[RFC PATCH v2 24/44] target/loongarch: Implement vsllwil vextl

[Song Gao]

This patch includes:
- VSLLWIL.{H.B/W.H/D.W};
- VSLLWIL.{HU.BU/WU.HU/DU.WU};
- VEXTL.Q.D, VEXTL.QU.DU.

Signed-off-by: Song Gao <gaosong@loongson.cn>
---
 target/loongarch/disas.c                    |  9 +++++
 target/loongarch/helper.h                   |  9 +++++
 target/loongarch/insn_trans/trans_lsx.c.inc | 21 +++++++++++
 target/loongarch/insns.decode               |  9 +++++
 target/loongarch/lsx_helper.c               | 40 +++++++++++++++++++++
 5 files changed, 88 insertions(+)

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index f7d0fb4441..087cac10ad 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -1139,3 +1139,12 @@ INSN_LSX(vrotri_b,         vv_i)
 INSN_LSX(vrotri_h,         vv_i)
 INSN_LSX(vrotri_w,         vv_i)
 INSN_LSX(vrotri_d,         vv_i)
+
+INSN_LSX(vsllwil_h_b,      vv_i)
+INSN_LSX(vsllwil_w_h,      vv_i)
+INSN_LSX(vsllwil_d_w,      vv_i)
+INSN_LSX(vextl_q_d,        vv)
+INSN_LSX(vsllwil_hu_bu,    vv_i)
+INSN_LSX(vsllwil_wu_hu,    vv_i)
+INSN_LSX(vsllwil_du_wu,    vv_i)
+INSN_LSX(vextl_qu_du,      vv)
diff --git a/target/loongarch/helper.h b/target/loongarch/helper.h
index 1eeb614427..0266b9a4ad 100644
--- a/target/loongarch/helper.h
+++ b/target/loongarch/helper.h
@@ -367,3 +367,12 @@ DEF_HELPER_3(vmskgez_b, void, env, i32, i32)
 DEF_HELPER_3(vmsknz_b, void, env, i32,i32)
 
 DEF_HELPER_FLAGS_4(vnori_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_4(vsllwil_h_b, void, env, i32, i32, i32)
+DEF_HELPER_4(vsllwil_w_h, void, env, i32, i32, i32)
+DEF_HELPER_4(vsllwil_d_w, void, env, i32, i32, i32)
+DEF_HELPER_3(vextl_q_d, void, env, i32, i32)
+DEF_HELPER_4(vsllwil_hu_bu, void, env, i32, i32, i32)
+DEF_HELPER_4(vsllwil_wu_hu, void, env, i32, i32, i32)
+DEF_HELPER_4(vsllwil_du_wu, void, env, i32, i32, i32)
+DEF_HELPER_3(vextl_qu_du, void, env, i32, i32)
diff --git a/target/loongarch/insn_trans/trans_lsx.c.inc 
b/target/loongarch/insn_trans/trans_lsx.c.inc
index 84c8d92ad6..fb40aaf5ad 100644
--- a/target/loongarch/insn_trans/trans_lsx.c.inc
+++ b/target/loongarch/insn_trans/trans_lsx.c.inc
@@ -39,6 +39,18 @@ static bool gen_vv(DisasContext *ctx, arg_vv *a,
     return true;
 }
 
