From nobody Tue Feb 10 20:07:02 2026 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; dkim=fail; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (208.118.235.17 [208.118.235.17]) by mx.zohomail.com with SMTPS id 1513622916949577.0953740536079; Mon, 18 Dec 2017 10:48:36 -0800 (PST) Received: from localhost ([::1]:53191 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eR0Sm-0005b4-LM for importer@patchew.org; Mon, 18 Dec 2017 13:48:32 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:55704) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eQzUS-0008D1-Qq for qemu-devel@nongnu.org; Mon, 18 Dec 2017 12:46:14 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1eQzUQ-00020t-HE for qemu-devel@nongnu.org; Mon, 18 Dec 2017 12:46:12 -0500 Received: from mail-pl0-x241.google.com ([2607:f8b0:400e:c01::241]:34835) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1eQzUQ-0001zG-9N for qemu-devel@nongnu.org; Mon, 18 Dec 2017 12:46:10 -0500 Received: by mail-pl0-x241.google.com with SMTP id b96so5246524pli.2 for ; Mon, 18 Dec 2017 09:46:10 -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 t84sm26209657pfe.160.2017.12.18.09.46.07 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Mon, 18 Dec 2017 09:46:07 -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=B9w/xv6dl+dsoGKHoDlcAQW8Ls7nRo+YPhDgGizIB2U=; b=AS/hvW+wQGZ7T1x5egFaHVGg31uyBicf4pApqN41rVHsepYAfXnh4nYbtxHMODa7gA TN8XUu8Yptuc57Gk6tQmdzTMuy3AZkUqU1ZgYMvuqQqBvxJb8G7UGKDICOZHW2v1U6nr SO71ddve34BnGkyZr+NcsApHfN5ZpZZM+TZ+Y= 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=B9w/xv6dl+dsoGKHoDlcAQW8Ls7nRo+YPhDgGizIB2U=; b=uY29g+QqgBuG1tMbqIPPyIGK8BZHutS/4BDu0fPxqCIbH0STl8kEsOMmo/U2Z296CA tK6/rU++0SGgnLrH0nfCAnuA1mofXQgEYehjhltklFcGusZJy/zI5GfDtu5qczXnQipJ qXYBVS69vFiMZ/JGXcj5vqdVoGF4EtbbI9JtHAhfkEANmp/tbq1wp/xcmxl6w1B8ITNs qnkWf6to6IRYQHFw3u2+akQ5whIolct3DmImq6QSubusdN/k/EObc19dFjlQQTe4opp1 2OGq+xzxBSSOtTGqJcqbBj9SrhvIFyUsnVQL3fcpyt+hFn5sn7IqPRaBhr4gDSZga/gy SwfA== X-Gm-Message-State: AKGB3mKohPcPeUeD3ZdtYE1Q0l67N0QYGat6OJtfEDmWIeebW0kfrp4/ 3O4+RXGEjau8DpSSDUBoCiJwZJLLHhA= X-Google-Smtp-Source: ACJfBouq3XDOcFu32b6UlHxSFS0bxlUmrDJgnaSQo4afCumj5bAwLmprj3Krzo28qDgpm5KDj7qv0Q== X-Received: by 10.84.209.136 with SMTP id y8mr442838plh.439.1513619168832; Mon, 18 Dec 2017 09:46:08 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Date: Mon, 18 Dec 2017 09:45:38 -0800 Message-Id: <20171218174552.18871-10-richard.henderson@linaro.org> X-Mailer: git-send-email 2.14.3 In-Reply-To: <20171218174552.18871-1-richard.henderson@linaro.org> References: <20171218174552.18871-1-richard.henderson@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:400e:c01::241 Subject: [Qemu-devel] [PATCH 09/23] target/arm: Handle SVE registers when using clear_vec_high 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, qemu-arm@nongnu.org Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail-DKIM: fail (Header signature does not verify) X-ZohoMail: RDKM_2 RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" When storing to an AdvSIMD FP register, all of the high bits of the SVE register are zeroed. Therefore, call it more often with is_q as a parameter. Signed-off-by: Richard Henderson --- target/arm/translate-a64.c | 157 +++++++++++++++--------------------------= ---- 1 file changed, 51 insertions(+), 106 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index b951045820..9e15a4b1ae 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -533,17 +533,19 @@ static TCGv_i32 read_fp_sreg(DisasContext *s, int reg) return v; } =20 -/* Clear the bits above an 64-bit vector. +/* Clear the bits above an N-bit vector, for N =3D (is_q ? 