From patchwork Tue Jan 16 03:33:50 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 124586 Delivered-To: patch@linaro.org Received: by 10.46.64.148 with SMTP id r20csp876424lje; Mon, 15 Jan 2018 19:40:25 -0800 (PST) X-Google-Smtp-Source: ACJfBotlzQ3hAVR25cFsyZGvJzZXLx6LftUoB467iHJDyjcqcMZkkREZOjnAq8/rTL/2miwqs62C X-Received: by 10.37.90.213 with SMTP id o204mr7123602ybb.383.1516074025226; Mon, 15 Jan 2018 19:40:25 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1516074025; cv=none; d=google.com; s=arc-20160816; b=qGv7cgiqh0wnL3Ah7Yh3QqRTJPJh5a0oqAneDuz457a6BOiTHZsRS7K2YcIVX4gguj r5xNhtgT7QdrCl6ngkSe6C96MQViheO8X5b+F62vA87XucXCxOduGYHc4AUsTx9vNRGr Y3kX+h1Z3I9/R5xSuz8Sq8ze+Bt5gkVkBZBJLswv4YRuBFiQoILskew9lQmvK0v63tfE Bssa8y3KgrVGctraSANCjkruqGlhyNHod0x497e0rwnBtmuX6A6UnD0oymvie0Rb0pO0 O+kWHyPW+L6ybDdVmI3NWBaGk2kAmKUBtOF57f0MdIey9GTnYBzJ8uJgUIcr1UeQYL/1 8jsg== 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=5kVqaC9jYifYInx0rAEb9tmqpPiIsEl17bRDg5OIZWw=; b=t4tP+f7xNHVXz1y1dGi9CrZ2y8M55lQlPXdz0YbiSt3Hy0zNnXUnXrFg6KzL/LTHSw D0remFN/O9sSAlsFTWhfGzhl4+SQrrkFDDTCystrYm6ZOTdSF+VtQLuU4o4JTFb6oxfM UyneNRGlvkuLmpjwUIswUkEmR3qs+bhxFxTGQE0BBdeImiqtmpFfDO6BO0Enk1DChhhj SD9f8GU6lhyZdgCTGIWVh5iCChk0/P7tT+m2KZeqRQi67dLXNKfulNF9cyBjE+XYbP2w h6hEJWQpb1cFh+J6lMoamkSQeOZWFGLxo1gtA/QJa6FQ5muD3cn3yL7tCgDhM41yvoS2 IHiA== ARC-Authentication-Results: i=1; mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=iuS75Nde; 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 b204si273859ywc.663.2018.01.15.19.40.24 for (version=TLS1 cipher=AES128-SHA bits=128/128); Mon, 15 Jan 2018 19:40:25 -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=iuS75Nde; 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]:59136 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ebI6q-0001Ft-Go for patch@linaro.org; Mon, 15 Jan 2018 22:40:24 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:59689) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ebI1P-00059D-6h for qemu-devel@nongnu.org; Mon, 15 Jan 2018 22:34:49 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ebI1N-0003IS-0T for qemu-devel@nongnu.org; Mon, 15 Jan 2018 22:34:47 -0500 Received: from mail-pf0-x243.google.com ([2607:f8b0:400e:c00::243]:45706) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1ebI1M-0003IE-Nv for qemu-devel@nongnu.org; Mon, 15 Jan 2018 22:34:44 -0500 Received: by mail-pf0-x243.google.com with SMTP id a88so7487636pfe.12 for ; Mon, 15 Jan 2018 19:34:44 -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=5kVqaC9jYifYInx0rAEb9tmqpPiIsEl17bRDg5OIZWw=; b=iuS75Nde6rVEia22sPVUjipdjYzj2ZUeCiMHHNPqXoJabMNyV78d/toh78cX3fDM1O ft4fHMAsze+FAqXHqQBd5g1zr2mgLTrrmRThuf7aBSG4LJxg70kJ0KXd1ev2WI3PhFSF 4Ba8pi1sxe07Tms99kHkFeLzNrHMUJKUzATJM= 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=5kVqaC9jYifYInx0rAEb9tmqpPiIsEl17bRDg5OIZWw=; b=hE7nmU/fA6cPI5t9z+SD33N4NiCWUihX/e3CUK6zojNekamKbX31d07ASL+JSM6Zd0 q5WdsMwWpt2eHjJ7A/VmN/rvAtit772aPnRb9FOAJgTvyVYOpCTYVLZKTdHH8FsKeLH5 BD13z15jD9KS8KzB1Dm2q3SQ0hOYW/q+310AYKK/s6gjIQVeHWh0QVtlPLUJh4UuvZd8 LBrTEaxur7g0XMjopksLoj8b9PjflTBIBG8skaVLYuBd4OJ49aO6kVplxonRG5r6QHvQ iDMDVr5o1xLQGEKwAMHG+eEl5IiegYO8ajkXH/ddm/1Y4PIhSw9TccjiGu4EmWSnK+xv TTbA== X-Gm-Message-State: AKGB3mJttCIsahb9XpH8UAHI1J+wGtpNFl5Uv5PCVXxebiZgE1IWqMDY vUHJeA4l5ufdJNZ/FsHL0levDQL9UbQ= X-Received: by 10.98.223.196 with SMTP id d65mr26101775pfl.176.1516073683231; Mon, 15 Jan 2018 19:34:43 -0800 (PST) Received: from cloudburst.twiddle.net.com (24-181-135-57.dhcp.knwc.wa.charter.com. [24.181.135.57]) by smtp.gmail.com with ESMTPSA id c83sm1281024pfk.8.2018.01.15.19.34.41 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Mon, 