+static bool gen_vv_i(DisasContext *ctx, arg_vv_i *a,
+                     void (*func)(TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32))
+{
+    TCGv_i32 vd = tcg_constant_i32(a->vd);
+    TCGv_i32 vj = tcg_constant_i32(a->vj);
+    TCGv_i32 imm = tcg_constant_i32(a->imm);
+
+    CHECK_SXE;
+    func(cpu_env, vd, vj, imm);
+    return true;
+}
+
 static bool gvec_vvv(DisasContext *ctx, arg_vvv *a, MemOp mop,
                      void (*func)(unsigned, uint32_t, uint32_t,
                                   uint32_t, uint32_t, uint32_t))
@@ -2654,3 +2666,12 @@ TRANS(vrotri_b, gvec_vv_i, MO_8, tcg_gen_gvec_rotri)
 TRANS(vrotri_h, gvec_vv_i, MO_16, tcg_gen_gvec_rotri)
 TRANS(vrotri_w, gvec_vv_i, MO_32, tcg_gen_gvec_rotri)
 TRANS(vrotri_d, gvec_vv_i, MO_64, tcg_gen_gvec_rotri)
+
+TRANS(vsllwil_h_b, gen_vv_i, gen_helper_vsllwil_h_b)
+TRANS(vsllwil_w_h, gen_vv_i, gen_helper_vsllwil_w_h)
+TRANS(vsllwil_d_w, gen_vv_i, gen_helper_vsllwil_d_w)
+TRANS(vextl_q_d, gen_vv, gen_helper_vextl_q_d)
+TRANS(vsllwil_hu_bu, gen_vv_i, gen_helper_vsllwil_hu_bu)
+TRANS(vsllwil_wu_hu, gen_vv_i, gen_helper_vsllwil_wu_hu)
+TRANS(vsllwil_du_wu, gen_vv_i, gen_helper_vsllwil_du_wu)
+TRANS(vextl_qu_du, gen_vv, gen_helper_vextl_qu_du)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index 7c0b0c4ac8..23dd338026 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -839,3 +839,12 @@ vrotri_b         0111 00101010 00000 01 ... ..... .....   
@vv_ui3
 vrotri_h         0111 00101010 00000 1 .... ..... .....   @vv_ui4
 vrotri_w         0111 00101010 00001 ..... ..... .....    @vv_ui5
 vrotri_d         0111 00101010 0001 ...... ..... .....    @vv_ui6
+
+vsllwil_h_b      0111 00110000 10000 01 ... ..... .....   @vv_ui3
+vsllwil_w_h      0111 00110000 10000 1 .... ..... .....   @vv_ui4
+vsllwil_d_w      0111 00110000 10001 ..... ..... .....    @vv_ui5
+vextl_q_d        0111 00110000 10010 00000 ..... .....    @vv
+vsllwil_hu_bu    0111 00110000 11000 01 ... ..... .....   @vv_ui3
+vsllwil_wu_hu    0111 00110000 11000 1 .... ..... .....   @vv_ui4
+vsllwil_du_wu    0111 00110000 11001 ..... ..... .....    @vv_ui5
+vextl_qu_du      0111 00110000 11010 00000 ..... .....    @vv
diff --git a/target/loongarch/lsx_helper.c b/target/loongarch/lsx_helper.c
index 198ab3088b..72efdd5a74 100644
--- a/target/loongarch/lsx_helper.c
+++ b/target/loongarch/lsx_helper.c
@@ -1031,3 +1031,43 @@ void HELPER(vnori_b)(void *vd, void *vj, uint64_t imm, 
uint32_t v)
         Vd->B(i) = ~(Vj->B(i) | (uint8_t)imm);
     }
 }
+
+#define VSLLWIL(NAME, BIT, T1, T2, E1, E2)                \
+void HELPER(NAME)(CPULoongArchState *env,                 \
+                  uint32_t vd, uint32_t vj, uint32_t imm) \
+{                                                         \
+    int i;                                                \
+    VReg temp;                                            \
+    VReg *Vd = &(env->fpr[vd].vreg);                      \
+    VReg *Vj = &(env->fpr[vj].vreg);                      \
+    temp.D(0) = 0;                                        \
+    temp.D(1) = 0;                                        \
+    for (i = 0; i < LSX_LEN/BIT; i++) {                   \
+        temp.E1(i) = (T1)(T2)Vj->E2(i) << (imm % BIT);    \
+    }                                                     \
+    Vd->D(0) = temp.D(0);                                 \
+    Vd->D(1) = temp.D(1);                                 \
+}
+
+void HELPER(vextl_q_d)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    Vd->Q(0) = int128_makes64(Vj->D(0));
+}
+
+void HELPER(vextl_qu_du)(CPULoongArchState *env, uint32_t vd, uint32_t vj)
+{
+    VReg *Vd = &(env->fpr[vd].vreg);
+    VReg *Vj = &(env->fpr[vj].vreg);
+
+    Vd->Q(0) = int128_make64(Vj->D(0));
+}
+
+VSLLWIL(vsllwil_h_b, 16, int16_t, int8_t, H, B)
+VSLLWIL(vsllwil_w_h, 32, int32_t, int16_t, W, H)
+VSLLWIL(vsllwil_d_w, 64, int64_t, int32_t, D, W)
+VSLLWIL(vsllwil_hu_bu, 16, uint16_t, uint8_t, H, B)
+VSLLWIL(vsllwil_wu_hu, 32, uint32_t, uint16_t, W, H)
+VSLLWIL(vsllwil_du_wu, 64, uint64_t, uint32_t, D, W)
-- 
2.31.1