target/arm: Convert FCVT* (vector, integer) to decodetree

Remove handle_2misc_64 as these were the last insns decoded
by that function.  Remove helper_advsimd_f16to[su]inth as unused;
we now always go through helper_vfp_to[su]hh or a specialized
vector function instead.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20241211163036.2297116-65-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

target/arm/helper.h

@@ -665,6 +665,8 @@ DEF_HELPER_FLAGS_4(gvec_vcvt_ud, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vcvt_rz_ds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vcvt_rz_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ud, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)

target/arm/tcg/a64.decode

@@ -1793,6 +1793,31 @@ SCVTF_vi        0.00 1110 0.1 00001 11011 0 ..... .....     @qrr_sd
 UCVTF_vi        0.10 1110 011 11001 11011 0 ..... .....     @qrr_h
 UCVTF_vi        0.10 1110 0.1 00001 11011 0 ..... .....     @qrr_sd
 
+FCVTNS_vi       0.00 1110 011 11001 10101 0 ..... .....     @qrr_h
+FCVTNS_vi       0.00 1110 0.1 00001 10101 0 ..... .....     @qrr_sd
+FCVTNU_vi       0.10 1110 011 11001 10101 0 ..... .....     @qrr_h
+FCVTNU_vi       0.10 1110 0.1 00001 10101 0 ..... .....     @qrr_sd
+
+FCVTPS_vi       0.00 1110 111 11001 10101 0 ..... .....     @qrr_h
+FCVTPS_vi       0.00 1110 1.1 00001 10101 0 ..... .....     @qrr_sd
+FCVTPU_vi       0.10 1110 111 11001 10101 0 ..... .....     @qrr_h
+FCVTPU_vi       0.10 1110 1.1 00001 10101 0 ..... .....     @qrr_sd
+
+FCVTMS_vi       0.00 1110 011 11001 10111 0 ..... .....     @qrr_h
+FCVTMS_vi       0.00 1110 0.1 00001 10111 0 ..... .....     @qrr_sd
+FCVTMU_vi       0.10 1110 011 11001 10111 0 ..... .....     @qrr_h
+FCVTMU_vi       0.10 1110 0.1 00001 10111 0 ..... .....     @qrr_sd
+
+FCVTZS_vi       0.00 1110 111 11001 10111 0 ..... .....     @qrr_h
+FCVTZS_vi       0.00 1110 1.1 00001 10111 0 ..... .....     @qrr_sd
+FCVTZU_vi       0.10 1110 111 11001 10111 0 ..... .....     @qrr_h
+FCVTZU_vi       0.10 1110 1.1 00001 10111 0 ..... .....     @qrr_sd
+
+FCVTAS_vi       0.00 1110 011 11001 11001 0 ..... .....     @qrr_h
+FCVTAS_vi       0.00 1110 0.1 00001 11001 0 ..... .....     @qrr_sd
+FCVTAU_vi       0.10 1110 011 11001 11001 0 ..... .....     @qrr_h
+FCVTAU_vi       0.10 1110 0.1 00001 11001 0 ..... .....     @qrr_sd
+
 &fcvt_q         rd rn esz q shift
 @fcvtq_h        . q:1 . ...... 001 .... ...... rn:5 rd:5    \
                 &fcvt_q esz=1 shift=%fcvt_f_sh_h

target/arm/tcg/helper-a64.c

@@ -618,38 +618,6 @@ uint32_t HELPER(advsimd_rinth)(uint32_t x, void *fp_status)
     return ret;
 }
 
