[PATCH RESEND v5 16/57] target/loongarch: Implement xvaddi/xvsubi

[Song Gao]

This patch includes:
- XVADDI.{B/H/W/D}U;
- XVSUBI.{B/H/W/D}U.

Signed-off-by: Song Gao <gaosong@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/loongarch/insns.decode               |  9 +++++++
 target/loongarch/disas.c                    | 14 +++++++++++
 target/loongarch/insn_trans/trans_vec.c.inc | 28 +++++++++++++++++++++
 3 files changed, 51 insertions(+)

diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 04bd238995..c48dca70b8 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -1311,6 +1311,15 @@ xvsub_w          0111 01000000 11010 ..... ..... .....   
 @vvv
 xvsub_d          0111 01000000 11011 ..... ..... .....    @vvv
 xvsub_q          0111 01010010 11011 ..... ..... .....    @vvv
 
+xvaddi_bu        0111 01101000 10100 ..... ..... .....    @vv_ui5
+xvaddi_hu        0111 01101000 10101 ..... ..... .....    @vv_ui5
+xvaddi_wu        0111 01101000 10110 ..... ..... .....    @vv_ui5
+xvaddi_du        0111 01101000 10111 ..... ..... .....    @vv_ui5
+xvsubi_bu        0111 01101000 11000 ..... ..... .....    @vv_ui5
+xvsubi_hu        0111 01101000 11001 ..... ..... .....    @vv_ui5
+xvsubi_wu        0111 01101000 11010 ..... ..... .....    @vv_ui5
+xvsubi_du        0111 01101000 11011 ..... ..... .....    @vv_ui5
+
 xvreplgr2vr_b    0111 01101001 11110 00000 ..... .....    @vr
 xvreplgr2vr_h    0111 01101001 11110 00001 ..... .....    @vr
 xvreplgr2vr_w    0111 01101001 11110 00010 ..... .....    @vr
diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index c47f455ed0..20df9c7c99 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1713,6 +1713,11 @@ static void output_vr_x(DisasContext *ctx, arg_vr *a, 
const char *mnemonic)
     output(ctx, mnemonic, "x%d, r%d", a->vd, a->rj);
 }
 
+static void output_vv_i_x(DisasContext *ctx, arg_vv_i *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "x%d, x%d, 0x%x", a->vd, a->vj, a->imm);
+}
+
 INSN_LASX(xvadd_b,           vvv)
 INSN_LASX(xvadd_h,           vvv)
 INSN_LASX(xvadd_w,           vvv)
@@ -1724,6 +1729,15 @@ INSN_LASX(xvsub_w,           vvv)
 INSN_LASX(xvsub_d,           vvv)
 INSN_LASX(xvsub_q,           vvv)
 
+INSN_LASX(xvaddi_bu,         vv_i)
+INSN_LASX(xvaddi_hu,         vv_i)
+INSN_LASX(xvaddi_wu,         vv_i)
+INSN_LASX(xvaddi_du,         vv_i)
+INSN_LASX(xvsubi_bu,         vv_i)
+INSN_LASX(xvsubi_hu,         vv_i)
+INSN_LASX(xvsubi_wu,         vv_i)
+INSN_LASX(xvsubi_du,         vv_i)
+
 INSN_LASX(xvreplgr2vr_b,     vr)
 INSN_LASX(xvreplgr2vr_h,     vr)
 INSN_LASX(xvreplgr2vr_w,     vr)
diff --git a/target/loongarch/insn_trans/trans_vec.c.inc 
b/target/loongarch/insn_trans/trans_vec.c.inc
index a7323e0490..610a492d0c 100644
--- a/target/loongarch/insn_trans/trans_vec.c.inc
+++ b/target/loongarch/insn_trans/trans_vec.c.inc
@@ -266,6 +266,17 @@ static bool gvec_vv_i(DisasContext *ctx, arg_vv_i *a, 
MemOp mop,
     return gvec_vv_i_vl(ctx, a, 16, mop, func);
 }
 
+static bool gvec_xx_i(DisasContext *ctx, arg_vv_i *a, MemOp mop,
+                      void (*func)(unsigned, uint32_t, uint32_t,
+                                   int64_t, uint32_t, uint32_t))
+{
+    if (!check_vec(ctx, 32)) {
+        return true;
+    }
+
+    return gvec_vv_i_vl(ctx,a, 32, mop, func);
+}
+
 static bool gvec_subi_vl(DisasContext *ctx, arg_vv_i *a,
                          uint32_t oprsz, MemOp mop)
 {
@@ -285,6 +296,15 @@ static bool gvec_subi(DisasContext *ctx, arg_vv_i *a, 
MemOp mop)
     return gvec_subi_vl(ctx, a, 16, mop);
 }
 
+static bool gvec_xsubi(DisasContext *ctx, arg_vv_i *a, MemOp mop)
+{
+    if (!check_vec(ctx, 32)) {
+        return true;
+    }
+
+    return gvec_subi_vl(ctx, a, 32, mop);
+}
+
 TRANS(vadd_b, LSX, gvec_vvv, MO_8, tcg_gen_gvec_add)
 TRANS(vadd_h, LSX, gvec_vvv, MO_16, tcg_gen_gvec_add)
 TRANS(vadd_w, LSX, gvec_vvv, MO_32, tcg_gen_gvec_add)
@@ -365,6 +385,14 @@ TRANS(vsubi_bu, LSX, gvec_subi, MO_8)
 TRANS(vsubi_hu, LSX, gvec_subi, MO_16)
 TRANS(vsubi_wu, LSX, gvec_subi, MO_32)
 TRANS(vsubi_du, LSX, gvec_subi, MO_64)
+TRANS(xvaddi_bu, LASX, gvec_xx_i, MO_8, tcg_gen_gvec_addi)
+TRANS(xvaddi_hu, LASX, gvec_xx_i, MO_16, tcg_gen_gvec_addi)
+TRANS(xvaddi_wu, LASX, gvec_xx_i, MO_32, tcg_gen_gvec_addi)
+TRANS(xvaddi_du, LASX, gvec_xx_i, MO_64, tcg_gen_gvec_addi)
+TRANS(xvsubi_bu, LASX, gvec_xsubi, MO_8)
+TRANS(xvsubi_hu, LASX, gvec_xsubi, MO_16)
+TRANS(xvsubi_wu, LASX, gvec_xsubi, MO_32)
+TRANS(xvsubi_du, LASX, gvec_xsubi, MO_64)
 
 TRANS(vneg_b, LSX, gvec_vv, MO_8, tcg_gen_gvec_neg)
 TRANS(vneg_h, LSX, gvec_vv, MO_16, tcg_gen_gvec_neg)
-- 
2.39.1