[PATCH v5 05/17] target/riscv: rvb: pack two words into one register

[frank.chang@sifive.com]

From: Kito Cheng <kito.cheng@sifive.com>

Signed-off-by: Kito Cheng <kito.cheng@sifive.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/riscv/insn32-64.decode           |  3 ++
 target/riscv/insn32.decode              |  3 ++
 target/riscv/insn_trans/trans_rvb.c.inc | 30 +++++++++++++++++++
 target/riscv/translate.c                | 40 +++++++++++++++++++++++++
 4 files changed, 76 insertions(+)

diff --git a/target/riscv/insn32-64.decode b/target/riscv/insn32-64.decode
index 89498a9a28a..d28c0bcf2c1 100644
--- a/target/riscv/insn32-64.decode
+++ b/target/riscv/insn32-64.decode
@@ -91,3 +91,6 @@ hsv_d     0110111  .....   ..... 100 00000 1110011 @r2_s
 clzw       0110000 00000 ..... 001 ..... 0011011 @r2
 ctzw       0110000 00001 ..... 001 ..... 0011011 @r2
 cpopw      0110000 00010 ..... 001 ..... 0011011 @r2
+
+packw      0000100 .......... 100 ..... 0111011 @r
+packuw     0100100 .......... 100 ..... 0111011 @r
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index d0b3f109b4e..7f32b8c6d15 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -602,3 +602,6 @@ cpop       011000 000010 ..... 001 ..... 0010011 @r2
 andn       0100000 .......... 111 ..... 0110011 @r
 orn        0100000 .......... 110 ..... 0110011 @r
 xnor       0100000 .......... 100 ..... 0110011 @r
+pack       0000100 .......... 100 ..... 0110011 @r
+packu      0100100 .......... 100 ..... 0110011 @r
+packh      0000100 .......... 111 ..... 0110011 @r
diff --git a/target/riscv/insn_trans/trans_rvb.c.inc b/target/riscv/insn_trans/trans_rvb.c.inc
index 73c4693a263..2d24dafac09 100644
--- a/target/riscv/insn_trans/trans_rvb.c.inc
+++ b/target/riscv/insn_trans/trans_rvb.c.inc
@@ -53,6 +53,24 @@ static bool trans_xnor(DisasContext *ctx, arg_xnor *a)
     return gen_arith(ctx, a, tcg_gen_eqv_tl);
 }
 
+static bool trans_pack(DisasContext *ctx, arg_pack *a)
+{
+    REQUIRE_EXT(ctx, RVB);
+    return gen_arith(ctx, a, gen_pack);
+}
+
+static bool trans_packu(DisasContext *ctx, arg_packu *a)
+{
+    REQUIRE_EXT(ctx, RVB);
+    return gen_arith(ctx, a, gen_packu);
+}
+
+static bool trans_packh(DisasContext *ctx, arg_packh *a)
+{
+    REQUIRE_EXT(ctx, RVB);
+    return gen_arith(ctx, a, gen_packh);
+}
+
 /* RV64-only instructions */
 #ifdef TARGET_RISCV64
 
@@ -74,4 +92,16 @@ static bool trans_cpopw(DisasContext *ctx, arg_cpopw *a)
     return gen_unary(ctx, a, gen_cpopw);
 }
 
+static bool trans_packw(DisasContext *ctx, arg_packw *a)
+{
+    REQUIRE_EXT(ctx, RVB);
+    return gen_arith(ctx, a, gen_packw);
+}
+
+static bool trans_packuw(DisasContext *ctx, arg_packuw *a)
+{
+    REQUIRE_EXT(ctx, RVB);
+    return gen_arith(ctx, a, gen_packuw);
+}
+
 #endif
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index b20a58c63b4..4333207aeff 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -536,6 +536,29 @@ static bool gen_arith_div_uw(DisasContext *ctx, arg_r *a,
 
 #endif
 
+static void gen_pack(TCGv ret, TCGv arg1, TCGv arg2)
+{
+    tcg_gen_deposit_tl(ret, arg1, arg2,
+                       TARGET_LONG_BITS / 2,
+                       TARGET_LONG_BITS / 2);
+}
+
+static void gen_packu(TCGv ret, TCGv arg1, TCGv arg2)
+{
+    TCGv t = tcg_temp_new();
+    tcg_gen_shri_tl(t, arg1, TARGET_LONG_BITS / 2);
+    tcg_gen_deposit_tl(ret, arg2, t, 0, TARGET_LONG_BITS / 2);
+    tcg_temp_free(t);
+}
+
+static void gen_packh(TCGv ret, TCGv arg1, TCGv arg2)
+{
+    TCGv t = tcg_temp_new();
+    tcg_gen_ext8u_tl(t, arg2);
+    tcg_gen_deposit_tl(ret, arg1, t, 8, TARGET_LONG_BITS - 8);
+    tcg_temp_free(t);
+}
+
 #ifdef TARGET_RISCV64
 
 static void gen_ctzw(TCGv ret, TCGv arg1)
@@ -557,6 +580,23 @@ static void gen_cpopw(TCGv ret, TCGv arg1)
     tcg_gen_ctpop_tl(ret, arg1);
 }
 
+static void gen_packw(TCGv ret, TCGv arg1, TCGv arg2)
+{
+    TCGv t = tcg_temp_new();
+    tcg_gen_ext16s_i64(t, arg2);
+    tcg_gen_deposit_i64(ret, arg1, t, 16, 48);
+    tcg_temp_free(t);
+}
+
+static void gen_packuw(TCGv ret, TCGv arg1, TCGv arg2)
+{
+    TCGv t = tcg_temp_new();
+    tcg_gen_shri_i64(t, arg1, 16);
+    tcg_gen_deposit_i64(ret, arg2, t, 0, 16);
+    tcg_gen_ext32s_i64(ret, ret);
+    tcg_temp_free(t);
+}
+
 #endif
 
 static bool gen_arith(DisasContext *ctx, arg_r *a,
-- 
2.17.1