From 3e96b205286dfb8bbf363229709e4f8648fce379 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 16 Jun 2020 18:08:38 +0100 Subject: [PATCH] target/arm: Convert simple fp Neon 2-reg-misc insns Convert the Neon 2-reg-misc insns which are implemented with simple calls to functions that take the input, output and fpstatus pointer. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20200616170844.13318-16-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 8 ++++++ target/arm/translate-neon.inc.c | 62 +++++++++++++++++++++++++++++++++++++++++ target/arm/translate.c | 56 +++++-------------------------------- target/arm/translate.h | 1 + 4 files changed, 78 insertions(+), 49 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index f0bb34a49e..ea8d5fd99c 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -497,11 +497,19 @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm SHA1SU1 1111 001 11 . 11 .. 10 .... 0 0111 0 . 0 .... @2misc_q1 SHA256SU0 1111 001 11 . 11 .. 10 .... 0 0111 1 . 0 .... @2misc_q1 + VRINTX 1111 001 11 . 11 .. 10 .... 0 1001 . . 0 .... @2misc + VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0 VCVT_F32_F16 1111 001 11 . 11 .. 10 .... 0 1110 0 . 0 .... @2misc_q0 VRECPE 1111 001 11 . 11 .. 11 .... 0 1000 . . 0 .... @2misc VRSQRTE 1111 001 11 . 11 .. 11 .... 0 1001 . . 0 .... @2misc + VRECPE_F 1111 001 11 . 11 .. 11 .... 0 1010 . . 0 .... @2misc + VRSQRTE_F 1111 001 11 . 11 .. 11 .... 0 1011 . . 0 .... @2misc + VCVT_FS 1111 001 11 . 11 .. 11 .... 0 1100 . . 0 .... @2misc + VCVT_FU 1111 001 11 . 11 .. 11 .... 0 1101 . . 0 .... @2misc + VCVT_SF 1111 001 11 . 11 .. 11 .... 0 1110 . . 0 .... @2misc + VCVT_UF 1111 001 11 . 11 .. 11 .... 0 1111 . . 0 .... @2misc ] # Subgroup for size != 0b11 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index 2b5dc86f62..ab183e47d7 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -3706,3 +3706,65 @@ static bool trans_VQNEG(DisasContext *s, arg_2misc *a) }; return do_2misc(s, a, fn[a->size]); } + +static bool do_2misc_fp(DisasContext *s, arg_2misc *a, + NeonGenOneSingleOpFn *fn) +{ + int pass; + TCGv_ptr fpst; + + /* Handle a 2-reg-misc operation by iterating 32 bits at a time */ + 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->size != 2) { + /* TODO: FP16 will be the size == 1 case */ + return false; + } + + if ((a->vd | a->vm) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = get_fpstatus_ptr(1); + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 tmp = neon_load_reg(a->vm, pass); + fn(tmp, tmp, fpst); + neon_store_reg(a->vd, pass, tmp); + } + tcg_temp_free_ptr(fpst); + + return true; +} + +#define DO_2MISC_FP(INSN, FUNC) \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + return do_2misc_fp(s, a, FUNC); \ + } + +DO_2MISC_FP(VRECPE_F, gen_helper_recpe_f32) +DO_2MISC_FP(VRSQRTE_F, gen_helper_rsqrte_f32) +DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos) +DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos) +DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs) +DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs) + +static bool trans_VRINTX(DisasContext *s, arg_2misc *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + return do_2misc_fp(s, a, gen_helper_rints_exact); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index 3cbd2ab0c9..48377860c7 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -4947,6 +4947,13 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_2RM_VRSQRTE: case NEON_2RM_VQABS: case NEON_2RM_VQNEG: + case NEON_2RM_VRECPE_F: + case NEON_2RM_VRSQRTE_F: + case NEON_2RM_VCVT_FS: + case NEON_2RM_VCVT_FU: + case NEON_2RM_VCVT_SF: + case NEON_2RM_VCVT_UF: + case NEON_2RM_VRINTX: /* handled by decodetree */ return 1; case NEON_2RM_VTRN: @@ -5052,13 +5059,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tcg_rmode); break; } - case NEON_2RM_VRINTX: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_rints_exact(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } case NEON_2RM_VCVTAU: case NEON_2RM_VCVTAS: case NEON_2RM_VCVTNU: @@ -5093,48 +5093,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(fpst); break; } - case NEON_2RM_VRECPE_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_recpe_f32(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VRSQRTE_F: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_rsqrte_f32(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVT_FS: /* VCVT.F32.S32 */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_sitos(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVT_FU: /* VCVT.F32.U32 */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_uitos(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVT_SF: /* VCVT.S32.F32 */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_tosizs(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_2RM_VCVT_UF: /* VCVT.U32.F32 */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_touizs(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } default: /* Reserved op values were caught by the * neon_2rm_sizes[] check earlier. diff --git a/target/arm/translate.h b/target/arm/translate.h index 4dbeee4c89..19650a9e2d 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -373,6 +373,7 @@ typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64); typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32); typedef void NeonGenTwoOpWidenFn(TCGv_i64, TCGv_i32, TCGv_i32); +typedef void NeonGenOneSingleOpFn(TCGv_i32, TCGv_i32, TCGv_ptr); typedef void NeonGenTwoSingleOpFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); typedef void NeonGenTwoDoubleOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); typedef void NeonGenOne64OpFn(TCGv_i64, TCGv_i64); -- 2.11.0