[PULL 18/43] target/arm: Convert SQSHL, UQSHL to decodetree

Maintainers: Richard Henderson <richard.henderson@linaro.org>, Paolo Bonzini <pbonzini@redhat.com>, Peter Maydell <peter.maydell@linaro.org>, Radoslaw Biernacki <rad@semihalf.com>, Leif Lindholm <quic_llindhol@quicinc.com>, Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>, "Edgar E. Iglesias" <edgar.iglesias@gmail.com>, Alistair Francis <alistair@alistair23.me>, Gerd Hoffmann <kraxel@redhat.com>, Eduardo Habkost <eduardo@habkost.net>, Cleber Rosa <crosa@redhat.com>, "Philippe Mathieu-Daudé" <philmd@linaro.org>, Wainer dos Santos Moschetta <wainersm@redhat.com>, Beraldo Leal <bleal@redhat.com>
There is a newer version of this series
[PULL 18/43] target/arm: Convert SQSHL, UQSHL to decodetree
Posted by Peter Maydell 5 months, 3 weeks ago
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: 20240528203044.612851-14-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/a64.decode      |  4 ++
 target/arm/tcg/translate-a64.c | 74 ++++++++++++++++++++++------------
 2 files changed, 53 insertions(+), 25 deletions(-)

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 9e027760367..85caf379486 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -760,6 +760,8 @@ SSHL_s          0101 1110 111 ..... 01000 1 ..... ..... @rrr_d
 USHL_s          0111 1110 111 ..... 01000 1 ..... ..... @rrr_d
 SRSHL_s         0101 1110 111 ..... 01010 1 ..... ..... @rrr_d
 URSHL_s         0111 1110 111 ..... 01010 1 ..... ..... @rrr_d
+SQSHL_s         0101 1110 ..1 ..... 01001 1 ..... ..... @rrr_e
+UQSHL_s         0111 1110 ..1 ..... 01001 1 ..... ..... @rrr_e
 
 ### Advanced SIMD scalar pairwise
 
@@ -886,6 +888,8 @@ SSHL_v          0.00 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e
 USHL_v          0.10 1110 ..1 ..... 01000 1 ..... ..... @qrrr_e
 SRSHL_v         0.00 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e
 URSHL_v         0.10 1110 ..1 ..... 01010 1 ..... ..... @qrrr_e
+SQSHL_v         0.00 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e
+UQSHL_v         0.10 1110 ..1 ..... 01001 1 ..... ..... @qrrr_e
 
 ### Advanced SIMD scalar x indexed element
 
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index c88702dad66..97bd69eb3f8 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5119,6 +5119,49 @@ TRANS(USHL_s, do_int3_scalar_d, a, gen_ushl_i64)
 TRANS(SRSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_s64)
 TRANS(URSHL_s, do_int3_scalar_d, a, gen_helper_neon_rshl_u64)
 
+typedef struct ENVScalar2 {
+    NeonGenTwoOpEnvFn *gen_bhs[3];
+    NeonGenTwo64OpEnvFn *gen_d;
+} ENVScalar2;
+
+static bool do_env_scalar2(DisasContext *s, arg_rrr_e *a, const ENVScalar2 *f)
+{
+    if (!fp_access_check(s)) {
+        return true;
+    }
+    if (a->esz == MO_64) {
+        TCGv_i64 t0 = read_fp_dreg(s, a->rn);
+        TCGv_i64 t1 = read_fp_dreg(s, a->rm);
+        f->gen_d(t0, tcg_env, t0, t1);
+        write_fp_dreg(s, a->rd, t0);
+    } else {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
+
+        read_vec_element_i32(s, t0, a->rn, 0, a->esz);
+        read_vec_element_i32(s, t1, a->rm, 0, a->esz);
+        f->gen_bhs[a->esz](t0, tcg_env, t0, t1);
+        write_fp_sreg(s, a->rd, t0);
+    }
+    return true;
+}
+
+static const ENVScalar2 f_scalar_sqshl = {
+    { gen_helper_neon_qshl_s8,
+      gen_helper_neon_qshl_s16,
+      gen_helper_neon_qshl_s32 },
+    gen_helper_neon_qshl_s64,
+};
+TRANS(SQSHL_s, do_env_scalar2, a, &f_scalar_sqshl)
+
+static const ENVScalar2 f_scalar_uqshl = {
+    { gen_helper_neon_qshl_u8,
+      gen_helper_neon_qshl_u16,
+      gen_helper_neon_qshl_u32 },
+    gen_helper_neon_qshl_u64,
+};
+TRANS(UQSHL_s, do_env_scalar2, a, &f_scalar_uqshl)
+
 static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a,
                           gen_helper_gvec_3_ptr * const fns[3])
 {
@@ -5368,6 +5411,8 @@ TRANS(SSHL_v, do_gvec_fn3, a, gen_gvec_sshl)
 TRANS(USHL_v, do_gvec_fn3, a, gen_gvec_ushl)
 TRANS(SRSHL_v, do_gvec_fn3, a, gen_gvec_srshl)
 TRANS(URSHL_v, do_gvec_fn3, a, gen_gvec_urshl)
+TRANS(SQSHL_v, do_gvec_fn3, a, gen_neon_sqshl)
+TRANS(UQSHL_v, do_gvec_fn3, a, gen_neon_uqshl)
 
