From patchwork Fri Oct 29 08:59:14 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Frank Chang X-Patchwork-Id: 12592375 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8C508C43217 for ; Fri, 29 Oct 2021 10:03:09 +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 F41106115C for ; Fri, 29 Oct 2021 10:03:08 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org F41106115C Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=sifive.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=nongnu.org Received: from localhost ([::1]:54350 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1mgOj6-00082O-4F for qemu-devel@archiver.kernel.org; Fri, 29 Oct 2021 06:03:08 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:36406) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1mgNnv-0001Ow-CU for qemu-devel@nongnu.org; Fri, 29 Oct 2021 05:04:03 -0400 Received: from mail-pg1-x533.google.com ([2607:f8b0:4864:20::533]:33669) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1mgNnt-0006mW-82 for qemu-devel@nongnu.org; Fri, 29 Oct 2021 05:04:03 -0400 Received: by mail-pg1-x533.google.com with SMTP id r28so9383166pga.0 for ; Fri, 29 Oct 2021 02:04:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sifive.com; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=ZnqWrFe8O7jUIE4YX1KKCfzYzeawOf99VzWI5tbzbK8=; b=KEgvwbb9nfnK9NOI5uvDSpm1oZfsCFjdkQMr6qozXDYPrECgxUYxIjdffDx35jenJp Amm7TUyoIW16TQxEKV/yRzHLhW1Qiz37gaenm0mBqN7zrkHvGOsVpETlXSkrNUfnWFjr OVUEnbbOWOeQ6GGpy80Oj/6RDdZINLY8aPA01yoEZRBCkeO934OL4nNvgkd1FYJB6H52 QISc47Q66jze4R93VkIqXtTwWq+96AqF0M13zhrpc5kgYnCFYa1q26X+f1u2khbp++zA ezIv6uu/3d7qhN9ayoqc3GKaIYna0C6XPS9rd+5VYDjR4XdPOsa0bqcZNXxi5gWpC/kt aQzQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=ZnqWrFe8O7jUIE4YX1KKCfzYzeawOf99VzWI5tbzbK8=; b=IQ6lqesBpHBMEgvJC7iR44+zVdcSPfO8A2nMfAArluKknuMZqInHkkewOz4hzOCait 4ppr5ee7e6tQ9moOwqRxIgbgjSGxaQh8QLPDwrdw5HL4Ynq3WLoJufyADo0Qob56i6Qx 0U1857xbv3T2WoS7hdFQdjUCW3uhuufL1DuXReeL1p1gguimeWTypuVVc044R+4nIRcD SWq5h5eFF4OhaGl/F1YWvhJl11NBszt2cGrrxiHUWmKxdSDHzXPDfAT+iotyW1Ntf+WZ nZEzzAL29wsc1jo2DYjOLffbi/1TXC13PP22V5euTfaigFQuv4TI72RsPqvEbBwNS9pl uuig== X-Gm-Message-State: AOAM533MxvJvIFwOdJ2OoJH+AaBrRRztSJYt6RDgTyxOakWxsw/QXgAz B2/VqDNfaUGlCsp4h5/9M6qDnOjXM51sWV3j X-Google-Smtp-Source: ABdhPJyjg8vmI6JeYS5AYlAgrLqvAP8XeecYHZ6XEYK2FqYhqShTLJfxggQ3W8qlautz1Ik0cqpPQw== X-Received: by 2002:a63:a319:: with SMTP id s25mr7295886pge.305.1635498239796; Fri, 29 Oct 2021 02:03:59 -0700 (PDT) Received: from localhost.localdomain ([2402:7500:46b:ce55:983b:6962:38ac:e1b9]) by smtp.gmail.com with ESMTPSA id t13sm5081477pgn.94.2021.10.29.02.03.57 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 29 Oct 2021 02:03:59 -0700 (PDT) From: frank.chang@sifive.com To: qemu-devel@nongnu.org Subject: [PATCH v9 69/76] target/riscv: rvv-1.0: floating-point reciprocal square-root estimate instruction Date: Fri, 29 Oct 2021 16:59:14 +0800 Message-Id: <20211029085922.255197-70-frank.chang@sifive.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20211029085922.255197-1-frank.chang@sifive.com> References: <20211029085922.255197-1-frank.chang@sifive.com> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::533; envelope-from=frank.chang@sifive.com; helo=mail-pg1-x533.