + +static bool trans_vsha2ch_vv(DisasContext *s, arg_rmrr *a) +{ + if (vsha_check(s, a)) { + uint32_t data = 0; + TCGLabel *over = gen_new_label(); + TCGv_i32 egs; + + if (!s->vstart_eq_zero || !s->vl_eq_vlmax) { + /* save opcode for unwinding in case we throw an exception */ + decode_save_opc(s); + egs = tcg_constant_i32(ZVKNH_EGS); + gen_helper_egs_check(egs, cpu_env); + tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); + } + + data = FIELD_DP32(data, VDATA, VM, a->vm); + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); + data = FIELD_DP32(data, VDATA, VTA, s->vta); + data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); + data = FIELD_DP32(data, VDATA, VMA, s->vma); + + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1), + vreg_ofs(s, a->rs2), cpu_env, s->cfg_ptr->vlen / 8, + s->cfg_ptr->vlen / 8, data, + s->sew == MO_32 ? + gen_helper_vsha2ch32_vv : gen_helper_vsha2ch64_vv); + + mark_vs_dirty(s); + gen_set_label(over); + return true; + } + return false; +} diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c index 73cd1f91d9..50f7e9e166 100644 --- a/target/riscv/vcrypto_helper.c +++ b/target/riscv/vcrypto_helper.c @@ -397,3 +397,241 @@ void HELPER(vaeskf2_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm, /* set tail elements to 1s */ vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4); } + +static inline uint32_t sig0_sha256(uint32_t x) +{ + return ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3); +} + +static inline uint32_t sig1_sha256(uint32_t x) +{ + return ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10); +} + +static inline uint64_t sig0_sha512(uint64_t x) +{ + return ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7); +} + +static inline uint64_t sig1_sha512(uint64_t x) +{ + return ror64(x, 19) ^ ror64(x, 61) ^ (x >> 6); +} + +static inline void vsha2ms_e32(uint32_t *vd, uint32_t *vs1, uint32_t *vs2) +{ + uint32_t res[4]; + res[0] = sig1_sha256(vs1[H4(2)]) + vs2[H4(1)] + sig0_sha256(vd[H4(1)]) + + vd[H4(0)]; + res[1] = sig1_sha256(vs1[H4(3)]) + vs2[H4(2)] + sig0_sha256(vd[H4(2)]) + + vd[H4(1)]; + res[2] = + sig1_sha256(res[0]) + vs2[H4(3)] + sig0_sha256(vd[H4(3)]) + vd[H4(2)]; + res[3] = + sig1_sha256(res[1]) + vs1[H4(0)] + sig0_sha256(vs2[H4(0)]) + vd[H4(3)]; + vd[H4(3)] = res[3]; + vd[H4(2)] = res[2]; + vd[H4(1)] = res[1]; + vd[H4(0)] = res[0]; +} + +static inline void vsha2ms_e64(uint64_t *vd, uint64_t *vs1, uint64_t *vs2) +{ + uint64_t res[4]; + res[0] = sig1_sha512(vs1[2]) + vs2[1] + sig0_sha512(vd[1]) + vd[0]; + res[1] = sig1_sha512(vs1[3]) + vs2[2] + sig0_sha512(vd[2]) + vd[1]; + res[2] = sig1_sha512(res[0]) + vs2[3] + sig0_sha512(vd[3]) + vd[2]; + res[3] = sig1_sha512(res[1]) + vs1[0] + sig0_sha512(vs2[0]) + vd[3]; + vd[3] = res[3]; + vd[2] = res[2]; + vd[1] = res[1]; + vd[0] = res[0]; +} + +void HELPER(vsha2ms_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + uint32_t sew = FIELD_EX64(env->vtype, VTYPE, VSEW); + uint32_t esz = sew == MO_32 ? 