diff mbox series

[v2,24/69] target/arm: Convert FMOV, FABS, FNEG (scalar) to decodetree

Message ID 20241210161733.1830573-25-richard.henderson@linaro.org (mailing list archive)
State New
Headers show
Series target/arm: AArch64 decodetree conversion, final part | expand

Commit Message

Richard Henderson Dec. 10, 2024, 4:16 p.m. UTC
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/translate-a64.c | 105 +++++++++++++++++++++++----------
 target/arm/tcg/a64.decode      |   7 +++
 2 files changed, 81 insertions(+), 31 deletions(-)

Comments

Peter Maydell Dec. 11, 2024, 3:50 p.m. UTC | #1
On Tue, 10 Dec 2024 at 16:23, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  target/arm/tcg/translate-a64.c | 105 +++++++++++++++++++++++----------
>  target/arm/tcg/a64.decode      |   7 +++
>  2 files changed, 81 insertions(+), 31 deletions(-)

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>

thanks
-- PMM
diff mbox series

Patch

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index f67360c4c5..383ee7f3f0 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -8283,6 +8283,67 @@  static bool trans_CSEL(DisasContext *s, arg_CSEL *a)
     return true;
 }
 
+typedef struct FPScalar1Int {
+    void (*gen_h)(TCGv_i32, TCGv_i32);
+    void (*gen_s)(TCGv_i32, TCGv_i32);
+    void (*gen_d)(TCGv_i64, TCGv_i64);
+} FPScalar1Int;
+
+static bool do_fp1_scalar_int(DisasContext *s, arg_rr_e *a,
+                              const FPScalar1Int *f)
+{
+    switch (a->esz) {
+    case MO_64:
+        if (fp_access_check(s)) {
+            TCGv_i64 t = read_fp_dreg(s, a->rn);
+            f->gen_d(t, t);
+            write_fp_dreg(s, a->rd, t);
+        }
+        break;
+    case MO_32:
+        if (fp_access_check(s)) {
+            TCGv_i32 t = read_fp_sreg(s, a->rn);
+            f->gen_s(t, t);
+            write_fp_sreg(s, a->rd, t);
+        }
+        break;
+    case MO_16:
+        if (!dc_isar_feature(aa64_fp16, s)) {
+            return false;
+        }
+        if (fp_access_check(s)) {
+            TCGv_i32 t = read_fp_hreg(s, a->rn);
+            f->gen_h(t, t);
+            write_fp_sreg(s, a->rd, t);
+        }
+        break;
+    default:
+        return false;
+    }
+    return true;
+}
+
+static const FPScalar1Int f_scalar_fmov = {
+    tcg_gen_mov_i32,
+    tcg_gen_mov_i32,
+    tcg_gen_mov_i64,
+};
+TRANS(FMOV_s, do_fp1_scalar_int, a, &f_scalar_fmov)
+
+static const FPScalar1Int f_scalar_fabs = {
+    gen_vfp_absh,
+    gen_vfp_abss,
+    gen_vfp_absd,
+};
+TRANS(FABS_s, do_fp1_scalar_int, a, &f_scalar_fabs)
+
+static const FPScalar1Int f_scalar_fneg = {
+    gen_vfp_negh,
+    gen_vfp_negs,
+    gen_vfp_negd,
+};
+TRANS(FNEG_s, do_fp1_scalar_int, a, &f_scalar_fneg)
+
 /* Floating-point data-processing (1 source) - half precision */
 static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn)
 {
@@ -8291,15 +8352,6 @@  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 0x0: /* FMOV */
-        tcg_gen_mov_i32(tcg_res, tcg_op);
-        break;
-    case 0x1: /* FABS */
-        gen_vfp_absh(tcg_res, tcg_op);
-        break;
-    case 0x2: /* FNEG */
-        gen_vfp_negh(tcg_res, tcg_op);
-        break;
     case 0x3: /* FSQRT */
         fpst = fpstatus_ptr(FPST_FPCR_F16);
         gen_helper_sqrt_f16(tcg_res, tcg_op, fpst);
@@ -8327,6 +8379,9 @@  static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn)
         gen_helper_advsimd_rinth(tcg_res, tcg_op, fpst);
         break;
     default:
+    case 0x0: /* FMOV */
+    case 0x1: /* FABS */
+    case 0x2: /* FNEG */
         g_assert_not_reached();
     }
 
