target/riscv: rvv-1.0: stride load and store instructions

Signed-off-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20211210075704.23951-21-frank.chang@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

1 files changed, 69 insertions, 130 deletions

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 78fae78284..9141292994 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -178,38 +178,36 @@ static inline int vext_elem_mask(void *v0, int index)
 typedef void vext_ldst_elem_fn(CPURISCVState *env, target_ulong addr,
                                uint32_t idx, void *vd, uintptr_t retaddr);
 
-#define GEN_VEXT_LD_ELEM(NAME, MTYPE, ETYPE, H, LDSUF)     \
+#define GEN_VEXT_LD_ELEM(NAME, ETYPE, H, LDSUF)            \
 static void NAME(CPURISCVState *env, abi_ptr addr,         \
                  uint32_t idx, void *vd, uintptr_t retaddr)\
 {                                                          \
-    MTYPE data;                                            \
     ETYPE *cur = ((ETYPE *)vd + H(idx));                   \
-    data = cpu_##LDSUF##_data_ra(env, addr, retaddr);      \
-    *cur = data;                                           \
+    *cur = cpu_##LDSUF##_data_ra(env, addr, retaddr);      \
 }                                                          \
 
-GEN_VEXT_LD_ELEM(ldb_b, int8_t,  int8_t,  H1, ldsb)
-GEN_VEXT_LD_ELEM(ldb_h, int8_t,  int16_t, H2, ldsb)
-GEN_VEXT_LD_ELEM(ldb_w, int8_t,  int32_t, H4, ldsb)
-GEN_VEXT_LD_ELEM(ldb_d, int8_t,  int64_t, H8, ldsb)
-GEN_VEXT_LD_ELEM(ldh_h, int16_t, int16_t, H2, ldsw)
-GEN_VEXT_LD_ELEM(ldh_w, int16_t, int32_t, H4, ldsw)
-GEN_VEXT_LD_ELEM(ldh_d, int16_t, int64_t, H8, ldsw)
-GEN_VEXT_LD_ELEM(ldw_w, int32_t, int32_t, H4, ldl)
-GEN_VEXT_LD_ELEM(ldw_d, int32_t, int64_t, H8, ldl)
-GEN_VEXT_LD_ELEM(lde_b, int8_t,  int8_t,  H1, ldsb)
-GEN_VEXT_LD_ELEM(lde_h, int16_t, int16_t, H2, ldsw)
-GEN_VEXT_LD_ELEM(lde_w, int32_t, int32_t, H4, ldl)
-GEN_VEXT_LD_ELEM(lde_d, int64_t, int64_t, H8, ldq)
-GEN_VEXT_LD_ELEM(ldbu_b, uint8_t,  uint8_t,  H1, ldub)
-GEN_VEXT_LD_ELEM(ldbu_h, uint8_t,  uint16_t, H2, ldub)
-GEN_VEXT_LD_ELEM(ldbu_w, uint8_t,  uint32_t, H4, ldub)
-GEN_VEXT_LD_ELEM(ldbu_d, uint8_t,  uint64_t, H8, ldub)
-GEN_VEXT_LD_ELEM(ldhu_h, uint16_t, uint16_t, H2, lduw)
-GEN_VEXT_LD_ELEM(ldhu_w, uint16_t, uint32_t, H4, lduw)
-GEN_VEXT_LD_ELEM(ldhu_d, uint16_t, uint64_t, H8, lduw)
-GEN_VEXT_LD_ELEM(ldwu_w, uint32_t, uint32_t, H4, ldl)
-GEN_VEXT_LD_ELEM(ldwu_d, uint32_t, uint64_t, H8, ldl)
+GEN_VEXT_LD_ELEM(ldb_b, int8_t,  H1, ldsb)
+GEN_VEXT_LD_ELEM(ldb_h, int16_t, H2, ldsb)
+GEN_VEXT_LD_ELEM(ldb_w, int32_t, H4, ldsb)
+GEN_VEXT_LD_ELEM(ldb_d, int64_t, H8, ldsb)
+GEN_VEXT_LD_ELEM(ldh_h, int16_t, H2, ldsw)
+GEN_VEXT_LD_ELEM(ldh_w, int32_t, H4, ldsw)
+GEN_VEXT_LD_ELEM(ldh_d, int64_t, H8, ldsw)
+GEN_VEXT_LD_ELEM(ldw_w, int32_t, H4, ldl)
+GEN_VEXT_LD_ELEM(ldw_d, int64_t, H8, ldl)
+GEN_VEXT_LD_ELEM(lde_b, int8_t,  H1, ldsb)
+GEN_VEXT_LD_ELEM(lde_h, int16_t, H2, ldsw)
+GEN_VEXT_LD_ELEM(lde_w, int32_t, H4, ldl)
+GEN_VEXT_LD_ELEM(lde_d, int64_t, H8, ldq)
+GEN_VEXT_LD_ELEM(ldbu_b, uint8_t,  H1, ldub)
+GEN_VEXT_LD_ELEM(ldbu_h, uint16_t, H2, ldub)
+GEN_VEXT_LD_ELEM(ldbu_w, uint32_t, H4, ldub)
+GEN_VEXT_LD_ELEM(ldbu_d, uint64_t, H8, ldub)
+GEN_VEXT_LD_ELEM(ldhu_h, uint16_t, H2, lduw)
+GEN_VEXT_LD_ELEM(ldhu_w, uint32_t, H4, lduw)
+GEN_VEXT_LD_ELEM(ldhu_d, uint64_t, H8, lduw)
+GEN_VEXT_LD_ELEM(ldwu_w, uint32_t, H4, ldl)
+GEN_VEXT_LD_ELEM(ldwu_d, uint64_t, H8, ldl)
 
