[Qemu-devel] [PATCH 6/8] target-arm: A64: Add integer ops from SIMD 3-same group

[Peter Maydell]

Add some of the integer operations in the SIMD 3-same group:
specifically, the comparisons, addition and subtraction.

Signed-off-by: Peter Maydell <address@hidden>
---
 target-arm/translate-a64.c | 141 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 140 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 82f8e8e..893c05b 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -6009,7 +6009,146 @@ static void disas_simd_3same_float(DisasContext *s, 
uint32_t insn)
 /* Integer op subgroup of C3.6.16. */
 static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int is_q = extract32(insn, 30, 1);
+    int u = extract32(insn, 29, 1);
+    int size = extract32(insn, 22, 2);
+    int opcode = extract32(insn, 11, 5);
+    int rm = extract32(insn, 16, 5);
+    int rn = extract32(insn, 5, 5);
+    int rd = extract32(insn, 0, 5);
+    int pass;
+
+    switch (opcode) {
+    case 0x13: /* MUL, PMUL */
+        if (u && size != 0) {
+            unallocated_encoding(s);
+            return;
+        }
+        /* fall through */
+    case 0x0: /* SHADD, UHADD */
+    case 0x2: /* SRHADD, URHADD */
+    case 0x4: /* SHSUB, UHSUB */
+    case 0xc: /* SMAX, UMAX */
+    case 0xd: /* SMIN, UMIN */
+    case 0xe: /* SABD, UABD */
+    case 0xf: /* SABA, UABA */
+    case 0x12: /* MLA, MLS */
+        if (size == 3) {
+            unallocated_encoding(s);
+            return;
+        }
+        break;
+    case 0x1: /* SQADD */
+    case 0x5: /* SQSUB */
+    case 0x8: /* SSHL, USHL */
+    case 0x9: /* SQSHL, UQSHL */
+    case 0xa: /* SRSHL, URSHL */
+    case 0xb: /* SQRSHL, UQRSHL */
+        if (size == 3 && !is_q) {
+            unallocated_encoding(s);
+            return;
+        }
+        unsupported_encoding(s, insn);
+        return;
+    default:
+        if (size == 3 && !is_q) {
+            unallocated_encoding(s);
+            return;
+        }
+        break;
+    }
+
+    if (size == 3) {
+        for (pass = 0; pass < (is_q ? 2 : 1); pass++) {
+            TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+            TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+            TCGv_i64 tcg_res = tcg_temp_new_i64();
+
+            read_vec_element(s, tcg_op1, rn, pass, MO_64);
+            read_vec_element(s, tcg_op2, rm, pass, MO_64);
+
+            handle_3same_64(s, opcode, u, tcg_res, tcg_op1, tcg_op2);
+
+            write_vec_element(s, tcg_res, rd, pass, MO_64);
+
+            tcg_temp_free_i64(tcg_res);
+            tcg_temp_free_i64(tcg_op1);
+            tcg_temp_free_i64(tcg_op2);
+        }
+    } else {
+        for (pass = 0; pass < (is_q ? 4 : 2); pass++) {
+            TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+            TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+            TCGv_i32 tcg_res = tcg_temp_new_i32();
+            TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+            typedef void NeonGenFn(TCGv_i32, TCGv_i32, TCGv_i32);
+            NeonGenFn *genfn;
+
+            read_vec_element(s, tcg_tmp, rn, pass, MO_32);
+            tcg_gen_trunc_i64_i32(tcg_op1, tcg_tmp);
+            read_vec_element(s, tcg_tmp, rm, pass, MO_32);
+            tcg_gen_trunc_i64_i32(tcg_op2, tcg_tmp);
+
+            switch (opcode) {
+            case 0x6: /* CMGT, CMHI */
+            {
+                NeonGenFn *ceqtstfns[3][2] = {
+                    { gen_helper_neon_cgt_s8, gen_helper_neon_cgt_u8 },
+                    { gen_helper_neon_cgt_s16, gen_helper_neon_cgt_u16 },
+                    { gen_helper_neon_cgt_s32, gen_helper_neon_cgt_u32 },
+                };
+                genfn = ceqtstfns[size][u];
+                break;
+            }
+            case 0x7: /* CMGE, CMHS */
+            {
+                NeonGenFn *ceqtstfns[3][2] = {
+                    { gen_helper_neon_cge_s8, gen_helper_neon_cge_u8 },
+                    { gen_helper_neon_cge_s16, gen_helper_neon_cge_u16 },
+                    { gen_helper_neon_cge_s32, gen_helper_neon_cge_u32 },
+                };
+                genfn = ceqtstfns[size][u];
+                break;
+            }
+            case 0x10: /* ADD, SUB */
+            {
+                NeonGenFn *addfns[3][2] = {
+                    { gen_helper_neon_add_u8, gen_helper_neon_sub_u8 },
+                    { gen_helper_neon_add_u16, gen_helper_neon_sub_u16 },
+                    { tcg_gen_add_i32, tcg_gen_sub_i32 },
+                };
+                genfn = addfns[size][u];
+                break;
+            }
+            case 0x11: /* CMTST, CMEQ */
+            {
+                NeonGenFn *ceqtstfns[3][2] = {
+                    { gen_helper_neon_tst_u8, gen_helper_neon_ceq_u8 },
+                    { gen_helper_neon_tst_u16, gen_helper_neon_ceq_u16 },
+                    { gen_helper_neon_tst_u32, gen_helper_neon_ceq_u32 },
+                };
+                genfn = ceqtstfns[size][u];
+                break;
+            }
+            default:
+                g_assert_not_reached();
+            }
+
+            genfn(tcg_res, tcg_op1, tcg_op2);
+
+            tcg_gen_extu_i32_i64(tcg_tmp, tcg_res);
+            write_vec_element(s, tcg_tmp, rd, pass, MO_32);
+
+            tcg_temp_free_i32(tcg_res);
+            tcg_temp_free_i32(tcg_op1);
+            tcg_temp_free_i32(tcg_op2);
+            tcg_temp_free_i64(tcg_tmp);
+        }
+    }
+
+    if (!is_q) {
+        clear_vec_high(s, rd);
+    }
 }
 
 /* C3.6.16 AdvSIMD three same
-- 
1.8.5