target/loongarch: Implement vinsgr2vr vpickve2gr vreplgr2vr

This patch includes:
- VINSGR2VR.{B/H/W/D};
- VPICKVE2GR.{B/H/W/D}[U];
- VREPLGR2VR.{B/H/W/D}.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20230504122810.4094787-39-gaosong@loongson.cn>

3 files changed, 173 insertions, 0 deletions

diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index ecf0c7b577..7255a2aa4f 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -818,6 +818,21 @@ static void output_vvvv(DisasContext *ctx, arg_vvvv *a, const char *mnemonic)
     output(ctx, mnemonic, "v%d, v%d, v%d, v%d", a->vd, a->vj, a->vk, a->va);
 }
 
+static void output_vr_i(DisasContext *ctx, arg_vr_i *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, r%d, 0x%x", a->vd, a->rj, a->imm);
+}
+
+static void output_rv_i(DisasContext *ctx, arg_rv_i *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "r%d, v%d, 0x%x", a->rd, a->vj,  a->imm);
+}
+
+static void output_vr(DisasContext *ctx, arg_vr *a, const char *mnemonic)
+{
+    output(ctx, mnemonic, "v%d, r%d", a->vd, a->rj);
+}
+
 INSN_LSX(vadd_b,           vvv)
 INSN_LSX(vadd_h,           vvv)
 INSN_LSX(vadd_w,           vvv)
@@ -1561,3 +1576,21 @@ INSN_LSX(vsetallnez_b,     cv)
 INSN_LSX(vsetallnez_h,     cv)
 INSN_LSX(vsetallnez_w,     cv)
 INSN_LSX(vsetallnez_d,     cv)
+
+INSN_LSX(vinsgr2vr_b,      vr_i)
+INSN_LSX(vinsgr2vr_h,      vr_i)
+INSN_LSX(vinsgr2vr_w,      vr_i)
+INSN_LSX(vinsgr2vr_d,      vr_i)
+INSN_LSX(vpickve2gr_b,     rv_i)
+INSN_LSX(vpickve2gr_h,     rv_i)
+INSN_LSX(vpickve2gr_w,     rv_i)
+INSN_LSX(vpickve2gr_d,     rv_i)
+INSN_LSX(vpickve2gr_bu,    rv_i)
+INSN_LSX(vpickve2gr_hu,    rv_i)
+INSN_LSX(vpickve2gr_wu,    rv_i)
+INSN_LSX(vpickve2gr_du,    rv_i)
+
+INSN_LSX(vreplgr2vr_b,     vr)
+INSN_LSX(vreplgr2vr_h,     vr)
+INSN_LSX(vreplgr2vr_w,     vr)
+INSN_LSX(vreplgr2vr_d,     vr)
diff --git a/target/loongarch/insn_trans/trans_lsx.c.inc b/target/loongarch/insn_trans/trans_lsx.c.inc
index 964c3c47bf..e722b79bea 100644
--- a/target/loongarch/insn_trans/trans_lsx.c.inc
+++ b/target/loongarch/insn_trans/trans_lsx.c.inc
@@ -3823,3 +3823,113 @@ TRANS(vsetallnez_b, gen_cv, gen_helper_vsetallnez_b)
 TRANS(vsetallnez_h, gen_cv, gen_helper_vsetallnez_h)
 TRANS(vsetallnez_w, gen_cv, gen_helper_vsetallnez_w)
 TRANS(vsetallnez_d, gen_cv, gen_helper_vsetallnez_d)
+
+static bool trans_vinsgr2vr_b(DisasContext *ctx, arg_vr_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_st8_i64(cpu_gpr[a->rj], cpu_env,
+                    offsetof(CPULoongArchState, fpr[a->vd].vreg.B(a->imm)));
+    return true;
+}
+
+static bool trans_vinsgr2vr_h(DisasContext *ctx, arg_vr_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_st16_i64(cpu_gpr[a->rj], cpu_env,
+                    offsetof(CPULoongArchState, fpr[a->vd].vreg.H(a->imm)));
+    return true;
+}
+
+static bool trans_vinsgr2vr_w(DisasContext *ctx, arg_vr_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_st32_i64(cpu_gpr[a->rj], cpu_env,
+                     offsetof(CPULoongArchState, fpr[a->vd].vreg.W(a->imm)));
+    return true;
+}
+
+static bool trans_vinsgr2vr_d(DisasContext *ctx, arg_vr_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_st_i64(cpu_gpr[a->rj], cpu_env,
+                   offsetof(CPULoongArchState, fpr[a->vd].vreg.D(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_b(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld8s_i64(cpu_gpr[a->rd], cpu_env,
+                     offsetof(CPULoongArchState, fpr[a->vj].vreg.B(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_h(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld16s_i64(cpu_gpr[a->rd], cpu_env,
+                      offsetof(CPULoongArchState, fpr[a->vj].vreg.H(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_w(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld32s_i64(cpu_gpr[a->rd], cpu_env,
+                      offsetof(CPULoongArchState, fpr[a->vj].vreg.W(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_d(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld_i64(cpu_gpr[a->rd], cpu_env,
+                   offsetof(CPULoongArchState, fpr[a->vj].vreg.D(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_bu(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld8u_i64(cpu_gpr[a->rd], cpu_env,
+                     offsetof(CPULoongArchState, fpr[a->vj].vreg.B(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_hu(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld16u_i64(cpu_gpr[a->rd], cpu_env,
+                      offsetof(CPULoongArchState, fpr[a->vj].vreg.H(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_wu(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld32u_i64(cpu_gpr[a->rd], cpu_env,
+                      offsetof(CPULoongArchState, fpr[a->vj].vreg.W(a->imm)));
+    return true;
+}
+
+static bool trans_vpickve2gr_du(DisasContext *ctx, arg_rv_i *a)
+{
+    CHECK_SXE;
+    tcg_gen_ld_i64(cpu_gpr[a->rd], cpu_env,
+                   offsetof(CPULoongArchState, fpr[a->vj].vreg.D(a->imm)));
+    return true;
+}
+
+static bool gvec_dup(DisasContext *ctx, arg_vr *a, MemOp mop)
+{
+    CHECK_SXE;
+
+    tcg_gen_gvec_dup_i64(mop, vec_full_offset(a->vd),
+                         16, ctx->vl/8, cpu_gpr[a->rj]);
+    return true;
+}
+
+TRANS(vreplgr2vr_b, gvec_dup, MO_8)
+TRANS(vreplgr2vr_h, gvec_dup, MO_16)
+TRANS(vreplgr2vr_w, gvec_dup, MO_32)
+TRANS(vreplgr2vr_d, gvec_dup, MO_64)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index d8feeadc41..d1d255ab82 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -496,6 +496,9 @@ dbcl             0000 00000010 10101 ...............      @i15
 &vv_i         vd vj imm
 &vvvv         vd vj vk va
 &vvv_fcond    vd vj vk fcond
+&vr_i         vd rj imm
+&rv_i         rd vj imm
+&vr           vd rj
 