@@ -8345,15 +8400,6 @@  static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn)
     tcg_res = tcg_temp_new_i32();
 
     switch (opcode) {
-    case 0x0: /* FMOV */
-        tcg_gen_mov_i32(tcg_res, tcg_op);
-        goto done;
-    case 0x1: /* FABS */
-        gen_vfp_abss(tcg_res, tcg_op);
-        goto done;
-    case 0x2: /* FNEG */
-        gen_vfp_negs(tcg_res, tcg_op);
-        goto done;
     case 0x3: /* FSQRT */
         gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_env);
         goto done;
@@ -8389,6 +8435,9 @@  static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn)
         gen_fpst = gen_helper_frint64_s;
         break;
     default:
+    case 0x0: /* FMOV */
+    case 0x1: /* FABS */
+    case 0x2: /* FNEG */
         g_assert_not_reached();
     }
 
@@ -8413,22 +8462,10 @@  static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn)
     TCGv_ptr fpst;
     int rmode = -1;
 
-    switch (opcode) {
-    case 0x0: /* FMOV */
-        gen_gvec_fn2(s, false, rd, rn, tcg_gen_gvec_mov, 0);
-        return;
-    }
-
     tcg_op = read_fp_dreg(s, rn);
     tcg_res = tcg_temp_new_i64();
 
     switch (opcode) {
-    case 0x1: /* FABS */
-        gen_vfp_absd(tcg_res, tcg_op);
-        goto done;
-    case 0x2: /* FNEG */
-        gen_vfp_negd(tcg_res, tcg_op);
-        goto done;
     case 0x3: /* FSQRT */
         gen_helper_vfp_sqrtd(tcg_res, tcg_op, tcg_env);
         goto done;
@@ -8461,6 +8498,9 @@  static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn)
         gen_fpst = gen_helper_frint64_d;
         break;
     default:
+    case 0x0: /* FMOV */
+    case 0x1: /* FABS */
+    case 0x2: /* FNEG */
         g_assert_not_reached();
     }
 
@@ -8581,7 +8621,7 @@  static void disas_fp_1src(DisasContext *s, uint32_t insn)
             goto do_unallocated;
         }
         /* fall through */
-    case 0x0 ... 0x3:
+    case 0x3:
     case 0x8 ... 0xc:
     case 0xe ... 0xf:
         /* 32-to-32 and 64-to-64 ops */
@@ -8631,6 +8671,9 @@  static void disas_fp_1src(DisasContext *s, uint32_t insn)
 
     default:
     do_unallocated:
+    case 0x0: /* FMOV */
+    case 0x1: /* FABS */
+    case 0x2: /* FNEG */
         unallocated_encoding(s);
         break;
     }
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 7868b1cb24..b9cc8963da 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -47,6 +47,7 @@ 
 @rr_h           ........ ... ..... ...... rn:5 rd:5     &rr_e esz=1
 @rr_d           ........ ... ..... ...... rn:5 rd:5     &rr_e esz=3
 @rr_sd          ........ ... ..... ...... rn:5 rd:5     &rr_e esz=%esz_sd
+@rr_hsd         ........ ... ..... ...... rn:5 rd:5     &rr_e esz=%esz_hsd
 
 @rrr_b          ........ ... rm:5 ...... rn:5 rd:5      &rrr_e esz=0
 @rrr_h          ........ ... rm:5 ...... rn:5 rd:5      &rrr_e esz=1
@@ -1321,6 +1322,12 @@  FMAXV_s         0110 1110 00 11000 01111 10 ..... .....     @rr_q1e2
 FMINV_h         0.00 1110 10 11000 01111 10 ..... .....     @qrr_h
 FMINV_s         0110 1110 10 11000 01111 10 ..... .....     @rr_q1e2
 
+# Floating-point data processing (1 source)
+
+FMOV_s          00011110 .. 1 000000 10000 ..... .....      @rr_hsd
+FABS_s          00011110 .. 1 000001 10000 ..... .....      @rr_hsd
+FNEG_s          00011110 .. 1 000010 10000 ..... .....      @rr_hsd
+
 # Floating-point Immediate
 
 FMOVI_s         0001 1110 .. 1 imm:8 100 00000 rd:5         esz=%esz_hsd