 #define GEN_VEXT_ST_ELEM(NAME, ETYPE, H, STSUF)            \
 static void NAME(CPURISCVState *env, abi_ptr addr,         \
@@ -241,8 +239,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
                  target_ulong stride, CPURISCVState *env,
                  uint32_t desc, uint32_t vm,
                  vext_ldst_elem_fn *ldst_elem,
-                 uint32_t esz, uint32_t msz, uintptr_t ra,
-                 MMUAccessType access_type)
+                 uint32_t esz, uintptr_t ra, MMUAccessType access_type)
 {
     uint32_t i, k;
     uint32_t nf = vext_nf(desc);
@@ -253,7 +250,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
         if (!vm && !vext_elem_mask(v0, i)) {
             continue;
         }
-        probe_pages(env, base + stride * i, nf * msz, ra, access_type);
+        probe_pages(env, base + stride * i, nf * esz, ra, access_type);
     }
     /* do real access */
     for (i = 0; i < env->vl; i++) {
@@ -262,71 +259,42 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
             continue;
         }
         while (k < nf) {
-            target_ulong addr = base + stride * i + k * msz;
+            target_ulong addr = base + stride * i + k * esz;
             ldst_elem(env, addr, i + k * vlmax, vd, ra);
             k++;
         }
     }
 }
 
