From patchwork Fri Jan 4 22:31:09 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 1020928 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=nongnu.org (client-ip=209.51.188.17; helo=lists.gnu.org; envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=linaro.org Authentication-Results: ozlabs.org; dkim=fail reason="signature verification failed" (1024-bit key; unprotected) header.d=linaro.org header.i=@linaro.org header.b="TqrIethi"; dkim-atps=neutral Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 43Wgjs11wHz9s4s for ; Sat, 5 Jan 2019 10:20:00 +1100 (AEDT) Received: from localhost ([127.0.0.1]:56647 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gfY1K-0002uo-6M for incoming@patchwork.ozlabs.org; Fri, 04 Jan 2019 17:32:50 -0500 Received: from eggsout.gnu.org ([209.51.188.92]:54833 helo=eggs.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gfY07-0002hZ-Tc for qemu-devel@nongnu.org; Fri, 04 Jan 2019 17:31:38 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gfY06-0001Qa-VI for qemu-devel@nongnu.org; Fri, 04 Jan 2019 17:31:35 -0500 Received: from mail-it1-x143.google.com ([2607:f8b0:4864:20::143]:33666) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1gfY06-0001NY-Qp for qemu-devel@nongnu.org; Fri, 04 Jan 2019 17:31:34 -0500 Received: by mail-it1-x143.google.com with SMTP id m8so2327407itk.0 for ; Fri, 04 Jan 2019 14:31:34 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:subject:date:message-id:in-reply-to:references; bh=13baR0fYl6duiBYqIpKDqOz4EjDaN2cM4w2ffhmehW8=; b=TqrIethis2KNSQswGFi4CJFpenX8Tljjgqs4j9LEAclSCN+/s0U+HOrOwGCXjzqxid 2IwreALKGvdw3wL4SPn9qqyiZq91epnPJA11PgiKngwYLnAsRUEic0JpHqWVsbx8CXlX 4hMDspAsOeEjhRfo4WBSKl8pnd7w2R+neZBHE= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references; bh=13baR0fYl6duiBYqIpKDqOz4EjDaN2cM4w2ffhmehW8=; b=HeBB6DVzdI/JEEubAkQeUbBNFjbFHDNnwLl4ffFAUYc3uvkqbaF469+5c3pSQfNa2V 85t20zZ7UYkFs5yIwGh83XYfRbDhI4IZBAQHzZKQ0YKt+w+Di6+nRRejZ1rZTak/q3/1 yviTqPJvFFLRqUY4sTpLKY4x9iz8OIA63zCAhURx433vN8wf0/c1dkJyAAf9MOCAv+BU Z0MNFejedL8hqKb2BTiRZ8SizmGgLFx5S5GooNA4YjOvIBCifSTaeY3Wjhq53Z0OG9WB H7KEtr+NLELux64o3Pm8HcSxKvCQWuzifRlZJM2RFPP+Avh7SZBy7wZgRI/rwHG8ncfu 3VPA== X-Gm-Message-State: AJcUukertxSVuNEZgAu8RQXLmvpUtBQ2DM+9xqBdoxLuv37WwsUsLweI vX6WjZHCLVWm94Lqwh8hVN5LL2CtoUg= X-Google-Smtp-Source: ALg8bN4gw8VI7mgCSmqILPQR2SIAL2tNIyK/h3LJf41Az2dsemfgTWw1CiuFC8OxqiM6x7mkJ0L35Q== X-Received: by 2002:a24:185:: with SMTP id 127mr2184486itk.55.1546641093768; Fri, 04 Jan 2019 14:31:33 -0800 (PST) Received: from cloudburst.twiddle.net ([172.56.12.23]) by smtp.gmail.com with ESMTPSA id t6sm27793259ioc.87.2019.01.04.14.31.31 for (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Fri, 04 Jan 2019 14:31:33 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Date: Sat, 5 Jan 2019 08:31:09 +1000 Message-Id: <20190104223116.14037-4-richard.henderson@linaro.org> X-Mailer: git-send-email 2.17.2 In-Reply-To: <20190104223116.14037-1-richard.henderson@linaro.org> References: <20190104223116.14037-1-richard.henderson@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:4864:20::143 Subject: [Qemu-devel] [PATCH v2 03/10] tcg: Add write_aofs to GVecGen4 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+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" This allows writing 2 output, 3 input operations. Signed-off-by: Richard Henderson --- tcg/tcg-op-gvec.h | 2 ++ tcg/tcg-op-gvec.c | 27 +++++++++++++++++++-------- 2 files changed, 21 insertions(+), 8 deletions(-) diff --git a/tcg/tcg-op-gvec.h b/tcg/tcg-op-gvec.h index d65b9d9d4c..2cb447112e 100644 --- a/tcg/tcg-op-gvec.h +++ b/tcg/tcg-op-gvec.h @@ -181,6 +181,8 @@ typedef struct { uint8_t vece; /* Prefer i64 to v64. */ bool prefer_i64; + /* Write aofs as a 2nd dest operand. */ + bool write_aofs; } GVecGen4; void tcg_gen_gvec_2(uint32_t dofs, uint32_t aofs, diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index 81689d02f7..c10d3d7b26 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -665,7 +665,7 @@ static void expand_3_i32(uint32_t dofs, uint32_t aofs, /* Expand OPSZ bytes worth of three-operand operations using i32 elements. */ static void expand_4_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t cofs, uint32_t oprsz, + uint32_t cofs, uint32_t oprsz, bool write_aofs, void (*fni)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_i32)) { TCGv_i32 t0 = tcg_temp_new_i32(); @@ -680,6 +680,9 @@ static void expand_4_i32(uint32_t dofs, uint32_t aofs, uint32_t bofs, tcg_gen_ld_i32(t3, cpu_env, cofs + i); fni(t0, t1, t2, t3); tcg_gen_st_i32(t0, cpu_env, dofs + i); + if (write_aofs) { + tcg_gen_st_i32(t1, cpu_env, aofs + i); + } } tcg_temp_free_i32(t3); tcg_temp_free_i32(t2); @@ -769,7 +772,7 @@ static void expand_3_i64(uint32_t dofs, uint32_t aofs, /* Expand OPSZ bytes worth of three-operand operations using i64 elements. */ static void expand_4_i64(uint32_t dofs, uint32_t aofs, uint32_t bofs, - uint32_t cofs, uint32_t oprsz, + uint32_t cofs, uint32_t oprsz, bool write_aofs, void (*fni)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64)) { TCGv_i64 t0 = tcg_temp_new_i64(); @@ -784,6 +787,9 @@ static void expand_4_i64(uint32_t dofs, uint32_t aofs, uint32_t bofs, tcg_gen_ld_i64(t3, cpu_env, cofs + i); fni(t0, t1, t2, t3); tcg_gen_st_i64(t0, cpu_env, dofs + i); + if (write_aofs) { + tcg_gen_st_i64(t1, cpu_env, aofs + i); + } } tcg_temp_free_i64(t3); tcg_temp_free_i64(t2); @@ -880,7 +886,7 @@ static void expand_3_vec(unsigned vece, uint32_t dofs, uint32_t aofs, /* Expand OPSZ bytes worth of four-operand operations using host vectors. */ static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, uint32_t oprsz, - uint32_t tysz, TCGType type, + uint32_t tysz, TCGType type, bool write_aofs, void (*fni)(unsigned, TCGv_vec, TCGv_vec, TCGv_vec, TCGv_vec)) { @@ -896,6 +902,9 @@ static void expand_4_vec(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_ld_vec(t3, cpu_env, cofs + i); fni(vece, t0, t1, t2, t3); tcg_gen_st_vec(t0, cpu_env, dofs + i); + if (write_aofs) { + tcg_gen_st_vec(t1, cpu_env, aofs + i); + } } tcg_temp_free_vec(t3); tcg_temp_free_vec(t2); @@ -1187,7 +1196,7 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, */ some = QEMU_ALIGN_DOWN(oprsz, 32); expand_4_vec(g->vece, dofs, aofs, bofs, cofs, some, - 32, TCG_TYPE_V256, g->fniv); + 32, TCG_TYPE_V256, g->write_aofs, g->fniv); if (some == oprsz) { break; } @@ -1200,18 +1209,20 @@ void tcg_gen_gvec_4(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t cofs, /* fallthru */ case TCG_TYPE_V128: expand_4_vec(g->vece, dofs, aofs, bofs, cofs, oprsz, - 16, TCG_TYPE_V128, g->fniv); + 16, TCG_TYPE_V128, g->write_aofs, g->fniv); break; case TCG_TYPE_V64: expand_4_vec(g->vece, dofs, aofs, bofs, cofs, oprsz, - 8, TCG_TYPE_V64, g->fniv); + 8, TCG_TYPE_V64, g->write_aofs, g->fniv); break; case 0: if (g->fni8 && check_size_impl(oprsz, 8)) { - expand_4_i64(dofs, aofs, bofs, cofs, oprsz, g->fni8); + expand_4_i64(dofs, aofs, bofs, cofs, oprsz, + g->write_aofs, g->fni8); } else if (g->fni4 && check_size_impl(oprsz, 4)) { - expand_4_i32(dofs, aofs, bofs, cofs, oprsz, g->fni4); + expand_4_i32(dofs, aofs, bofs, cofs, oprsz, + g->write_aofs, g->fni4); } else { assert(g->fno != NULL); tcg_gen_gvec_4_ool(dofs, aofs, bofs, cofs,