From patchwork Sat May 2 22:45:03 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 186072 Delivered-To: patch@linaro.org Received: by 2002:a92:3d9a:0:0:0:0:0 with SMTP id k26csp2288215ilf; Sat, 2 May 2020 15:52:38 -0700 (PDT) X-Google-Smtp-Source: APiQypLjipQsnG6t3oLXmwFnFSLIzQNOVJcgpw0Au+gBPH8A9dL+1UlfUp5Fa5jLCAJ0C5WAHE44 X-Received: by 2002:ad4:45ae:: with SMTP id y14mr10336983qvu.145.1588459957953; Sat, 02 May 2020 15:52:37 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1588459957; cv=none; d=google.com; s=arc-20160816; b=Iw7F5obG8ZSs0y3iPXzU6mtLLwKEUHRe8bjkWdJndpQLDsNW8xDY1Y2PLnwcMdsMmY CCAG3CVXttCgqBuAYkXNbojJOolKM7tKhB4JpUA2AYrV77C5OEsgEnNnyiq/0U0UhN+g isKnyRKCPDKz4cMqIZ/zowfdcm7Pdm2JnVCCYYuPrPwMkMMrcyGLua+4PYtKhjCSmAqB CjVeKSB886GR4jbIvNGxdLAVnVAotWRHUO3BOu9Y41aC89mg5m8mjC0Ir/dVZ/cJje+O ZjFMjZZoteXJSHToR9xNQL2caZMVrZfrXXc8ik9IrFjIBVf+B3qr5oFpU444mHAPYGm5 0Ckw== 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:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=6qcliVaePe6nHnDvPPzkZjTUmRFhb2EK04O2+8P0WDs=; b=pc8BQQaYDc3B0+yHXA3Q/jUZzWPnjWZyWrqG0pDf7dn5h+GA6Vet1HaOBJH/OlLcyc Olxxni2N5JGZ+tfsB2K8mdSAew4PRPypjoa9GnFc7LCTsFVtRBhOV6k2I61GCiJVtfpU zw+85PmsjllzJIYGqcBVbVQ9wjceYtEaF2dMPqx+ulabvvRBUantzNurp7WgA87kM/gs Rq/XbzcFWF6sQDHtI5uP6oBZnVvTDYKp9N5nZrKCt6uOUaHORDVOm8NZ/jBq9jwbjjMu ywhAa3e8BE8TzIy4xNInLRtEjIqS1na90PpbBlhplSL819RiadTWVz60djb3SY3u7S6W 7OzQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=cFSSfl6b; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:470:142::17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [2001:470:142::17]) by mx.google.com with ESMTPS id v9si3963447qtq.203.2020.05.02.15.52.37 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Sat, 02 May 2020 15:52:37 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:470:142::17 as permitted sender) client-ip=2001:470:142::17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=cFSSfl6b; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:470:142::17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1]:56434 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jV0zt-00088v-BT for patch@linaro.org; Sat, 02 May 2020 18:52:37 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:51722) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jV0t1-0003Ps-Bd for qemu-devel@nongnu.org; Sat, 02 May 2020 18:45:32 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.90_1) (envelope-from ) id 1jV0sz-0004uN-Oo for qemu-devel@nongnu.org; Sat, 02 May 2020 18:45:30 -0400 Received: from mail-pj1-x1041.google.com ([2607:f8b0:4864:20::1041]:39404) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1jV0sz-0004s4-3Q for qemu-devel@nongnu.org; Sat, 02 May 2020 18:45:29 -0400 Received: by mail-pj1-x1041.google.com with SMTP id e6so1858756pjt.4 for ; Sat, 02 May 2020 15:45:28 -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=6qcliVaePe6nHnDvPPzkZjTUmRFhb2EK04O2+8P0WDs=; b=cFSSfl6brnL1I5iRetZgNowAIefhuuoyKUJra5RgM6E2nnoh2dJE/Y9AyviJQ4jEPQ a3ACRmR7jykaQ0rG7ehzIWyPV0uxtNCbHA9uM0uPWTnr+pAnv4dn/t3exyEslYkApbEx h3UEqOVdY4Bq9Xp7WmYN8jc3vxMCMbnNs+u84p3hnr10/FQAvpBvUHVaqKhjcNQpzMVc A7Pc47rRzVCO2OZIz2OHixHiwUcW64hjIXBnl1ERiPDS7Ns7pIVjXehkRSzl6vo5JATx LgzJ1ByVGeAw+VRqPQzETmv/VsXYyz6UZjilZjIvzRu9O0WswjsdpftaaaT++DQB4zSr BwvA== 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=6qcliVaePe6nHnDvPPzkZjTUmRFhb2EK04O2+8P0WDs=; b=qI36Dncb0Q4WyI0tyVmElTRLs/4g/VKeohhWNOhTUHKbUvSCM3yzawgIJUUNQjXwrd 1uT5JgiPK19KlsVcrUwQScGRdZWpVQxi7yB242StBlDa7j4awYdLwvFTWEInMM3kb/7T Gr50EUEg4NNIkV7vn7sSvziwAZSqAMu9Z2XlGvcJiPEhlpsJCUSeP9XTZiSqdHcYj9gF aNmj5KbQ2dS2EYq/zPsRqOdD/S7X/aTF/pBaKR9f4Z82/mKqWYZ2KTDbXQzAZHhNrp+/ 2Rmtw14RiTy03LiJKTV/RUMi4RlkNcvnTbNNRro9jHdks988oqkITul99AS8piLL0nCK 8trg== X-Gm-Message-State: AGi0PuY+JPtBjh7tYziXHkk39+GsUDtZ3ajhU/XdKPrwNZjp3Vg5yHE7 