From patchwork Mon Dec 18 17:17:58 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 122270 Delivered-To: patch@linaro.org Received: by 10.140.22.227 with SMTP id 90csp3127789qgn; Mon, 18 Dec 2017 09:46:34 -0800 (PST) X-Google-Smtp-Source: ACJfBovDTLuSSpTYBVa2c+IpDLULvJOMoI8a5alw9YXDNhrpMkFV3lqTmX24aAsrY6BQlvznSOMC X-Received: by 10.129.51.72 with SMTP id z69mr446988ywz.390.1513619194892; Mon, 18 Dec 2017 09:46:34 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1513619194; cv=none; d=google.com; s=arc-20160816; b=OxmvaGY5labLQshayrSEo8YTUXpZR2N0UgrP49Qcw8kyLBYQ1asllYYxtizFdOuzHy SXVWSYjo7xc1DwTAKYMBOMWJwzBwqwfACTZvjbJgqqTPPPx/saa5HR6j88XskE0S2YlE D5PAUOHeZDHi401h4Vz25CqMsy8oBtNLPsadev10mc78BP7XLOXAyc+O66yQ4o2/Kfd8 JFVX4AF5a7OW+7GNytXZykAVEV7Fe0oT0EukV1vNXE7ywv1Ev+uu21+k10kYkrEVrYag k9GGG14VLC0vBb+L7f3yND0rPQsF/UBcLmXIKkVWJZllZonBwLh3Ldd4nFPgTRrZ+Jfz RtyA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:cc:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:subject:references:in-reply-to :message-id:date:to:from:dkim-signature:arc-authentication-results; bh=RkiWrDh1A4Eq7qdNT4gb8Zr8zGbgABfWRPg7U04keV0=; b=C5dTMIZPcAihBZ2bQxvLBO5Vj3TzAxosGUXiGux8XKFk5OvHYt00N4RV012l9MQRuP aSqp4ZoBxbEIrwoY5vOuD2HZ+fi2oVCEDWALBQ0uUqoKZVf6WnQZ0oj1ov0Y8UoLxdlu N2Nr+Z+YPfzkHEn7HJ2y8cktZgOwJ0NWtg4M3BJY1GHKNlG8OInRZn1TIvzQaC1h6fqO ULrMbi2S2p6g/Smta7P+yp8+oJ3c3xYEfKX0kC2DoznEw70BqWIJi963qlOXao52OasB a1cXPTKgoNIw13GdoAsPmZYuPKG1LvowSUlDJGFMUa3ftZTxX6D0RlCQSYQPspD7Pp9g 32Bg== ARC-Authentication-Results: i=1; mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=YIK7sHxy; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) smtp.mailfrom=qemu-devel-bounces+patch=linaro.org@nongnu.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [2001:4830:134:3::11]) by mx.google.com with ESMTPS id h3si2751941ybi.790.2017.12.18.09.46.34 for (version=TLS1 cipher=AES128-SHA bits=128/128); Mon, 18 Dec 2017 09:46:34 -0800 (PST) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) client-ip=2001:4830:134:3::11; Authentication-Results: mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=YIK7sHxy; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) smtp.mailfrom=qemu-devel-bounces+patch=linaro.org@nongnu.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1]:59097 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eQzUo-00080Z-9V for patch@linaro.org; Mon, 18 Dec 2017 12:46:34 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37648) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eQz3w-0000rC-Q6 for qemu-devel@nongnu.org; Mon, 18 Dec 2017 12:18:50 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1eQz3r-0001cF-M8 for qemu-devel@nongnu.org; Mon, 18 Dec 2017 12:18:48 -0500 Received: from mail-pf0-x244.google.com ([2607:f8b0:400e:c00::244]:36778) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1eQz3r-0001bD-CP for qemu-devel@nongnu.org; Mon, 18 Dec 2017 12:18:43 -0500 Received: by mail-pf0-x244.google.com with SMTP id p84so9944796pfd.3 for ; Mon, 18 Dec 2017 09:18:43 -0800 (PST) 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; bh=RkiWrDh1A4Eq7qdNT4gb8Zr8zGbgABfWRPg7U04keV0=; b=YIK7sHxyZX6ZO73QLRYYKnTH6zrn5OSHhprPjjABgT23nCKf1UeevIQmpLAhp6MwN2 Q7f4jM1cLdhlurmoqPu0+9GWxiKSCVJhZaow1ggqU0ETVb7j3yajdwdTuQzVcVANrKRh bgZAoqLVXpGdCqnK/AF9KmGv2Srhv9+DrY8K4= 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; bh=RkiWrDh1A4Eq7qdNT4gb8Zr8zGbgABfWRPg7U04keV0=; b=U5wvMro/OcF2exZPT+szuOEXJomDLxI7pvwlt0XiSwn1fy5Rt5373PjSE4uKxPSJH3 GBel4XlWTgasl6I4qe7tHaHm3Hjl5h/aSuH+tkMNm0F1BNtOmFJbzD0xgbMwhrrwP3kT BTht02Q5i0go3X6FypQ9QDzywNXQcA4FPAtE+QStN3wKd8rV225YtMIyKTIYY2IPTjgO zj3/nzc35fO2ZyXUVj8wBV55CuFb2udDJCwZXJ7aYFCSKcqnMdHw3sPIdUH4SZWR6Ohu rl8ZPhAdFjZi3cFZQJMGleA6+Egj9sUzHmuaixHTupCCuVNbW/FOo5lXvZEmbBnvxgPD sZkQ== X-Gm-Message-State: AKGB3mJ/QOyvaFfSuYgZ8XH5vDJAYqcAWZb3CyEFAh6o6JPRYfp3n+d0 Ir2jeTodoZIpUUrPe5rXJtfFNhvSC0g= X-Received: by 10.98.192.202 with SMTP id g71mr405259pfk.33.1513617522003; Mon, 18 Dec 2017 09:18:42 -0800 (PST) Received: from