[v3,3/4] target/mips: implement Octeon-specific arithmetic instructions

Commit Message

Pavel Dovgalyuk June 20, 2022, 12:05 p.m. UTC

This patch implements several Octeon-specific instructions:
- BADDU
- DMUL
- EXTS/EXTS32
- CINS/CINS32
- POP/DPOP
- SEQ/SEQI
- SNE/SNEI

Signed-off-by: Pavel Dovgalyuk <[e-mail]>

--

v3 changes:
   - Fixed length field for EXTS/CINS
     (bug found by Richard Henderson)
v2 changes:
   - Using existing tcg instructions for exts, cins, pop
     (suggested by Richard Henderson)
---
 target/mips/tcg/octeon.decode      |   26 ++++++
 target/mips/tcg/octeon_translate.c |  155 ++++++++++++++++++++++++++++++++++++
 2 files changed, 181 insertions(+)

Comments

Richard Henderson June 20, 2022, 4:06 p.m. UTC | #1

On 6/20/22 05:05, Pavel Dovgalyuk wrote:
> This patch implements several Octeon-specific instructions:
> - BADDU
> - DMUL
> - EXTS/EXTS32
> - CINS/CINS32
> - POP/DPOP
> - SEQ/SEQI
> - SNE/SNEI
> 
> Signed-off-by: Pavel Dovgalyuk<[e-mail]>

Reviewed-by: Richard Henderson <[e-mail]>

r~

Patch

diff --git a/target/mips/tcg/octeon.decode b/target/mips/tcg/octeon.decode
index 8062715578..8929ad088e 100644
--- a/target/mips/tcg/octeon.decode
+++ b/target/mips/tcg/octeon.decode
@@ -13,3 +13,29 @@ 
 
 %bbit_p      28:1 16:5
 BBIT         11 set:1 . 10 rs:5 ..... offset:16 p=%bbit_p
+
+# Arithmetic
+# BADDU rd, rs, rt
+# DMUL rd, rs, rt
+# EXTS rt, rs, p, lenm1
+# EXTS32 rt, rs, p, lenm1
+# CINS rt, rs, p, lenm1
+# CINS32 rt, rs, p, lenm1
+# DPOP rd, rs
+# POP rd, rs
+# SEQ rd, rs, rt
+# SEQI rt, rs, immediate
+# SNE rd, rs, rt
+# SNEI rt, rs, immediate
+
+@r3          ...... rs:5 rt:5 rd:5 ..... ......
+%bitfield_p  0:1 6:5
+@bitfield    ...... rs:5 rt:5 lenm1:5 ..... ..... . p=%bitfield_p
+
+BADDU        011100 ..... ..... ..... 00000 101000 @r3
+DMUL         011100 ..... ..... ..... 00000 000011 @r3
+EXTS         011100 ..... ..... ..... ..... 11101 . @bitfield
+CINS         011100 ..... ..... ..... ..... 11001 . @bitfield
+POP          011100 rs:5 00000 rd:5 00000 10110 dw:1
+SEQNE        011100 rs:5 rt:5 rd:5 00000 10101 ne:1
+SEQNEI       011100 rs:5 rt:5 imm:s10 10111 ne:1
diff --git a/target/mips/tcg/octeon_translate.c b/target/mips/tcg/octeon_translate.c
index 1558f74a8e..6a207d2e7e 100644
--- a/target/mips/tcg/octeon_translate.c
+++ b/target/mips/tcg/octeon_translate.c
@@ -44,3 +44,158 @@  static bool trans_BBIT(DisasContext *ctx, arg_BBIT *a)
     tcg_temp_free(t0);
     return true;
 }
+
+static bool trans_BADDU(DisasContext *ctx, arg_BADDU *a)
+{
+    TCGv t0, t1;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+    gen_load_gpr(t1, a->rt);
+
+    tcg_gen_add_tl(t0, t0, t1);
+    tcg_gen_andi_i64(cpu_gpr[a->rd], t0, 0xff);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+
+    return true;
+}
+
+static bool trans_DMUL(DisasContext *ctx, arg_DMUL *a)
+{
+    TCGv t0, t1;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+    gen_load_gpr(t1, a->rt);
+
+    tcg_gen_mul_i64(cpu_gpr[a->rd], t0, t1);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+
+    return true;
+}
+
+static bool trans_EXTS(DisasContext *ctx, arg_EXTS *a)
+{
+    TCGv t0;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+    tcg_gen_sextract_tl(t0, t0, a->p, a->lenm1 + 1);
+    gen_store_gpr(t0, a->rt);
+    tcg_temp_free(t0);
+
+    return true;
+}
+
+static bool trans_CINS(DisasContext *ctx, arg_CINS *a)
+{
+    TCGv t0;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+    tcg_gen_deposit_z_tl(t0, t0, a->p, a->lenm1 + 1);
+    gen_store_gpr(t0, a->rt);
+    tcg_temp_free(t0);
+
+    return true;
+}
+
+static bool trans_POP(DisasContext *ctx, arg_POP *a)
+{
+    TCGv t0;
+
+    if (a->rd == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+    if (!a->dw) {
+        tcg_gen_andi_i64(t0, t0, 0xffffffff);
+    }
+    tcg_gen_ctpop_tl(t0, t0);
+    gen_store_gpr(t0, a->rd);
+    tcg_temp_free(t0);
+
+    return true;
+}
+
+static bool trans_SEQNE(DisasContext *ctx, arg_SEQNE *a)
+{
+    TCGv t0, t1;
+
+    if (a->rd == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+
+    gen_load_gpr(t0, a->rs);
+    gen_load_gpr(t1, a->rt);
+
+    if (a->ne) {
+        tcg_gen_setcond_tl(TCG_COND_NE, cpu_gpr[a->rd], t1, t0);
+    } else {
+        tcg_gen_setcond_tl(TCG_COND_EQ, cpu_gpr[a->rd], t1, t0);
+    }
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+
+    return true;
+}
+
+static bool trans_SEQNEI(DisasContext *ctx, arg_SEQNEI *a)
+{
+    TCGv t0;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+
+    gen_load_gpr(t0, a->rs);
+
+    /* Sign-extend to 64 bit value */
+    target_ulong imm = a->imm;
+    if (a->ne) {
+        tcg_gen_setcondi_tl(TCG_COND_NE, cpu_gpr[a->rt], t0, imm);
+    } else {
+        tcg_gen_setcondi_tl(TCG_COND_EQ, cpu_gpr[a->rt], t0, imm);
+    }
+
+    tcg_temp_free(t0);
+
+    return true;
+}