From nobody Mon Feb 9 21:12:10 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; 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 1518175757381877.9516172646028; Fri, 9 Feb 2018 03:29:17 -0800 (PST) Received: from localhost ([::1]:36037 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ek6rk-0006ee-Bp for importer@patchew.org; Fri, 09 Feb 2018 06:29:16 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:39876) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ek6St-000146-Ci for qemu-devel@nongnu.org; Fri, 09 Feb 2018 06:03:40 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ek6Sr-00020Z-Sd for qemu-devel@nongnu.org; Fri, 09 Feb 2018 06:03:35 -0500 Received: from orth.archaic.org.uk ([2001:8b0:1d0::2]:46262) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1ek6Sr-0001zI-HK for qemu-devel@nongnu.org; Fri, 09 Feb 2018 06:03:33 -0500 Received: from pm215 by orth.archaic.org.uk with local (Exim 4.89) (envelope-from ) id 1ek6Sq-0002dP-6t for qemu-devel@nongnu.org; Fri, 09 Feb 2018 11:03:32 +0000 From: Peter Maydell To: qemu-devel@nongnu.org Date: Fri, 9 Feb 2018 11:03:07 +0000 Message-Id: <20180209110314.11766-24-peter.maydell@linaro.org> X-Mailer: git-send-email 2.16.1 In-Reply-To: <20180209110314.11766-1-peter.maydell@linaro.org> References: <20180209110314.11766-1-peter.maydell@linaro.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2001:8b0:1d0::2 Subject: [Qemu-devel] [PULL 23/30] target/arm: Expand vector registers for SVE 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: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 From: Richard Henderson Change vfp.regs as a uint64_t to vfp.zregs as an ARMVectorReg. The previous patches have made the change in representation relatively painless. Reviewed-by: Alex Benn=C3=A9e Signed-off-by: Richard Henderson Reviewed-by: Peter Maydell Message-id: 20180123035349.24538-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/cpu.h | 59 +++++++++++++++++++++++++++++++-----------= ---- target/arm/machine.c | 35 ++++++++++++++++++++++++++- target/arm/translate-a64.c | 8 +++---- target/arm/translate.c | 7 +++--- 4 files changed, 81 insertions(+), 28 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 57be0b000b..0e3cd52aa3 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -153,6 +153,42 @@ typedef struct { uint32_t base_mask; } TCR; =20 +/* Define a maximum sized vector register. + * For 32-bit, this is a 128-bit NEON/AdvSIMD register. + * For 64-bit, this is a 2048-bit SVE register. + * + * Note that the mapping between S, D, and Q views of the register bank + * differs between AArch64 and AArch32. + * In AArch32: + * Qn =3D regs[n].d[1]:regs[n].d[0] + * Dn =3D regs[n / 2].d[n & 1] + * Sn =3D regs[n / 4].d[n % 4 / 2], + * bits 31..0 for even n, and bits 63..32 for odd n + * (and regs[16] to regs[31] are inaccessible) + * In AArch64: + * Zn =3D regs[n].d[*] + * Qn =3D regs[n].d[1]:regs[n].d[0] + * Dn =3D regs[n].d[0] + * Sn =3D regs[n].d[0] bits 31..0 + * + * This corresponds to the architecturally defined mapping between + * the two execution states, and means we do not need to explicitly + * map these registers when changing states. + * + * Align the data for use with TCG host vector operations. + */ + +#ifdef TARGET_AARCH64 +# define ARM_MAX_VQ 16 +#else +# define ARM_MAX_VQ 1 +#endif + +typedef struct ARMVectorReg { + uint64_t d[2 * ARM_MAX_VQ] QEMU_ALIGNED(16); +} ARMVectorReg; + + typedef struct CPUARMState { /* Regs for current mode. */ uint32_t regs[16]; @@ -477,22 +513,7 @@ typedef struct CPUARMState { =20 /* VFP coprocessor state. */ struct { - /* VFP/Neon register state. Note that the mapping between S, D and= Q - * views of the register bank differs between AArch64 and AArch32: - * In AArch32: - * Qn =3D regs[2n+1]:regs[2n] - * Dn =3D regs[n] - * Sn =3D regs[n/2] bits 31..0 for even n, and bits 63..32 for od= d n - * (and regs[32] to regs[63] are inaccessible) - * In AArch64: - * Qn =3D regs[2n+1]:regs[2n] - * Dn =3D regs[2n] - * Sn =3D regs[2n] bits 31..0 - * This corresponds to the architecturally defined mapping between - * the two execution states, and means we do not need to explicitly - * map these registers when changing states. - */ - uint64_t regs[64] QEMU_ALIGNED(16); + ARMVectorReg zregs[32]; =20 uint32_t xregs[16]; /* We store these fpcsr fields separately for convenience. */ @@ -2799,7 +2820,7 @@ static inline void *arm_get_el_change_hook_opaque(ARM= CPU *cpu) */ static inline uint64_t *aa32_vfp_dreg(CPUARMState *env, unsigned regno) { - return &env->vfp.regs[regno]; + return &env->vfp.zregs[regno >> 1].d[regno & 1]; } =20 /** @@ -2808,7 +2829,7 @@ static inline uint64_t *aa32_vfp_dreg(CPUARMState *en= v, unsigned regno) */ static inline uint64_t *aa32_vfp_qreg(CPUARMState *env, unsigned