target/riscv: vector register gather instruction

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20200701152549.1218-60-zhiwei_liu@c-sky.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

4 files changed, 150 insertions, 0 deletions

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 29a5eb7..eca1ab5 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1136,3 +1136,12 @@ DEF_HELPER_6(vslide1down_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vslide1down_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vslide1down_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vslide1down_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vrgather_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 36123f7..80d5ff7 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -574,6 +574,9 @@ vslide1up_vx    001110 . ..... ..... 110 ..... 1010111 @r_vm
 vslidedown_vx   001111 . ..... ..... 100 ..... 1010111 @r_vm
 vslidedown_vi   001111 . ..... ..... 011 ..... 1010111 @r_vm
 vslide1down_vx  001111 . ..... ..... 110 ..... 1010111 @r_vm
+vrgather_vv     001100 . ..... ..... 000 ..... 1010111 @r_vm
+vrgather_vx     001100 . ..... ..... 100 ..... 1010111 @r_vm
+vrgather_vi     001100 . ..... ..... 011 ..... 1010111 @r_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 4ed6d1e..c0b7745 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2776,3 +2776,81 @@ GEN_OPIVI_TRANS(vslideup_vi, 1, vslideup_vx, slideup_check)
 GEN_OPIVX_TRANS(vslidedown_vx, opivx_check)
 GEN_OPIVX_TRANS(vslide1down_vx, opivx_check)
 GEN_OPIVI_TRANS(vslidedown_vi, 1, vslidedown_vx, opivx_check)
+
+/* Vector Register Gather Instruction */
+static bool vrgather_vv_check(DisasContext *s, arg_rmrr *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+            vext_check_reg(s, a->rd, false) &&
+            vext_check_reg(s, a->rs1, false) &&
+            vext_check_reg(s, a->rs2, false) &&
+            (a->rd != a->rs2) && (a->rd != a->rs1));
+}
+
+GEN_OPIVV_TRANS(vrgather_vv, vrgather_vv_check)
+
+static bool vrgather_vx_check(DisasContext *s, arg_rmrr *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+            vext_check_reg(s, a->rd, false) &&
+            vext_check_reg(s, a->rs2, false) &&
+            (a->rd != a->rs2));
+}
+
+/* vrgather.vx vd, vs2, rs1, vm # vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
+static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a)
+{
+    if (!vrgather_vx_check(s, a)) {
+        return false;
+    }
+
+    if (a->vm && s->vl_eq_vlmax) {
+        int vlmax = s->vlen / s->mlen;
+        TCGv_i64 dest = tcg_temp_new_i64();
+
+        if (a->rs1 == 0) {
+            vec_element_loadi(s, dest, a->rs2, 0);
+        } else {
+            vec_element_loadx(s, dest, a->rs2, cpu_gpr[a->rs1], vlmax);
+        }
+
+        tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
+                             MAXSZ(s), MAXSZ(s), dest);
+        tcg_temp_free_i64(dest);
+    } else {
+        static gen_helper_opivx * const fns[4] = {
+            gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
+            gen_helper_vrgather_vx_w, gen_helper_vrgather_vx_d
+        };
+        return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s);
+    }
+    return true;
+}
+
+/* vrgather.vi vd, vs2, imm, vm # vd[i] = (imm >= VLMAX) ? 0 : vs2[imm] */
+static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a)
+{
+    if (!vrgather_vx_check(s, a)) {
+        return false;
+    }
+
+    if (a->vm && s->vl_eq_vlmax) {
+        if (a->rs1 >= s->vlen / s->mlen) {
+            tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd),
+                                 MAXSZ(s), MAXSZ(s), 0);
+        } else {
+            tcg_gen_gvec_dup_mem(s->sew, vreg_ofs(s, a->rd),
+                                 endian_ofs(s, a->rs2, a->rs1),
+                                 MAXSZ(s), MAXSZ(s));
+        }
+    } else {
+        static gen_helper_opivx * const fns[4] = {
+            gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
+            gen_helper_vrgather_vx_w, gen_helper_vrgather_vx_d
+        };
+        return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s, 1);
+    }
+    return true;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 51c4bc5..3179b1f 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4811,3 +4811,63 @@ GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_b, uint8_t, H1, clearb)
 GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_h, uint16_t, H2, clearh)
 GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, uint32_t, H4, clearl)
 GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8, clearq)
+
+/* Vector Register Gather Instruction */
+#define GEN_VEXT_VRGATHER_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 vlmax = env_archcpu(env)->cfg.vlen / mlen;                   \
+    uint32_t vm = vext_vm(desc);                                          \
+    uint32_t vl = env->vl;                                                \
+    uint32_t index, i;                                                    \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        index = *((ETYPE *)vs1 + H(i));                                   \
+        if (index >= vlmax) {                                             \
+            *((ETYPE *)vd + H(i)) = 0;                                    \
+        } else {                                                          \
+            *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index));           \
+        }                                                                 \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+/* vd[i] = (vs1[i] >= VLMAX) ? 0 : vs2[vs1[i]]; */
+GEN_VEXT_VRGATHER_VV(vrgather_vv_b, uint8_t, H1, clearb)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_h, uint16_t, H2, clearh)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_w, uint32_t, H4, clearl)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, H8, clearq)
+
+#define GEN_VEXT_VRGATHER_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 vlmax = env_archcpu(env)->cfg.vlen / mlen;                   \
+    uint32_t vm = vext_vm(desc);                                          \
+    uint32_t vl = env->vl;                                                \
+    uint32_t index = s1, i;                                               \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        if (index >= vlmax) {                                             \
+            *((ETYPE *)vd + H(i)) = 0;                                    \
+        } else {                                                          \
+            *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index));           \
+        }                                                                 \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+/* vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
+GEN_VEXT_VRGATHER_VX(vrgather_vx_b, uint8_t, H1, clearb)
+GEN_VEXT_VRGATHER_VX(vrgather_vx_h, uint16_t, H2, clearh)
+GEN_VEXT_VRGATHER_VX(vrgather_vx_w, uint32_t, H4, clearl)
+GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq)