From nobody Thu Nov 28 10:49:09 2024 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 Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1694075910582755.7085714983668; Thu, 7 Sep 2023 01:38:30 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qeARI-0003x4-P5; Thu, 07 Sep 2023 04:32:36 -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 1qeARG-0003oY-Ez for qemu-devel@nongnu.org; Thu, 07 Sep 2023 04:32:34 -0400 Received: from mail.loongson.cn ([114.242.206.163]) by eggs.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qeARD-0002Jx-O9 for qemu-devel@nongnu.org; Thu, 07 Sep 2023 04:32:34 -0400 Received: from loongson.cn (unknown [10.2.5.185]) by gateway (Coremail) with SMTP id _____8Cx5_GTivlkBTkhAA--.562S3; Thu, 07 Sep 2023 16:32:19 +0800 (CST) Received: from localhost.localdomain (unknown [10.2.5.185]) by localhost.localdomain (Coremail) with SMTP id AQAAf8Bxxsx+ivlk8FVwAA--.49124S23; Thu, 07 Sep 2023 16:32:18 +0800 (CST) From: Song Gao To: qemu-devel@nongnu.org Cc: richard.henderson@linaro.org, maobibo@loongson.cn Subject: [PATCH RESEND v5 21/57] target/loongarch: Implement xavg/xvagr Date: Thu, 7 Sep 2023 16:31:22 +0800 Message-Id: <20230907083158.3975132-22-gaosong@loongson.cn> X-Mailer: git-send-email 2.39.1 In-Reply-To: <20230907083158.3975132-1-gaosong@loongson.cn> References: <20230907083158.3975132-1-gaosong@loongson.cn> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-CM-TRANSID: AQAAf8Bxxsx+ivlk8FVwAA--.49124S23 X-CM-SenderInfo: 5jdr20tqj6z05rqj20fqof0/ X-Coremail-Antispam: 1Uk129KBjDUn29KB7ZKAUJUUUUU529EdanIXcx71UUUUU7KY7 ZEXasCq-sGcSsGvfJ3UbIjqfuFe4nvWSU5nxnvy29KBjDU0xBIdaVrnUUvcSsGvfC2Kfnx nUUI43ZEXa7xR_UUUUUUUUU== 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: pass client-ip=114.242.206.163; envelope-from=gaosong@loongson.cn; helo=mail.loongson.cn 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_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+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1694075911315100001 Content-Type: text/plain; charset="utf-8" This patch includes: - XVAVG.{B/H/W/D/}[U]; - XVAVGR.{B/H/W/D}[U]. Signed-off-by: Song Gao Reviewed-by: Richard Henderson --- target/loongarch/insns.decode | 17 ++++++++++++++++ target/loongarch/disas.c | 17 ++++++++++++++++ target/loongarch/vec_helper.c | 22 +++++++++++---------- target/loongarch/insn_trans/trans_vec.c.inc | 16 +++++++++++++++ 4 files changed, 62 insertions(+), 10 deletions(-) diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode index e1d8b30179..a2cb39750d 100644 --- a/target/loongarch/insns.decode +++ b/target/loongarch/insns.decode @@ -1406,6 +1406,23 @@ xvaddwod_w_hu_h 0111 01000100 00001 ..... ..... ...= .. @vvv xvaddwod_d_wu_w 0111 01000100 00010 ..... ..... ..... @vvv xvaddwod_q_du_d 0111 01000100 00011 ..... ..... ..... @vvv =20 +xvavg_b 0111 01000110 01000 ..... ..... ..... @vvv +xvavg_h 0111 01000110 01001 ..... ..... ..... @vvv +xvavg_w 0111 01000110 01010 ..... ..... ..... @vvv +xvavg_d 0111 01000110 01011 ..... ..... ..... @vvv +xvavg_bu 0111 01000110 01100 ..... ..... ..... @vvv +xvavg_hu 0111 01000110 01101 ..... ..... ..... @vvv +xvavg_wu 0111 01000110 01110 ..... ..... ..... @vvv +xvavg_du 0111 01000110 01111 ..... ..... ..... @vvv +xvavgr_b 0111 01000110 10000 ..... ..... ..... @vvv +xvavgr_h 0111 01000110 10001 ..... ..... ..... @vvv +xvavgr_w 0111 01000110 10010 ..... ..... ..... @vvv +xvavgr_d 0111 01000110 10011 ..... ..... ..... @vvv +xvavgr_bu 0111 01000110 10100 ..... ..... ..... @vvv +xvavgr_hu 0111 01000110 10101 ..... ..... ..... @vvv +xvavgr_wu 0111 01000110 10110 ..... ..... ..... @vvv +xvavgr_du 0111 01000110 10111 ..... ..... ..... @vvv + xvreplgr2vr_b 0111 01101001 11110 