target/riscv: vector integer merge and move instructions

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20200701152549.1218-24-zhiwei_liu@c-sky.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

4 files changed, 225 insertions, 0 deletions

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 1249ee2..9851086 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -675,3 +675,20 @@ DEF_HELPER_6(vwmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vwmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vwmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vwmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vmerge_vvm_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmerge_vvm_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmerge_vvm_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmerge_vvm_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmerge_vxm_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmerge_vxm_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmerge_vxm_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmerge_vxm_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_4(vmv_v_v_b, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vmv_v_v_h, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vmv_v_v_w, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vmv_v_v_d, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vmv_v_x_b, void, ptr, i64, env, i32)
+DEF_HELPER_4(vmv_v_x_h, void, ptr, i64, env, i32)
+DEF_HELPER_4(vmv_v_x_w, void, ptr, i64, env, i32)
+DEF_HELPER_4(vmv_v_x_d, void, ptr, i64, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 843c15f..238aa01 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -71,6 +71,7 @@
 @r_nfvm  ... ... vm:1 ..... ..... ... ..... ....... &rnfvm %nf %rs2 %rs1 %rd
 @r_vm    ...... vm:1 ..... ..... ... ..... ....... &rmrr %rs2 %rs1 %rd
 @r_vm_1  ...... . ..... ..... ... ..... .......    &rmrr vm=1 %rs2 %rs1 %rd
+@r_vm_0  ...... . ..... ..... ... ..... .......    &rmrr vm=0 %rs2 %rs1 %rd
 @r_wdvm  ..... wd:1 vm:1 ..... ..... ... ..... ....... &rwdvm %rs2 %rs1 %rd
 @r2_zimm . zimm:11  ..... ... ..... ....... %rs1 %rd
 
@@ -402,6 +403,12 @@ vwmacc_vx       111101 . ..... ..... 110 ..... 1010111 @r_vm
 vwmaccsu_vv     111110 . ..... ..... 010 ..... 1010111 @r_vm
 vwmaccsu_vx     111110 . ..... ..... 110 ..... 1010111 @r_vm
 vwmaccus_vx     111111 . ..... ..... 110 ..... 1010111 @r_vm
+vmv_v_v         010111 1 00000 ..... 000 ..... 1010111 @r2
+vmv_v_x         010111 1 00000 ..... 100 ..... 1010111 @r2
+vmv_v_i         010111 1 00000 ..... 011 ..... 1010111 @r2
+vmerge_vvm      010111 0 ..... ..... 000 ..... 1010111 @r_vm_0
+vmerge_vxm      010111 0 ..... ..... 100 ..... 1010111 @r_vm_0
+vmerge_vim      010111 0 ..... ..... 011 ..... 1010111 @r_vm_0
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 24e43c6..f9532eb 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1618,3 +1618,116 @@ GEN_OPIVX_WIDEN_TRANS(vwmaccu_vx)
 GEN_OPIVX_WIDEN_TRANS(vwmacc_vx)
 GEN_OPIVX_WIDEN_TRANS(vwmaccsu_vx)
 GEN_OPIVX_WIDEN_TRANS(vwmaccus_vx)
+
+/* Vector Integer Merge and Move Instructions */
+static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
+{
+    if (vext_check_isa_ill(s) &&
+        vext_check_reg(s, a->rd, false) &&
+        vext_check_reg(s, a->rs1, false)) {
+
+        if (s->vl_eq_vlmax) {
+            tcg_gen_gvec_mov(s->sew, vreg_ofs(s, a->rd),
+                             vreg_ofs(s, a->rs1),
+                             MAXSZ(s), MAXSZ(s));
+        } else {
+            uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+            static gen_helper_gvec_2_ptr * const fns[4] = {
+                gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h,
+                gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d,
+            };
+            TCGLabel *over = gen_new_label();
+            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+            tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
+                               cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
+            gen_set_label(over);
+        }
+        return true;
+    }
+    return false;
+}
+
