From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.6 required=3.0 tests=DKIM_INVALID,DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id BFB1CC43331 for ; Thu, 26 Mar 2020 23:18:28 +0000 (UTC) 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 mail.kernel.org (Postfix) with ESMTPS id 786E820714 for ; Thu, 26 Mar 2020 23:18:28 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=linaro.org header.i=@linaro.org header.b="dOg/KZgb" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 786E820714 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=linaro.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Received: from localhost ([::1]:34728 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jHblb-0000Ix-KM for qemu-devel@archiver.kernel.org; Thu, 26 Mar 2020 19:18:27 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:58270) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jHbcP-0002GS-BP for qemu-devel@nongnu.org; Thu, 26 Mar 2020 19:08:59 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1jHbcN-0001Pj-0D for qemu-devel@nongnu.org; Thu, 26 Mar 2020 19:08:57 -0400 Received: from mail-pj1-x1034.google.com ([2607:f8b0:4864:20::1034]:33988) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1jHbcM-0001Ob-Ox for qemu-devel@nongnu.org; Thu, 26 Mar 2020 19:08:54 -0400 Received: by mail-pj1-x1034.google.com with SMTP id q16so3754705pje.1 for ; Thu, 26 Mar 2020 16:08:54 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=TZZOTv3OeZghjguCKNcfyc5uGnx4cEJVuFPp8if3XZ4=; b=dOg/KZgbX2SBMbO9mQ0Ao9i5826dhyaAIyqQl4wUUff6lLjBDZgOGDTkzfcGu3TK/r W4br3S0TCsczqKk4GHtocBDF3a5Oz+qGdzeJMwLcfHYxs3t+et3RN0SB5sUo7Ji3AbIX jrayJCIXq0CjPVr15Dvy65cSNyPC2e4MxMdQyH754ZpJo4auUn+NQWhuFq9k+Wd417qi 7yTWqGq4JKEfEmKb/x0bUbk6BvhisXKwVWOZVytNXv/QrlVecmdd0mPCR+yMQJoAaF17 q/d+Bc+Anz5J98EfMAUp48ve59a19jadmDfzhqfb9sQFRaXwYjU6ZbIsh5yKsAd+rIP6 L7Uw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=TZZOTv3OeZghjguCKNcfyc5uGnx4cEJVuFPp8if3XZ4=; b=cnuE6t+euSjSP21d/u+ud0ZYF4xr0R0NoXSEGeSsY75sQx8nKpYz+Uypf0BTXt1pBY YfHwebHrFQzE4R2lQ20R+L3wX9vYabEvytac3+DXBESQleTCZg2A98a3Ac9W1vgX4rix IY3Me+JcWsanhV5SV0r0ZW5VmC7ec7+9v9yw+VgheTduFwQDJsH83uj7HUbQb9EAhWH6 5p4WHE66Ytxo8c7BBKF+vuaMPhJl9NmphJ7JUrvPzxFs9tB1h5Z9udvF9YcG7q5SygL0 I/5Ve43PHLrDlp13LdA4Rczt3Mgj/Tu4b57UNh7bHUZNI2Uds8axHeMfh6X7EfGuZPEp EqRA== X-Gm-Message-State: ANhLgQ0dSE4z9VJuY0VZVz4XvNhyRE9o8jWXC/mtMl6fQBp2ZBKMEujk d9GvGSAD14Ol6cEWy8cGQJaAAAcIe5o= X-Google-Smtp-Source: ADFU+vsjOAyTGZ49UgZRNjcLuMxav9HG+zOFihrMxAMo+JimgI4DOemXKgszKGmHg+EMzlRKGEP6/Q== X-Received: by 2002:a17:902:9890:: with SMTP id s16mr10062525plp.71.1585264132994; Thu, 26 Mar 2020 16:08:52 -0700 (PDT) Received: from localhost.localdomain (174-21-138-234.tukw.qwest.net. [174.21.138.234]) by smtp.gmail.com with ESMTPSA id i187sm2530037pfg.33.2020.03.26.16.08.51 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 26 Mar 2020 16:08:52 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PATCH 10/31] target/arm: Implement SVE2 saturating add/subtract (predicated) Date: Thu, 26 Mar 2020 16:08:17 -0700 Message-Id: <20200326230838.31112-11-richard.henderson@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20200326230838.31112-1-richard.henderson@linaro.org> References: <20200326230838.31112-1-richard.henderson@linaro.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:4864:20::1034 X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: rajav@quicinc.com, qemu-arm@nongnu.org, apazos@quicinc.com Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" Signed-off-by: Richard Henderson --- target/arm/helper-sve.h | 54 +++++++++++ target/arm/sve.decode | 11 +++ target/arm/sve_helper.c | 182 +++++++++++++++++++++++++------------ target/arm/translate-sve.c | 7 ++ 4 files changed, 198 insertions(+), 56 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 028c3b85a8..368185944a 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -371,6 +371,60 @@ DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_sqsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_uqsub_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_suqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve2_usqadd_zpzz_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_asr_zpzw_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_asr_zpzw_h, TCG_CALL_NO_RWG, diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 86a6bf7088..86aee38668 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -1150,3 +1150,14 @@ SMAXP 01000100 .. 