ph0qDJ6iVJkZUDo1ypY6ewLlFH+sEaQ= X-Received: by 2002:a17:90a:df88:: with SMTP id p8mr8285165pjv.119.1588459526988; Sat, 02 May 2020 15:45:26 -0700 (PDT) Received: from localhost.localdomain (174-21-149-226.tukw.qwest.net. [174.21.149.226]) by smtp.gmail.com with ESMTPSA id h5sm2956182pjv.4.2020.05.02.15.45.25 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 02 May 2020 15:45:26 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PATCH v2 15/15] target/arm: Vectorize SABA/UABA Date: Sat, 2 May 2020 15:45:03 -0700 Message-Id: <20200502224503.2282-16-richard.henderson@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20200502224503.2282-1-richard.henderson@linaro.org> References: <20200502224503.2282-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::1041; envelope-from=richard.henderson@linaro.org; helo=mail-pj1-x1041.google.com X-detected-operating-system: by eggs.gnu.org: Error: [-] PROGRAM ABORT : Malformed IPv6 address (bad octet value). Location : parse_addr6(), p0f-client.c:67 X-Received-From: 2607:f8b0:4864:20::1041 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: peter.maydell@linaro.org Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" Include 64-bit element size in preparation for SVE2. Signed-off-by: Richard Henderson --- target/arm/helper.h | 17 +++-- target/arm/translate.h | 5 ++ target/arm/neon_helper.c | 10 --- target/arm/translate-a64.c | 17 ++--- target/arm/translate.c | 134 +++++++++++++++++++++++++++++++++++-- target/arm/vec_helper.c | 24 +++++++ 6 files changed, 174 insertions(+), 33 deletions(-) -- 2.20.1 diff --git a/target/arm/helper.h b/target/arm/helper.h index 4678d3a6f4..1857f4ee46 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -284,13 +284,6 @@ DEF_HELPER_2(neon_pmax_s8, i32, i32, i32) DEF_HELPER_2(neon_pmax_u16, i32, i32, i32) DEF_HELPER_2(neon_pmax_s16, i32, i32, i32) -DEF_HELPER_2(neon_abd_u8, i32, i32, i32) -DEF_HELPER_2(neon_abd_s8, i32, i32, i32) -DEF_HELPER_2(neon_abd_u16, i32, i32, i32) -DEF_HELPER_2(neon_abd_s16, i32, i32, i32) -DEF_HELPER_2(neon_abd_u32, i32, i32, i32) -DEF_HELPER_2(neon_abd_s32, i32, i32, i32) - DEF_HELPER_2(neon_shl_u16, i32, i32, i32) DEF_HELPER_2(neon_shl_s16, i32, i32, i32) DEF_HELPER_2(neon_rshl_u8, i32, i32, i32) @@ -741,6 +734,16 @@ DEF_HELPER_FLAGS_4(gvec_uabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_uabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_uabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_saba_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_saba_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_saba_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_saba_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_uaba_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uaba_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uaba_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uaba_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate.h b/target/arm/translate.h index d4c4111a5c..70139efcee 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -342,6 +342,11 @@ void gen_gvec_sabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index 448be93fa1..2ef75e04c8 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -576,16 +576,6 @@ NEON_POP(pmax_s16, neon_s16, 2) NEON_POP(pmax_u16, neon_u16, 2) #undef NEON_FN -#define NEON_FN(dest, src1, src2) \ - dest = (src1 > src2) ? (src1 - src2) : (src2 - src1) -NEON_VOP(abd_s8, neon_s8, 4) -NEON_VOP(abd_u8, neon_u8, 4) -NEON_VOP(abd_s16, neon_s16, 2) -NEON_VOP(abd_u16, neon_u16, 2) -NEON_VOP(abd_s32, neon_s32, 1) -NEON_VOP(abd_u32, neon_u32, 1) -#undef NEON_FN - #define NEON_FN(dest, src1, src2) do { \ int8_t tmp; \ tmp = (int8_t)src2; \ diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 38f72bf550..da140d8b91 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -11214,6 +11214,13 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sabd, size); } return; + case 0xf: /* SABA, UABA */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uaba, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_saba, size); + } + return; case 0x10: /* ADD, SUB */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_sub, size); @@ -11346,16 +11353,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genenvfn = fns[size][u]; break; } - case 0xf: /* SABA, UABA */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_abd_s8, gen_helper_neon_abd_u8 }, - { gen_helper_neon_abd_s16, gen_helper_neon_abd_u16 }, - { gen_helper_neon_abd_s32, gen_helper_neon_abd_u32 }, - }; - genfn = fns[size][u]; - break; - } case 0x16: /* SQDMULH, SQRDMULH */ { static NeonGenTwoOpEnvFn * const fns[2][2] = { diff --git a/target/arm/translate.c b/target/arm/translate.c index e0c4de2898..4af52ab7e8 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -5494,6 +5494,124 @@ void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +static void gen_saba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + gen_sabd_i32(t, a, b); + tcg_gen_add_i32(d, d, t); + tcg_temp_free_i32(t); +} + +static void gen_saba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + gen_sabd_i64(t, a, b); + tcg_gen_add_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_saba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + gen_sabd_vec(vece, t, a, b); + tcg_gen_add_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_add_vec, + INDEX_op_smin_vec, INDEX_op_smax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_saba_i32, + .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_saba_i64, + .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_uaba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + gen_uabd_i32(t, a, b); + tcg_gen_add_i32(d, d, t); + tcg_temp_free_i32(t); +} + +static void gen_uaba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + gen_uabd_i64(t, a, b); + tcg_gen_add_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_uaba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + gen_uabd_vec(vece, t, a, b); + tcg_gen_add_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_add_vec, + INDEX_op_umin_vec, INDEX_op_umax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_uaba_i32, + .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_uaba_i64, + .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -5772,6 +5890,16 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) vec_size, vec_size); } return 0; + + case NEON_3R_VABA: + if (u) { + gen_gvec_uaba(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { + gen_gvec_saba(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + return 0; } if (size == 3) { @@ -5902,12 +6030,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQRSHL: GEN_NEON_INTEGER_OP_ENV(qrshl); break; - case NEON_3R_VABA: - GEN_NEON_INTEGER_OP(abd); - tcg_temp_free_i32(tmp2); - tmp2 = neon_load_reg(rd, pass); - gen_neon_add(size, tmp, tmp2); - break; case NEON_3R_VPMAX: GEN_NEON_INTEGER_OP(pmax); break; diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index a4972d02fc..1be41a8baf 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -1431,3 +1431,27 @@ DO_ABD(gvec_uabd_s, uint32_t) DO_ABD(gvec_uabd_d, uint64_t) #undef DO_ABD + +#define DO_ABA(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + \ + for (i = 0; i < opr_sz / sizeof(TYPE); ++i) { \ + d[i] += n[i] < m[i] ? m[i] - n[i] : n[i] - m[i]; \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_ABA(gvec_saba_b, int8_t) +DO_ABA(gvec_saba_h, int16_t) +DO_ABA(gvec_saba_s, int32_t) +DO_ABA(gvec_saba_d, int64_t) + +DO_ABA(gvec_uaba_b, uint8_t) +DO_ABA(gvec_uaba_h, uint16_t) +DO_ABA(gvec_uaba_s, uint32_t) +DO_ABA(gvec_uaba_d, uint64_t) + +#undef DO_ABD