-#define GEN_VEXT_LD_STRIDE(NAME, MTYPE, ETYPE, LOAD_FN)                 \
+#define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN)                        \
 void HELPER(NAME)(void *vd, void * v0, target_ulong base,               \
                   target_ulong stride, CPURISCVState *env,              \
                   uint32_t desc)                                        \
 {                                                                       \
     uint32_t vm = vext_vm(desc);                                        \
     vext_ldst_stride(vd, v0, base, stride, env, desc, vm, LOAD_FN,      \
-                     sizeof(ETYPE), sizeof(MTYPE),                      \
-                     GETPC(), MMU_DATA_LOAD);                           \
-}
-
-GEN_VEXT_LD_STRIDE(vlsb_v_b,  int8_t,   int8_t,   ldb_b)
-GEN_VEXT_LD_STRIDE(vlsb_v_h,  int8_t,   int16_t,  ldb_h)
-GEN_VEXT_LD_STRIDE(vlsb_v_w,  int8_t,   int32_t,  ldb_w)
-GEN_VEXT_LD_STRIDE(vlsb_v_d,  int8_t,   int64_t,  ldb_d)
-GEN_VEXT_LD_STRIDE(vlsh_v_h,  int16_t,  int16_t,  ldh_h)
-GEN_VEXT_LD_STRIDE(vlsh_v_w,  int16_t,  int32_t,  ldh_w)
-GEN_VEXT_LD_STRIDE(vlsh_v_d,  int16_t,  int64_t,  ldh_d)
-GEN_VEXT_LD_STRIDE(vlsw_v_w,  int32_t,  int32_t,  ldw_w)
-GEN_VEXT_LD_STRIDE(vlsw_v_d,  int32_t,  int64_t,  ldw_d)
-GEN_VEXT_LD_STRIDE(vlse_v_b,  int8_t,   int8_t,   lde_b)
-GEN_VEXT_LD_STRIDE(vlse_v_h,  int16_t,  int16_t,  lde_h)
-GEN_VEXT_LD_STRIDE(vlse_v_w,  int32_t,  int32_t,  lde_w)
-GEN_VEXT_LD_STRIDE(vlse_v_d,  int64_t,  int64_t,  lde_d)
-GEN_VEXT_LD_STRIDE(vlsbu_v_b, uint8_t,  uint8_t,  ldbu_b)
-GEN_VEXT_LD_STRIDE(vlsbu_v_h, uint8_t,  uint16_t, ldbu_h)
-GEN_VEXT_LD_STRIDE(vlsbu_v_w, uint8_t,  uint32_t, ldbu_w)
-GEN_VEXT_LD_STRIDE(vlsbu_v_d, uint8_t,  uint64_t, ldbu_d)
-GEN_VEXT_LD_STRIDE(vlshu_v_h, uint16_t, uint16_t, ldhu_h)
-GEN_VEXT_LD_STRIDE(vlshu_v_w, uint16_t, uint32_t, ldhu_w)
-GEN_VEXT_LD_STRIDE(vlshu_v_d, uint16_t, uint64_t, ldhu_d)
-GEN_VEXT_LD_STRIDE(vlswu_v_w, uint32_t, uint32_t, ldwu_w)
-GEN_VEXT_LD_STRIDE(vlswu_v_d, uint32_t, uint64_t, ldwu_d)
-
-#define GEN_VEXT_ST_STRIDE(NAME, MTYPE, ETYPE, STORE_FN)                \
+                     sizeof(ETYPE), GETPC(), MMU_DATA_LOAD);            \
+}
+
+GEN_VEXT_LD_STRIDE(vlse8_v,  int8_t,  lde_b)
+GEN_VEXT_LD_STRIDE(vlse16_v, int16_t, lde_h)
+GEN_VEXT_LD_STRIDE(vlse32_v, int32_t, lde_w)
+GEN_VEXT_LD_STRIDE(vlse64_v, int64_t, lde_d)
+
+#define GEN_VEXT_ST_STRIDE(NAME, ETYPE, STORE_FN)                       \
 void HELPER(NAME)(void *vd, void *v0, target_ulong base,                \
                   target_ulong stride, CPURISCVState *env,              \
                   uint32_t desc)                                        \
 {                                                                       \
     uint32_t vm = vext_vm(desc);                                        \
     vext_ldst_stride(vd, v0, base, stride, env, desc, vm, STORE_FN,     \
-                     sizeof(ETYPE), sizeof(MTYPE),                      \
-                     GETPC(), MMU_DATA_STORE);                          \
-}
-
-GEN_VEXT_ST_STRIDE(vssb_v_b, int8_t,  int8_t,  stb_b)
-GEN_VEXT_ST_STRIDE(vssb_v_h, int8_t,  int16_t, stb_h)
-GEN_VEXT_ST_STRIDE(vssb_v_w, int8_t,  int32_t, stb_w)
-GEN_VEXT_ST_STRIDE(vssb_v_d, int8_t,  int64_t, stb_d)
-GEN_VEXT_ST_STRIDE(vssh_v_h, int16_t, int16_t, sth_h)
-GEN_VEXT_ST_STRIDE(vssh_v_w, int16_t, int32_t, sth_w)
-GEN_VEXT_ST_STRIDE(vssh_v_d, int16_t, int64_t, sth_d)
-GEN_VEXT_ST_STRIDE(vssw_v_w, int32_t, int32_t, stw_w)
-GEN_VEXT_ST_STRIDE(vssw_v_d, int32_t, int64_t, stw_d)
-GEN_VEXT_ST_STRIDE(vsse_v_b, int8_t,  int8_t,  ste_b)
-GEN_VEXT_ST_STRIDE(vsse_v_h, int16_t, int16_t, ste_h)
-GEN_VEXT_ST_STRIDE(vsse_v_w, int32_t, int32_t, ste_w)
-GEN_VEXT_ST_STRIDE(vsse_v_d, int64_t, int64_t, ste_d)
+                     sizeof(ETYPE), GETPC(), MMU_DATA_STORE);           \
+}
+
+GEN_VEXT_ST_STRIDE(vsse8_v,  int8_t,  ste_b)
+GEN_VEXT_ST_STRIDE(vsse16_v, int16_t, ste_h)
+GEN_VEXT_ST_STRIDE(vsse32_v, int32_t, ste_w)
+GEN_VEXT_ST_STRIDE(vsse64_v, int64_t, ste_d)
 