 
 /*
@@ -9381,13 +9426,6 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u,
         }
         gen_cmtst_i64(tcg_rd, tcg_rn, tcg_rm);
         break;
-    case 0x9: /* SQSHL, UQSHL */
-        if (u) {
-            gen_helper_neon_qshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        } else {
-            gen_helper_neon_qshl_s64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
-        }
-        break;
     case 0xb: /* SQRSHL, UQRSHL */
         if (u) {
             gen_helper_neon_qrshl_u64(tcg_rd, tcg_env, tcg_rn, tcg_rm);
@@ -9406,6 +9444,7 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u,
     case 0x1: /* SQADD / UQADD */
     case 0x5: /* SQSUB / UQSUB */
     case 0x8: /* SSHL, USHL */
+    case 0x9: /* SQSHL, UQSHL */
     case 0xa: /* SRSHL, URSHL */
         g_assert_not_reached();
     }
@@ -9428,7 +9467,6 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
     TCGv_i64 tcg_rd;
 
     switch (opcode) {
-    case 0x9: /* SQSHL, UQSHL */
     case 0xb: /* SQRSHL, UQRSHL */
         break;
     case 0x6: /* CMGT, CMHI */
@@ -9450,6 +9488,7 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
     case 0x1: /* SQADD, UQADD */
     case 0x5: /* SQSUB, UQSUB */
     case 0x8: /* SSHL, USHL */
+    case 0x9: /* SQSHL, UQSHL */
     case 0xa: /* SRSHL, URSHL */
         unallocated_encoding(s);
         return;
@@ -9477,16 +9516,6 @@ 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 0x9: /* SQSHL, UQSHL */
-        {
-            static NeonGenTwoOpEnvFn * const fns[3][2] = {
-                { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 },
-                { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 },
-                { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 },
-            };
-            genenvfn = fns[size][u];
-            break;
-        }
         case 0xb: /* SQRSHL, UQRSHL */
         {
             static NeonGenTwoOpEnvFn * const fns[3][2] = {
@@ -9510,6 +9539,7 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
         default:
         case 0x1: /* SQADD, UQADD */
         case 0x5: /* SQSUB, UQSUB */
+        case 0x9: /* SQSHL, UQSHL */
             g_assert_not_reached();
         }
 
@@ -10927,6 +10957,7 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     case 0x01: /* SQADD, UQADD */
     case 0x05: /* SQSUB, UQSUB */
     case 0x08: /* SSHL, USHL */
+    case 0x09: /* SQSHL, UQSHL */
     case 0x0a: /* SRSHL, URSHL */
         unallocated_encoding(s);
         return;
@@ -10937,13 +10968,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
     }
 
     switch (opcode) {
-    case 0x09: /* SQSHL, UQSHL */
-        if (u) {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_uqshl, size);
-        } else {
-            gen_gvec_fn3(s, is_q, rd, rn, rm, gen_neon_sqshl, size);
-        }
-        return;
     case 0x0c: /* SMAX, UMAX */
         if (u) {
             gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size);
-- 
2.34.1