 #
 # LSX Formats
@@ -512,6 +515,15 @@ dbcl             0000 00000010 10101 ...............      @i15
 @vv_i5           .... ........ ..... imm:s5 vj:5 vd:5    &vv_i
 @vvvv               .... ........ va:5 vk:5 vj:5 vd:5    &vvvv
 @vvv_fcond      .... ........ fcond:5  vk:5 vj:5 vd:5    &vvv_fcond
+@vr_ui4         .... ........ ..... . imm:4 rj:5 vd:5    &vr_i
+@vr_ui3        .... ........ ..... .. imm:3 rj:5 vd:5    &vr_i
+@vr_ui2       .... ........ ..... ... imm:2 rj:5 vd:5    &vr_i
+@vr_ui1      .... ........ ..... .... imm:1 rj:5 vd:5    &vr_i
+@rv_ui4         .... ........ ..... . imm:4 vj:5 rd:5    &rv_i
+@rv_ui3        .... ........ ..... .. imm:3 vj:5 rd:5    &rv_i
+@rv_ui2       .... ........ ..... ... imm:2 vj:5 rd:5    &rv_i
+@rv_ui1      .... ........ ..... .... imm:1 vj:5 rd:5    &rv_i
+@vr               .... ........ ..... ..... rj:5 vd:5    &vr
 
 vadd_b           0111 00000000 10100 ..... ..... .....    @vvv
 vadd_h           0111 00000000 10101 ..... ..... .....    @vvv
@@ -1167,3 +1179,21 @@ vsetallnez_b     0111 00101001 11001 01100 ..... 00 ...   @cv
 vsetallnez_h     0111 00101001 11001 01101 ..... 00 ...   @cv
 vsetallnez_w     0111 00101001 11001 01110 ..... 00 ...   @cv
 vsetallnez_d     0111 00101001 11001 01111 ..... 00 ...   @cv
+
+vinsgr2vr_b      0111 00101110 10111 0 .... ..... .....   @vr_ui4
+vinsgr2vr_h      0111 00101110 10111 10 ... ..... .....   @vr_ui3
+vinsgr2vr_w      0111 00101110 10111 110 .. ..... .....   @vr_ui2
+vinsgr2vr_d      0111 00101110 10111 1110 . ..... .....   @vr_ui1
+vpickve2gr_b     0111 00101110 11111 0 .... ..... .....   @rv_ui4
+vpickve2gr_h     0111 00101110 11111 10 ... ..... .....   @rv_ui3
+vpickve2gr_w     0111 00101110 11111 110 .. ..... .....   @rv_ui2
+vpickve2gr_d     0111 00101110 11111 1110 . ..... .....   @rv_ui1
+vpickve2gr_bu    0111 00101111 00111 0 .... ..... .....   @rv_ui4
+vpickve2gr_hu    0111 00101111 00111 10 ... ..... .....   @rv_ui3
+vpickve2gr_wu    0111 00101111 00111 110 .. ..... .....   @rv_ui2
+vpickve2gr_du    0111 00101111 00111 1110 . ..... .....   @rv_ui1
+
+vreplgr2vr_b     0111 00101001 11110 00000 ..... .....    @vr
+vreplgr2vr_h     0111 00101001 11110 00001 ..... .....    @vr
+vreplgr2vr_w     0111 00101001 11110 00010 ..... .....    @vr
+vreplgr2vr_d     0111 00101001 11110 00011 ..... .....    @vr