From patchwork Wed Oct 2 13:57:07 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Savini X-Patchwork-Id: 13819828 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 2903DCF6D28 for ; Wed, 2 Oct 2024 13:58:00 +0000 (UTC) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1svzrB-0007Jk-S5; Wed, 02 Oct 2024 09:57:34 -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 1svzqx-0007F7-7Z for qemu-devel@nongnu.org; Wed, 02 Oct 2024 09:57:23 -0400 Received: from mail-ej1-x62b.google.com ([2a00:1450:4864:20::62b]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1svzqv-0003XD-L7 for qemu-devel@nongnu.org; Wed, 02 Oct 2024 09:57:18 -0400 Received: by mail-ej1-x62b.google.com with SMTP id a640c23a62f3a-a8d0d82e76aso1078617566b.3 for ; Wed, 02 Oct 2024 06:57:16 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=embecosm.com; s=google; t=1727877436; x=1728482236; darn=nongnu.org; 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=dBJVgoGbVEBWCKNsYWowDSG5FlAgb+PmFPWTiOzZRq8=; b=cuFnPkRk4qJHhcbZwWPqeUddItysQQUi5grPE3vl1JeeuYexphDGxu4tkpP2VBdFle dWG3ZSLqzDEm867cnJGQeXRtubsCsSf74R3wSPHmGeJcEGvuM+kTYsf5yPTKI/k/J2Vu GTM8pxOnnWlmX9XS+i+OOTTME7TdY2FuevemquX73brmlJlO20CtHkBZPt5UlD9vWfQ9 3KaeIBCl36PLH1GlNEIbKm2b7uEx/TvWLH3ywCnQLHgR6glwqxm/prMZR24cFVGEFjgc JsNIRcI5lO+0tVbzyWQy2pNhtEDjYQXFneXY9NfJMik7aKSiT7sKwWjfQn2bXKKSUu+n lKqQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1727877436; x=1728482236; 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=dBJVgoGbVEBWCKNsYWowDSG5FlAgb+PmFPWTiOzZRq8=; b=iHeK9tHZx8ppXIYGbPdLkmBSWiMqDzR1FpUaw/kVWHzAid2n4lbsYy32P7zVbLpQHx f+miZhlN/ErNotYrOEU6W2pwuaVkjLmt2WI6rwDY0x0xaUHnBd+cP+utOXhZ+yKxwIh+ WtlvVr4frgsDLDekO2PZT3m1y09sGsQg6JL+URnxMkKaFR/XoT9sGj1xe3+vXQB70fkk sFyomHW+jXLkx6MiGADedF/crs0P+/PdLk2Uh17krsbW1vxWYJF01oIwTAkMDSLRRyxW hnM2xiN3ZN+P/xaI/ctJCitiqlR7J/Sfcg7EUUplCNftivipV/aalaPVc5JkLLNFk59E wdeg== X-Gm-Message-State: AOJu0Yw8upGPJIu5M6wVszGspFtBQ6gCLbrFLKrQS269onGH7FbNy+B3 /GwbptAQ/8aBxGdtBXloBSNMn3yJjk4cCFIRGyZiNC+FEF3I597czaIf2lei3AGTGEAQGedX0Mm 7/AU= X-Google-Smtp-Source: AGHT+IGVrRNaX3N4Uh0UxUnYWKoPCTGvCx05N/H4p7a6zbGPRvniW83vmxJP3sNMLJbGtnS7ZLqIaw== X-Received: by 2002:a17:907:989:b0:a7a:a892:8e05 with SMTP id a640c23a62f3a-a98f8269b77mr336659866b.33.1727877435666; Wed, 02 Oct 2024 06:57:15 -0700 (PDT) Received: from paolo-laptop-amd.sou.embecosm-corp.com ([212.69.42.53]) by smtp.gmail.com with ESMTPSA id a640c23a62f3a-a93c299ac8esm869975266b.222.2024.10.02.06.57.14 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 02 Oct 2024 06:57:15 -0700 (PDT) From: Paolo Savini To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Cc: Paolo Savini , Richard Handerson , Palmer Dabbelt , Alistair Francis , Bin Meng , Weiwei Li , Daniel Henrique Barboza , Liu Zhiwei , Helene Chelin , Nathan Egge , Max Chou Subject: [RFC v2 1/2] target/riscv: rvv: reduce the overhead for simple RISC-V vector unit-stride loads and stores Date: Wed, 2 Oct 2024 14:57:07 +0100 Message-ID: <20241002135708.99146-2-paolo.savini@embecosm.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20241002135708.99146-1-paolo.savini@embecosm.com> References: <20241002135708.99146-1-paolo.savini@embecosm.com> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::62b; envelope-from=paolo.savini@embecosm.com; helo=mail-ej1-x62b.