[RFC PATCH 16/42] target/mips/tx79: Introduce PSUB* opcodes (Parallel Subtract)

[Philippe Mathieu-Daudé]

Introduce the 'Parallel Subtract' opcodes:

 - PSUBB (Parallel Subtract Byte)
 - PSUBH (Parallel Subtract Halfword)
 - PSUBW (Parallel Subtract Word)

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
---
 target/mips/tx79.decode      |  6 ++++
 target/mips/tx79_translate.c | 61 ++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+)

diff --git a/target/mips/tx79.decode b/target/mips/tx79.decode
index 26c80b9bce5..d1c07c7d901 100644
--- a/target/mips/tx79.decode
+++ b/target/mips/tx79.decode
@@ -29,6 +29,12 @@ MTHI1           011100 .....  0000000000 00000 010001   @rs
 MFLO1           011100 0000000000  ..... 00000 010010   @rd
 MTLO1           011100 .....  0000000000 00000 010011   @rs
 
+# MMI0
+
+PSUBW           011100 ..... ..... ..... 00001 001000   @rs_rt_rd
+PSUBH           011100 ..... ..... ..... 00101 001000   @rs_rt_rd
+PSUBB           011100 ..... ..... ..... 01001 001000   @rs_rt_rd
+
 # MMI2
 
 PCPYLD          011100 ..... ..... ..... 01110 001001   @rs_rt_rd
diff --git a/target/mips/tx79_translate.c b/target/mips/tx79_translate.c
index 28d07baaa73..23146f6bfac 100644
--- a/target/mips/tx79_translate.c
+++ b/target/mips/tx79_translate.c
@@ -115,6 +115,67 @@ static bool trans_MTLO1(DisasContext *ctx, arg_rtype *a)
  * PSUBUW  rd, rs, rt        Parallel Subtract with Unsigned saturation Word
  */
 
+static bool trans_parallel_substract(DisasContext *ctx, arg_rtype *a, unsigned 
wlen)
+{
+    TCGv_i64 ax, bx, t0, t1, t2;
+
+    if (a->rd == 0) {
+        /* nop */
+        return true;
+    }
+
+    ax = tcg_temp_new_i64();
+    bx = tcg_temp_new_i64();
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+    t2 = tcg_temp_new_i64();
+
+    /* Lower halve */
+    gen_load_gpr(ax, a->rs);
+    gen_load_gpr(bx, a->rt);
+    for (int i = 0; i < (64 / wlen); i++) {
+        tcg_gen_sextract_i64(t0, ax, wlen * i, wlen);
+        tcg_gen_sextract_i64(t1, bx, wlen * i, wlen);
+        tcg_gen_sub_i64(t2, t0, t1);
+        tcg_gen_deposit_i64(cpu_gpr[a->rd], cpu_gpr[a->rd], t2, wlen * i, 
wlen);
+    }
+    /* Upper halve */
+    gen_load_gpr_hi(ax, a->rs);
+    gen_load_gpr_hi(bx, a->rt);
+    for (int i = 0; i < (64 / wlen); i++) {
+        tcg_gen_sextract_i64(t0, ax, wlen * i, wlen);
+        tcg_gen_sextract_i64(t1, bx, wlen * i, wlen);
+        tcg_gen_sub_i64(t2, t0, t1);
+        tcg_gen_deposit_i64(cpu_gpr_hi[a->rd], cpu_gpr_hi[a->rd], t2, wlen * 
i, wlen);
+    }
+
+    tcg_temp_free(t2);
+    tcg_temp_free(t1);
+    tcg_temp_free(t0);
+    tcg_temp_free(bx);
+    tcg_temp_free(ax);
+
+    return true;
+}
+
+/* Parallel Subtract Byte */
+static bool trans_PSUBB(DisasContext *ctx, arg_rtype *a)
+{
+    return trans_parallel_substract(ctx, a, 8);
+}
+
+/* Parallel Subtract Halfword */
+static bool trans_PSUBH(DisasContext *ctx, arg_rtype *a)
+{
+    return trans_parallel_substract(ctx, a, 16);
+}
+
+/* Parallel Subtract Word */
+static bool trans_PSUBW(DisasContext *ctx, arg_rtype *a)
+{
+    return trans_parallel_substract(ctx, a, 32);
+}
+
 /*
  *     Min/Max (4 instructions)
  *     ------------------------
-- 
2.26.2