cloudburst.twiddle.net (174-21-7-63.tukw.qwest.net. [174.21.7.63]) by smtp.gmail.com with ESMTPSA id y19sm21050272pgv.19.2017.12.18.09.18.40 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Mon, 18 Dec 2017 09:18:41 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Date: Mon, 18 Dec 2017 09:17:58 -0800 Message-Id: <20171218171758.16964-27-richard.henderson@linaro.org> X-Mailer: git-send-email 2.14.3 In-Reply-To: <20171218171758.16964-1-richard.henderson@linaro.org> References: <20171218171758.16964-1-richard.henderson@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:400e:c00::244 Subject: [Qemu-devel] [PATCH v7 26/26] tcg: Add generic helpers for saturating arithmetic 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: , Cc: peter.maydell@linaro.org Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" No vector ops as yet. SSE only has direct support for 8- and 16-bit saturation; handling 32- and 64-bit saturation is much more expensive. Signed-off-by: Richard Henderson --- accel/tcg/tcg-runtime.h | 20 ++++ tcg/tcg-op-gvec.h | 10 ++ accel/tcg/tcg-runtime-gvec.c | 268 +++++++++++++++++++++++++++++++++++++++++++ tcg/tcg-op-gvec.c | 92 +++++++++++++++ 4 files changed, 390 insertions(+) -- 2.14.3 diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h index d1b3542946..ec187a094b 100644 --- a/accel/tcg/tcg-runtime.h +++ b/accel/tcg/tcg-runtime.h @@ -157,6 +157,26 @@ DEF_HELPER_FLAGS_4(gvec_mul16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_mul32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_mul64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ssadd8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ssadd16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ssadd32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ssadd64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_sssub8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sssub16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sssub32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sssub64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_usadd8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_usadd16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_usadd32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_usadd64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_ussub8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ussub16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ussub32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ussub64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(gvec_neg8, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_neg16, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_neg32, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/tcg/tcg-op-gvec.h b/tcg/tcg-op-gvec.h index 3a927ce24d..64116d4291 100644 --- a/tcg/tcg-op-gvec.h +++ b/tcg/tcg-op-gvec.h @@ -179,6 +179,16 @@ void tcg_gen_gvec_sub(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_mul(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t opsz, uint32_t clsz); +/* Saturated arithmetic. */ +void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t opsz, uint32_t clsz); +void tcg_gen_gvec_sssub(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t opsz, uint32_t clsz); +void tcg_gen_gvec_usadd(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t opsz, uint32_t clsz); +void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t opsz, uint32_t clsz); + void tcg_gen_gvec_and(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t opsz, uint32_t clsz); void tcg_gen_gvec_or(unsigned vece, uint32_t dofs, uint32_t aofs, diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c index ff26be0744..398ca54e1e 100644 --- a/accel/tcg/tcg-runtime-gvec.c +++ b/accel/tcg/tcg-runtime-gvec.c @@ -614,3 +614,271 @@ DO_EXT(gvec_extu32, uint32_t, uint64_t) DO_EXT(gvec_exts8, int8_t, int16_t) DO_EXT(gvec_exts16, int16_t, int32_t) DO_EXT(gvec_exts32, int32_t, int64_t) + +void HELPER(gvec_ssadd8)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int8_t)) { + int r = *(int8_t *)(a + i) + *(int8_t *)(b + i); + if (r > INT8_MAX) { + r = INT8_MAX; + } else if (r < INT8_MIN) { + r = INT8_MIN; + } + *(int8_t *)(d + i) = r; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_ssadd16)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int16_t)) { + int r = *(int16_t *)(a + i) + *(int16_t *)(b + i); + if (r > INT16_MAX) { + r = INT16_MAX; + } else if (r < INT16_MIN) { + r = INT16_MIN; + } + *(int16_t *)(d + i) = r; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_ssadd32)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int32_t)) { + int32_t ai = *(int32_t *)(a + i); + int32_t bi = *(int32_t *)(b + i); + int32_t di = ai + bi; + if (((di ^ ai) &~ (ai ^ bi)) < 0) { + /* Signed overflow. */ + di = (di < 0 ? INT32_MAX : INT32_MIN); + } + *(int32_t *)(d + i) = di; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_ssadd64)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int64_t)) { + int64_t ai = *(int64_t *)(a + i); + int64_t bi = *(int64_t *)(b + i); + int64_t di = ai + bi; + if (((di ^ ai) &~ (ai ^ bi)) < 0) { + /* Signed overflow. */ + di = (di < 0 ? INT64_MAX : INT64_MIN); + } + *(int64_t *)(d + i) = di; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_sssub8)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint8_t)) { + int r = *(uint8_t *)(a + i) - *(uint8_t *)(b + i); + if (r > INT8_MAX) { + r = INT8_MAX; + } else if (r < INT8_MIN) { + r = INT8_MIN; + } + *(uint8_t *)(d + i) = r; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_sssub16)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int16_t)) { + int r = *(int16_t *)(a + i) - *(int16_t *)(b + i); + if (r > INT16_MAX) { + r = INT16_MAX; + } else if (r < INT16_MIN) { + r = INT16_MIN; + } + *(int16_t *)(d + i) = r; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_sssub32)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int32_t)) { + int32_t ai = *(int32_t *)(a + i); + int32_t bi = *(int32_t *)(b + i); + int32_t di = ai - bi; + if (((di ^ ai) & (ai ^ bi)) < 0) { + /* Signed overflow. */ + di = (di < 0 ? INT32_MAX : INT32_MIN); + } + *(int32_t *)(d + i) = di; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_sssub64)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(int64_t)) { + int64_t ai = *(int64_t *)(a + i); + int64_t bi = *(int64_t *)(b + i); + int64_t di = ai - bi; + if (((di ^ ai) & (ai ^ bi)) < 0) { + /* Signed overflow. */ + di = (di < 0 ? INT64_MAX : INT64_MIN); + } + *(int64_t *)(d + i) = di; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_usadd8)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint8_t)) { + unsigned r = *(uint8_t *)(a + i) + *(uint8_t *)(b + i); + if (r > UINT8_MAX) { + r = UINT8_MAX; + } + *(uint8_t *)(d + i) = r; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_usadd16)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint16_t)) { + unsigned r = *(uint16_t *)(a + i) + *(uint16_t *)(b + i); + if (r > UINT16_MAX) { + r = UINT16_MAX; + } + *(uint16_t *)(d + i) = r; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_usadd32)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint32_t)) { + uint32_t ai = *(uint32_t *)(a + i); + uint32_t bi = *(uint32_t *)(b + i); + uint32_t di = ai + bi; + if (di < ai) { + di = UINT32_MAX; + } + *(uint32_t *)(d + i) = di; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_usadd64)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint64_t)) { + uint64_t ai = *(uint64_t *)(a + i); + uint64_t bi = *(uint64_t *)(b + i); + uint64_t di = ai + bi; + if (di < ai) { + di = UINT64_MAX; + } + *(uint64_t *)(d + i) = di; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_ussub8)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint8_t)) { + int r = *(uint8_t *)(a + i) - *(uint8_t *)(b + i); + if (r < 0) { + r = 0; + } + *(uint8_t *)(d + i) = r; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_ussub16)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint16_t)) { + int r = *(uint16_t *)(a + i) - *(uint16_t *)(b + i); + if (r < 0) { + r = 0; + } + *(uint16_t *)(d + i) = r; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_ussub32)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint32_t)) { + uint32_t ai = *(uint32_t *)(a + i); + uint32_t bi = *(uint32_t *)(b + i); + uint32_t di = ai - bi; + if (ai < bi) { + di = 0; + } + *(uint32_t *)(d + i) = di; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_ussub64)(void *d, void *a, void *b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(uint64_t)) { + uint64_t ai = *(uint64_t *)(a + i); + uint64_t bi = *(uint64_t *)(b + i); + uint64_t di = ai - bi; + if (ai < bi) { + di = 0; + } + *(uint64_t *)(d + i) = di; + } + clear_high(d, oprsz, desc); +} diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index a6df90b284..ddf0354106 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -1393,6 +1393,98 @@ void tcg_gen_gvec_mul(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_gvec_3(dofs, aofs, bofs, opsz, maxsz, &g[vece]); } +void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t opsz, uint32_t maxsz) +{ + static const GVecGen3 g[4] = { + { .fno = gen_helper_gvec_ssadd8, .vece = MO_8 }, + { .fno = gen_helper_gvec_ssadd16, .vece = MO_16 }, + { .fno = gen_helper_gvec_ssadd32, .vece = MO_32 }, + { .fno = gen_helper_gvec_ssadd64, .vece = MO_64 } + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3(dofs, aofs, bofs, opsz, maxsz, &g[vece]); +} + +void tcg_gen_gvec_sssub(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t opsz, uint32_t maxsz) +{ + static const GVecGen3 g[4] = { + { .fno = gen_helper_gvec_sssub8, .vece = MO_8 }, + { .fno = gen_helper_gvec_sssub16, .vece = MO_16 }, + { .fno = gen_helper_gvec_sssub32, .vece = MO_32 }, + { .fno = gen_helper_gvec_sssub64, .vece = MO_64 } + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3(dofs, aofs, bofs, opsz, maxsz, &g[vece]); +} + +static void tcg_gen_vec_usadd32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 max = tcg_const_i32(-1); + tcg_gen_add_i32(d, a, b); + tcg_gen_movcond_i32(TCG_COND_LTU, d, d, a, max, d); + tcg_temp_free_i32(max); +} + +static void tcg_gen_vec_usadd32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 max = tcg_const_i64(-1); + tcg_gen_add_i64(d, a, b); + tcg_gen_movcond_i64(TCG_COND_LTU, d, d, a, max, d); + tcg_temp_free_i64(max); +} + +void tcg_gen_gvec_usadd(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t opsz, uint32_t maxsz) +{ + static const GVecGen3 g[4] = { + { .fno = gen_helper_gvec_usadd8, .vece = MO_8 }, + { .fno = gen_helper_gvec_usadd16, .vece = MO_16 }, + { .fni4 = tcg_gen_vec_usadd32_i32, + .fno = gen_helper_gvec_usadd32, + .vece = MO_32 }, + { .fni8 = tcg_gen_vec_usadd32_i64, + .fno = gen_helper_gvec_usadd64, + .vece = MO_64 } + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3(dofs, aofs, bofs, opsz, maxsz, &g[vece]); +} + +static void tcg_gen_vec_ussub32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 min = tcg_const_i32(0); + tcg_gen_sub_i32(d, a, b); + tcg_gen_movcond_i32(TCG_COND_LTU, d, a, b, min, d); + tcg_temp_free_i32(min); +} + +static void tcg_gen_vec_ussub32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 min = tcg_const_i64(0); + tcg_gen_sub_i64(d, a, b); + tcg_gen_movcond_i64(TCG_COND_LTU, d, a, b, min, d); + tcg_temp_free_i64(min); +} + +void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t bofs, uint32_t opsz, uint32_t maxsz) +{ + static const GVecGen3 g[4] = { + { .fno = gen_helper_gvec_ussub8, .vece = MO_8 }, + { .fno = gen_helper_gvec_ussub16, .vece = MO_16 }, + { .fni4 = tcg_gen_vec_ussub32_i32, + .fno = gen_helper_gvec_ussub32, + .vece = MO_32 }, + { .fni8 = tcg_gen_vec_ussub32_i64, + .fno = gen_helper_gvec_ussub64, + .vece = MO_64 } + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3(dofs, aofs, bofs, opsz, maxsz, &g[vece]); +} + /* Perform a vector negation using normal negation and a mask. Compare gen_subv_mask above. */ static void gen_negv_mask(TCGv_i64 d, TCGv_i64 b, TCGv_i64 m)