Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/translate-a64.c | 86 +++++++++++++++++-----------------
 target/arm/tcg/a64.decode      |  5 ++
 2 files changed, 48 insertions(+), 43 deletions(-)

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 07b9cdd78f..264d2eeb27 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -5908,6 +5908,47 @@ TRANS(SQDMLSL_vi, do_3op_widening,
       a->esz | MO_SIGN, a->q, a->rd, a->rn, a->rm, a->idx,
       a->esz == MO_16 ? gen_sqdmlsl_h : gen_sqdmlsl_s, true)
 
+static bool do_addsub_wide(DisasContext *s, arg_qrrr_e *a,
+                           MemOp sign, bool sub)
+{
+    TCGv_i64 tcg_op0, tcg_op1;
+    MemOp esz = a->esz;
+    int half = 8 >> esz;
+    bool top = a->q;
+    int top_swap = top ? 0 : half - 1;
+    int top_half = top ? half : 0;
+
+    /* There are no 64x64->128 bit operations. */
+    if (esz >= MO_64) {
+        return false;
+    }
+    if (!fp_access_check(s)) {
+        return true;
+    }
+    tcg_op0 = tcg_temp_new_i64();
+    tcg_op1 = tcg_temp_new_i64();
+
+    for (int elt_fwd = 0; elt_fwd < half; ++elt_fwd) {
+        int elt = elt_fwd ^ top_swap;
+
+        read_vec_element(s, tcg_op1, a->rm, elt + top_half, esz | sign);
+        read_vec_element(s, tcg_op0, a->rn, elt, esz + 1);
+        if (sub) {
+            tcg_gen_sub_i64(tcg_op0, tcg_op0, tcg_op1);
+        } else {
+            tcg_gen_add_i64(tcg_op0, tcg_op0, tcg_op1);
+        }
+        write_vec_element(s, tcg_op0, a->rd, elt, esz + 1);
+    }
+    clear_vec_high(s, 1, a->rd);
+    return true;
+}
+
+TRANS(SADDW, do_addsub_wide, a, MO_SIGN, false)
+TRANS(UADDW, do_addsub_wide, a, 0, false)
+TRANS(SSUBW, do_addsub_wide, a, MO_SIGN, true)
+TRANS(USUBW, do_addsub_wide, a, 0, true)
+
 /*
  * Advanced SIMD scalar/vector x indexed element
  */
@@ -10790,37 +10831,6 @@ static void gen_neon_addl(int size, bool is_sub, TCGv_i64 tcg_res,
     genfn(tcg_res, tcg_op1, tcg_op2);
 }
 
-static void handle_3rd_wide(DisasContext *s, int is_q, int is_u, int size,
-                            int opcode, int rd, int rn, int rm)
-{
-    TCGv_i64 tcg_res[2];
-    int part = is_q ? 2 : 0;
-    int pass;
-
-    for (pass = 0; pass < 2; pass++) {
-        TCGv_i64 tcg_op1 = tcg_temp_new_i64();
-        TCGv_i32 tcg_op2 = tcg_temp_new_i32();
-        TCGv_i64 tcg_op2_wide = tcg_temp_new_i64();
-        static NeonGenWidenFn * const widenfns[3][2] = {
-            { gen_helper_neon_widen_s8, gen_helper_neon_widen_u8 },
-            { gen_helper_neon_widen_s16, gen_helper_neon_widen_u16 },
-            { tcg_gen_ext_i32_i64, tcg_gen_extu_i32_i64 },
-        };
-        NeonGenWidenFn *widenfn = widenfns[size][is_u];
-
-        read_vec_element(s, tcg_op1, rn, pass, MO_64);
-        read_vec_element_i32(s, tcg_op2, rm, part + pass, MO_32);
-        widenfn(tcg_op2_wide, tcg_op2);
-        tcg_res[pass] = tcg_temp_new_i64();
-        gen_neon_addl(size, (opcode == 3),
-                      tcg_res[pass], tcg_op1, tcg_op2_wide);
-    }
-
-    for (pass = 0; pass < 2; pass++) {
-        write_vec_element(s, tcg_res[pass], rd, pass, MO_64);
-    }
-}
-
 static void do_narrow_round_high_u32(TCGv_i32 res, TCGv_i64 in)
 {
     tcg_gen_addi_i64(in, in, 1U << 31);
@@ -10889,18 +10899,6 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
     int rd = extract32(insn, 0, 5);
 
     switch (opcode) {
-    case 1: /* SADDW, SADDW2, UADDW, UADDW2 */
-    case 3: /* SSUBW, SSUBW2, USUBW, USUBW2 */
-        /* 64 x 128 -> 128 */
-        if (size == 3) {
-            unallocated_encoding(s);
-            return;
-        }
-        if (!fp_access_check(s)) {
-            return;
-        }
-        handle_3rd_wide(s, is_q, is_u, size, opcode, rd, rn, rm);
-        break;
     case 4: /* ADDHN, ADDHN2, RADDHN, RADDHN2 */
     case 6: /* SUBHN, SUBHN2, RSUBHN, RSUBHN2 */
         /* 128 x 128 -> 64 */
@@ -10948,7 +10946,9 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
         return;
     default:
     case 0: /* SADDL, SADDL2, UADDL, UADDL2 */
+    case 1: /* SADDW, SADDW2, UADDW, UADDW2 */
     case 2: /* SSUBL, SSUBL2, USUBL, USUBL2 */
+    case 3: /* SSUBW, SSUBW2, USUBW, USUBW2 */
     case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
     case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
     case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index cf69e7e1be..32e2f3a0d5 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -993,6 +993,11 @@ SQDMLAL_v       0.00 1110 101 ..... 10010 0 ..... ..... @qrrr_s
 SQDMLSL_v       0.00 1110 011 ..... 10110 0 ..... ..... @qrrr_h
 SQDMLSL_v       0.00 1110 101 ..... 10110 0 ..... ..... @qrrr_s
 
+SADDW           0.00 1110 ..1 ..... 00010 0 ..... ..... @qrrr_e
+UADDW           0.10 1110 ..1 ..... 00010 0 ..... ..... @qrrr_e
+SSUBW           0.00 1110 ..1 ..... 00110 0 ..... ..... @qrrr_e
+USUBW           0.10 1110 ..1 ..... 00110 0 ..... ..... @qrrr_e
+
 ### Advanced SIMD scalar x indexed element
 
 FMUL_si         0101 1111 00 .. .... 1001 . 0 ..... .....   @rrx_h
-- 
2.43.0

On Tue, 9 Jul 2024 at 01:07, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
> ---
>  target/arm/tcg/translate-a64.c | 86 +++++++++++++++++-----------------
>  target/arm/tcg/a64.decode      |  5 ++
>  2 files changed, 48 insertions(+), 43 deletions(-)

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

thanks
-- PMM