target/riscv: rvv: Early exit when vstart >= vl

According to v-spec (section 5.4):
When vstart ≥ vl, there are no body elements, and no elements are
updated in any destination vector register group, including that
no tail elements are updated with agnostic values.

vmsbf.m, vmsif.m, vmsof.m, viota.m, vcompress instructions themselves
require vstart to be zero. So they don't need the early exit.

Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-4@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

1 files changed, 27 insertions, 0 deletions

diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc
index 391c61fe93..6750f5d04a 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -652,6 +652,7 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data,
 
     TCGLabel *over = gen_new_label();
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
     mask = tcg_temp_new_ptr();
@@ -818,6 +819,7 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2,
 
     TCGLabel *over = gen_new_label();
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
     mask = tcg_temp_new_ptr();
@@ -925,6 +927,7 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
 
     TCGLabel *over = gen_new_label();
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
     mask = tcg_temp_new_ptr();
@@ -1067,6 +1070,7 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data,
 
     TCGLabel *over = gen_new_label();
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
     mask = tcg_temp_new_ptr();
@@ -1225,6 +1229,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
     }
 
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     if (a->vm && s->vl_eq_vlmax) {
         gvec_fn(s->sew, vreg_ofs(s, a->rd),
@@ -1272,6 +1277,7 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
 
     TCGLabel *over = gen_new_label();
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
     mask = tcg_temp_new_ptr();
@@ -1436,6 +1442,7 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
 
     TCGLabel *over = gen_new_label();
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
     mask = tcg_temp_new_ptr();
@@ -1522,6 +1529,7 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
         uint32_t data = 0;
         TCGLabel *over = gen_new_label();
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         data = FIELD_DP32(data, VDATA, VM, a->vm);
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1602,6 +1610,7 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
         uint32_t data = 0;
         TCGLabel *over = gen_new_label();
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         data = FIELD_DP32(data, VDATA, VM, a->vm);
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -1679,6 +1688,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
@@ -1860,6 +1870,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
         };                                                         \
         TCGLabel *over = gen_new_label();                          \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
@@ -2070,6 +2081,7 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
             };
             TCGLabel *over = gen_new_label();
             tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
             tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, a->rs1),
                                cpu_env, s->cfg_ptr->vlen / 8,
@@ -2093,6 +2105,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
         TCGv s1;
         TCGLabel *over = gen_new_label();
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         s1 = get_gpr(s, a->rs1, EXT_SIGN);
 
@@ -2148,6 +2161,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
             };
             TCGLabel *over = gen_new_label();
             tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
             s1 = tcg_constant_i64(simm);
             dest = tcg_temp_new_ptr();
@@ -2300,6 +2314,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, RISCV_FRM_DYN);                              \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
@@ -2330,6 +2345,7 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
 
     TCGLabel *over = gen_new_label();
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     dest = tcg_temp_new_ptr();
     mask = tcg_temp_new_ptr();
@@ -2418,6 +2434,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)           \
         TCGLabel *over = gen_new_label();                        \
         gen_set_rm(s, RISCV_FRM_DYN);                            \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);        \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);\
                                                                  \
         data = FIELD_DP32(data, VDATA, VM, a->vm);               \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);           \
@@ -2492,6 +2509,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, RISCV_FRM_DYN);                              \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
@@ -2613,6 +2631,7 @@ static bool do_opfv(DisasContext *s, arg_rmr *a,
         TCGLabel *over = gen_new_label();
         gen_set_rm(s, rm);
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         data = FIELD_DP32(data, VDATA, VM, a->vm);
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -2726,6 +2745,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
             };
             TCGLabel *over = gen_new_label();
             tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+            tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
             t1 = tcg_temp_new_i64();
             /* NaN-box f[rs1] */
@@ -2814,6 +2834,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, FRM);                                        \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
@@ -2865,6 +2886,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, RISCV_FRM_DYN);                              \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
         tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
@@ -2930,6 +2952,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, FRM);                                        \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
@@ -2983,6 +3006,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         TCGLabel *over = gen_new_label();                          \
         gen_set_rm(s, FRM);                                        \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, VM, a->vm);                 \
         tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
@@ -3070,6 +3094,7 @@ static bool trans_##NAME(DisasContext *s, arg_r *a)                \
         gen_helper_gvec_4_ptr *fn = gen_helper_##NAME;             \
         TCGLabel *over = gen_new_label();                          \
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);          \
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
                                                                    \
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
         tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
@@ -3238,6 +3263,7 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
         uint32_t data = 0;
         TCGLabel *over = gen_new_label();
         tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+        tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
         data = FIELD_DP32(data, VDATA, VM, a->vm);
         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
@@ -3748,6 +3774,7 @@ static bool int_ext_op(DisasContext *s, arg_rmr *a, uint8_t seq)
     gen_helper_gvec_3_ptr *fn;
     TCGLabel *over = gen_new_label();
     tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
+    tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over);
 
     static gen_helper_gvec_3_ptr * const fns[6][4] = {
         {