128 : 64). * If SVE is not enabled, then there are only 128 bits in the vector. */ -static void clear_vec_high(DisasContext *s, int rd) +static void clear_vec_high(DisasContext *s, bool is_q, int rd) { unsigned ofs =3D fp_reg_offset(s, rd, MO_64); unsigned vsz =3D vec_full_reg_size(s); - TCGv_i64 tcg_zero =3D tcg_const_i64(0); =20 - tcg_gen_st_i64(tcg_zero, cpu_env, ofs + 8); - tcg_temp_free_i64(tcg_zero); + if (is_q) { + TCGv_i64 tcg_zero =3D tcg_const_i64(0); + tcg_gen_st_i64(tcg_zero, cpu_env, ofs + 8); + tcg_temp_free_i64(tcg_zero); + } if (vsz > 16) { tcg_gen_gvec_dup8i(ofs + 16, vsz - 16, vsz - 16, 0); } @@ -554,7 +556,7 @@ void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v) unsigned ofs =3D fp_reg_offset(s, reg, MO_64); =20 tcg_gen_st_i64(v, cpu_env, ofs); - clear_vec_high(s, reg); + clear_vec_high(s, false, reg); } =20 static void write_fp_sreg(DisasContext *s, int reg, TCGv_i32 v) @@ -915,6 +917,8 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv= _i64 tcg_addr, int size) =20 tcg_temp_free_i64(tmplo); tcg_temp_free_i64(tmphi); + + clear_vec_high(s, true, destidx); } =20 /* @@ -2670,12 +2674,13 @@ static void disas_ldst_multiple_struct(DisasContext= *s, uint32_t insn) /* For non-quad operations, setting a slice of the low * 64 bits of the register clears the high 64 bits (in * the ARM ARM pseudocode this is implicit in the fact - * that 'rval' is a 64 bit wide variable). We optimize - * by noticing that we only need to do this the first - * time we touch a register. + * that 'rval' is a 64 bit wide variable). + * For quad operations, we might still need to zero the + * high bits of SVE. We optimize by noticing that we = only + * need to do this the first time we touch a register. */ - if (!is_q && e =3D=3D 0 && (r =3D=3D 0 || xs =3D=3D se= lem - 1)) { - clear_vec_high(s, tt); + if (e =3D=3D 0 && (r =3D=3D 0 || xs =3D=3D selem - 1))= { + clear_vec_high(s, is_q, tt); } } tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes); @@ -2818,10 +2823,9 @@ static void disas_ldst_single_struct(DisasContext *s= , uint32_t insn) write_vec_element(s, tcg_tmp, rt, 0, MO_64); if (is_q) { write_vec_element(s, tcg_tmp, rt, 1, MO_64); - } else { - clear_vec_high(s, rt); } tcg_temp_free_i64(tcg_tmp); + clear_vec_high(s, is_q, rt); } else { /* Load/store one element per register */ if (is_load) { @@ -6659,7 +6663,6 @@ static void handle_vec_simd_sqshrn(DisasContext *s, b= ool is_scalar, bool is_q, } =20 if (!is_q) { - clear_vec_high(s, rd); write_vec_element(s, tcg_final, rd, 0, MO_64); } else { write_vec_element(s, tcg_final, rd, 1, MO_64); @@ -6672,7 +6675,8 @@ static void handle_vec_simd_sqshrn(DisasContext *s, b= ool is_scalar, bool is_q, tcg_temp_free_i64(tcg_rd); tcg_temp_free_i32(tcg_rd_narrowed); tcg_temp_free_i64(tcg_final); - return; + + clear_vec_high(s, is_q, rd); } =20 /* SQSHLU, UQSHL, SQSHL: saturating left shifts */ @@ -6736,10 +6740,7 @@ static void handle_simd_qshl(DisasContext *s, bool s= calar, bool is_q, tcg_temp_free_i64(tcg_op); } tcg_temp_free_i64(tcg_shift); - - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } else { TCGv_i32 tcg_shift =3D tcg_const_i32(shift); static NeonGenTwoOpEnvFn * const fns[2][2][3] =3D { @@ -6788,8 +6789,8 @@ static void handle_simd_qshl(DisasContext *s, bool sc= alar, bool is_q, } tcg_temp_free_i32(tcg_shift); =20 - if (!is_q && !scalar) { - clear_vec_high(s, rd); + if (!scalar) { + clear_vec_high(s, is_q, rd); } } } @@ -6831,10 +6832,8 @@ static void handle_simd_intfp_conv(DisasContext *s, = int rd, int rn, write_vec_element(s, tcg_double, rd, pass, MO_64); } } - tcg_temp_free_i64(tcg_int64); tcg_temp_free_i64(tcg_double); - } else { TCGv_i32 tcg_int32 =3D tcg_temp_new_i32(); TCGv_i32 tcg_float =3D tcg_temp_new_i32(); @@ -6887,20 +6886,17 @@ static void handle_simd_intfp_conv(DisasContext *s,= int rd, int rn, write_vec_element_i32(s, tcg_float, rd, pass, size); } } - tcg_temp_free_i32(tcg_int32); tcg_temp_free_i32(tcg_float); - - if ((size =3D=3D MO_32 && elements =3D=3D 2) || - (size =3D=3D MO_16 && elements =3D=3D 4)) { - clear_vec_high(s, rd); - } } =20 tcg_temp_free_ptr(tcg_fpst); if (fracbits || size =3D=3D MO_64) { tcg_temp_free_i32(tcg_shift); } + if (elements > 1) { + clear_vec_high(s, (elements << size) > 8, rd); + } } =20 /* UCVTF/SCVTF - Integer to FP conversion */ @@ -6988,9 +6984,7 @@ static void handle_simd_shift_fpint_conv(DisasContext= *s, bool is_scalar, write_vec_element(s, tcg_op, rd, pass, MO_64); tcg_temp_free_i64(tcg_op); } - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } else { int maxpass =3D is_scalar ? 1 : is_q ? 4 : 2; for (pass =3D 0; pass < maxpass; pass++) { @@ -7009,8 +7003,8 @@ static void handle_simd_shift_fpint_conv(DisasContext= *s, bool is_scalar, } tcg_temp_free_i32(tcg_op); } - if (!is_q && !is_scalar) { - clear_vec_high(s, rd); + if (!is_scalar) { + clear_vec_high(s, is_q, rd); } } =20 @@ -7491,13 +7485,9 @@ static void handle_3same_float(DisasContext *s, int = size, int elements, tcg_temp_free_i32(tcg_op2); } } - tcg_temp_free_ptr(fpst); =20 - if ((elements << size) < 4) { - /* scalar, or non-quad vector op */ - clear_vec_high(s, rd); - } + clear_vec_high(s, elements * (size ? 8 : 4) > 8, rd); } =20 /* AdvSIMD scalar three same @@ -8005,13 +7995,10 @@ static void handle_2misc_fcmp_zero(DisasContext *s,= int opcode, } write_vec_element(s, tcg_res, rd, pass, MO_64); } - if (is_scalar) { - clear_vec_high(s, rd); - } - tcg_temp_free_i64(tcg_res); tcg_temp_free_i64(tcg_zero); tcg_temp_free_i64(tcg_op); + clear_vec_high(s, !is_scalar, rd); } else { TCGv_i32 tcg_op =3D tcg_temp_new_i32(); TCGv_i32 tcg_zero =3D tcg_const_i32(0); @@ -8063,8 +8050,8 @@ static void handle_2misc_fcmp_zero(DisasContext *s, i= nt opcode, tcg_temp_free_i32(tcg_res); tcg_temp_free_i32(tcg_zero); tcg_temp_free_i32(tcg_op); - if (!is_q && !is_scalar) { - clear_vec_high(s, rd); + if (!is_scalar) { + clear_vec_high(s, is_q, rd); } } =20 @@ -8100,12 +8087,9 @@ static void handle_2misc_reciprocal(DisasContext *s,= int opcode, } write_vec_element(s, tcg_res, rd, pass, MO_64); } - if (is_scalar) { - clear_vec_high(s, rd); - } - tcg_temp_free_i64(tcg_res); tcg_temp_free_i64(tcg_op); + clear_vec_high(s, !is_scalar, rd); } else { TCGv_i32 tcg_op =3D tcg_temp_new_i32(); TCGv_i32 tcg_res =3D tcg_temp_new_i32(); @@ -8145,8 +8129,8 @@ static void handle_2misc_reciprocal(DisasContext *s, = int opcode, } tcg_temp_free_i32(tcg_res); tcg_temp_free_i32(tcg_op); - if (!is_q && !is_scalar) { - clear_vec_high(s, rd); + if (!is_scalar) { + clear_vec_high(s, is_q, rd); } } tcg_temp_free_ptr(fpst); @@ -8259,9 +8243,7 @@ static void handle_2misc_narrow(DisasContext *s, bool= scalar, write_vec_element_i32(s, tcg_res[pass], rd, destelt + pass, MO_32); tcg_temp_free_i32(tcg_res[pass]); } - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } =20 /* Remaining saturating accumulating ops */ @@ -8286,12 +8268,9 @@ static void handle_2misc_satacc(DisasContext *s, boo= l is_scalar, bool is_u, } write_vec_element(s, tcg_rd, rd, pass, MO_64); } - if (is_scalar) { - clear_vec_high(s, rd); - } - tcg_temp_free_i64(tcg_rd); tcg_temp_free_i64(tcg_rn); + clear_vec_high(s, !is_scalar, rd); } else { TCGv_i32 tcg_rn =3D tcg_temp_new_i32(); TCGv_i32 tcg_rd =3D tcg_temp_new_i32(); @@ -8349,13 +8328,9 @@ static void handle_2misc_satacc(DisasContext *s, boo= l is_scalar, bool is_u, } write_vec_element_i32(s, tcg_rd, rd, pass, MO_32); } - - if (!is_q) { - clear_vec_high(s, rd); - } - tcg_temp_free_i32(tcg_rd); tcg_temp_free_i32(tcg_rn); + clear_vec_high(s, is_q, rd); } } =20 @@ -8855,9 +8830,7 @@ static void handle_vec_simd_shri(DisasContext *s, boo= l is_q, bool is_u, tcg_temp_free_i64(tcg_round); =20 done: - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } =20 static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, unsigned shift) @@ -9045,19 +9018,18 @@ static void handle_vec_simd_shrn(DisasContext *s, b= ool is_q, } =20 if (!is_q) { - clear_vec_high(s, rd); write_vec_element(s, tcg_final, rd, 0, MO_64); } else { write_vec_element(s, tcg_final, rd, 1, MO_64); } - if (round) { tcg_temp_free_i64(tcg_round); } tcg_temp_free_i64(tcg_rn); tcg_temp_free_i64(tcg_rd); tcg_temp_free_i64(tcg_final); - return; + + clear_vec_high(s, is_q, rd); } =20 =20 @@ -9451,9 +9423,7 @@ static void handle_3rd_narrowing(DisasContext *s, int= is_q, int is_u, int size, write_vec_element_i32(s, tcg_res[pass], rd, pass + part, MO_32); tcg_temp_free_i32(tcg_res[pass]); } - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } =20 static void handle_pmull_64(DisasContext *s, int is_q, int rd, int rn, int= rm) @@ -9877,9 +9847,7 @@ static void handle_simd_3same_pair(DisasContext *s, i= nt is_q, int u, int opcode, write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_32); tcg_temp_free_i32(tcg_res[pass]); } - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } =20 if (fpst) { @@ -10372,10 +10340,7 @@ static void disas_simd_3same_int(DisasContext *s, = uint32_t insn) tcg_temp_free_i32(tcg_op2); } } - - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } =20 /* AdvSIMD three same @@ -10611,10 +10576,7 @@ static void disas_simd_three_reg_same_fp16(DisasCo= ntext *s, uint32_t insn) =20 tcg_temp_free_ptr(fpst); =20 - if (!is_q) { - /* non-quad vector op */ - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } =20 /* AdvSIMD three same extra @@ -10846,9 +10808,7 @@ static void handle_rev(DisasContext *s, int opcode,= bool u, write_vec_element(s, tcg_tmp, rd, i, grp_size); tcg_temp_free_i64(tcg_tmp); } - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } else { int revmask =3D (1 << grp_size) - 1; int esize =3D 8 << size; @@ -11499,9 +11459,7 @@ static void disas_simd_two_reg_misc(DisasContext *s= , uint32_t insn) tcg_temp_free_i32(tcg_op); } } - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); =20 if (need_rmode) { gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env); @@ -11778,9 +11736,7 @@ static void disas_simd_two_reg_misc_fp16(DisasConte= xt *s, uint32_t insn) tcg_temp_free_i32(tcg_op); } =20 - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } =20 if (need_rmode) { @@ -12029,12 +11985,8 @@ static void disas_simd_indexed(DisasContext *s, ui= nt32_t insn) tcg_temp_free_i64(tcg_op); tcg_temp_free_i64(tcg_res); } - - if (is_scalar) { - clear_vec_high(s, rd); - } - tcg_temp_free_i64(tcg_idx); + clear_vec_high(s, !is_scalar, rd); } else if (!is_long) { /* 32 bit floating point, or 16 or 32 bit integer. * For the 16 bit scalar case we use the usual Neon helpers and @@ -12198,12 +12150,8 @@ static void disas_simd_indexed(DisasContext *s, ui= nt32_t insn) tcg_temp_free_i32(tcg_op); tcg_temp_free_i32(tcg_res); } - tcg_temp_free_i32(tcg_idx); - - if (!is_q) { - clear_vec_high(s, rd); - } + clear_vec_high(s, is_q, rd); } else { /* long ops: 16x16->32 or 32x32->64 */ TCGv_i64 tcg_res[2]; @@ -12279,10 +12227,7 @@ static void disas_simd_indexed(DisasContext *s, ui= nt32_t insn) tcg_temp_free_i64(tcg_passres); } tcg_temp_free_i64(tcg_idx); - - if (is_scalar) { - clear_vec_high(s, rd); - } + clear_vec_high(s, !is_scalar, rd); } else { TCGv_i32 tcg_idx =3D tcg_temp_new_i32(); =20 --=20 2.14.3