Introduce the PINTEH opcode (Parallel Interleave Even Halfword).

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
---
 target/mips/tx79.decode      |  1 +
 target/mips/tx79_translate.c | 45 ++++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)

diff --git a/target/mips/tx79.decode b/target/mips/tx79.decode
index 653910371d2..fbd2be569ad 100644
--- a/target/mips/tx79.decode
+++ b/target/mips/tx79.decode
@@ -57,6 +57,7 @@ PXOR            011100 ..... ..... ..... 10011 001001   @rs_rt_rd
 
 # MMI3
 
+PINTEH          011100 ..... ..... ..... 01010 101001   @rs_rt_rd
 PCPYUD          011100 ..... ..... ..... 01110 101001   @rs_rt_rd
 POR             011100 ..... ..... ..... 10010 101001   @rs_rt_rd
 PNOR            011100 ..... ..... ..... 10011 101001   @rs_rt_rd
diff --git a/target/mips/tx79_translate.c b/target/mips/tx79_translate.c
index ac75d95b82b..47d84c465a2 100644
--- a/target/mips/tx79_translate.c
+++ b/target/mips/tx79_translate.c
@@ -638,3 +638,48 @@ static bool trans_PCPYUD(DisasContext *s, arg_rtype *a)
 
     return true;
 }
+
+/* Parallel Interleave Even Halfword */
+static bool trans_PINTEH(DisasContext *ctx, arg_rtype *a)
+{
+    TCGv_i64 ax, bx;
+
+    if (a->rd == 0) {
+        /* nop */
+        return true;
+    }
+
+    if (unlikely(a->rs == 0 && a->rt == 0)) {
+        tcg_gen_movi_i64(cpu_gpr[a->rd], 0);
+        tcg_gen_movi_i64(cpu_gpr_hi[a->rd], 0);
+        return true;
+    }
+
+    ax = tcg_temp_new_i64();
+    bx = tcg_temp_new_i64();
+
+    /* Lower halve */
+    gen_load_gpr(ax, a->rs);
+    gen_load_gpr(bx, a->rt);
+    if (a->rd != a->rt) {
+        tcg_gen_mov_i64(cpu_gpr[a->rd], bx);
+    }
+    tcg_gen_deposit_i64(cpu_gpr[a->rd], cpu_gpr[a->rd], ax, 16, 16);
+    tcg_gen_shri_i64(ax, ax, 32);
+    tcg_gen_deposit_i64(cpu_gpr[a->rd], cpu_gpr[a->rd], ax, 48, 16);
+
+    /* Upper halve */
+    gen_load_gpr_hi(ax, a->rs);
+    gen_load_gpr_hi(bx, a->rt);
+    if (a->rd != a->rt) {
+        tcg_gen_mov_i64(cpu_gpr_hi[a->rd], bx);
+    }
+    tcg_gen_deposit_i64(cpu_gpr_hi[a->rd], cpu_gpr_hi[a->rd], ax, 16, 16);
+    tcg_gen_shri_i64(ax, ax, 32);
+    tcg_gen_deposit_i64(cpu_gpr_hi[a->rd], cpu_gpr_hi[a->rd], ax, 48, 16);
+
+    tcg_temp_free(bx);
+    tcg_temp_free(ax);
+
+    return true;
+}
-- 
2.26.2

On 2/14/21 9:58 AM, Philippe Mathieu-Daudé wrote:
> +    /* Lower halve */
> +    gen_load_gpr(ax, a->rs);
> +    gen_load_gpr(bx, a->rt);
> +    if (a->rd != a->rt) {
> +        tcg_gen_mov_i64(cpu_gpr[a->rd], bx);
> +    }
> +    tcg_gen_deposit_i64(cpu_gpr[a->rd], cpu_gpr[a->rd], ax, 16, 16);
> +    tcg_gen_shri_i64(ax, ax, 32);
> +    tcg_gen_deposit_i64(cpu_gpr[a->rd], cpu_gpr[a->rd], ax, 48, 16);

  mask = tcg_constant_i64(0x0000ffff0000ffffull);
  tcg_gen_shli_i64(x, a, 8);
  tcg_gen_and_i64(x, x, mask);
  tcg_gen_and_i64(y, b, mask);
  tcg_gen_or_i64(d, x, y);

and then you can use trans_parallel_logic.


r~