From patchwork Fri Mar 5 17:14:36 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 393539 Delivered-To: patch@linaro.org Received: by 2002:a02:8562:0:0:0:0:0 with SMTP id g89csp631050jai; Fri, 5 Mar 2021 09:46:38 -0800 (PST) X-Google-Smtp-Source: ABdhPJzCL0j0wWVS86YtWE8OborKbjo4WbLD3XJzGEFdivtanlqcl8EmroMejhaySn2BQh41C6zv X-Received: by 2002:a5d:93cc:: with SMTP id j12mr9110836ioo.15.1614966398100; Fri, 05 Mar 2021 09:46:38 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1614966398; cv=none; d=google.com; s=arc-20160816; b=ULxGs19izLXZvWI5bhLOPibTgXKWIkPlWoV1w7DVId60HRMhfdmXSMnyjcDf16DQak LwxRDMD2a32eES0E9FRrRZEsadgpRgv0n1eqWpCutp9JsGtCNKWZ0Vs+V7LsSRkNpY/s BrXhSj3/qgnxa+38ITmpSZqEt0uoKEk5YHwnsba0369MDr2Gmie+XR7hzLF6Kfhz1C4a r9FqDIp/fJjc54uERdlA13kQNygGmY0UkBgiz/QkPXgydBNxIPOI9xrrjCQjzhOb61SK AaWfIouAj/OJGst3Y4GhhCSzyzXwM3yE6fBVHo67Ohx0HiP+73i7ul627RcO/6AsXEZe GPBQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to: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=zVqGSrKzLfhvd258ri2U23l305SxgQDBtncJihq44bU=; b=lAG2z7RiZ1MpghdqSefUbevsDG775MlTLVSd1HJGcVjpGBH/y9ShoSb4UOdk3FwM9s SnWtD7vej5HvyqNrqH5pGYLXlBbSL9W4EhP2bDf/x5Bx8vWR8M7H6hqRBkNoYs1r9NEX yS2RMny+gDYFnjQe3S7WvmhNrLxqT1J+lInI89hxCQcoBI74c09l/6ehZ1I2vL+sZpD7 hASHPafGOlBjQYxkIXnEaHUJQjjPz2dD5YTKpRo4FgJRsx9XKqtkOcwCv0+VCS6JCQKA VSZt+AO5bZkm82712hl5QvjvzVMxkp+zanHqA1L+bdfrLEptHz7FN2K7Z9tME9SfM4TM dyGQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=q9zNWeYg; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 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. [209.51.188.17]) by mx.google.com with ESMTPS id k11si2950802ilo.42.2021.03.05.09.46.38 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Fri, 05 Mar 2021 09:46:38 -0800 (PST) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=q9zNWeYg; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 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]:39140 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1lIEX6-0000cD-La for patch@linaro.org; Fri, 05 Mar 2021 12:46:36 -0500 Received: from eggs.gnu.org ([2001:470:142:3::10]:38170) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1lIE3E-0006n6-Ga for qemu-devel@nongnu.org; Fri, 05 Mar 2021 12:15:45 -0500 Received: from mail-wr1-x431.google.com ([2a00:1450:4864:20::431]:41023) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1lIE2y-0007UU-Pz for qemu-devel@nongnu.org; Fri, 05 Mar 2021 12:15:41 -0500 Received: by mail-wr1-x431.google.com with SMTP id f12so2876443wrx.8 for ; Fri, 05 Mar 2021 09:15:26 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:subject:date:message-id:in-reply-to:references:mime-version :content-transfer-encoding; bh=zVqGSrKzLfhvd258ri2U23l305SxgQDBtncJihq44bU=; b=q9zNWeYg2b9DvYHRurvLQ3xucLGiE54c69mCKoPvbICZaBYoUlBE4A9Uigwwqd8j55 Hkw7anfjnjKZfxA0rwD8a/m5smwlivG7k9yJwC+KqSKj1+tBbqc1ep/fxhdIjmckqVDV IMuBWzTDTG/Nw5VaBYeEpc8Dlrde/wCi115+SMc/wGEzSDfKNT1Jz4F02b+TH1S0Kaw2 INFylwYnOewYC6od9/vnYPbsq1O6eLZpQ57EBD2qzJPbfL2BvlfQ1Lf4AJft+r0PjU7P PpkF6kWlem4CpUVgNf5P0krGU+RlNu/qI+RjzoRo2r9AfBCPAGvupGDHEq/R5WN+QLRt 0wiQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=zVqGSrKzLfhvd258ri2U23l305SxgQDBtncJihq44bU=; b=NpooN71Gf2iVVSvFz+a6cbXd+l8RndNkCKOgb5DmAUPL2/xfotMRoXwJDfHvM/c074 XmsGPbnPg+Z6dehxw39wgWKUVqpryXrD05YN6TJY/B0hkyGVsL2YioQ8o16mjfCnaGwt T8vNURO2BpBEkCpf1rRttaOXjg2oxDGjcTA7pe093FhXfL1axHGGm8C3/6NmSV+ramV0 f63vBV2kE2UFqwfyvWktmiHRuvjgG/egm7vjySeXWf6H/kzfgQPZO3TONRr9ZhzpKM8a Zj5GWGl2fP50b9ckbd+fD/B9gkj7eH3gXETP29QH1C7JQvXkWIgVgNwt4xBXXcfqScWP sGIQ== X-Gm-Message-State: AOAM530XP+69cGFQPOYm05z05s23OTiyHUNvGH/y44PZI3OhoouWo/j2 /fXiDl7deO4iKg9djhP6qSJWQ0+I312Ssw== X-Received: by 2002:adf:f841:: with SMTP id d1mr10378790wrq.36.1614964525592; Fri, 