From 1f4dd04c2312a6673895575535f872cdb6708817 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 28 May 2024 13:30:19 -0700 Subject: [PATCH] target/arm: Convert SUQADD, USQADD to decodetree These are faux 2-operand instructions, reading from rd. Sort them next to the other three-operand same insns for clarity. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240528203044.612851-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 8 +++++ target/arm/tcg/translate-a64.c | 64 ++++------------------------------ 2 files changed, 14 insertions(+), 58 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 19010af03b..7c350ba833 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -45,6 +45,7 @@ @rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd @rrr_hsd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_hsd @rrr_e ........ esz:2 . rm:5 ...... rn:5 rd:5 &rrr_e +@r2r_e ........ esz:2 . ..... ...... rm:5 rd:5 &rrr_e rn=%rd @rrx_h ........ .. .. rm:4 .... . . rn:5 rd:5 &rrx_e esz=1 idx=%hlm @rrx_s ........ .. . rm:5 .... . . rn:5 rd:5 &rrx_e esz=2 idx=%hl @@ -60,6 +61,7 @@ @qrrr_h . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=1 @qrrr_sd . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=%esz_sd @qrrr_e . q:1 ...... esz:2 . rm:5 ...... rn:5 rd:5 &qrrr_e +@qr2r_e . q:1 ...... esz:2 . ..... ...... rm:5 rd:5 &qrrr_e rn=%rd @qrrx_h . q:1 .. .... .. .. rm:4 .... . . rn:5 rd:5 \ &qrrx_e esz=1 idx=%hlm @@ -750,6 +752,9 @@ UQADD_s 0111 1110 ..1 ..... 00001 1 ..... ..... @rrr_e SQSUB_s 0101 1110 ..1 ..... 00101 1 ..... ..... @rrr_e UQSUB_s 0111 1110 ..1 ..... 00101 1 ..... ..... @rrr_e +SUQADD_s 0101 1110 ..1 00000 00111 0 ..... ..... @r2r_e +USQADD_s 0111 1110 ..1 00000 00111 0 ..... ..... @r2r_e + ### Advanced SIMD scalar pairwise FADDP_s 0101 1110 0011 0000 1101 10 ..... ..... @rr_h @@ -868,6 +873,9 @@ UQADD_v 0.10 1110 ..1 ..... 00001 1 ..... ..... @qrrr_e SQSUB_v 0.00 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e UQSUB_v 0.10 1110 ..1 ..... 00101 1 ..... ..... @qrrr_e +SUQADD_v 0.00 1110 ..1 00000 00111 0 ..... ..... @qr2r_e +USQADD_v 0.10 1110 ..1 00000 00111 0 ..... ..... @qr2r_e + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 3956c41543..c0637bda0f 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5096,6 +5096,8 @@ TRANS(SQADD_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqadd_bhs, gen_sqadd_d) TRANS(SQSUB_s, do_satacc_s, a, MO_SIGN, MO_SIGN, gen_sqsub_bhs, gen_sqsub_d) TRANS(UQADD_s, do_satacc_s, a, 0, 0, gen_uqadd_bhs, gen_uqadd_d) TRANS(UQSUB_s, do_satacc_s, a, 0, 0, gen_uqsub_bhs, gen_uqsub_d) +TRANS(SUQADD_s, do_satacc_s, a, MO_SIGN, 0, gen_suqadd_bhs, gen_suqadd_d) +TRANS(USQADD_s, do_satacc_s, a, 0, MO_SIGN, gen_usqadd_bhs, gen_usqadd_d) static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, gen_helper_gvec_3_ptr * const fns[3]) @@ -5339,6 +5341,8 @@ TRANS(SQADD_v, do_gvec_fn3, a, gen_gvec_sqadd_qc) TRANS(UQADD_v, do_gvec_fn3, a, gen_gvec_uqadd_qc) TRANS(SQSUB_v, do_gvec_fn3, a, gen_gvec_sqsub_qc) TRANS(UQSUB_v, do_gvec_fn3, a, gen_gvec_uqsub_qc) +TRANS(SUQADD_v, do_gvec_fn3, a, gen_gvec_suqadd_qc) +TRANS(USQADD_v, do_gvec_fn3, a, gen_gvec_usqadd_qc) /* * Advanced SIMD scalar/vector x indexed element @@ -10009,48 +10013,6 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, clear_vec_high(s, is_q, rd); } -/* Remaining saturating accumulating ops */ -static void handle_2misc_satacc(DisasContext *s, bool is_scalar, bool is_u, - bool is_q, unsigned size, int rn, int rd) -{ - TCGv_i64 res, qc, a, b; - - if (!is_scalar) { - gen_gvec_fn3(s, is_q, rd, rd, rn, - is_u ? gen_gvec_usqadd_qc : gen_gvec_suqadd_qc, size); - return; - } - - res = tcg_temp_new_i64(); - qc = tcg_temp_new_i64(); - a = tcg_temp_new_i64(); - b = tcg_temp_new_i64(); - - /* Read and extend scalar inputs to 64-bits. */ - read_vec_element(s, a, rd, 0, size | (is_u ? 0 : MO_SIGN)); - read_vec_element(s, b, rn, 0, size | (is_u ? MO_SIGN : 0)); - tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); - - if (size == MO_64) { - if (is_u) { - gen_usqadd_d(res, qc, a, b); - } else { - gen_suqadd_d(res, qc, a, b); - } - } else { - if (is_u) { - gen_usqadd_bhs(res, qc, a, b, size); - } else { - gen_suqadd_bhs(res, qc, a, b, size); - /* Truncate signed 64-bit result for writeback. */ - tcg_gen_ext_i64(res, res, size); - } - } - - write_fp_dreg(s, rd, res); - tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc)); -} - /* AdvSIMD scalar two reg misc * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----+---+-----------+------+-----------+--------+-----+------+------+ @@ -10070,12 +10032,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) TCGv_ptr tcg_fpstatus; switch (opcode) { - case 0x3: /* USQADD / SUQADD*/ - if (!fp_access_check(s)) { - return; - } - handle_2misc_satacc(s, true, u, false, size, rn, rd); - return; case 0x7: /* SQABS / SQNEG */ break; case 0xa: /* CMLT */ @@ -10175,6 +10131,7 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) } break; default: + case 0x3: /* USQADD / SUQADD */ unallocated_encoding(s); return; } @@ -11662,16 +11619,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) return; } break; - case 0x3: /* SUQADD, USQADD */ - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_2misc_satacc(s, false, u, is_q, size, rn, rd); - return; case 0x7: /* SQABS, SQNEG */ if (size == 3 && !is_q) { unallocated_encoding(s); @@ -11846,6 +11793,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) break; } default: + case 0x3: /* SUQADD, USQADD */ unallocated_encoding(s); return; }