4 : 8; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + if (sew == MO_32) { + vsha2ms_e32(((uint32_t *)vd) + i * 4, ((uint32_t *)vs1) + i * 4, + ((uint32_t *)vs2) + i * 4); + } else { + /* If not 32 then SEW should be 64 */ + vsha2ms_e64(((uint64_t *)vd) + i * 4, ((uint64_t *)vs1) + i * 4, + ((uint64_t *)vs2) + i * 4); + } + } + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +static inline uint64_t sum0_64(uint64_t x) +{ + return ror64(x, 28) ^ ror64(x, 34) ^ ror64(x, 39); +} + +static inline uint32_t sum0_32(uint32_t x) +{ + return ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22); +} + +static inline uint64_t sum1_64(uint64_t x) +{ + return ror64(x, 14) ^ ror64(x, 18) ^ ror64(x, 41); +} + +static inline uint32_t sum1_32(uint32_t x) +{ + return ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25); +} + +#define ch(x, y, z) ((x & y) ^ ((~x) & z)) + +#define maj(x, y, z) ((x & y) ^ (x & z) ^ (y & z)) + +static void vsha2c_64(uint64_t *vs2, uint64_t *vd, uint64_t *vs1) +{ + uint64_t a = vs2[3], b = vs2[2], e = vs2[1], f = vs2[0]; + uint64_t c = vd[3], d = vd[2], g = vd[1], h = vd[0]; + uint64_t W0 = vs1[0], W1 = vs1[1]; + uint64_t T1 = h + sum1_64(e) + ch(e, f, g) + W0; + uint64_t T2 = sum0_64(a) + maj(a, b, c); + + h = g; + g = f; + f = e; + e = d + T1; + d = c; + c = b; + b = a; + a = T1 + T2; + + T1 = h + sum1_64(e) + ch(e, f, g) + W1; + T2 = sum0_64(a) + maj(a, b, c); + h = g; + g = f; + f = e; + e = d + T1; + d = c; + c = b; + b = a; + a = T1 + T2; + + vd[0] = f; + vd[1] = e; + vd[2] = b; + vd[3] = a; +} + +static void vsha2c_32(uint32_t *vs2, uint32_t *vd, uint32_t *vs1) +{ + uint32_t a = vs2[H4(3)], b = vs2[H4(2)], e = vs2[H4(1)], f = vs2[H4(0)]; + uint32_t c = vd[H4(3)], d = vd[H4(2)], g = vd[H4(1)], h = vd[H4(0)]; + uint32_t W0 = vs1[H4(0)], W1 = vs1[H4(1)]; + uint32_t T1 = h + sum1_32(e) + ch(e, f, g) + W0; + uint32_t T2 = sum0_32(a) + maj(a, b, c); + + h = g; + g = f; + f = e; + e = d + T1; + d = c; + c = b; + b = a; + a = T1 + T2; + + T1 = h + sum1_32(e) + ch(e, f, g) + W1; + T2 = sum0_32(a) + maj(a, b, c); + h = g; + g = f; + f = e; + e = d + T1; + d = c; + c = b; + b = a; + a = T1 + T2; + + vd[H4(0)] = f; + vd[H4(1)] = e; + vd[H4(2)] = b; + vd[H4(3)] = a; +} + +void HELPER(vsha2ch32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + const uint32_t esz = 4; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, + ((uint32_t *)vs1) + 4 * i + 2); + } + + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +void HELPER(vsha2ch64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + const uint32_t esz = 8; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, + ((uint64_t *)vs1) + 4 * i + 2); + } + + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +void HELPER(vsha2cl32_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + const uint32_t esz = 4; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + vsha2c_32(((uint32_t *)vs2) + 4 * i, ((uint32_t *)vd) + 4 * i, + (((uint32_t *)vs1) + 4 * i)); + } + + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +} + +void HELPER(vsha2cl64_vv)(void *vd, void *vs1, void *vs2, CPURISCVState *env, + uint32_t desc) +{ + uint32_t esz = 8; + uint32_t total_elems; + uint32_t vta = vext_vta(desc); + + for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { + vsha2c_64(((uint64_t *)vs2) + 4 * i, ((uint64_t *)vd) + 4 * i, + (((uint64_t *)vs1) + 4 * i)); + } + + /* set tail elements to 1s */ + total_elems = vext_get_total_elems(env, desc, esz); + vext_set_elems_1s(vd, vta, env->vl * esz, total_elems * esz); + env->vstart = 0; +}