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 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: Helene CHELIN This patch improves the performance of the emulation of the RVV unit-stride loads and stores in the following cases: - when the data being loaded/stored per iteration amounts to 8 bytes or less. - when the vector length is 16 bytes (VLEN=128) and there's no grouping of the vector registers (LMUL=1). The optimization consists of avoiding the overhead of probing the RAM of the host machine and doing a loop load/store on the input data grouped in chunks of as many bytes as possible (8,4,2,1 bytes). Co-authored-by: Helene CHELIN Co-authored-by: Paolo Savini Signed-off-by: Helene CHELIN --- target/riscv/vector_helper.c | 46 ++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 29849a8b66..4b444c6bc5 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -633,6 +633,52 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, VSTART_CHECK_EARLY_EXIT(env); + /* For data sizes <= 64 bits and for LMUL=1 with VLEN=128 bits we get a + * better performance by doing a simple simulation of the load/store + * without the overhead of prodding the host RAM */ + if ((nf == 1) && ((evl << log2_esz) <= 8 || + ((vext_lmul(desc) == 0) && (simd_maxsz(desc) == 16)))) { + + uint32_t evl_b = evl << log2_esz; + + for (uint32_t j = env->vstart; j < evl_b;) { + addr = base + j; + if ((evl_b - j) >= 8) { + if (is_load) + lde_d_tlb(env, adjust_addr(env, addr), j, vd, ra); + else + ste_d_tlb(env, adjust_addr(env, addr), j, vd, ra); + j += 8; + } + else if ((evl_b - j) >= 4) { + if (is_load) + lde_w_tlb(env, adjust_addr(env, addr), j, vd, ra); + else + ste_w_tlb(env, adjust_addr(env, addr), j, vd, ra); + j += 4; + } + else if ((evl_b - j) >= 2) { + if (is_load) + lde_h_tlb(env, adjust_addr(env, addr), j, vd, ra); + else + ste_h_tlb(env, adjust_addr(env, addr), j, vd, ra); + j += 2; + } + else { + if (is_load) + lde_b_tlb(env, adjust_addr(env, addr), j, vd, ra); + else + ste_b_tlb(env, adjust_addr(env, addr), j, vd, ra); + j += 1; + } + } + + env->vstart = 0; + vext_set_tail_elems_1s(evl, vd, desc, nf, esz, max_elems); + return; + } + + vext_cont_ldst_elements(&info, base, env->vreg, env->vstart, evl, desc, log2_esz, false); /* Probe the page(s). Exit with exception for any invalid page. */ From patchwork Wed Oct 2 13:57:08 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Savini X-Patchwork-Id: 13819829 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 2ED47CF6D2C for ; Wed, 2 Oct 2024 13:58:07 +0000 (UTC) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1svzrC-0007Ka-OL; Wed, 02 Oct 2024 09:57:35 -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 1svzr2-0007GA-9Z for qemu-devel@nongnu.org; Wed, 02 Oct 2024 09:57:25 -0400 Received: from mail-wr1-x431.google.com ([2a00:1450:4864:20::431]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1svzqx-0003Xq-Lg for qemu-devel@nongnu.org; Wed, 02 Oct 2024 09:57:23 -0400 Received: by mail-wr1-x431.google.com with SMTP id ffacd0b85a97d-37cdac05af9so4324999f8f.0 for ; Wed, 02 Oct 2024 06:57:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=embecosm.com; s=google; t=1727877437; x=1728482237; darn=nongnu.org; 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=GKy/CyRSVUaBnXxnNttl6Oo4OhYAsB0CU8IGh0o82+4=; b=JtlhEycWAVzli2HeBora4alL3cXhk4Ka1XOgG/vDeN57mAWb8d+mJgok5VEQ12HFD8 