-/*
- * Half-precision floating point conversion functions
- *
- * There are a multitude of conversion functions with various
- * different rounding modes. This is dealt with by the calling code
- * setting the mode appropriately before calling the helper.
- */
-
-uint32_t HELPER(advsimd_f16tosinth)(uint32_t a, void *fpstp)
-{
-    float_status *fpst = fpstp;
-
-    /* Invalid if we are passed a NaN */
-    if (float16_is_any_nan(a)) {
-        float_raise(float_flag_invalid, fpst);
-        return 0;
-    }
-    return float16_to_int16(a, fpst);
-}
-
-uint32_t HELPER(advsimd_f16touinth)(uint32_t a, void *fpstp)
-{
-    float_status *fpst = fpstp;
-
-    /* Invalid if we are passed a NaN */
-    if (float16_is_any_nan(a)) {
-        float_raise(float_flag_invalid, fpst);
-        return 0;
-    }
-    return float16_to_uint16(a, fpst);
-}
-
 static int el_from_spsr(uint32_t spsr)
 {
     /* Return the exception level that this SPSR is requesting a return to,

target/arm/tcg/helper-a64.h

@@ -74,8 +74,6 @@ DEF_HELPER_3(advsimd_mulx2h, i32, i32, i32, ptr)
 DEF_HELPER_4(advsimd_muladd2h, i32, i32, i32, i32, ptr)
 DEF_HELPER_2(advsimd_rinth_exact, f16, f16, ptr)
 DEF_HELPER_2(advsimd_rinth, f16, f16, ptr)
-DEF_HELPER_2(advsimd_f16tosinth, i32, f16, ptr)
-DEF_HELPER_2(advsimd_f16touinth, i32, f16, ptr)
 
 DEF_HELPER_2(exception_return, void, env, i64)
 DEF_HELPER_FLAGS_2(dc_zva, TCG_CALL_NO_WG, void, env, i64)

target/arm/tcg/translate-a64.c

@@ -9348,56 +9348,38 @@ static gen_helper_gvec_2_ptr * const f_fcvtzu_vf[] = {
 TRANS(FCVTZU_vf, do_gvec_op2_fpst,
       a->esz, a->q, a->rd, a->rn, a->shift, f_fcvtzu_vf)
 