regno) { - return &env->vfp.regs[2 * regno]; + return &env->vfp.zregs[regno].d[0]; } =20 /** @@ -2817,7 +2838,7 @@ static inline uint64_t *aa32_vfp_qreg(CPUARMState *en= v, unsigned regno) */ static inline uint64_t *aa64_vfp_qreg(CPUARMState *env, unsigned regno) { - return &env->vfp.regs[2 * regno]; + return &env->vfp.zregs[regno].d[0]; } =20 #endif diff --git a/target/arm/machine.c b/target/arm/machine.c index a85c2430d3..cb0e1c92bb 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -50,7 +50,40 @@ static const VMStateDescription vmstate_vfp =3D { .minimum_version_id =3D 3, .needed =3D vfp_needed, .fields =3D (VMStateField[]) { - VMSTATE_UINT64_ARRAY(env.vfp.regs, ARMCPU, 64), + /* For compatibility, store Qn out of Zn here. */ + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[0].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[1].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[2].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[3].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[4].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[5].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[6].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[7].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[8].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[9].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[10].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[11].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[12].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[13].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[14].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[15].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[16].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[17].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[18].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[19].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[20].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[21].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[22].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[23].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[24].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[25].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[26].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[27].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[28].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[29].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[30].d, ARMCPU, 0, 2), + VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[31].d, ARMCPU, 0, 2), + /* The xregs array is a little awkward because element 1 (FPSCR) * requires a specific accessor, so we have to split it up in * the vmstate: diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 62ece804e2..352a79bad1 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -525,8 +525,8 @@ static inline int vec_reg_offset(DisasContext *s, int r= egno, { int offs =3D 0; #ifdef HOST_WORDS_BIGENDIAN - /* This is complicated slightly because vfp.regs[2n] is - * still the low half and vfp.regs[2n+1] the high half + /* This is complicated slightly because vfp.zregs[n].d[0] is + * still the low half and vfp.zregs[n].d[1] the high half * of the 128 bit vector, even on big endian systems. * Calculate the offset assuming a fully bigendian 128 bits, * then XOR to account for the order of the two 64 bit halves. @@ -536,7 +536,7 @@ static inline int vec_reg_offset(DisasContext *s, int r= egno, #else offs +=3D element * (1 << size); #endif - offs +=3D offsetof(CPUARMState, vfp.regs[regno * 2]); + offs +=3D offsetof(CPUARMState, vfp.zregs[regno]); assert_fp_access_checked(s); return offs; } @@ -545,7 +545,7 @@ static inline int vec_reg_offset(DisasContext *s, int r= egno, static inline int vec_full_reg_offset(DisasContext *s, int regno) { assert_fp_access_checked(s); - return offsetof(CPUARMState, vfp.regs[regno * 2]); + return offsetof(CPUARMState, vfp.zregs[regno]); } =20 /* Return a newly allocated pointer to the vector register. */ diff --git a/target/arm/translate.c b/target/arm/translate.c index 55826b7e5a..a8c13d3758 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -1512,13 +1512,12 @@ static inline void gen_vfp_st(DisasContext *s, int = dp, TCGv_i32 addr) } } =20 -static inline long -vfp_reg_offset (int dp, int reg) +static inline long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { - return offsetof(CPUARMState, vfp.regs[reg]); + return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); } else { - long ofs =3D offsetof(CPUARMState, vfp.regs[reg >> 1]); + long ofs =3D offsetof(CPUARMState, vfp.zregs[reg >> 2].d[(reg >> 1= ) & 1]); if (reg & 1) { ofs +=3D offsetof(CPU_DoubleU, l.upper); } else { --=20 2.16.1