target/arm: Convert FSQRT (scalar) to decodetree

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20241211163036.2297116-28-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index b9cc8963da885a6692e7de59083d224da16acae1..3b1e8e0776088f439f8571c9238ce0d3d9e14c0f 100644 (file)
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -1327,6 +1327,7 @@ FMINV_s         0110 1110 10 11000 01111 10 ..... .....     @rr_q1e2
 FMOV_s          00011110 .. 1 000000 10000 ..... .....      @rr_hsd
 FABS_s          00011110 .. 1 000001 10000 ..... .....      @rr_hsd
 FNEG_s          00011110 .. 1 000010 10000 ..... .....      @rr_hsd
+FSQRT_s         00011110 .. 1 000011 10000 ..... .....      @rr_hsd
 
 # Floating-point Immediate
 

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 2a5cb70475212a34be0f34c2fbeb297f8813d5b3..f3989246f9c8df6db96908685266a09d235a42df 100644 (file)
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -8344,6 +8344,63 @@ static const FPScalar1Int f_scalar_fneg = {
 };
 TRANS(FNEG_s, do_fp1_scalar_int, a, &f_scalar_fneg)
 
+typedef struct FPScalar1 {
+    void (*gen_h)(TCGv_i32, TCGv_i32, TCGv_ptr);
+    void (*gen_s)(TCGv_i32, TCGv_i32, TCGv_ptr);
+    void (*gen_d)(TCGv_i64, TCGv_i64, TCGv_ptr);
+} FPScalar1;
+
+static bool do_fp1_scalar(DisasContext *s, arg_rr_e *a,
+                          const FPScalar1 *f, int rmode)
+{
+    TCGv_i32 tcg_rmode = NULL;
+    TCGv_ptr fpst;
+    TCGv_i64 t64;
+    TCGv_i32 t32;
+    int check = fp_access_check_scalar_hsd(s, a->esz);
+
+    if (check <= 0) {
+        return check == 0;
+    }
+
+    fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
+    if (rmode >= 0) {
+        tcg_rmode = gen_set_rmode(rmode, fpst);
+    }
+
+    switch (a->esz) {
+    case MO_64:
+        t64 = read_fp_dreg(s, a->rn);
+        f->gen_d(t64, t64, fpst);
+        write_fp_dreg(s, a->rd, t64);
+        break;
+    case MO_32:
+        t32 = read_fp_sreg(s, a->rn);
+        f->gen_s(t32, t32, fpst);
+        write_fp_sreg(s, a->rd, t32);
+        break;
+    case MO_16:
+        t32 = read_fp_hreg(s, a->rn);
+        f->gen_h(t32, t32, fpst);
+        write_fp_sreg(s, a->rd, t32);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    if (rmode >= 0) {
+        gen_restore_rmode(tcg_rmode, fpst);
+    }
+    return true;
+}
+
+static const FPScalar1 f_scalar_fsqrt = {
+    gen_helper_vfp_sqrth,
+    gen_helper_vfp_sqrts,
+    gen_helper_vfp_sqrtd,
+};
+TRANS(FSQRT_s, do_fp1_scalar, a, &f_scalar_fsqrt, -1)
+
 /* Floating-point data-processing (1 source) - half precision */
 static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn)
 {
@@ -8352,10 +8409,6 @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn)
     TCGv_i32 tcg_res = tcg_temp_new_i32();
 
     switch (opcode) {
-    case 0x3: /* FSQRT */
-        fpst = fpstatus_ptr(FPST_FPCR_F16);
-        gen_helper_vfp_sqrth(tcg_res, tcg_op, fpst);
-        break;
     case 0x8: /* FRINTN */
     case 0x9: /* FRINTP */
     case 0xa: /* FRINTM */
@@ -8382,6 +8435,7 @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn)
     case 0x0: /* FMOV */
     case 0x1: /* FABS */
     case 0x2: /* FNEG */
+    case 0x3: /* FSQRT */
         g_assert_not_reached();
     }
 
@@ -8400,9 +8454,6 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn)
     tcg_res = tcg_temp_new_i32();
 
     switch (opcode) {
-    case 0x3: /* FSQRT */
-        gen_fpst = gen_helper_vfp_sqrts;
-        break;
     case 0x6: /* BFCVT */
         gen_fpst = gen_helper_bfcvt;
         break;
@@ -8438,6 +8489,7 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn)
     case 0x0: /* FMOV */
     case 0x1: /* FABS */
     case 0x2: /* FNEG */
+    case 0x3: /* FSQRT */
         g_assert_not_reached();
     }
 
@@ -8465,9 +8517,6 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn)
     tcg_res = tcg_temp_new_i64();
 
     switch (opcode) {
-    case 0x3: /* FSQRT */
-        gen_fpst = gen_helper_vfp_sqrtd;
-        break;
     case 0x8: /* FRINTN */
     case 0x9: /* FRINTP */
     case 0xa: /* FRINTM */
@@ -8500,6 +8549,7 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn)
     case 0x0: /* FMOV */
     case 0x1: /* FABS */
     case 0x2: /* FNEG */
+    case 0x3: /* FSQRT */
         g_assert_not_reached();
     }
 
@@ -8619,7 +8669,6 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
             goto do_unallocated;
         }
         /* fall through */
-    case 0x3:
     case 0x8 ... 0xc:
     case 0xe ... 0xf:
         /* 32-to-32 and 64-to-64 ops */
@@ -8672,6 +8721,7 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
     case 0x0: /* FMOV */
     case 0x1: /* FABS */
     case 0x2: /* FNEG */
+    case 0x3: /* FSQRT */
         unallocated_encoding(s);
         break;
     }