rZrxmUr+ltjCbATUjEwQXlvNgMfhcL/t9MnURfz729adD4dfwRbzJLfsVDTSYmJcrDW4 BOjCQABmqDcBJxv18hs6nudC/zZiT3ZhNkRhYkoCM+C5MR2UdtP+wPoC2621aIGJmXU1 8PG59ISplDP85AnriQlbsRKV1bH6LfY8StI13E2Rs4/gVw4Z9RuMEfNCGXzbqfFGlV8s w4k6pecBJZgH2fWHpM8jfIr/txKRCqWfEDoBowwx8FQNTIXzUW/LGYoopankwisXY+Lt J55Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1727877437; x=1728482237; 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=GKy/CyRSVUaBnXxnNttl6Oo4OhYAsB0CU8IGh0o82+4=; b=NqbVgNhaKKcecf4ePOxtCr+HBg84q6k+pyO1A0UNhaD/7b5lNAqEulqMwu6EMz06tR ssqYAeGST6zdVZbQQcsedbVBWpqcXHpL/1Cu8Cfr1cOvGEV/12n6b3nWZwqCLLTrrMri AguyOSM9v2wCTma6Y0YaiIj311fY+uTIh2qK3fxmDHLU62KOI3LfiOuKQz6hElxt1qvN 3j6X99On+iBqDYfwA8Ua6/ojvFtfpVYxOr5RpJrTRpnictYAK7A++GWRlnkwTx4UPeXu oJSot5JzZSsrsCzuwmkNg09fGhCq1BlGu2VyW2N2wZYwE+sPZcExZhIMhrdPUy7JfQdN pzIA== X-Gm-Message-State: AOJu0Yw4Cfux1aU6+WzcsBc6gRkWvMfC2Jn7/IM7WSsJGPX4NuoNVyMs 6U8uJ3uWG1fEz/1WgrQ5c2UDZOS+Mwz8GtwGyWXeT+5l2KxIiiTxKnqtsNfDDBuK56iX4nccwiX MDNU= X-Google-Smtp-Source: AGHT+IFR39d4gig7DSpI5U0MPULdgJV8iuJ8JxiwkrdcgvKsbu3yx5fSkmPzCk+HmEfGAzfA+S0wNw== X-Received: by 2002:a5d:4603:0:b0:374:c3cd:73de with SMTP id ffacd0b85a97d-37cfb9d4418mr2890448f8f.35.1727877437497; Wed, 02 Oct 2024 06:57:17 -0700 (PDT) Received: from paolo-laptop-amd.sou.embecosm-corp.com ([212.69.42.53]) by smtp.gmail.com with ESMTPSA id a640c23a62f3a-a93c299ac8esm869975266b.222.2024.10.02.06.57.16 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 02 Oct 2024 06:57:17 -0700 (PDT) From: Paolo Savini To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Cc: Paolo Savini , Richard Handerson , Palmer Dabbelt , Alistair Francis , Bin Meng , Weiwei Li , Daniel Henrique Barboza , Liu Zhiwei , Helene Chelin , Nathan Egge , Max Chou Subject: [RFC v2 2/2] target/riscv: use a simplified loop to emulate rvv loads/stores only in user mode. Date: Wed, 2 Oct 2024 14:57:08 +0100 Message-ID: <20241002135708.99146-3-paolo.savini@embecosm.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20241002135708.99146-1-paolo.savini@embecosm.com> References: <20241002135708.99146-1-paolo.savini@embecosm.com> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::431; envelope-from=paolo.savini@embecosm.com; helo=mail-wr1-x431.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 autolearn=unavailable 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 The simplified emulation of vector loads and stores that bypasses the memory probing in the vext_ldst_us helper function seem to benefit only the user mode. We therefore limit this approach to the user mode configuration. Signed-off-by: Paolo Savini --- target/riscv/vector_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 9026661573..08f71abc22 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -648,6 +648,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, VSTART_CHECK_EARLY_EXIT(env); +#ifdef CONFIG_USER_ONLY /* For data sizes <= 64 bits and for LMUL=1 with VLEN=128 bits we get a * better performance by doing a simple simulation of the load/store * without the overhead of prodding the host RAM */ @@ -692,7 +693,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc, vext_set_tail_elems_1s(evl, vd, desc, nf, esz, max_elems); return; } - +#endif vext_cont_ldst_elements(&info, base, env->vreg, env->vstart, evl, desc, log2_esz, false);