From 567663a2af2457da8aa74f221b1f3f8a6d2eddf6 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 16 Jun 2020 18:08:26 +0100 Subject: [PATCH] target/arm: Convert VZIP, VUZP to decodetree Convert the Neon VZIP and VUZP insns in the 2-reg-misc group to decodetree. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20200616170844.13318-4-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 3 ++ target/arm/translate-neon.inc.c | 74 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 92 +---------------------------------------- 3 files changed, 79 insertions(+), 90 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index dd521baa07..ad9e17fd73 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -447,6 +447,9 @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc VPADAL_U 1111 001 11 . 11 .. 00 .... 0 1101 . . 0 .... @2misc + + VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc + VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc ] # Subgroup for size != 0b11 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index 2f7bd0d556..f4799dd977 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -3169,3 +3169,77 @@ static bool trans_VPADAL_U(DisasContext *s, arg_2misc *a) return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], accfn[a->size]); } + +typedef void ZipFn(TCGv_ptr, TCGv_ptr); + +static bool do_zip_uzp(DisasContext *s, arg_2misc *a, + ZipFn *fn) +{ + TCGv_ptr pd, pm; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vm) & 0x10)) { + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!fn) { + /* Bad size or size/q combination */ + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + pd = vfp_reg_ptr(true, a->vd); + pm = vfp_reg_ptr(true, a->vm); + fn(pd, pm); + tcg_temp_free_ptr(pd); + tcg_temp_free_ptr(pm); + return true; +} + +static bool trans_VUZP(DisasContext *s, arg_2misc *a) +{ + static ZipFn * const fn[2][4] = { + { + gen_helper_neon_unzip8, + gen_helper_neon_unzip16, + NULL, + NULL, + }, { + gen_helper_neon_qunzip8, + gen_helper_neon_qunzip16, + gen_helper_neon_qunzip32, + NULL, + } + }; + return do_zip_uzp(s, a, fn[a->q][a->size]); +} + +static bool trans_VZIP(DisasContext *s, arg_2misc *a) +{ + static ZipFn * const fn[2][4] = { + { + gen_helper_neon_zip8, + gen_helper_neon_zip16, + NULL, + NULL, + }, { + gen_helper_neon_qzip8, + gen_helper_neon_qzip16, + gen_helper_neon_qzip32, + NULL, + } + }; + return do_zip_uzp(s, a, fn[a->q][a->size]); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index 4405b034f7..442f287d86 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -2934,86 +2934,6 @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc) gen_rfe(s, pc, load_cpu_field(spsr)); } -static int gen_neon_unzip(int rd, int rm, int size, int q) -{ - TCGv_ptr pd, pm; - - if (!q && size == 2) { - return 1; - } - pd = vfp_reg_ptr(true, rd); - pm = vfp_reg_ptr(true, rm); - if (q) { - switch (size) { - case 0: - gen_helper_neon_qunzip8(pd, pm); - break; - case 1: - gen_helper_neon_qunzip16(pd, pm); - break; - case 2: - gen_helper_neon_qunzip32(pd, pm); - break; - default: - abort(); - } - } else { - switch (size) { - case 0: - gen_helper_neon_unzip8(pd, pm); - break; - case 1: - gen_helper_neon_unzip16(pd, pm); - break; - default: - abort(); - } - } - tcg_temp_free_ptr(pd); - tcg_temp_free_ptr(pm); - return 0; -} - -static int gen_neon_zip(int rd, int rm, int size, int q) -{ - TCGv_ptr pd, pm; - - if (!q && size == 2) { - return 1; - } - pd = vfp_reg_ptr(true, rd); - pm = vfp_reg_ptr(true, rm); - if (q) { - switch (size) { - case 0: - gen_helper_neon_qzip8(pd, pm); - break; - case 1: - gen_helper_neon_qzip16(pd, pm); - break; - case 2: - gen_helper_neon_qzip32(pd, pm); - break; - default: - abort(); - } - } else { - switch (size) { - case 0: - gen_helper_neon_zip8(pd, pm); - break; - case 1: - gen_helper_neon_zip16(pd, pm); - break; - default: - abort(); - } - } - tcg_temp_free_ptr(pd); - tcg_temp_free_ptr(pm); - return 0; -} - static void gen_neon_trn_u8(TCGv_i32 t0, TCGv_i32 t1) { TCGv_i32 rd, tmp; @@ -5082,6 +5002,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_2RM_VREV64: case NEON_2RM_VPADDL: case NEON_2RM_VPADDL_U: case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U: + case NEON_2RM_VUZP: + case NEON_2RM_VZIP: /* handled by decodetree */ return 1; case NEON_2RM_VTRN: @@ -5097,16 +5019,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) goto elementwise; } break; - case NEON_2RM_VUZP: - if (gen_neon_unzip(rd, rm, size, q)) { - return 1; - } - break; - case NEON_2RM_VZIP: - if (gen_neon_zip(rd, rm, size, q)) { - return 1; - } - break; case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN: /* also VQMOVUN; op field and mnemonics don't line up */ if (rm & 1) { -- 2.11.0