+typedef void gen_helper_vmv_vx(TCGv_ptr, TCGv_i64, TCGv_env, TCGv_i32);
+static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
+{
+    if (vext_check_isa_ill(s) &&
+        vext_check_reg(s, a->rd, false)) {
+
+        TCGv s1;
+        TCGLabel *over = gen_new_label();
+        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+        s1 = tcg_temp_new();
+        gen_get_gpr(s1, a->rs1);
+
+        if (s->vl_eq_vlmax) {
+            tcg_gen_gvec_dup_tl(s->sew, vreg_ofs(s, a->rd),
+                                MAXSZ(s), MAXSZ(s), s1);
+        } else {
+            TCGv_i32 desc ;
+            TCGv_i64 s1_i64 = tcg_temp_new_i64();
+            TCGv_ptr dest = tcg_temp_new_ptr();
+            uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+            static gen_helper_vmv_vx * const fns[4] = {
+                gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
+                gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
+            };
+
+            tcg_gen_ext_tl_i64(s1_i64, s1);
+            desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+            tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd));
+            fns[s->sew](dest, s1_i64, cpu_env, desc);
+
+            tcg_temp_free_ptr(dest);
+            tcg_temp_free_i32(desc);
+            tcg_temp_free_i64(s1_i64);
+        }
+
+        tcg_temp_free(s1);
+        gen_set_label(over);
+        return true;
+    }
+    return false;
+}
+
+static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
+{
+    if (vext_check_isa_ill(s) &&
+        vext_check_reg(s, a->rd, false)) {
+
+        int64_t simm = sextract64(a->rs1, 0, 5);
+        if (s->vl_eq_vlmax) {
+            tcg_gen_gvec_dup_imm(s->sew, vreg_ofs(s, a->rd),
+                                 MAXSZ(s), MAXSZ(s), simm);
+        } else {
+            TCGv_i32 desc;
+            TCGv_i64 s1;
+            TCGv_ptr dest;
+            uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+            static gen_helper_vmv_vx * const fns[4] = {
+                gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
+                gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
+            };
+            TCGLabel *over = gen_new_label();
+            tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+            s1 = tcg_const_i64(simm);
+            dest = tcg_temp_new_ptr();
+            desc = tcg_const_i32(simd_desc(0, s->vlen / 8, data));
+            tcg_gen_addi_ptr(dest, cpu_env, vreg_ofs(s, a->rd));
+            fns[s->sew](dest, s1, cpu_env, desc);
+
+            tcg_temp_free_ptr(dest);
+            tcg_temp_free_i32(desc);
+            tcg_temp_free_i64(s1);
+            gen_set_label(over);
+        }
+        return true;
+    }
+    return false;
+}
+
+GEN_OPIVV_TRANS(vmerge_vvm, opivv_vadc_check)
+GEN_OPIVX_TRANS(vmerge_vxm, opivx_vadc_check)
+GEN_OPIVI_TRANS(vmerge_vim, 0, vmerge_vxm, opivx_vadc_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 9dd2d57..92d90d0 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2024,3 +2024,91 @@ GEN_VEXT_VX(vwmaccsu_vx_w, 4, 8, clearq)
 GEN_VEXT_VX(vwmaccus_vx_b, 1, 2, clearh)
 GEN_VEXT_VX(vwmaccus_vx_h, 2, 4, clearl)
 GEN_VEXT_VX(vwmaccus_vx_w, 4, 8, clearq)
+
+/* Vector Integer Merge and Move Instructions */
+#define GEN_VEXT_VMV_VV(NAME, ETYPE, H, CLEAR_FN)                    \
+void HELPER(NAME)(void *vd, void *vs1, CPURISCVState *env,           \
+                  uint32_t desc)                                     \
+{                                                                    \
+    uint32_t vl = env->vl;                                           \
+    uint32_t esz = sizeof(ETYPE);                                    \
+    uint32_t vlmax = vext_maxsz(desc) / esz;                         \
+    uint32_t i;                                                      \
+                                                                     \
+    for (i = 0; i < vl; i++) {                                       \
+        ETYPE s1 = *((ETYPE *)vs1 + H(i));                           \
+        *((ETYPE *)vd + H(i)) = s1;                                  \
+    }                                                                \
