[PATCH v9 60/61] target/riscv: vector compress 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              |  1 +
 target/riscv/insn_trans/trans_rvv.inc.c | 32 +++++++++++++++++++++++++
 target/riscv/vector_helper.c            | 26 ++++++++++++++++++++
 4 files changed, 64 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 3da863ac13..8d97114d81 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1139,3 +1139,8 @@ 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)
+
+DEF_HELPER_6(vcompress_vm_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vcompress_vm_d, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e07ff7eff6..a37e205eb7 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -575,6 +575,7 @@ 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
+vcompress_vm    010111 - ..... ..... 010 ..... 1010111 @r
 
 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 f6547f7e6d..ebc4e8174f 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2854,3 +2854,35 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr 
*a)
     }
     return true;
 }
+
+/* Vector Compress Instruction */
+static bool vcompress_vm_check(DisasContext *s, arg_r *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_reg(s, a->rd, false) &&
+            vext_check_reg(s, a->rs2, false) &&
+            vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs1, 1) &&
+            (a->rd != a->rs2));
+}
+
+static bool trans_vcompress_vm(DisasContext *s, arg_r *a)
+{
+    if (vcompress_vm_check(s, a)) {
+        uint32_t data = 0;
+        static gen_helper_gvec_4_ptr * const fns[4] = {
+            gen_helper_vcompress_vm_b, gen_helper_vcompress_vm_h,
+            gen_helper_vcompress_vm_w, gen_helper_vcompress_vm_d,
+        };
+        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, LMUL, s->lmul);
+        tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
+                           vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
+                           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 220fa76d54..e9e0b1e7a8 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4871,3 +4871,29 @@ 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)
+
+/* Vector Compress Instruction */
+#define GEN_VEXT_VCOMPRESS_VM(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 vl = env->vl;                                                \
+    uint32_t num = 0, i;                                                  \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vext_elem_mask(vs1, mlen, i)) {                              \
+            continue;                                                     \
+        }                                                                 \
+        *((ETYPE *)vd + H(num)) = *((ETYPE *)vs2 + H(i));                 \
+        num++;                                                            \
+    }                                                                     \
+    CLEAR_FN(vd, num, num * sizeof(ETYPE), vlmax * sizeof(ETYPE));        \
+}
+
+/* Compress into vd elements of vs2 where vs1 is enabled */
+GEN_VEXT_VCOMPRESS_VM(vcompress_vm_b, uint8_t, H1, clearb)
+GEN_VEXT_VCOMPRESS_VM(vcompress_vm_h, uint16_t, H2, clearh)
+GEN_VEXT_VCOMPRESS_VM(vcompress_vm_w, uint32_t, H4, clearl)
+GEN_VEXT_VCOMPRESS_VM(vcompress_vm_d, uint64_t, H8, clearq)
-- 
2.23.0