15 Jan 2018 19:34:42 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Date: Mon, 15 Jan 2018 19:33:50 -0800 Message-Id: <20180116033404.31532-13-richard.henderson@linaro.org> X-Mailer: git-send-email 2.14.3 In-Reply-To: <20180116033404.31532-1-richard.henderson@linaro.org> References: <20180116033404.31532-1-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::243 Subject: [Qemu-devel] [PATCH v9 12/26] tcg: Add generic vector helpers with a scalar immediate operand 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" We already have immediate shifts. Add addition, multiplication, and logical operations with an immediate. Subtraction can thus be done with negation of the constant. Signed-off-by: Richard Henderson --- accel/tcg/tcg-runtime.h | 14 ++++ tcg/tcg-op-gvec.h | 22 ++++- accel/tcg/tcg-runtime-gvec.c | 132 ++++++++++++++++++++++++++++++ tcg/tcg-op-gvec.c | 186 ++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 352 insertions(+), 2 deletions(-) -- 2.14.3 diff --git a/accel/tcg/tcg-runtime.h b/accel/tcg/tcg-runtime.h index ec187a094b..30bb10f9f1 100644 --- a/accel/tcg/tcg-runtime.h +++ b/accel/tcg/tcg-runtime.h @@ -147,6 +147,11 @@ DEF_HELPER_FLAGS_4(gvec_add16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_add32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_add64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_adds8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_adds16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_adds32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_adds64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + DEF_HELPER_FLAGS_4(gvec_sub8, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sub16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sub32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) @@ -157,6 +162,11 @@ 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_muls8, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_muls16, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_muls32, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_muls64, TCG_CALL_NO_RWG, void, ptr, ptr, i64, 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) @@ -189,6 +199,10 @@ DEF_HELPER_FLAGS_4(gvec_xor, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_andc, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_orc, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_andi, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_xori, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) +DEF_HELPER_FLAGS_4(gvec_ori, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) + DEF_HELPER_FLAGS_3(gvec_shl8i, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_shl16i, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_shl32i, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/tcg/tcg-op-gvec.h b/tcg/tcg-op-gvec.h index 98fdab22f6..1fbb94a0cd 100644 --- a/tcg/tcg-op-gvec.h +++ b/tcg/tcg-op-gvec.h @@ -35,6 +35,12 @@ void tcg_gen_gvec_2_ool(uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz, int32_t data, gen_helper_gvec_2 *fn); +/* Similarly, passing an extra data value. */ +typedef void gen_helper_gvec_2i(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32); +void tcg_gen_gvec_2i_ool(uint32_t dofs, uint32_t aofs, TCGv_i64 c, + uint32_t oprsz, uint32_t maxsz, int32_t data, + gen_helper_gvec_2i *fn); + /* Similarly, passing an extra pointer (e.g. env or float_status). */ typedef void gen_helper_gvec_2_ptr(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); void tcg_gen_gvec_2_ptr(uint32_t dofs, uint32_t aofs, @@ -102,8 +108,10 @@ typedef struct { void (*fni4)(TCGv_i32, TCGv_i32, int32_t); /* Expand inline with a host vector type. */ void (*fniv)(unsigned, TCGv_vec, TCGv_vec, int64_t); - /* Expand out-of-line helper w/descriptor. */ + /* Expand out-of-line helper w/descriptor, data in descriptor. */ gen_helper_gvec_2 *fno; + /* Expand out-of-line helper w/descriptor, data as argument. */ + gen_helper_gvec_2i *fnoi; /* The opcode, if any, to which this corresponds. */ TCGOpcode opc; /* The vector element size, if applicable. */ @@ -179,6 +187,11 @@ 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 oprsz, uint32_t maxsz); +void tcg_gen_gvec_addi(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_muli(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); + /* Saturated arithmetic. */ void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz); @@ -200,6 +213,13 @@ void tcg_gen_gvec_andc(unsigned vece, uint32_t dofs, uint32_t aofs, void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_andi(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_xori(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); +void tcg_gen_gvec_ori(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz); + void tcg_gen_gvec_dup_mem(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t s, uint32_t m); void tcg_gen_gvec_dup_i32(unsigned vece, uint32_t dofs, uint32_t s, diff --git a/accel/tcg/tcg-runtime-gvec.c b/accel/tcg/tcg-runtime-gvec.c index e84c900670..378658124f 100644 --- a/accel/tcg/tcg-runtime-gvec.c +++ b/accel/tcg/tcg-runtime-gvec.c @@ -97,6 +97,54 @@ void HELPER(gvec_add64)(void *d, void *a, void *b, uint32_t desc) clear_high(d, oprsz, desc); } +void HELPER(gvec_adds8)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec8 vecb = (vec8){ b, b, b, b, b, b, b, b, b, b, b, b, b, b, b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec8)) { + *(vec8 *)(d + i) = *(vec8 *)(a + i) + vecb; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_adds16)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec16 vecb = (vec16){ b, b, b, b, b, b, b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec16)) { + *(vec16 *)(d + i) = *(vec16 *)(a + i) + vecb; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_adds32)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec32 vecb = (vec32){ b, b, b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec32)) { + *(vec32 *)(d + i) = *(vec32 *)(a + i) + vecb; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_adds64)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec64 vecb = (vec64){ b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec64)) { + *(vec64 *)(d + i) = *(vec64 *)(a + i) + vecb; + } + clear_high(d, oprsz, desc); +} + void HELPER(gvec_sub8)(void *d, void *a, void *b, uint32_t desc) { intptr_t oprsz = simd_oprsz(desc); @@ -185,6 +233,54 @@ void HELPER(gvec_mul64)(void *d, void *a, void *b, uint32_t desc) clear_high(d, oprsz, desc); } +void HELPER(gvec_muls8)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec8 vecb = (vec8){ b, b, b, b, b, b, b, b, b, b, b, b, b, b, b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec8)) { + *(vec8 *)(d + i) = *(vec8 *)(a + i) * vecb; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_muls16)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec16 vecb = (vec16){ b, b, b, b, b, b, b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec16)) { + *(vec16 *)(d + i) = *(vec16 *)(a + i) * vecb; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_muls32)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec32 vecb = (vec32){ b, b, b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec32)) { + *(vec32 *)(d + i) = *(vec32 *)(a + i) * vecb; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_muls64)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec64 vecb = (vec64){ b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec64)) { + *(vec64 *)(d + i) = *(vec64 *)(a + i) * vecb; + } + clear_high(d, oprsz, desc); +} + void HELPER(gvec_neg8)(void *d, void *a, uint32_t desc) { intptr_t oprsz = simd_oprsz(desc); @@ -343,6 +439,42 @@ void HELPER(gvec_orc)(void *d, void *a, void *b, uint32_t desc) clear_high(d, oprsz, desc); } +void HELPER(gvec_andi)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec64 vecb = (vec64){ b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec64)) { + *(vec64 *)(d + i) = *(vec64 *)(a + i) & vecb; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_xori)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec64 vecb = (vec64){ b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec64)) { + *(vec64 *)(d + i) = *(vec64 *)(a + i) ^ vecb; + } + clear_high(d, oprsz, desc); +} + +void HELPER(gvec_ori)(void *d, void *a, uint64_t b, uint32_t desc) +{ + intptr_t oprsz = simd_oprsz(desc); + vec64 vecb = (vec64){ b, b }; + intptr_t i; + + for (i = 0; i < oprsz; i += sizeof(vec64)) { + *(vec64 *)(d + i) = *(vec64 *)(a + i) | vecb; + } + clear_high(d, oprsz, desc); +} + void HELPER(gvec_shl8i)(void *d, void *a, uint32_t desc) { intptr_t oprsz = simd_oprsz(desc); diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index d65a5b1b82..59570cc17e 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -106,6 +106,28 @@ void tcg_gen_gvec_2_ool(uint32_t dofs, uint32_t aofs, tcg_temp_free_i32(desc); } +/* Generate a call to a gvec-style helper with two vector operands + and one scalar operand. */ +void tcg_gen_gvec_2i_ool(uint32_t dofs, uint32_t aofs, TCGv_i64 c, + uint32_t oprsz, uint32_t maxsz, int32_t data, + gen_helper_gvec_2i *fn) +{ + TCGv_ptr a0, a1; + TCGv_i32 desc = tcg_const_i32(simd_desc(oprsz, maxsz, data)); + + a0 = tcg_temp_new_ptr(); + a1 = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(a0, cpu_env, dofs); + tcg_gen_addi_ptr(a1, cpu_env, aofs); + + fn(a0, a1, c, desc); + + tcg_temp_free_ptr(a0); + tcg_temp_free_ptr(a1); + tcg_temp_free_i32(desc); +} + /* Generate a call to a gvec-style helper with three vector operands. */ void tcg_gen_gvec_3_ool(uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz, int32_t data, @@ -859,7 +881,13 @@ void tcg_gen_gvec_2i(uint32_t dofs, uint32_t aofs, uint32_t oprsz, } else if (g->fni4 && check_size_impl(oprsz, 4)) { expand_2i_i32(dofs, aofs, oprsz, c, g->load_dest, g->fni4); } else { - tcg_gen_gvec_2_ool(dofs, aofs, oprsz, maxsz, c, g->fno); + if (g->fno) { + tcg_gen_gvec_2_ool(dofs, aofs, oprsz, maxsz, c, g->fno); + } else { + TCGv_i64 tcg_c = tcg_const_i64(c); + tcg_gen_gvec_2i_ool(dofs, aofs, tcg_c, oprsz, maxsz, c, g->fnoi); + tcg_temp_free_i64(tcg_c); + } return; } @@ -1183,6 +1211,59 @@ void tcg_gen_gvec_add(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); } +static void tcg_gen_vec_addi8_i64(TCGv_i64 d, TCGv_i64 a, int64_t b) +{ + TCGv_i64 t = tcg_const_i64((b & 0xff) * (-1ull / 0xff)); + tcg_gen_vec_add8_i64(d, a, t); + tcg_temp_free_i64(t); +} + +static void tcg_gen_vec_addi16_i64(TCGv_i64 d, TCGv_i64 a, int64_t b) +{ + TCGv_i64 t = tcg_const_i64((b & 0xffff) * (-1ull / 0xffff)); + tcg_gen_vec_add16_i64(d, a, t); + tcg_temp_free_i64(t); +} + +static void tcg_gen_addi_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, b); + tcg_gen_add_vec(vece, d, a, t); + tcg_temp_free_vec(t); +} + +void tcg_gen_gvec_addi(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen2i g[4] = { + { .fni8 = tcg_gen_vec_addi8_i64, + .fniv = tcg_gen_addi_vec, + .fnoi = gen_helper_gvec_adds8, + .opc = INDEX_op_add_vec, + .vece = MO_8 }, + { .fni8 = tcg_gen_vec_addi16_i64, + .fniv = tcg_gen_addi_vec, + .fnoi = gen_helper_gvec_adds16, + .opc = INDEX_op_add_vec, + .vece = MO_16 }, + { .fni4 = tcg_gen_addi_i32, + .fniv = tcg_gen_addi_vec, + .fnoi = gen_helper_gvec_adds32, + .opc = INDEX_op_add_vec, + .vece = MO_32 }, + { .fni8 = tcg_gen_addi_i64, + .fniv = tcg_gen_addi_vec, + .fnoi = gen_helper_gvec_adds64, + .opc = INDEX_op_add_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, + }; + + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_2i(dofs, aofs, oprsz, maxsz, c, &g[vece]); +} + /* Perform a vector subtraction using normal subtraction and a mask. Compare gen_addv_mask above. */ static void gen_subv_mask(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b, TCGv_i64 m) @@ -1291,6 +1372,43 @@ void tcg_gen_gvec_mul(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); } +static void tcg_gen_muli_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, b); + tcg_gen_mul_vec(vece, d, a, t); + tcg_temp_free_vec(t); +} + +void tcg_gen_gvec_muli(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen2i g[4] = { + { .fniv = tcg_gen_muli_vec, + .fnoi = gen_helper_gvec_muls8, + .opc = INDEX_op_mul_vec, + .vece = MO_8 }, + { .fniv = tcg_gen_muli_vec, + .fnoi = gen_helper_gvec_muls16, + .opc = INDEX_op_mul_vec, + .vece = MO_16 }, + { .fni4 = tcg_gen_muli_i32, + .fniv = tcg_gen_muli_vec, + .fnoi = gen_helper_gvec_muls32, + .opc = INDEX_op_mul_vec, + .vece = MO_32 }, + { .fni8 = tcg_gen_muli_i64, + .fniv = tcg_gen_muli_vec, + .fnoi = gen_helper_gvec_muls64, + .opc = INDEX_op_mul_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, + }; + + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_2i(dofs, aofs, oprsz, maxsz, c, &g[vece]); +} + void tcg_gen_gvec_ssadd(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { @@ -1523,6 +1641,72 @@ void tcg_gen_gvec_orc(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g); } +static void tcg_gen_andi_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, b); + tcg_gen_and_vec(vece, d, a, t); + tcg_temp_free_vec(t); +} + +void tcg_gen_gvec_andi(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen2i g = { + .fni8 = tcg_gen_andi_i64, + .fniv = tcg_gen_andi_vec, + .fnoi = gen_helper_gvec_andi, + .opc = INDEX_op_and_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 + }; + tcg_gen_gvec_2i(dofs, aofs, oprsz, maxsz, c, &g); +} + +static void tcg_gen_xori_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, b); + tcg_gen_xor_vec(vece, d, a, t); + tcg_temp_free_vec(t); +} + +void tcg_gen_gvec_xori(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen2i g = { + .fni8 = tcg_gen_xori_i64, + .fniv = tcg_gen_xori_vec, + .fnoi = gen_helper_gvec_xori, + .opc = INDEX_op_xor_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 + }; + tcg_gen_gvec_2i(dofs, aofs, oprsz, maxsz, c, &g); +} + +static void tcg_gen_ori_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + tcg_gen_dupi_vec(vece, t, b); + tcg_gen_or_vec(vece, d, a, t); + tcg_temp_free_vec(t); +} + +void tcg_gen_gvec_ori(unsigned vece, uint32_t dofs, uint32_t aofs, + int64_t c, uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen2i g = { + .fni8 = tcg_gen_ori_i64, + .fniv = tcg_gen_ori_vec, + .fnoi = gen_helper_gvec_ori, + .opc = INDEX_op_or_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 + }; + tcg_gen_gvec_2i(dofs, aofs, oprsz, maxsz, c, &g); +} + void tcg_gen_vec_shl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c) { uint64_t mask = ((0xff << c) & 0xff) * (-1ull / 0xff);