-static void handle_2misc_64(DisasContext *s, int opcode, bool u,
+static gen_helper_gvec_2_ptr * const f_fcvt_s_vi[] = {
-                            TCGv_i64 tcg_rd, TCGv_i64 tcg_rn,
+    gen_helper_gvec_vcvt_rm_sh,
-                            TCGv_i32 tcg_rmode, TCGv_ptr tcg_fpstatus)
+    gen_helper_gvec_vcvt_rm_ss,
-{
+    gen_helper_gvec_vcvt_rm_sd,
-    /* Handle 64->64 opcodes which are shared between the scalar and
+};
-     * vector 2-reg-misc groups. We cover every integer opcode where size == 3
+
-     * is valid in either group and also the double-precision fp ops.
+static gen_helper_gvec_2_ptr * const f_fcvt_u_vi[] = {
-     * The caller only need provide tcg_rmode and tcg_fpstatus if the op
+    gen_helper_gvec_vcvt_rm_uh,
-     * requires them.
+    gen_helper_gvec_vcvt_rm_us,
-     */
+    gen_helper_gvec_vcvt_rm_ud,
-    switch (opcode) {
+};
-    case 0x1a: /* FCVTNS */
+
-    case 0x1b: /* FCVTMS */
+TRANS(FCVTNS_vi, do_gvec_op2_fpst,
-    case 0x1c: /* FCVTAS */
+      a->esz, a->q, a->rd, a->rn, float_round_nearest_even, f_fcvt_s_vi)
-    case 0x3a: /* FCVTPS */
+TRANS(FCVTNU_vi, do_gvec_op2_fpst,
-    case 0x3b: /* FCVTZS */
+      a->esz, a->q, a->rd, a->rn, float_round_nearest_even, f_fcvt_u_vi)
-        gen_helper_vfp_tosqd(tcg_rd, tcg_rn, tcg_constant_i32(0), tcg_fpstatus);
+TRANS(FCVTPS_vi, do_gvec_op2_fpst,
-        break;
+      a->esz, a->q, a->rd, a->rn, float_round_up, f_fcvt_s_vi)
-    case 0x5a: /* FCVTNU */
+TRANS(FCVTPU_vi, do_gvec_op2_fpst,
-    case 0x5b: /* FCVTMU */
+      a->esz, a->q, a->rd, a->rn, float_round_up, f_fcvt_u_vi)
-    case 0x5c: /* FCVTAU */
+TRANS(FCVTMS_vi, do_gvec_op2_fpst,
-    case 0x7a: /* FCVTPU */
+      a->esz, a->q, a->rd, a->rn, float_round_down, f_fcvt_s_vi)
-    case 0x7b: /* FCVTZU */
+TRANS(FCVTMU_vi, do_gvec_op2_fpst,
-        gen_helper_vfp_touqd(tcg_rd, tcg_rn, tcg_constant_i32(0), tcg_fpstatus);
+      a->esz, a->q, a->rd, a->rn, float_round_down, f_fcvt_u_vi)
-        break;
+TRANS(FCVTZS_vi, do_gvec_op2_fpst,
-    default:
+      a->esz, a->q, a->rd, a->rn, float_round_to_zero, f_fcvt_s_vi)
-    case 0x4: /* CLS, CLZ */
+TRANS(FCVTZU_vi, do_gvec_op2_fpst,
-    case 0x5: /* NOT */
+      a->esz, a->q, a->rd, a->rn, float_round_to_zero, f_fcvt_u_vi)
-    case 0x7: /* SQABS, SQNEG */
+TRANS(FCVTAS_vi, do_gvec_op2_fpst,
-    case 0x8: /* CMGT, CMGE */
+      a->esz, a->q, a->rd, a->rn, float_round_ties_away, f_fcvt_s_vi)
-    case 0x9: /* CMEQ, CMLE */
+TRANS(FCVTAU_vi, do_gvec_op2_fpst,
-    case 0xa: /* CMLT */
+      a->esz, a->q, a->rd, a->rn, float_round_ties_away, f_fcvt_u_vi)
-    case 0xb: /* ABS, NEG */
-    case 0x2f: /* FABS */
-    case 0x6f: /* FNEG */
-    case 0x7f: /* FSQRT */
-    case 0x18: /* FRINTN */
-    case 0x19: /* FRINTM */
-    case 0x38: /* FRINTP */
-    case 0x39: /* FRINTZ */
-    case 0x58: /* FRINTA */
-    case 0x79: /* FRINTI */
-    case 0x59: /* FRINTX */
-    case 0x1e: /* FRINT32Z */
-    case 0x5e: /* FRINT32X */
-    case 0x1f: /* FRINT64Z */
-    case 0x5f: /* FRINT64X */
-        g_assert_not_reached();
-    }
-}
 
 static void handle_2misc_fcmp_zero(DisasContext *s, int opcode,
                                    bool is_scalar, bool is_u, bool is_q,
@@ -9758,30 +9740,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
             }
             handle_2misc_fcmp_zero(s, opcode, false, u, is_q, size, rn, rd);
             return;
-        case 0x1a: /* FCVTNS */
-        case 0x1b: /* FCVTMS */
-        case 0x3a: /* FCVTPS */
-        case 0x3b: /* FCVTZS */
-        case 0x5a: /* FCVTNU */
-        case 0x5b: /* FCVTMU */
-        case 0x7a: /* FCVTPU */
-        case 0x7b: /* FCVTZU */
-            need_fpstatus = true;
-            rmode = extract32(opcode, 5, 1) | (extract32(opcode, 0, 1) << 1);
-            if (size == 3 && !is_q) {
-                unallocated_encoding(s);
-                return;
-            }
-            break;
-        case 0x5c: /* FCVTAU */
-        case 0x1c: /* FCVTAS */
-            need_fpstatus = true;
-            rmode = FPROUNDING_TIEAWAY;
-            if (size == 3 && !is_q) {
-                unallocated_encoding(s);
-                return;
-            }
-            break;
         case 0x3c: /* URECPE */
             if (size == 3) {
                 unallocated_encoding(s);
@@ -9831,6 +9789,16 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
         case 0x5f: /* FRINT64X */
         case 0x1d: /* SCVTF */
         case 0x5d: /* UCVTF */
+        case 0x1a: /* FCVTNS */
+        case 0x1b: /* FCVTMS */
+        case 0x3a: /* FCVTPS */
+        case 0x3b: /* FCVTZS */
+        case 0x5a: /* FCVTNU */
+        case 0x5b: /* FCVTMU */
+        case 0x7a: /* FCVTPU */
+        case 0x7b: /* FCVTZU */
+        case 0x5c: /* FCVTAU */
+        case 0x1c: /* FCVTAS */
             unallocated_encoding(s);
             return;
         }
@@ -9871,26 +9839,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
         tcg_rmode = NULL;
     }
 
