From nobody Mon Feb 9 23:12:09 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; dmarc=fail(p=none dis=none) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1518894584947436.1153906903522; Sat, 17 Feb 2018 11:09:44 -0800 (PST) Received: from localhost ([::1]:48448 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1en7rg-0005O4-1x for importer@patchew.org; Sat, 17 Feb 2018 14:09:40 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:40505) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1en7A2-0001DX-7o for qemu-devel@nongnu.org; Sat, 17 Feb 2018 13:24:35 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1en79z-0001yw-Ad for qemu-devel@nongnu.org; Sat, 17 Feb 2018 13:24:34 -0500 Received: from mail-pl0-x243.google.com ([2607:f8b0:400e:c01::243]:34791) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1en79z-0001yY-32 for qemu-devel@nongnu.org; Sat, 17 Feb 2018 13:24:31 -0500 Received: by mail-pl0-x243.google.com with SMTP id bd10so3450055plb.1 for ; Sat, 17 Feb 2018 10:24:31 -0800 (PST) Received: from cloudburst.twiddle.net ([50.0.192.64]) by smtp.gmail.com with ESMTPSA id h15sm13466712pfi.56.2018.02.17.10.24.28 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Sat, 17 Feb 2018 10:24:29 -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=5Y5i1Z/QDoiE237plg9CGLy21f/g2av1w+1fO98BbyU=; b=D6Xv3L8wcdUuu17M6/nAzjHQfUC82mYwKRU2s1p89C9WCeDQG2erUwT8LxN4sa+Scd zeOmL49xGuJ3El7P0RJ7lK+erpektPOX0NLF9bFnkqk0I1iKkbPVa2DAHdO5pA/AXs50 FrmCvhnQuBwWNXk7GY6/hG2zVlo0rUgFRuHrM= 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=5Y5i1Z/QDoiE237plg9CGLy21f/g2av1w+1fO98BbyU=; b=IowTsfAX4U2IlcqD9+1Ct4vHTOOZCTaPhXJ+xITskFtBpzsb14u+LIf6JDX4X/Iw1B blDcH5H7+fdaUU+VVzJ19p3zi/OwtDCiKN5EeZ2PXSosEuNqvuesD26VjCzLxbHHZ5uZ bpRbL6GGKW4r1izq3dqY5FJ2QI6IgJxtgVl4M6cn+J7u3vbGeeyoT6ZXVCaM9EY3QYII T2YS7IwOIZNMEbdSrPGUKssTp957UH9E8AiNga+y4DNufWBnYsVRW5/JXjGIKiP+5PW1 4YrFZHh9uurx7C7WVmOmLRTbbfDMx8DOoW4IxZqhtaYpsDuO/aV/ATB4hu2xIWLzelwY hMXQ== X-Gm-Message-State: APf1xPBn5M1qKn2Pm/VBLbvRajNhFLLZeNhgOs0txYuz4ckzGk87miIM H5a1AWJvhP7gJ72pMKZ9v7fpC+5DUv4= X-Google-Smtp-Source: AH8x227YF1d8mRWn6k639XQnDH4ktC6rbZ4TI3Oel3JOjqAy+gpvB83phqBMZfKX0l4gyOkeu/6aIQ== X-Received: by 2002:a17:902:6bcb:: with SMTP id m11-v6mr2326167plt.326.1518891869820; Sat, 17 Feb 2018 10:24:29 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Date: Sat, 17 Feb 2018 10:22:56 -0800 Message-Id: <20180217182323.25885-41-richard.henderson@linaro.org> X-Mailer: git-send-email 2.14.3 In-Reply-To: <20180217182323.25885-1-richard.henderson@linaro.org> References: <20180217182323.25885-1-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::243 Subject: [Qemu-devel] [PATCH v2 40/67] target/arm: Implement SVE Integer Compare - Scalars Group 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: 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" Signed-off-by: Richard Henderson --- target/arm/helper-sve.h | 2 + target/arm/sve_helper.c | 31 ++++++++++++++++ target/arm/translate-sve.c | 92 ++++++++++++++++++++++++++++++++++++++++++= ++++ target/arm/sve.decode | 8 ++++ 4 files changed, 133 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index dd4f8f754d..1863106d0f 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -678,3 +678,5 @@ DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr= , ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) =20 DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sve_while, TCG_CALL_NO_RWG, i32, ptr, i32, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index dd884bdd1c..80b78da834 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -2716,3 +2716,34 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32= _t pred_desc) } return sum; } + +uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uintptr_t oprsz =3D extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t esz =3D extract32(pred_desc, SIMD_DATA_SHIFT, 2); + uint64_t esz_mask =3D pred_esz_masks[esz]; + ARMPredicateReg *d =3D vd; + uint32_t flags; + intptr_t i; + + /* Begin with a zero predicate register. */ + flags =3D do_zero(d, oprsz); + if (count =3D=3D 0) { + return flags; + } + + /* Scale from predicate element count to bits. */ + count <<=3D esz; + /* Bound to the bits in the predicate. */ + count =3D MIN(count, oprsz * 8); + + /* Set all of the requested bits. */ + for (i =3D 0; i < count / 64; ++i) { + d->p[i] =3D esz_mask; + } + if (count & 63) { + d->p[i] =3D ~(-1ull << (count & 63)) & esz_mask; + } + + return predtest_ones(d, oprsz, esz_mask); +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index 038800cc86..4b92a55c21 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -2847,6 +2847,98 @@ static void trans_SINCDECP_z(DisasContext *s, arg_in= cdec2_pred *a, do_sat_addsub_vec(s, a->esz, a->rd, a->rn, val, a->u, a->d); } =20 +/* + *** SVE Integer Compare Scalars Group + */ + +static void trans_CTERM(DisasContext *s, arg_CTERM *a, uint32_t insn) +{ + TCGCond cond =3D (a->ne ? TCG_COND_NE : TCG_COND_EQ); + TCGv_i64 rn =3D read_cpu_reg(s, a->rn, a->sf); + TCGv_i64 rm =3D read_cpu_reg(s, a->rm, a->sf); + TCGv_i64 cmp =3D tcg_temp_new_i64(); + + tcg_gen_setcond_i64(cond, cmp, rn, rm); + tcg_gen_extrl_i64_i32(cpu_NF, cmp); + tcg_temp_free_i64(cmp); + + /* VF =3D !NF & !CF. */ + tcg_gen_xori_i32(cpu_VF, cpu_NF, 1); + tcg_gen_andc_i32(cpu_VF, cpu_VF, cpu_CF); + + /* Both NF and VF actually look at bit 31. */ + tcg_gen_neg_i32(cpu_NF, cpu_NF); + tcg_gen_neg_i32(cpu_VF, cpu_VF); +} + +static void trans_WHILE(DisasContext *s, arg_WHILE *a, uint32_t insn) +{ + TCGv_i64 op0 =3D read_cpu_reg(s, a->rn, 1); + TCGv_i64 op1 =3D read_cpu_reg(s, a->rm, 1); + TCGv_i64 t0 =3D tcg_temp_new_i64(); + TCGv_i64 t1 =3D tcg_temp_new_i64(); + TCGv_i32 t2, t3; + TCGv_ptr ptr; + unsigned desc, vsz =3D vec_full_reg_size(s); + TCGCond cond; + + if (!a->sf) { + if (a->u) { + tcg_gen_ext32u_i64(op0, op0); + tcg_gen_ext32u_i64(op1, op1); + } else { + tcg_gen_ext32s_i64(op0, op0); + tcg_gen_ext32s_i64(op1, op1); + } + } + + /* For the helper, compress the different conditions into a computation + * of how many iterations for which the condition is true. + * + * This is slightly complicated by 0 <=3D UINT64_MAX, which is nominal= ly + * 2**64 iterations, overflowing to 0. Of course, predicate registers + * aren't that large, so any value >=3D predicate size is sufficient. + */ + tcg_gen_sub_i64(t0, op1, op0); + + /* t0 =3D MIN(op1 - op0, vsz). */ + if (a->eq) { + /* Equality means one more iteration. */ + tcg_gen_movi_i64(t1, vsz - 1); + tcg_gen_movcond_i64(TCG_COND_LTU, t0, t0, t1, t0, t1); + tcg_gen_addi_i64(t0, t0, 1); + } else { + tcg_gen_movi_i64(t1, vsz); + tcg_gen_movcond_i64(TCG_COND_LTU, t0, t0, t1, t0, t1); + } + + /* t0 =3D (condition true ? t0 : 0). */ + cond =3D (a->u + ? (a->eq ? TCG_COND_LEU : TCG_COND_LTU) + : (a->eq ? TCG_COND_LE : TCG_COND_LT)); + tcg_gen_movi_i64(t1, 0); + tcg_gen_movcond_i64(cond, t0, op0, op1, t0, t1); + + t2 =3D tcg_temp_new_i32(); + tcg_gen_extrl_i64_i32(t2, t0); + tcg_temp_free_i64(t0); + tcg_temp_free_i64(t1); + + desc =3D (vsz / 8) - 2; + desc =3D deposit32(desc, SIMD_DATA_SHIFT, 2, a->esz); + t3 =3D tcg_const_i32(desc); + + ptr =3D tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ptr, cpu_env, pred_full_reg_offset(s, a->rd)); + + gen_helper_sve_while(t2, ptr, t2, t3); + do_pred_flags(t2); + + tcg_temp_free_ptr(ptr); + tcg_temp_free_i32(t2); + tcg_temp_free_i32(t3); +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index 76c084d43e..b5bc7e9546 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -614,6 +614,14 @@ SINCDECP_r_64 00100101 .. 1010 d:1 u:1 10001 10 .... .= .... @incdec_pred # SVE saturating inc/dec vector by predicate count SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred =20 +### SVE Integer Compare - Scalars Group + +# SVE conditionally terminate scalars +CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 + +# SVE integer compare scalar count and limit +WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 + ### SVE Memory - 32-bit Gather and Unsized Contiguous Group =20 # SVE load predicate register --=20 2.14.3