00000 ..... ..... @vr xvreplgr2vr_h 0111 01101001 11110 00001 ..... ..... @vr xvreplgr2vr_w 0111 01101001 11110 00010 ..... ..... @vr diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c index e3e57e1d05..f9d9583fcc 100644 --- a/target/loongarch/disas.c +++ b/target/loongarch/disas.c @@ -1825,6 +1825,23 @@ INSN_LASX(xvaddwod_w_hu_h, vvv) INSN_LASX(xvaddwod_d_wu_w, vvv) INSN_LASX(xvaddwod_q_du_d, vvv) =20 +INSN_LASX(xvavg_b, vvv) +INSN_LASX(xvavg_h, vvv) +INSN_LASX(xvavg_w, vvv) +INSN_LASX(xvavg_d, vvv) +INSN_LASX(xvavg_bu, vvv) +INSN_LASX(xvavg_hu, vvv) +INSN_LASX(xvavg_wu, vvv) +INSN_LASX(xvavg_du, vvv) +INSN_LASX(xvavgr_b, vvv) +INSN_LASX(xvavgr_h, vvv) +INSN_LASX(xvavgr_w, vvv) +INSN_LASX(xvavgr_d, vvv) +INSN_LASX(xvavgr_bu, vvv) +INSN_LASX(xvavgr_hu, vvv) +INSN_LASX(xvavgr_wu, vvv) +INSN_LASX(xvavgr_du, vvv) + INSN_LASX(xvreplgr2vr_b, vr) INSN_LASX(xvreplgr2vr_h, vr) INSN_LASX(xvreplgr2vr_w, vr) diff --git a/target/loongarch/vec_helper.c b/target/loongarch/vec_helper.c index fc3b07e8d2..35b207aae1 100644 --- a/target/loongarch/vec_helper.c +++ b/target/loongarch/vec_helper.c @@ -350,16 +350,18 @@ DO_ODD_U_S(vaddwod_d_wu_w, 64, D, UD, W, UW, DO_ADD) #define DO_VAVG(a, b) ((a >> 1) + (b >> 1) + (a & b & 1)) #define DO_VAVGR(a, b) ((a >> 1) + (b >> 1) + ((a | b) & 1)) =20 -#define DO_3OP(NAME, BIT, E, DO_OP) \ -void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \ -{ \ - int i; \ - VReg *Vd =3D (VReg *)vd; \ - VReg *Vj =3D (VReg *)vj; \ - VReg *Vk =3D (VReg *)vk; \ - for (i =3D 0; i < LSX_LEN/BIT; i++) { \ - Vd->E(i) =3D DO_OP(Vj->E(i), Vk->E(i)); \ - } \ +#define DO_3OP(NAME, BIT, E, DO_OP) \ +void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t desc) \ +{ \ + int i; \ + VReg *Vd =3D (VReg *)vd; \ + VReg *Vj =3D (VReg *)vj; \ + VReg *Vk =3D (VReg *)vk; \ + int oprsz =3D simd_oprsz(desc); \ + \ + for (i =3D 0; i < oprsz / (BIT / 8); i++) { \ + Vd->E(i) =3D DO_OP(Vj->E(i), Vk->E(i)); \ + } \ } =20 DO_3OP(vavg_b, 8, B, DO_VAVG) diff --git a/target/loongarch/insn_trans/trans_vec.c.inc b/target/loongarch= /insn_trans/trans_vec.c.inc index 8234d4670a..270dd2a08f 100644 --- a/target/loongarch/insn_trans/trans_vec.c.inc +++ b/target/loongarch/insn_trans/trans_vec.c.inc @@ -1442,6 +1442,14 @@ TRANS(vavg_bu, LSX, gvec_vvv, MO_8, do_vavg_u) TRANS(vavg_hu, LSX, gvec_vvv, MO_16, do_vavg_u) TRANS(vavg_wu, LSX, gvec_vvv, MO_32, do_vavg_u) TRANS(vavg_du, LSX, gvec_vvv, MO_64, do_vavg_u) +TRANS(xvavg_b, LASX, gvec_xxx, MO_8, do_vavg_s) +TRANS(xvavg_h, LASX, gvec_xxx, MO_16, do_vavg_s) +TRANS(xvavg_w, LASX, gvec_xxx, MO_32, do_vavg_s) +TRANS(xvavg_d, LASX, gvec_xxx, MO_64, do_vavg_s) +TRANS(xvavg_bu, LASX, gvec_xxx, MO_8, do_vavg_u) +TRANS(xvavg_hu, LASX, gvec_xxx, MO_16, do_vavg_u) +TRANS(xvavg_wu, LASX, gvec_xxx, MO_32, do_vavg_u) +TRANS(xvavg_du, LASX, gvec_xxx, MO_64, do_vavg_u) =20 static void do_vavgr_s(unsigned vece, uint32_t vd_ofs, uint32_t vj_ofs, uint32_t vk_ofs, uint32_t oprsz, uint32_t maxsz) @@ -1523,6 +1531,14 @@ TRANS(vavgr_bu, LSX, gvec_vvv, MO_8, do_vavgr_u) TRANS(vavgr_hu, LSX, gvec_vvv, MO_16, do_vavgr_u) TRANS(vavgr_wu, LSX, gvec_vvv, MO_32, do_vavgr_u) TRANS(vavgr_du, LSX, gvec_vvv, MO_64, do_vavgr_u) +TRANS(xvavgr_b, LASX, gvec_xxx, MO_8, do_vavgr_s) +TRANS(xvavgr_h, LASX, gvec_xxx, MO_16, do_vavgr_s) +TRANS(xvavgr_w, LASX, gvec_xxx, MO_32, do_vavgr_s) +TRANS(xvavgr_d, LASX, gvec_xxx, MO_64, do_vavgr_s) +TRANS(xvavgr_bu, LASX, gvec_xxx, MO_8, do_vavgr_u) +TRANS(xvavgr_hu, LASX, gvec_xxx, MO_16, do_vavgr_u) +TRANS(xvavgr_wu, LASX, gvec_xxx, MO_32, do_vavgr_u) +TRANS(xvavgr_du, LASX, gvec_xxx, MO_64, do_vavgr_u) =20 static void gen_vabsd_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b) { --=20 2.39.1