05 Mar 2021 09:15:25 -0800 (PST) Received: from orth.archaic.org.uk (orth.archaic.org.uk. [81.2.115.148]) by smtp.gmail.com with ESMTPSA id m132sm5942357wmf.45.2021.03.05.09.15.24 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 05 Mar 2021 09:15:25 -0800 (PST) From: Peter Maydell To: qemu-devel@nongnu.org Subject: [PULL 10/49] target/arm: Speed up aarch64 TBL/TBX Date: Fri, 5 Mar 2021 17:14:36 +0000 Message-Id: <20210305171515.1038-11-peter.maydell@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20210305171515.1038-1-peter.maydell@linaro.org> References: <20210305171515.1038-1-peter.maydell@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2a00:1450:4864:20::431; envelope-from=peter.maydell@linaro.org; helo=mail-wr1-x431.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: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" From: Richard Henderson Always perform one call instead of two for 16-byte operands. Use byte loads/stores directly into the vector register file instead of extractions and deposits to a 64-bit local variable. In order to easily receive pointers into the vector register file, convert the helper to the gvec out-of-line signature. Move the helper into vec_helper.c, where it can make use of H1 and clear_tail. Signed-off-by: Richard Henderson Reviewed-by: Alex Bennée Tested-by: Alex Bennée Message-id: 20210224230532.276878-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper-a64.h | 2 +- target/arm/helper-a64.c | 32 --------------------- target/arm/translate-a64.c | 58 +++++--------------------------------- target/arm/vec_helper.c | 48 +++++++++++++++++++++++++++++++ 4 files changed, 56 insertions(+), 84 deletions(-) -- 2.20.1 diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index 7bd6aed659b..c139fa81f94 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -28,7 +28,7 @@ DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr) DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, ptr) -DEF_HELPER_FLAGS_5(simd_tbl, TCG_CALL_NO_RWG_SE, i64, env, i64, i64, i32, i32) +DEF_HELPER_FLAGS_4(simd_tblx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, ptr) DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, ptr) DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index 7f56c78fa6c..061c8ff846c 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -179,38 +179,6 @@ float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp) return float64_mul(a, b, fpst); } -uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices, - uint32_t rn, uint32_t numregs) -{ - /* Helper function for SIMD TBL and TBX. We have to do the table - * lookup part for the 64 bits worth of indices we're passed in. - * result is the initial results vector (either zeroes for TBL - * or some guest values for TBX), rn the register number where - * the table starts, and numregs the number of registers in the table. - * We return the results of the lookups. - */ - int shift; - - for (shift = 0; shift < 64; shift += 8) { - int index = extract64(indices, shift, 8); - if (index < 16 * numregs) { - /* Convert index (a byte offset into the virtual table - * which is a series of 128-bit vectors concatenated) - * into the correct register element plus a bit offset - * into that element, bearing in mind that the table - * can wrap around from V31 to V0. - */ - int elt = (rn * 2 + (index >> 3)) % 64; - int bitidx = (index & 7) * 8; - uint64_t *q = aa64_vfp_qreg(env, elt >> 1); - uint64_t val = extract64(q[elt & 1], bitidx, 8); - - result = deposit64(result, shift, 8, val); - } - } - return result; -} - /* 64bit/double versions of the neon float compare functions */ uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp) { diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 