010 100 101 ... ..... ..... @rdn_pg_rm UMAXP 01000100 .. 010 101 101 ... ..... ..... @rdn_pg_rm SMINP 01000100 .. 010 110 101 ... ..... ..... @rdn_pg_rm UMINP 01000100 .. 010 111 101 ... ..... ..... @rdn_pg_rm + +### SVE2 saturating add/subtract (predicated) + +SQADD_zpzz 01000100 .. 011 000 100 ... ..... ..... @rdn_pg_rm +UQADD_zpzz 01000100 .. 011 001 100 ... ..... ..... @rdn_pg_rm +SQSUB_zpzz 01000100 .. 011 010 100 ... ..... ..... @rdn_pg_rm +UQSUB_zpzz 01000100 .. 011 011 100 ... ..... ..... @rdn_pg_rm +SUQADD 01000100 .. 011 100 100 ... ..... ..... @rdn_pg_rm +USQADD 01000100 .. 011 101 100 ... ..... ..... @rdn_pg_rm +SQSUB_zpzz 01000100 .. 011 110 100 ... ..... ..... @rdm_pg_rn # SQSUBR +UQSUB_zpzz 01000100 .. 011 111 100 ... ..... ..... @rdm_pg_rn # UQSUBR diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index d7c181ddb8..bee00eaa44 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -678,6 +678,123 @@ DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS) DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS) DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D) +static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max) +{ + return val >= max ? max : val <= min ? min : val; +} + +#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX) +#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX) +#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX) + +static inline int64_t do_sqadd_d(int64_t n, int64_t m) +{ + int64_t r = n + m; + if (((r ^ n) & ~(n ^ m)) < 0) { + /* Signed overflow. */ + return r < 0 ? INT64_MAX : INT64_MIN; + } + return r; +} + +DO_ZPZZ(sve2_sqadd_zpzz_b, int8_t, H1_2, DO_SQADD_B) +DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H) +DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S) +DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d) + +#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX) +#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX) +#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX) + +static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m) +{ + uint64_t r = n + m; + return r < n ? UINT64_MAX : r; +} + +DO_ZPZZ(sve2_uqadd_zpzz_b, uint8_t, H1_2, DO_UQADD_B) +DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H) +DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S) +DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d) + +#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX) +#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX) +#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX) + +static inline int64_t do_sqsub_d(int64_t n, int64_t m) +{ + int64_t r = n - m; + if (((r ^ n) & (n ^ m)) < 0) { + /* Signed overflow. */ + return r < 0 ? INT64_MAX : INT64_MIN; + } + return r; +} + +DO_ZPZZ(sve2_sqsub_zpzz_b, int8_t, H1_2, DO_SQSUB_B) +DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H) +DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S) +DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d) + +#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX) +#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX) +#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX) + +static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m) +{ + return n > m ? n - m : 0; +} + +DO_ZPZZ(sve2_uqsub_zpzz_b, uint8_t, H1_2, DO_UQSUB_B) +DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H) +DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S) +DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d) + +#define DO_SUQADD_B(n, m) \ + do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX) +#define DO_SUQADD_H(n, m) \ + do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX) +#define DO_SUQADD_S(n, m) \ + do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX) + +static inline int64_t do_suqadd_d(int64_t n, uint64_t m) +{ + uint64_t r = n + m; + + /* Note that m - abs(n) cannot underflow. */ + if (n >= 0 && (r < m || r >= INT64_MAX)) { + return INT64_MAX; + } + return r; +} + +DO_ZPZZ(sve2_suqadd_zpzz_b, uint8_t, H1_2, DO_SUQADD_B) +DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H) +DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S) +DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d) + +#define DO_USQADD_B(n, m) \ + do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX) +#define DO_USQADD_H(n, m) \ + do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX) +#define DO_USQADD_S(n, m) \ + do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX) + +static inline uint64_t do_usqadd_d(uint64_t n, int64_t m) +{ + uint64_t r = n + m; + + if (m < 0) { + return n < -m ? 