[PATCH 49/67] target/arm: Convert FCVTN, BFCVTN to decodetree

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/translate-a64.c | 89 ++++++++++++++++++----------------
 target/arm/tcg/a64.decode      |  5 ++
 2 files changed, 52 insertions(+), 42 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 6c44e9d8a1..8b76c307af 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -9055,6 +9055,49 @@ TRANS(SQXTUN_v, do_2misc_narrow_vector, a, 
f_scalar_sqxtun)
 TRANS(SQXTN_v, do_2misc_narrow_vector, a, f_scalar_sqxtn)
 TRANS(UQXTN_v, do_2misc_narrow_vector, a, f_scalar_uqxtn)
 
+static void gen_fcvtn_hs(TCGv_i64 d, TCGv_i64 n)
+{
+    TCGv_i32 tcg_lo = tcg_temp_new_i32();
+    TCGv_i32 tcg_hi = tcg_temp_new_i32();
+    TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR);
+    TCGv_i32 ahp = get_ahp_flag();
+
+    tcg_gen_extr_i64_i32(tcg_lo, tcg_hi, n);
+    gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, fpst, ahp);
+    gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, fpst, ahp);
+    tcg_gen_deposit_i32(tcg_lo, tcg_lo, tcg_hi, 16, 16);
+    tcg_gen_extu_i32_i64(d, tcg_lo);
+}
+
+static void gen_fcvtn_sd(TCGv_i64 d, TCGv_i64 n)
+{
+    TCGv_i32 tmp = tcg_temp_new_i32();
+    gen_helper_vfp_fcvtsd(tmp, n, tcg_env);
+    tcg_gen_extu_i32_i64(d, tmp);
+}
+
+static ArithOneOp * const f_vector_fcvtn[] = {
+    NULL,
+    gen_fcvtn_hs,
+    gen_fcvtn_sd,
+};
+TRANS(FCVTN_v, do_2misc_narrow_vector, a, f_vector_fcvtn)
+
+static void gen_bfcvtn_hs(TCGv_i64 d, TCGv_i64 n)
+{
+    TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR);
+    TCGv_i32 tmp = tcg_temp_new_i32();
+    gen_helper_bfcvt_pair(tmp, n, fpst);
+    tcg_gen_extu_i32_i64(d, tmp);
+}
+
+static ArithOneOp * const f_vector_bfcvtn[] = {
+    NULL,
+    gen_bfcvtn_hs,
+    NULL,
+};
+TRANS_FEAT(BFCVTN_v, aa64_bf16, do_2misc_narrow_vector, a, f_vector_bfcvtn)
+
 /* Common vector code for handling integer to FP conversion */
 static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn,
                                    int elements, int is_signed,
@@ -9637,33 +9680,6 @@ static void handle_2misc_narrow(DisasContext *s, bool 
scalar,
         tcg_res[pass] = tcg_temp_new_i64();
 
         switch (opcode) {
-        case 0x16: /* FCVTN, FCVTN2 */
-            /* 32 bit to 16 bit or 64 bit to 32 bit float conversion */
-            if (size == 2) {
-                TCGv_i32 tmp = tcg_temp_new_i32();
-                gen_helper_vfp_fcvtsd(tmp, tcg_op, tcg_env);
-                tcg_gen_extu_i32_i64(tcg_res[pass], tmp);
-            } else {
-                TCGv_i32 tcg_lo = tcg_temp_new_i32();
-                TCGv_i32 tcg_hi = tcg_temp_new_i32();
-                TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR);
-                TCGv_i32 ahp = get_ahp_flag();
-
-                tcg_gen_extr_i64_i32(tcg_lo, tcg_hi, tcg_op);
-                gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, fpst, ahp);
-                gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, fpst, ahp);
-                tcg_gen_deposit_i32(tcg_lo, tcg_lo, tcg_hi, 16, 16);
-                tcg_gen_extu_i32_i64(tcg_res[pass], tcg_lo);
-            }
-            break;
-        case 0x36: /* BFCVTN, BFCVTN2 */
-            {
-                TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR);
-                TCGv_i32 tmp = tcg_temp_new_i32();
-                gen_helper_bfcvt_pair(tmp, tcg_op, fpst);
-                tcg_gen_extu_i32_i64(tcg_res[pass], tmp);
-            }
-            break;
         case 0x56:  /* FCVTXN, FCVTXN2 */
             {
                 /*
@@ -9679,6 +9695,8 @@ static void handle_2misc_narrow(DisasContext *s, bool 
scalar,
         default:
         case 0x12: /* XTN, SQXTUN */
         case 0x14: /* SQXTN, UQXTN */
+        case 0x16: /* FCVTN, FCVTN2 */
+        case 0x36: /* BFCVTN, BFCVTN2 */
             g_assert_not_reached();
         }
 
@@ -10092,21 +10110,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, 
uint32_t insn)
                 unallocated_encoding(s);
                 return;
             }
-            /* fall through */
-        case 0x16: /* FCVTN, FCVTN2 */
-            /* handle_2misc_narrow does a 2*size -> size operation, but these
-             * instructions encode the source size rather than dest size.
-             */
-            if (!fp_access_check(s)) {
-                return;
-            }
-            handle_2misc_narrow(s, false, opcode, 0, is_q, size - 1, rn, rd);
-            return;
-        case 0x36: /* BFCVTN, BFCVTN2 */
-            if (!dc_isar_feature(aa64_bf16, s) || size != 2) {
-                unallocated_encoding(s);
-                return;
-            }
             if (!fp_access_check(s)) {
                 return;
             }
@@ -10159,6 +10162,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, 
uint32_t insn)
             }
             break;
         default:
+        case 0x16: /* FCVTN, FCVTN2 */
+        case 0x36: /* BFCVTN, BFCVTN2 */
             unallocated_encoding(s);
             return;
         }
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 9a01037446..1412b99241 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -21,6 +21,7 @@
 
 %rd             0:5
 %esz_sd         22:1 !function=plus_2
+%esz_hs         22:1 !function=plus_1
 %esz_hsd        22:2 !function=xor_2
 %hl             11:1 21:1
 %hlm            11:1 20:2
@@ -74,6 +75,7 @@
 @qrr_b          . q:1 ...... .. ...... ...... rn:5 rd:5  &qrr_e esz=0
 @qrr_h          . q:1 ...... .. ...... ...... rn:5 rd:5  &qrr_e esz=1
 @qrr_bh         . q:1 ...... . esz:1 ...... ...... rn:5 rd:5  &qrr_e
+@qrr_hs         . q:1 ...... .. ...... ...... rn:5 rd:5  &qrr_e esz=%esz_hs
 @qrr_e          . q:1 ...... esz:2 ...... ...... rn:5 rd:5  &qrr_e
 
 @qrrr_b         . q:1 ...... ... rm:5 ...... rn:5 rd:5  &qrrr_e esz=0
@@ -1676,3 +1678,6 @@ XTN             0.00 1110 ..1 00001 00101 0 ..... .....   
  @qrr_e
 SQXTUN_v        0.10 1110 ..1 00001 00101 0 ..... .....     @qrr_e
 SQXTN_v         0.00 1110 ..1 00001 01001 0 ..... .....     @qrr_e
 UQXTN_v         0.10 1110 ..1 00001 01001 0 ..... .....     @qrr_e
+
+FCVTN_v         0.00 1110 0.1 00001 01101 0 ..... .....     @qrr_hs
+BFCVTN_v        0.00 1110 101 00001 01101 0 ..... .....     @qrr_h
-- 
2.43.0