[Qemu-devel] [PULL 30/38] target-arm: A64: Add integer ops from SIMD 3-same group

[Peter Maydell <peter.maydell@linaro.org>]

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

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 165 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 164 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index aa53ddc..9e7401c 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -72,6 +72,9 @@ typedef struct AArch64DecodeTable {
     AArch64DecodeFn *disas_fn;
 } AArch64DecodeTable;
 
+/* Function prototype for gen_ functions for calling Neon helpers */
+typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
+
 /* initialize TCG globals.  */
 void a64_translate_init(void)
 {
@@ -787,6 +790,25 @@ static void write_vec_element(DisasContext *s, TCGv_i64 tcg_src, int destidx,
     }
 }
 
+static void write_vec_element_i32(DisasContext *s, TCGv_i32 tcg_src,
+                                  int destidx, int element, TCGMemOp memop)
+{
+    int vect_off = vec_reg_offset(destidx, element, memop & MO_SIZE);
+    switch (memop) {
+    case MO_8:
+        tcg_gen_st8_i32(tcg_src, cpu_env, vect_off);
+        break;
+    case MO_16:
+        tcg_gen_st16_i32(tcg_src, cpu_env, vect_off);
+        break;
+    case MO_32:
+        tcg_gen_st_i32(tcg_src, cpu_env, vect_off);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 /* Clear the high 64 bits of a 128 bit vector (in general non-quad
  * vector ops all need to do this).
  */
@@ -6012,7 +6034,148 @@ 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;
+        }
+        unsupported_encoding(s, insn);
+        return;
+    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;
+    case 0x16: /* SQDMULH, SQRDMULH */
+        if (size == 0 || size == 3) {
+            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();
+            NeonGenTwoOpFn *genfn;
+
+            read_vec_element_i32(s, tcg_op1, rn, pass, MO_32);
+            read_vec_element_i32(s, tcg_op2, rm, pass, MO_32);
+
+            switch (opcode) {
+            case 0x6: /* CMGT, CMHI */
+            {
+                static NeonGenTwoOpFn * const fns[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 = fns[size][u];
+                break;
+            }
+            case 0x7: /* CMGE, CMHS */
+            {
+                static NeonGenTwoOpFn * const fns[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 = fns[size][u];
+                break;
+            }
+            case 0x10: /* ADD, SUB */
+            {
+                static NeonGenTwoOpFn * const fns[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 = fns[size][u];
+                break;
+            }
+            case 0x11: /* CMTST, CMEQ */
+            {
+                static NeonGenTwoOpFn * const fns[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 = fns[size][u];
+                break;
+            }
+            default:
+                g_assert_not_reached();
+            }
+
+            genfn(tcg_res, tcg_op1, tcg_op2);
+
+            write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
+
+            tcg_temp_free_i32(tcg_res);
+            tcg_temp_free_i32(tcg_op1);
+            tcg_temp_free_i32(tcg_op2);
+        }
+    }
+
+    if (!is_q) {
+        clear_vec_high(s, rd);
+    }
 }
 
 /* C3.6.16 AdvSIMD three same
-- 
1.8.5