From patchwork Thu Sep 14 02:26:09 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: gaosong X-Patchwork-Id: 1833892 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) 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=patchwork.ozlabs.org) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by legolas.ozlabs.org (Postfix) with ESMTPS id 4RmLzw1Yzlz1yh0 for ; Thu, 14 Sep 2023 12:36:28 +1000 (AEST) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qgc5I-0003bz-Q0; Wed, 13 Sep 2023 22:28:03 -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 1qgc4f-0003Bj-Tu for qemu-devel@nongnu.org; Wed, 13 Sep 2023 22:27:22 -0400 Received: from mail.loongson.cn ([114.242.206.163]) by eggs.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qgc4d-0004uf-89 for qemu-devel@nongnu.org; Wed, 13 Sep 2023 22:27:21 -0400 Received: from loongson.cn (unknown [10.2.5.185]) by gateway (Coremail) with SMTP id _____8Ax1fB5bwJlgPgmAA--.9916S3; Thu, 14 Sep 2023 10:27:05 +0800 (CST) Received: from localhost.localdomain (unknown [10.2.5.185]) by localhost.localdomain (Coremail) with SMTP id AQAAf8CxvdxmbwJlJ+UDAA--.7298S23; Thu, 14 Sep 2023 10:27:05 +0800 (CST) From: Song Gao To: qemu-devel@nongnu.org Cc: richard.henderson@linaro.org, maobibo@loongson.cn Subject: [PATCH v6 21/57] target/loongarch: Implement xavg/xvagr Date: Thu, 14 Sep 2023 10:26:09 +0800 Message-Id: <20230914022645.1151356-22-gaosong@loongson.cn> X-Mailer: git-send-email 2.39.1 In-Reply-To: <20230914022645.1151356-1-gaosong@loongson.cn> References: <20230914022645.1151356-1-gaosong@loongson.cn> MIME-Version: 1.0 X-CM-TRANSID: AQAAf8CxvdxmbwJlJ+UDAA--.7298S23 X-CM-SenderInfo: 5jdr20tqj6z05rqj20fqof0/ X-Coremail-Antispam: 1Uk129KBjDUn29KB7ZKAUJUUUUU529EdanIXcx71UUUUU7KY7 ZEXasCq-sGcSsGvfJ3UbIjqfuFe4nvWSU5nxnvy29KBjDU0xBIdaVrnUUvcSsGvfC2Kfnx nUUI43ZEXa7xR_UUUUUUUUU== 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+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org 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 +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) +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)) -#define DO_3OP(NAME, BIT, E, DO_OP) \ -void HELPER(NAME)(void *vd, void *vj, void *vk, uint32_t v) \ -{ \ - int i; \ - VReg *Vd = (VReg *)vd; \ - VReg *Vj = (VReg *)vj; \ - VReg *Vk = (VReg *)vk; \ - for (i = 0; i < LSX_LEN/BIT; i++) { \ - Vd->E(i) = 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 = (VReg *)vd; \ + VReg *Vj = (VReg *)vj; \ + VReg *Vk = (VReg *)vk; \ + int oprsz = simd_oprsz(desc); \ + \ + for (i = 0; i < oprsz / (BIT / 8); i++) { \ + Vd->E(i) = DO_OP(Vj->E(i), Vk->E(i)); \ + } \ } 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 322d43d50c..050a96088d 100644 --- a/target/loongarch/insn_trans/trans_vec.c.inc +++ b/target/loongarch/insn_trans/trans_vec.c.inc @@ -1419,6 +1419,14 @@ 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) 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) @@ -1500,6 +1508,14 @@ 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) static void gen_vabsd_s(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b) {