0 : r; + } + return r < n ? UINT64_MAX : r; +} + +DO_ZPZZ(sve2_usqadd_zpzz_b, uint8_t, H1_2, DO_USQADD_B) +DO_ZPZZ(sve2_usqadd_zpzz_h, uint16_t, H1_2, DO_USQADD_H) +DO_ZPZZ(sve2_usqadd_zpzz_s, uint32_t, H1_4, DO_USQADD_S) +DO_ZPZZ_D(sve2_usqadd_zpzz_d, uint64_t, do_usqadd_d) + #undef DO_ZPZZ #undef DO_ZPZZ_D @@ -1640,13 +1757,7 @@ void HELPER(sve_sqaddi_b)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int8_t)) { - int r = *(int8_t *)(a + i) + b; - if (r > INT8_MAX) { - r = INT8_MAX; - } else if (r < INT8_MIN) { - r = INT8_MIN; - } - *(int8_t *)(d + i) = r; + *(int8_t *)(d + i) = DO_SQADD_B(b, *(int8_t *)(a + i)); } } @@ -1655,13 +1766,7 @@ void HELPER(sve_sqaddi_h)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int16_t)) { - int r = *(int16_t *)(a + i) + b; - if (r > INT16_MAX) { - r = INT16_MAX; - } else if (r < INT16_MIN) { - r = INT16_MIN; - } - *(int16_t *)(d + i) = r; + *(int16_t *)(d + i) = DO_SQADD_H(b, *(int16_t *)(a + i)); } } @@ -1670,13 +1775,7 @@ void HELPER(sve_sqaddi_s)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int32_t)) { - int64_t r = *(int32_t *)(a + i) + b; - if (r > INT32_MAX) { - r = INT32_MAX; - } else if (r < INT32_MIN) { - r = INT32_MIN; - } - *(int32_t *)(d + i) = r; + *(int32_t *)(d + i) = DO_SQADD_S(b, *(int32_t *)(a + i)); } } @@ -1685,13 +1784,7 @@ void HELPER(sve_sqaddi_d)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(int64_t)) { - int64_t ai = *(int64_t *)(a + i); - int64_t r = ai + b; - if (((r ^ ai) & ~(ai ^ b)) < 0) { - /* Signed overflow. */ - r = (r < 0 ? INT64_MAX : INT64_MIN); - } - *(int64_t *)(d + i) = r; + *(int64_t *)(d + i) = do_sqadd_d(b, *(int64_t *)(a + i)); } } @@ -1704,13 +1797,7 @@ void HELPER(sve_uqaddi_b)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint8_t)) { - int r = *(uint8_t *)(a + i) + b; - if (r > UINT8_MAX) { - r = UINT8_MAX; - } else if (r < 0) { - r = 0; - } - *(uint8_t *)(d + i) = r; + *(uint8_t *)(d + i) = DO_UQADD_B(b, *(uint8_t *)(a + i)); } } @@ -1719,13 +1806,7 @@ void HELPER(sve_uqaddi_h)(void *d, void *a, int32_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint16_t)) { - int r = *(uint16_t *)(a + i) + b; - if (r > UINT16_MAX) { - r = UINT16_MAX; - } else if (r < 0) { - r = 0; - } - *(uint16_t *)(d + i) = r; + *(uint16_t *)(d + i) = DO_UQADD_H(b, *(uint16_t *)(a + i)); } } @@ -1734,13 +1815,7 @@ void HELPER(sve_uqaddi_s)(void *d, void *a, int64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint32_t)) { - int64_t r = *(uint32_t *)(a + i) + b; - if (r > UINT32_MAX) { - r = UINT32_MAX; - } else if (r < 0) { - r = 0; - } - *(uint32_t *)(d + i) = r; + *(uint32_t *)(d + i) = DO_UQADD_S(b, *(uint32_t *)(a + i)); } } @@ -1749,11 +1824,7 @@ void HELPER(sve_uqaddi_d)(void *d, void *a, uint64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint64_t)) { - uint64_t r = *(uint64_t *)(a + i) + b; - if (r < b) { - r = UINT64_MAX; - } - *(uint64_t *)(d + i) = r; + *(uint64_t *)(d + i) = do_uqadd_d(b, *(uint64_t *)(a + i)); } } @@ -1762,8 +1833,7 @@ void HELPER(sve_uqsubi_d)(void *d, void *a, uint64_t b, uint32_t desc) intptr_t i, oprsz = simd_oprsz(desc); for (i = 0; i < oprsz; i += sizeof(uint64_t)) { - uint64_t ai = *(uint64_t *)(a + i); - *(uint64_t *)(d + i) = (ai < b ? 0 : ai - b); + *(uint64_t *)(d + i) = do_uqsub_d(*(uint64_t *)(a + i), b); } } diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 5f137c0e92..21dfb2455a 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -5998,3 +5998,10 @@ DO_SVE2_ZPZZ(SMAXP, smaxp) DO_SVE2_ZPZZ(UMAXP, umaxp) DO_SVE2_ZPZZ(SMINP, sminp) DO_SVE2_ZPZZ(UMINP, uminp) + +DO_SVE2_ZPZZ(SQADD_zpzz, sqadd) +DO_SVE2_ZPZZ(UQADD_zpzz, uqadd) +DO_SVE2_ZPZZ(SQSUB_zpzz, sqsub) +DO_SVE2_ZPZZ(UQSUB_zpzz, uqsub) +DO_SVE2_ZPZZ(SUQADD, suqadd) +DO_SVE2_ZPZZ(USQADD, usqadd) -- 2.20.1