[PATCH v10 54/61] target/riscv: vector element index instruction

[LIU Zhiwei]

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/riscv/helper.h                   |  5 +++++
 target/riscv/insn32.decode              |  2 ++
 target/riscv/insn_trans/trans_rvv.inc.c | 25 +++++++++++++++++++++++++
 target/riscv/vector_helper.c            | 24 ++++++++++++++++++++++++
 4 files changed, 56 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 91db396979..c6695ea7a8 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1114,3 +1114,8 @@ DEF_HELPER_5(viota_m_b, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(viota_m_h, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(viota_m_w, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(viota_m_d, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_4(vid_v_b, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vid_v_h, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vid_v_w, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vid_v_d, void, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 415523573d..6f2e2df7d3 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -70,6 +70,7 @@
 @r2      .......   ..... ..... ... ..... ....... %rs1 %rd
 @r2_nfvm ... ... vm:1 ..... ..... ... ..... ....... &r2nfvm %nf %rs1 %rd
 @r2_vm   ...... vm:1 ..... ..... ... ..... ....... &rmr %rs2 %rd
+@r1_vm   ...... vm:1 ..... ..... ... ..... ....... %rd
 @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
@@ -561,6 +562,7 @@ vmsbf_m         010110 . ..... 00001 010 ..... 1010111 
@r2_vm
 vmsif_m         010110 . ..... 00011 010 ..... 1010111 @r2_vm
 vmsof_m         010110 . ..... 00010 010 ..... 1010111 @r2_vm
 viota_m         010110 . ..... 10000 010 ..... 1010111 @r2_vm
+vid_v           010110 . 00000 10001 010 ..... 1010111 @r1_vm
 
 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 b109732d11..e73e9dac33 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2508,3 +2508,28 @@ static bool trans_viota_m(DisasContext *s, arg_viota_m 
*a)
     }
     return false;
 }
+
+/* Vector Element Index Instruction */
+static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
+{
+    if (vext_check_isa_ill(s) &&
+        vext_check_reg(s, a->rd, false) &&
+        vext_check_overlap_mask(s, a->rd, a->vm, false)) {
+        uint32_t data = 0;
+        TCGLabel *over = gen_new_label();
+        tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
+        data = FIELD_DP32(data, VDATA, VM, a->vm);
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+        static gen_helper_gvec_2_ptr * const fns[4] = {
+            gen_helper_vid_v_b, gen_helper_vid_v_h,
+            gen_helper_vid_v_w, gen_helper_vid_v_d,
+        };
+        tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
+                           cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
+        gen_set_label(over);
+        return true;
+    }
+    return false;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d6283053f1..1dc2a1ccb1 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4673,3 +4673,27 @@ GEN_VEXT_VIOTA_M(viota_m_b, uint8_t, H1, clearb)
 GEN_VEXT_VIOTA_M(viota_m_h, uint16_t, H2, clearh)
 GEN_VEXT_VIOTA_M(viota_m_w, uint32_t, H4, clearl)
 GEN_VEXT_VIOTA_M(viota_m_d, uint64_t, H8, clearq)
+
+/* Vector Element Index Instruction */
+#define GEN_VEXT_VID_V(NAME, ETYPE, H, CLEAR_FN)                          \
+void HELPER(NAME)(void *vd, void *v0, CPURISCVState *env, uint32_t desc)  \
+{                                                                         \
+    uint32_t mlen = vext_mlen(desc);                                      \
+    uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen;                   \
+    uint32_t vm = vext_vm(desc);                                          \
+    uint32_t vl = env->vl;                                                \
+    int i;                                                                \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        *((ETYPE *)vd + H(i)) = i;                                        \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+GEN_VEXT_VID_V(vid_v_b, uint8_t, H1, clearb)
+GEN_VEXT_VID_V(vid_v_h, uint16_t, H2, clearh)
+GEN_VEXT_VID_V(vid_v_w, uint32_t, H4, clearl)
+GEN_VEXT_VID_V(vid_v_d, uint64_t, H8, clearq)
-- 
2.23.0