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=-18.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,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 00106C433ED for ; Fri, 30 Apr 2021 20:39:11 +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 55D7060C3E for ; Fri, 30 Apr 2021 20:39:11 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 55D7060C3E 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]:59632 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1lcZuo-00068R-AE for qemu-devel@archiver.kernel.org; Fri, 30 Apr 2021 16:39:10 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:51620) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1lcZiT-0008LD-10 for qemu-devel@nongnu.org; Fri, 30 Apr 2021 16:26:25 -0400 Received: from mail-pf1-x42d.google.com ([2607:f8b0:4864:20::42d]:37835) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1lcZiM-0005y6-EN for qemu-devel@nongnu.org; Fri, 30 Apr 2021 16:26:24 -0400 Received: by mail-pf1-x42d.google.com with SMTP id b15so5008655pfl.4 for ; Fri, 30 Apr 2021 13:26:17 -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=nkSSxMkXeoKQp4t8tpIye6M1xfm+ZviLl0PQ26Xf9wU=; b=vMO3T6RQFmb3d6g+dW0eXD4J+ZePZ6nM7eSwe5P6CuRKdoNYeL72k4mRGp+Uirol8O ecgdXqWvSOQ3RjltSCAUkAxAF9KvFXEVeahYLGk/oLwZcwcey2pU54RIBpdN3S+Q6Xt1 0AeJsWN4p6d+QZcBT8tzY5swx2btEmE3UV5tWk+5GFjlYhtm9MossS3y+LJrPyL3z4V5 0wTPLM5hzzs28gJlidLTx1B8NMLqZ15xyB9qGLOYnrjHEvoxoU44T3ZTgs+KXSoa+qzO BjBdZaEWbzC0s1K6cPctqmS2xeZAQyehqY7eZtP+SUw/fwPgEkktvdEkYKYuWKkNVSSn UsuQ== 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=nkSSxMkXeoKQp4t8tpIye6M1xfm+ZviLl0PQ26Xf9wU=; b=B7sA6EQDkkX+fwCwqhCL+Er6HVR3mQZbEvj53hlgYVVlM3qSWYUN/76ac74C19DS1d oeiZ+XDTJtXRM7t+LlYRhnYaVQ4JsjOgbmTjPk50tYP/Ygm5PoCbNrzlq4+W8R5N8QMq NMYGVfepgqacyOM02UXSCq7hgP8r3/LilPDmVU5NXgQ/7VA7jeTSxJna5OtQpstxMCbK qAIoyZAMdhTiRbkzwKivDgXickgAk0Li+cDLfU9vLxzNLOiCIxKPM1bu5UeyoQ9y5pw4 E+GWMdQDuhknm9pteYclpEQffxppqpb7tn7nihwbeWAFofZpB/O0B1TIM57EilFx7PyN T9XQ== X-Gm-Message-State: AOAM532NepHHdq6sSPSqseGU8cnZ01HBgePYeSdt8tegxHaEqOiYo/EG CY2Em5yzTRynZXBLn5OhZ0qnInicINLAqQ== X-Google-Smtp-Source: ABdhPJzpnrPuyd6Jx0et6d0UAazz6TF/EVI/aLZRwOMaFJGlORwlDVho9TdN/x/0XV5ceROfwusGOA== X-Received: by 2002:a63:1f53:: with SMTP id q19mr6073020pgm.421.1619814376803; Fri, 30 Apr 2021 13:26:16 -0700 (PDT) Received: from localhost.localdomain ([71.212.144.24]) by smtp.gmail.com with ESMTPSA id e6sm2905257pfd.219.2021.04.30.13.26.16 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 30 Apr 2021 13:26:16 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PATCH v6 09/82] target/arm: Implement SVE2 saturating add/subtract (predicated) Date: Fri, 30 Apr 2021 13:24:57 -0700 Message-Id: <20210430202610.1136687-10-richard.henderson@linaro.org> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210430202610.1136687-1-richard.henderson@linaro.org> References: <20210430202610.1136687-1-richard.henderson@linaro.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Received-SPF: pass client-ip=2607:f8b0:4864:20::42d; envelope-from=richard.henderson@linaro.org; helo=mail-pf1-x42d.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: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: qemu-arm@nongnu.org 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 | 194 ++++++++++++++++++++++++++----------- target/arm/translate-sve.c | 7 ++ 4 files changed, 210 insertions(+), 56 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 09bc067dd4..37461c9927 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 61a3321325..cd4f73265f 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -1148,3 +1148,14 @@ 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 7cc559d950..12a2078edb 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -678,6 +678,135 @@ 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; + + if (n < 0) { + /* Note that m - abs(n) cannot underflow. */ + if (r > INT64_MAX) { + /* Result is either very large positive or negative. */ + if (m > -n) { + /* m > abs(n), so r is a very large positive. */ + return INT64_MAX; + } + /* Result is negative. */ + } + } else { + /* Both inputs are positive: check for overflow. */ + if (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 @@ -1614,13 +1743,7 @@ 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)); } } @@ -1629,13 +1752,7 @@ 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)); } } @@ -1644,13 +1761,7 @@ 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)); } } @@ -1659,13 +1770,7 @@ 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)); } } @@ -1678,13 +1783,7 @@ 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)); } } @@ -1693,13 +1792,7 @@ 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)); } } @@ -1708,13 +1801,7 @@ 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)); } } @@ -1723,11 +1810,7 @@ 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)); } } @@ -1736,8 +1819,7 @@ 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 2d449c9b57..609d5ae7b7 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -5963,3 +5963,10 @@ 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) -- 2.25.1