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-riscv@nongnu.org, Frank Chang , Bin Meng , Richard Henderson , Palmer Dabbelt , Alistair Francis , LIU Zhiwei Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" From: Frank Chang Implement the floating-point reciprocal square-root estimate to 7 bits instruction. Signed-off-by: Frank Chang --- target/riscv/helper.h | 4 + target/riscv/insn32.decode | 1 + target/riscv/insn_trans/trans_rvv.c.inc | 1 + target/riscv/vector_helper.c | 183 ++++++++++++++++++++++++ 4 files changed, 189 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index a717a87a0e0..bdf06dfb24d 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -841,6 +841,10 @@ DEF_HELPER_5(vfsqrt_v_h, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfsqrt_v_w, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfsqrt_v_d, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfrsqrt7_v_h, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfrsqrt7_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfrsqrt7_v_d, void, ptr, ptr, ptr, env, i32) + DEF_HELPER_6(vfmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index c4fdc76a269..6e5f288943a 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -560,6 +560,7 @@ vfwmsac_vf 111110 . ..... ..... 101 ..... 1010111 @r_vm vfwnmsac_vv 111111 . ..... ..... 001 ..... 1010111 @r_vm vfwnmsac_vf 111111 . ..... ..... 101 ..... 1010111 @r_vm vfsqrt_v 010011 . ..... 00000 001 ..... 1010111 @r2_vm +vfrsqrt7_v 010011 . ..... 00100 001 ..... 1010111 @r2_vm vfmin_vv 000100 . ..... ..... 001 ..... 1010111 @r_vm vfmin_vf 000100 . ..... ..... 101 ..... 1010111 @r_vm vfmax_vv 000110 . ..... ..... 001 ..... 1010111 @r_vm diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index 53c8573f117..8fe718610a9 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -2407,6 +2407,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ } GEN_OPFV_TRANS(vfsqrt_v, opfv_check, RISCV_FRM_DYN) +GEN_OPFV_TRANS(vfrsqrt7_v, opfv_check, RISCV_FRM_DYN) /* Vector Floating-Point MIN/MAX Instructions */ GEN_OPFVV_TRANS(vfmin_vv, opfvv_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 22848d6b683..d5f3229bcb4 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -18,6 +18,7 @@ #include "qemu/osdep.h" #include "qemu/host-utils.h" +#include "qemu/bitops.h" #include "cpu.h" #include "exec/memop.h" #include "exec/exec-all.h" @@ -3404,6 +3405,188 @@ GEN_VEXT_V_ENV(vfsqrt_v_h, 2, 2) GEN_VEXT_V_ENV(vfsqrt_v_w, 4, 4) GEN_VEXT_V_ENV(vfsqrt_v_d, 8, 8) +/* + * Vector Floating-Point Reciprocal Square-Root Estimate Instruction + * + * Adapted from riscv-v-spec recip.c: + * https://github.com/riscv/riscv-v-spec/blob/master/recip.c + */ +static uint64_t frsqrt7(uint64_t f, int exp_size, int frac_size) +{ + uint64_t sign = extract64(f, frac_size + exp_size, 1); + uint64_t exp = extract64(f, frac_size, exp_size); + uint64_t frac = extract64(f, 0, frac_size); + + const uint8_t lookup_table[] = { + 52, 51, 50, 48, 47, 46, 44, 43, + 42, 41, 40, 39, 38, 36, 35, 34, + 33, 32, 31, 30, 30, 29, 28, 27, + 26, 25, 24, 23, 23, 22, 21, 20, + 19, 19, 18, 17, 16, 16, 15, 14, + 14, 13, 12, 12, 11, 10, 10, 9, + 9, 8, 7, 7, 6, 6, 5, 4, + 4, 3, 3, 2, 2, 1, 1, 0, + 127, 125, 123, 121, 119, 118, 116, 114, + 113, 111, 109, 108, 106, 105, 103, 102, + 100, 99, 97, 96, 95, 93, 92, 91, + 90, 88, 87, 86, 85, 84, 83, 82, + 80, 79, 78, 77, 76, 75, 74, 73, + 72, 71, 70, 70, 69, 68, 67, 66, + 65, 64, 63, 63, 62, 61, 60, 59, + 59, 58, 57, 56, 56, 55, 54, 53 + }; + const int precision = 7; + + if (exp == 0 && frac != 0) { /* subnormal */ + /* Normalize the subnormal. */ + while (extract64(frac, frac_size - 1, 1) == 0) { + exp--; + frac <<= 1; + } + + frac = (frac << 1) & MAKE_64BIT_MASK(0, frac_size); + } + + int idx = ((exp & 1) << (precision - 1)) | + (frac >> (frac_size - precision + 1)); + uint64_t out_frac = (uint64_t)(lookup_table[idx]) << + (frac_size - precision); + uint64_t out_exp = (3 * MAKE_64BIT_MASK(0, exp_size - 1) + ~exp) / 2; + + uint64_t val = 0; + val = deposit64(val, 0, frac_size, out_frac); + val = deposit64(val, frac_size, exp_size, out_exp); + val = deposit64(val, frac_size + exp_size, 