3aebdb4af9e..b591f096dfa 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -7532,10 +7532,8 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int is_tblx = extract32(insn, 12, 1); - int len = extract32(insn, 13, 2); - TCGv_i64 tcg_resl, tcg_resh, tcg_idx; - TCGv_i32 tcg_regno, tcg_numregs; + int is_tbx = extract32(insn, 12, 1); + int len = (extract32(insn, 13, 2) + 1) * 16; if (op2 != 0) { unallocated_encoding(s); @@ -7546,53 +7544,11 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) return; } - /* This does a table lookup: for every byte element in the input - * we index into a table formed from up to four vector registers, - * and then the output is the result of the lookups. Our helper - * function does the lookup operation for a single 64 bit part of - * the input. - */ - tcg_resl = tcg_temp_new_i64(); - tcg_resh = NULL; - - if (is_tblx) { - read_vec_element(s, tcg_resl, rd, 0, MO_64); - } else { - tcg_gen_movi_i64(tcg_resl, 0); - } - - if (is_q) { - tcg_resh = tcg_temp_new_i64(); - if (is_tblx) { - read_vec_element(s, tcg_resh, rd, 1, MO_64); - } else { - tcg_gen_movi_i64(tcg_resh, 0); - } - } - - tcg_idx = tcg_temp_new_i64(); - tcg_regno = tcg_const_i32(rn); - tcg_numregs = tcg_const_i32(len + 1); - read_vec_element(s, tcg_idx, rm, 0, MO_64); - gen_helper_simd_tbl(tcg_resl, cpu_env, tcg_resl, tcg_idx, - tcg_regno, tcg_numregs); - if (is_q) { - read_vec_element(s, tcg_idx, rm, 1, MO_64); - gen_helper_simd_tbl(tcg_resh, cpu_env, tcg_resh, tcg_idx, - tcg_regno, tcg_numregs); - } - tcg_temp_free_i64(tcg_idx); - tcg_temp_free_i32(tcg_regno); - tcg_temp_free_i32(tcg_numregs); - - write_vec_element(s, tcg_resl, rd, 0, MO_64); - tcg_temp_free_i64(tcg_resl); - - if (is_q) { - write_vec_element(s, tcg_resh, rd, 1, MO_64); - tcg_temp_free_i64(tcg_resh); - } - clear_vec_high(s, is_q, rd); + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rm), cpu_env, + is_q ? 16 : 8, vec_full_reg_size(s), + (len << 6) | (is_tbx << 5) | rn, + gen_helper_simd_tblx); } /* ZIP/UZP/TRN diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index 7174030377c..3fbeae87cb3 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -1937,3 +1937,51 @@ DO_VRINT_RMODE(gvec_vrint_rm_h, helper_rinth, uint16_t) DO_VRINT_RMODE(gvec_vrint_rm_s, helper_rints, uint32_t) #undef DO_VRINT_RMODE + +#ifdef TARGET_AARCH64 +void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc) +{ + const uint8_t *indices = vm; + CPUARMState *env = venv; + size_t oprsz = simd_oprsz(desc); + uint32_t rn = extract32(desc, SIMD_DATA_SHIFT, 5); + bool is_tbx = extract32(desc, SIMD_DATA_SHIFT + 5, 1); + uint32_t table_len = desc >> (SIMD_DATA_SHIFT + 6); + union { + uint8_t b[16]; + uint64_t d[2]; + } result; + + /* + * We must construct the final result in a temp, lest the output + * overlaps the input table. For TBL, begin with zero; for TBX, + * begin with the original register contents. Note that we always + * copy 16 bytes here to avoid an extra branch; clearing the high + * bits of the register for oprsz == 8 is handled below. + */ + if (is_tbx) { + memcpy(&result, vd, 16); + } else { + memset(&result, 0, 16); + } + + for (size_t i = 0; i < oprsz; ++i) { + uint32_t index = indices[H1(i)]; + + if (index < table_len) { + /* + * Convert index (a byte offset into the virtual table + * which is a series of 128-bit vectors concatenated) + * into the correct register element, bearing in mind + * that the table can wrap around from V31 to V0. + */ + const uint8_t *table = (const uint8_t *) + aa64_vfp_qreg(env, (rn + (index >> 4)) % 32); + result.b[H1(i)] = table[H1(index % 16)]; + } + } + + memcpy(vd, &result, 16); + clear_tail(vd, oprsz, simd_maxsz(desc)); +} +#endif