target/mips/tx79: Introduce PEXTL[BHW] opcodes (Parallel Extend Lower)

Introduce the 'Parallel Extend Lower' opcodes:

 - PEXTLB (Parallel Extend Upper from Byte)
 - PEXTLH (Parallel Extend Upper from Halfword)
 - PEXTLW (Parallel Extend Upper from Word)

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20210309145653.743937-13-f4bug@amsat.org>

2 files changed, 78 insertions, 0 deletions

diff --git a/target/mips/tcg/tx79.decode b/target/mips/tcg/tx79.decode
index ead5f8281e..98f21d33e3 100644
--- a/target/mips/tcg/tx79.decode
+++ b/target/mips/tcg/tx79.decode
@@ -34,6 +34,9 @@ MTLO1           011100 .....  0000000000 00000 010011   @rs
 PSUBW           011100 ..... ..... ..... 00001 001000   @rs_rt_rd
 PSUBH           011100 ..... ..... ..... 00101 001000   @rs_rt_rd
 PSUBB           011100 ..... ..... ..... 01001 001000   @rs_rt_rd
+PEXTLW          011100 ..... ..... ..... 10010 001000   @rs_rt_rd
+PEXTLH          011100 ..... ..... ..... 10110 001000   @rs_rt_rd
+PEXTLB          011100 ..... ..... ..... 11010 001000   @rs_rt_rd
 
 # MMI1
 
diff --git a/target/mips/tcg/tx79_translate.c b/target/mips/tcg/tx79_translate.c
index 68c56affc4..c4656a4c21 100644
--- a/target/mips/tcg/tx79_translate.c
+++ b/target/mips/tcg/tx79_translate.c
@@ -297,6 +297,81 @@ static void gen_pextw(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 a, TCGv_i64 b)
     tcg_gen_deposit_i64(dh, a, b, 0, 32);
 }
 
+static bool trans_PEXTLx(DisasContext *ctx, arg_rtype *a, unsigned wlen)
+{
+    TCGv_i64 ax, bx;
+
+    if (a->rd == 0) {
+        /* nop */
+        return true;
+    }
+
+    ax = tcg_temp_new_i64();
+    bx = tcg_temp_new_i64();
+
+    gen_load_gpr(ax, a->rs);
+    gen_load_gpr(bx, a->rt);
+
+    /* Lower half */
+    for (int i = 0; i < 64 / (2 * wlen); i++) {
+        tcg_gen_deposit_i64(cpu_gpr[a->rd],
+                            cpu_gpr[a->rd], bx, 2 * wlen * i, wlen);
+        tcg_gen_deposit_i64(cpu_gpr[a->rd],
+                            cpu_gpr[a->rd], ax, 2 * wlen * i + wlen, wlen);
+        tcg_gen_shri_i64(bx, bx, wlen);
+        tcg_gen_shri_i64(ax, ax, wlen);
+    }
+    /* Upper half */
+    for (int i = 0; i < 64 / (2 * wlen); i++) {
+        tcg_gen_deposit_i64(cpu_gpr_hi[a->rd],
+                            cpu_gpr_hi[a->rd], bx, 2 * wlen * i, wlen);
+        tcg_gen_deposit_i64(cpu_gpr_hi[a->rd],
+                            cpu_gpr_hi[a->rd], ax, 2 * wlen * i + wlen, wlen);
+        tcg_gen_shri_i64(bx, bx, wlen);
+        tcg_gen_shri_i64(ax, ax, wlen);
+    }
+
+    tcg_temp_free(bx);
+    tcg_temp_free(ax);
+
+    return true;
+}
+
+/* Parallel Extend Lower from Byte */
+static bool trans_PEXTLB(DisasContext *ctx, arg_rtype *a)
+{
+    return trans_PEXTLx(ctx, a, 8);
+}
+
+/* Parallel Extend Lower from Halfword */
+static bool trans_PEXTLH(DisasContext *ctx, arg_rtype *a)
+{
+    return trans_PEXTLx(ctx, a, 16);
+}
+
+/* Parallel Extend Lower from Word */
+static bool trans_PEXTLW(DisasContext *ctx, arg_rtype *a)
+{
+    TCGv_i64 ax, bx;
+
+    if (a->rd == 0) {
+        /* nop */
+        return true;
+    }
+
+    ax = tcg_temp_new_i64();
+    bx = tcg_temp_new_i64();
+
+    gen_load_gpr(ax, a->rs);
+    gen_load_gpr(bx, a->rt);
+    gen_pextw(cpu_gpr[a->rd], cpu_gpr_hi[a->rd], ax, bx);
+
+    tcg_temp_free(bx);
+    tcg_temp_free(ax);
+
+    return true;
+}
+
 /* Parallel Extend Upper from Word */
 static bool trans_PEXTUW(DisasContext *ctx, arg_rtype *a)
 {