-    if (size == 3) {
+    {
-        /* All 64-bit element operations can be shared with scalar 2misc */
-        int pass;
-
-        /* Coverity claims (size == 3 && !is_q) has been eliminated
-         * from all paths leading to here.
-         */
-        tcg_debug_assert(is_q);
-        for (pass = 0; pass < 2; pass++) {
-            TCGv_i64 tcg_op = tcg_temp_new_i64();
-            TCGv_i64 tcg_res = tcg_temp_new_i64();
-
-            read_vec_element(s, tcg_op, rn, pass, MO_64);
-
-            handle_2misc_64(s, opcode, u, tcg_res, tcg_op,
-                            tcg_rmode, tcg_fpstatus);
-
-            write_vec_element(s, tcg_res, rd, pass, MO_64);
-        }
-    } else {
         int pass;
 
         assert(size == 2);
@@ -9903,22 +9852,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
             {
                 /* Special cases for 32 bit elements */
                 switch (opcode) {
-                case 0x1a: /* FCVTNS */
-                case 0x1b: /* FCVTMS */
-                case 0x1c: /* FCVTAS */
-                case 0x3a: /* FCVTPS */
-                case 0x3b: /* FCVTZS */
-                    gen_helper_vfp_tosls(tcg_res, tcg_op,
-                                         tcg_constant_i32(0), tcg_fpstatus);
-                    break;
-                case 0x5a: /* FCVTNU */
-                case 0x5b: /* FCVTMU */
-                case 0x5c: /* FCVTAU */
-                case 0x7a: /* FCVTPU */
-                case 0x7b: /* FCVTZU */
-                    gen_helper_vfp_touls(tcg_res, tcg_op,
-                                         tcg_constant_i32(0), tcg_fpstatus);
-                    break;
                 case 0x7c: /* URSQRTE */
                     gen_helper_rsqrte_u32(tcg_res, tcg_op);
                     break;
@@ -9938,6 +9871,16 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
                 case 0x5e: /* FRINT32X */
                 case 0x1f: /* FRINT64Z */
                 case 0x5f: /* FRINT64X */
+                case 0x1a: /* FCVTNS */
+                case 0x1b: /* FCVTMS */
+                case 0x1c: /* FCVTAS */
+                case 0x3a: /* FCVTPS */
+                case 0x3b: /* FCVTZS */
+                case 0x5a: /* FCVTNU */
+                case 0x5b: /* FCVTMU */
+                case 0x5c: /* FCVTAU */
+                case 0x7a: /* FCVTPU */
+                case 0x7b: /* FCVTZU */
                     g_assert_not_reached();
                 }
             }
@@ -10006,36 +9949,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn)
     case 0x3d: /* FRECPE */
     case 0x3f: /* FRECPX */
         break;
-    case 0x1a: /* FCVTNS */
-        rmode = FPROUNDING_TIEEVEN;
-        break;
-    case 0x1b: /* FCVTMS */
-        rmode = FPROUNDING_NEGINF;
-        break;
-    case 0x1c: /* FCVTAS */
-        rmode = FPROUNDING_TIEAWAY;
-        break;
-    case 0x3a: /* FCVTPS */
-        rmode = FPROUNDING_POSINF;
-        break;
-    case 0x3b: /* FCVTZS */
-        rmode = FPROUNDING_ZERO;
-        break;
-    case 0x5a: /* FCVTNU */
-        rmode = FPROUNDING_TIEEVEN;
-        break;
-    case 0x5b: /* FCVTMU */
-        rmode = FPROUNDING_NEGINF;
-        break;
-    case 0x5c: /* FCVTAU */
-        rmode = FPROUNDING_TIEAWAY;
-        break;
-    case 0x7a: /* FCVTPU */
-        rmode = FPROUNDING_POSINF;
-        break;
-    case 0x7b: /* FCVTZU */
-        rmode = FPROUNDING_ZERO;
-        break;
     case 0x7d: /* FRSQRTE */
         break;
     default:
@@ -10051,6 +9964,16 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn)
     case 0x79: /* FRINTI */
     case 0x1d: /* SCVTF */
     case 0x5d: /* UCVTF */
+    case 0x1a: /* FCVTNS */
+    case 0x1b: /* FCVTMS */
+    case 0x1c: /* FCVTAS */
+    case 0x3a: /* FCVTPS */
+    case 0x3b: /* FCVTZS */
+    case 0x5a: /* FCVTNU */
+    case 0x5b: /* FCVTMU */
+    case 0x5c: /* FCVTAU */
+    case 0x7a: /* FCVTPU */
+    case 0x7b: /* FCVTZU */
         unallocated_encoding(s);
         return;
     }
@@ -10115,23 +10038,9 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn)
             read_vec_element_i32(s, tcg_op, rn, pass, MO_16);
 