1, sign); + return val; +} + +static float16 frsqrt7_h(float16 f, float_status *s) +{ + int exp_size = 5, frac_size = 10; + bool sign = float16_is_neg(f); + + /* + * frsqrt7(sNaN) = canonical NaN + * frsqrt7(-inf) = canonical NaN + * frsqrt7(-normal) = canonical NaN + * frsqrt7(-subnormal) = canonical NaN + */ + if (float16_is_signaling_nan(f, s) || + (float16_is_infinity(f) && sign) || + (float16_is_normal(f) && sign) || + (float16_is_zero_or_denormal(f) && !float16_is_zero(f) && sign)) { + s->float_exception_flags |= float_flag_invalid; + return float16_default_nan(s); + } + + /* frsqrt7(qNaN) = canonical NaN */ + if (float16_is_quiet_nan(f, s)) { + return float16_default_nan(s); + } + + /* frsqrt7(+-0) = +-inf */ + if (float16_is_zero(f)) { + s->float_exception_flags |= float_flag_divbyzero; + return float16_set_sign(float16_infinity, sign); + } + + /* frsqrt7(+inf) = +0 */ + if (float16_is_infinity(f) && !sign) { + return float16_set_sign(float16_zero, sign); + } + + /* +normal, +subnormal */ + uint64_t val = frsqrt7(f, exp_size, frac_size); + return make_float16(val); +} + +static float32 frsqrt7_s(float32 f, float_status *s) +{ + int exp_size = 8, frac_size = 23; + bool sign = float32_is_neg(f); + + /* + * frsqrt7(sNaN) = canonical NaN + * frsqrt7(-inf) = canonical NaN + * frsqrt7(-normal) = canonical NaN + * frsqrt7(-subnormal) = canonical NaN + */ + if (float32_is_signaling_nan(f, s) || + (float32_is_infinity(f) && sign) || + (float32_is_normal(f) && sign) || + (float32_is_zero_or_denormal(f) && !float32_is_zero(f) && sign)) { + s->float_exception_flags |= float_flag_invalid; + return float32_default_nan(s); + } + + /* frsqrt7(qNaN) = canonical NaN */ + if (float32_is_quiet_nan(f, s)) { + return float32_default_nan(s); + } + + /* frsqrt7(+-0) = +-inf */ + if (float32_is_zero(f)) { + s->float_exception_flags |= float_flag_divbyzero; + return float32_set_sign(float32_infinity, sign); + } + + /* frsqrt7(+inf) = +0 */ + if (float32_is_infinity(f) && !sign) { + return float32_set_sign(float32_zero, sign); + } + + /* +normal, +subnormal */ + uint64_t val = frsqrt7(f, exp_size, frac_size); + return make_float32(val); +} + +static float64 frsqrt7_d(float64 f, float_status *s) +{ + int exp_size = 11, frac_size = 52; + bool sign = float64_is_neg(f); + + /* + * frsqrt7(sNaN) = canonical NaN + * frsqrt7(-inf) = canonical NaN + * frsqrt7(-normal) = canonical NaN + * frsqrt7(-subnormal) = canonical NaN + */ + if (float64_is_signaling_nan(f, s) || + (float64_is_infinity(f) && sign) || + (float64_is_normal(f) && sign) || + (float64_is_zero_or_denormal(f) && !float64_is_zero(f) && sign)) { + s->float_exception_flags |= float_flag_invalid; + return float64_default_nan(s); + } + + /* frsqrt7(qNaN) = canonical NaN */ + if (float64_is_quiet_nan(f, s)) { + return float64_default_nan(s); + } + + /* frsqrt7(+-0) = +-inf */ + if (float64_is_zero(f)) { + s->float_exception_flags |= float_flag_divbyzero; + return float64_set_sign(float64_infinity, sign); + } + + /* frsqrt7(+inf) = +0 */ + if (float64_is_infinity(f) && !sign) { + return float64_set_sign(float64_zero, sign); + } + + /* +normal, +subnormal */ + uint64_t val = frsqrt7(f, exp_size, frac_size); + return make_float64(val); +} + +RVVCALL(OPFVV1, vfrsqrt7_v_h, OP_UU_H, H2, H2, frsqrt7_h) +RVVCALL(OPFVV1, vfrsqrt7_v_w, OP_UU_W, H4, H4, frsqrt7_s) +RVVCALL(OPFVV1, vfrsqrt7_v_d, OP_UU_D, H8, H8, frsqrt7_d) +GEN_VEXT_V_ENV(vfrsqrt7_v_h, 2, 2) +GEN_VEXT_V_ENV(vfrsqrt7_v_w, 4, 4) +GEN_VEXT_V_ENV(vfrsqrt7_v_d, 8, 8) + /* Vector Floating-Point MIN/MAX Instructions */ RVVCALL(OPFVV2, vfmin_vv_h, OP_UUU_H, H2, H2, H2, float16_minimum_number) RVVCALL(OPFVV2, vfmin_vv_w, OP_UUU_W, H4, H4, H4, float32_minimum_number)