+    CLEAR_FN(vd, vl, vl * esz, vlmax * esz);                         \
+}
+
+GEN_VEXT_VMV_VV(vmv_v_v_b, int8_t,  H1, clearb)
+GEN_VEXT_VMV_VV(vmv_v_v_h, int16_t, H2, clearh)
+GEN_VEXT_VMV_VV(vmv_v_v_w, int32_t, H4, clearl)
+GEN_VEXT_VMV_VV(vmv_v_v_d, int64_t, H8, clearq)
+
+#define GEN_VEXT_VMV_VX(NAME, ETYPE, H, CLEAR_FN)                    \
+void HELPER(NAME)(void *vd, uint64_t s1, CPURISCVState *env,         \
+                  uint32_t desc)                                     \
+{                                                                    \
+    uint32_t vl = env->vl;                                           \
+    uint32_t esz = sizeof(ETYPE);                                    \
+    uint32_t vlmax = vext_maxsz(desc) / esz;                         \
+    uint32_t i;                                                      \
+                                                                     \
+    for (i = 0; i < vl; i++) {                                       \
+        *((ETYPE *)vd + H(i)) = (ETYPE)s1;                           \
+    }                                                                \
+    CLEAR_FN(vd, vl, vl * esz, vlmax * esz);                         \
+}
+
+GEN_VEXT_VMV_VX(vmv_v_x_b, int8_t,  H1, clearb)
+GEN_VEXT_VMV_VX(vmv_v_x_h, int16_t, H2, clearh)
+GEN_VEXT_VMV_VX(vmv_v_x_w, int32_t, H4, clearl)
+GEN_VEXT_VMV_VX(vmv_v_x_d, int64_t, H8, clearq)
+
+#define GEN_VEXT_VMERGE_VV(NAME, ETYPE, H, CLEAR_FN)                 \
+void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,          \
+                  CPURISCVState *env, uint32_t desc)                 \
+{                                                                    \
+    uint32_t mlen = vext_mlen(desc);                                 \
+    uint32_t vl = env->vl;                                           \
+    uint32_t esz = sizeof(ETYPE);                                    \
+    uint32_t vlmax = vext_maxsz(desc) / esz;                         \
+    uint32_t i;                                                      \
+                                                                     \
+    for (i = 0; i < vl; i++) {                                       \
+        ETYPE *vt = (!vext_elem_mask(v0, mlen, i) ? vs2 : vs1);      \
+        *((ETYPE *)vd + H(i)) = *(vt + H(i));                        \
+    }                                                                \
+    CLEAR_FN(vd, vl, vl * esz, vlmax * esz);                         \
+}
+
+GEN_VEXT_VMERGE_VV(vmerge_vvm_b, int8_t,  H1, clearb)
+GEN_VEXT_VMERGE_VV(vmerge_vvm_h, int16_t, H2, clearh)
+GEN_VEXT_VMERGE_VV(vmerge_vvm_w, int32_t, H4, clearl)
+GEN_VEXT_VMERGE_VV(vmerge_vvm_d, int64_t, H8, clearq)
+
+#define GEN_VEXT_VMERGE_VX(NAME, ETYPE, H, CLEAR_FN)                 \
+void HELPER(NAME)(void *vd, void *v0, target_ulong s1,               \
+                  void *vs2, CPURISCVState *env, uint32_t desc)      \
+{                                                                    \
+    uint32_t mlen = vext_mlen(desc);                                 \
+    uint32_t vl = env->vl;                                           \
+    uint32_t esz = sizeof(ETYPE);                                    \
+    uint32_t vlmax = vext_maxsz(desc) / esz;                         \
+    uint32_t i;                                                      \
+                                                                     \
+    for (i = 0; i < vl; i++) {                                       \
+        ETYPE s2 = *((ETYPE *)vs2 + H(i));                           \
+        ETYPE d = (!vext_elem_mask(v0, mlen, i) ? s2 :               \
+                   (ETYPE)(target_long)s1);                          \
+        *((ETYPE *)vd + H(i)) = d;                                   \
+    }                                                                \
+    CLEAR_FN(vd, vl, vl * esz, vlmax * esz);                         \
+}
+
+GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t,  H1, clearb)
+GEN_VEXT_VMERGE_VX(vmerge_vxm_h, int16_t, H2, clearh)
+GEN_VEXT_VMERGE_VX(vmerge_vxm_w, int32_t, H4, clearl)
+GEN_VEXT_VMERGE_VX(vmerge_vxm_d, int64_t, H8, clearq)