             switch (fpop) {
-            case 0x1a: /* FCVTNS */
-            case 0x1b: /* FCVTMS */
-            case 0x1c: /* FCVTAS */
-            case 0x3a: /* FCVTPS */
-            case 0x3b: /* FCVTZS */
-                gen_helper_advsimd_f16tosinth(tcg_res, tcg_op, tcg_fpstatus);
-                break;
             case 0x3d: /* FRECPE */
                 gen_helper_recpe_f16(tcg_res, tcg_op, tcg_fpstatus);
                 break;
-            case 0x5a: /* FCVTNU */
-            case 0x5b: /* FCVTMU */
-            case 0x5c: /* FCVTAU */
-            case 0x7a: /* FCVTPU */
-            case 0x7b: /* FCVTZU */
-                gen_helper_advsimd_f16touinth(tcg_res, tcg_op, tcg_fpstatus);
-                break;
             case 0x7d: /* FRSQRTE */
                 gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus);
                 break;
@@ -10146,6 +10055,16 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn)
             case 0x58: /* FRINTA */
             case 0x79: /* FRINTI */
             case 0x59: /* FRINTX */
+            case 0x1a: /* FCVTNS */
+            case 0x1b: /* FCVTMS */
+            case 0x1c: /* FCVTAS */
+            case 0x3a: /* FCVTPS */
+            case 0x3b: /* FCVTZS */
+            case 0x5a: /* FCVTNU */
+            case 0x5b: /* FCVTMU */
+            case 0x5c: /* FCVTAU */
+            case 0x7a: /* FCVTPU */
+            case 0x7b: /* FCVTZU */
                 g_assert_not_reached();
             }
 

target/arm/tcg/vec_helper.c

@@ -2537,6 +2537,8 @@ DO_VCVT_FIXED(gvec_vcvt_rz_hu, helper_vfp_touhh_round_to_zero, uint16_t)
         clear_tail(d, oprsz, simd_maxsz(desc));                         \
     }
 
+DO_VCVT_RMODE(gvec_vcvt_rm_sd, helper_vfp_tosqd, uint64_t)
+DO_VCVT_RMODE(gvec_vcvt_rm_ud, helper_vfp_touqd, uint64_t)
 DO_VCVT_RMODE(gvec_vcvt_rm_ss, helper_vfp_tosls, uint32_t)
 DO_VCVT_RMODE(gvec_vcvt_rm_us, helper_vfp_touls, uint32_t)
 DO_VCVT_RMODE(gvec_vcvt_rm_sh, helper_vfp_toshh, uint16_t)