diff mbox series

[PULL,12/43] target/arm: Convert SQADD, SQSUB, UQADD, UQSUB to decodetree

Message ID 20240531120401.394550-13-peter.maydell@linaro.org
State New
Headers show
Series [PULL,01/43] hw/intc/arm_gic: Fix set pending of PPIs | expand

Commit Message

Peter Maydell May 31, 2024, 12:03 p.m. UTC 
From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240528203044.612851-8-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      | 11 ++++
 target/arm/tcg/translate-a64.c | 96 +++++++++++++++++++---------------
 2 files changed, 64 insertions(+), 43 deletions(-)
diff mbox series

Patch

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index f48adef5bba..19010af03bb 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -44,6 +44,7 @@ 
 @rrr_h          ........ ... rm:5 ...... rn:5 rd:5      &rrr_e esz=1
 @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
 
 @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
@@ -744,6 +745,11 @@  FRECPS_s        0101 1110 0.1 ..... 11111 1 ..... ..... @rrr_sd
 FRSQRTS_s       0101 1110 110 ..... 00111 1 ..... ..... @rrr_h
 FRSQRTS_s       0101 1110 1.1 ..... 11111 1 ..... ..... @rrr_sd
 
+SQADD_s         0101 1110 ..1 ..... 00001 1 ..... ..... @rrr_e
+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
+
 ### Advanced SIMD scalar pairwise
 
 FADDP_s         0101 1110 0011 0000 1101 10 ..... ..... @rr_h
@@ -857,6 +863,11 @@  BSL_v           0.10 1110 011 ..... 00011 1 ..... ..... @qrrr_b
 BIT_v           0.10 1110 101 ..... 00011 1 ..... ..... @qrrr_b
 BIF_v           0.10 1110 111 ..... 00011 1 ..... ..... @qrrr_b
 
+SQADD_v         0.00 1110 ..1 ..... 00001 1 ..... ..... @qrrr_e
+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
+
 ### 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 ca7ba6b1e8c..3956c415431 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5060,6 +5060,43 @@  static const FPScalar f_scalar_frsqrts = {
 };
 TRANS(FRSQRTS_s, do_fp3_scalar, a, &f_scalar_frsqrts)
 
+static bool do_satacc_s(DisasContext *s, arg_rrr_e *a,
+                MemOp sgn_n, MemOp sgn_m,
+                void (*gen_bhs)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp),
+                void (*gen_d)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64))
+{
+    TCGv_i64 t0, t1, t2, qc;
+    MemOp esz = a->esz;
+
+    if (!fp_access_check(s)) {
+        return true;
+    }
+
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+    qc = tcg_temp_new_i64();
+    read_vec_element(s, t1, a->rn, 0, esz | sgn_n);
+    read_vec_element(s, t2, a->rm, 0, esz | sgn_m);
+    tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
+
+    if (esz == MO_64) {
+        gen_d(t0, qc, t1, t2);
+    } else {
+        gen_bhs(t0, qc, t1, t2, esz);
+        tcg_gen_ext_i64(t0, t0, esz);
+    }
+
+    write_fp_dreg(s, a->rd, t0);
+    tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
+    return true;
+}
+
+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)
+
 static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a,
                           gen_helper_gvec_3_ptr * const fns[3])
 {
@@ -5298,6 +5335,11 @@  TRANS(BSL_v, do_bitsel, a->q, a->rd, a->rd, a->rn, a->rm)
 TRANS(BIT_v, do_bitsel, a->q, a->rd, a->rm, a->rn, a->rd)
 TRANS(BIF_v, do_bitsel, a->q, a->rd, a->rm, a->rd, a->rn)
 
+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)
+
 /*
  * Advanced SIMD scalar/vector x indexed element
  */
@@ -9291,29 +9333,8 @@  static void handle_3same_64(DisasContext *s, int opcode, bool u,
      * or scalar-three-reg-same groups.
      */
     TCGCond cond;
-    TCGv_i64 qc;
 
     switch (opcode) {
-    case 0x1: /* SQADD */
-        qc = tcg_temp_new_i64();
-        tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
-        if (u) {
-            gen_uqadd_d(tcg_rd, qc, tcg_rn, tcg_rm);
-        } else {
-            gen_sqadd_d(tcg_rd, qc, tcg_rn, tcg_rm);
-        }
-        tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
-        break;
-    case 0x5: /* SQSUB */
-        qc = tcg_temp_new_i64();
-        tcg_gen_ld_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
-        if (u) {
-            gen_uqsub_d(tcg_rd, qc, tcg_rn, tcg_rm);
-        } else {
-            gen_sqsub_d(tcg_rd, qc, tcg_rn, tcg_rm);
-        }
-        tcg_gen_st_i64(qc, tcg_env, offsetof(CPUARMState, vfp.qc));
-        break;
     case 0x6: /* CMGT, CMHI */
         cond = u ? TCG_COND_GTU : TCG_COND_GT;
     do_cmop:
@@ -9366,6 +9387,8 @@  static void handle_3same_64(DisasContext *s, int opcode, bool u,
         }
         break;
     default:
+    case 0x1: /* SQADD / UQADD */
+    case 0x5: /* SQSUB / UQSUB */
         g_assert_not_reached();
     }
 }
@@ -9387,8 +9410,6 @@  static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
     TCGv_i64 tcg_rd;
 
     switch (opcode) {
-    case 0x1: /* SQADD, UQADD */
-    case 0x5: /* SQSUB, UQSUB */
     case 0x9: /* SQSHL, UQSHL */
     case 0xb: /* SQRSHL, UQRSHL */
         break;
@@ -9410,6 +9431,8 @@  static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
         }
         break;
     default:
+    case 0x1: /* SQADD, UQADD */
+    case 0x5: /* SQSUB, UQSUB */
         unallocated_encoding(s);
         return;
     }
@@ -9436,12 +9459,6 @@  static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
         void (*genfn)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp) = NULL;
 
         switch (opcode) {
-        case 0x1: /* SQADD, UQADD */
-            genfn = u ? gen_uqadd_bhs : gen_sqadd_bhs;
-            break;
-        case 0x5: /* SQSUB, UQSUB */
-            genfn = u ? gen_uqsub_bhs : gen_sqsub_bhs;
-            break;
         case 0x9: /* SQSHL, UQSHL */
         {
             static NeonGenTwoOpEnvFn * const fns[3][2] = {
@@ -9473,6 +9490,8 @@  static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
             break;
         }
         default:
+        case 0x1: /* SQADD, UQADD */
+        case 0x5: /* SQSUB, UQSUB */
             g_assert_not_reached();
         }
 
@@ -10933,6 +10952,11 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
             return;
         }
         break;
+
+    case 0x01: /* SQADD, UQADD */
+    case 0x05: /* SQSUB, UQSUB */
+        unallocated_encoding(s);
+        return;
     }
 
     if (!fp_access_check(s)) {
@@ -10940,20 +10964,6 @@  static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x01: /* SQADD, UQADD */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqadd_qc, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqadd_qc, size);
-        }
-        return;
-    case 0x05: /* SQSUB, UQSUB */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqsub_qc, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqsub_qc, size);
-        }
-        return;
     case 0x08: /* SSHL, USHL */
         if (u) {
             gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_ushl, size);