 /*
  *** unit-stride: access elements stored contiguously in memory
@@ -335,20 +303,20 @@ GEN_VEXT_ST_STRIDE(vsse_v_d, int64_t, int64_t, ste_d)
 /* unmasked unit-stride load and store operation*/
 static void
 vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
-             vext_ldst_elem_fn *ldst_elem, uint32_t esz, uint32_t msz,
-             uintptr_t ra, MMUAccessType access_type)
+             vext_ldst_elem_fn *ldst_elem,
+             uint32_t esz, uintptr_t ra, MMUAccessType access_type)
 {
     uint32_t i, k;
     uint32_t nf = vext_nf(desc);
     uint32_t vlmax = vext_maxsz(desc) / esz;
 
     /* probe every access */
-    probe_pages(env, base, env->vl * nf * msz, ra, access_type);
+    probe_pages(env, base, env->vl * nf * esz, ra, access_type);
     /* load bytes from guest memory */
     for (i = 0; i < env->vl; i++) {
         k = 0;
         while (k < nf) {
-            target_ulong addr = base + (i * nf + k) * msz;
+            target_ulong addr = base + (i * nf + k) * esz;
             ldst_elem(env, addr, i + k * vlmax, vd, ra);
             k++;
         }
@@ -360,76 +328,47 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
  * stride = NF * sizeof (MTYPE)
  */
 
-#define GEN_VEXT_LD_US(NAME, MTYPE, ETYPE, LOAD_FN)                     \
+#define GEN_VEXT_LD_US(NAME, ETYPE, LOAD_FN)                            \
 void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base,         \
                          CPURISCVState *env, uint32_t desc)             \
 {                                                                       \
-    uint32_t stride = vext_nf(desc) * sizeof(MTYPE);                    \
+    uint32_t stride = vext_nf(desc) * sizeof(ETYPE);                    \
     vext_ldst_stride(vd, v0, base, stride, env, desc, false, LOAD_FN,   \
-                     sizeof(ETYPE), sizeof(MTYPE),                      \
-                     GETPC(), MMU_DATA_LOAD);                           \
+                     sizeof(ETYPE), GETPC(), MMU_DATA_LOAD);            \
 }                                                                       \
                                                                         \
 void HELPER(NAME)(void *vd, void *v0, target_ulong base,                \
                   CPURISCVState *env, uint32_t desc)                    \
 {                                                                       \
     vext_ldst_us(vd, base, env, desc, LOAD_FN,                          \
-                 sizeof(ETYPE), sizeof(MTYPE), GETPC(), MMU_DATA_LOAD); \
-}
-
-GEN_VEXT_LD_US(vlb_v_b,  int8_t,   int8_t,   ldb_b)
-GEN_VEXT_LD_US(vlb_v_h,  int8_t,   int16_t,  ldb_h)
-GEN_VEXT_LD_US(vlb_v_w,  int8_t,   int32_t,  ldb_w)
-GEN_VEXT_LD_US(vlb_v_d,  int8_t,   int64_t,  ldb_d)
-GEN_VEXT_LD_US(vlh_v_h,  int16_t,  int16_t,  ldh_h)
-GEN_VEXT_LD_US(vlh_v_w,  int16_t,  int32_t,  ldh_w)
-GEN_VEXT_LD_US(vlh_v_d,  int16_t,  int64_t,  ldh_d)
-GEN_VEXT_LD_US(vlw_v_w,  int32_t,  int32_t,  ldw_w)
-GEN_VEXT_LD_US(vlw_v_d,  int32_t,  int64_t,  ldw_d)
-GEN_VEXT_LD_US(vle_v_b,  int8_t,   int8_t,   lde_b)
-GEN_VEXT_LD_US(vle_v_h,  int16_t,  int16_t,  lde_h)
-GEN_VEXT_LD_US(vle_v_w,  int32_t,  int32_t,  lde_w)
-GEN_VEXT_LD_US(vle_v_d,  int64_t,  int64_t,  lde_d)
-GEN_VEXT_LD_US(vlbu_v_b, uint8_t,  uint8_t,  ldbu_b)
-GEN_VEXT_LD_US(vlbu_v_h, uint8_t,  uint16_t, ldbu_h)
-GEN_VEXT_LD_US(vlbu_v_w, uint8_t,  uint32_t, ldbu_w)
-GEN_VEXT_LD_US(vlbu_v_d, uint8_t,  uint64_t, ldbu_d)
-GEN_VEXT_LD_US(vlhu_v_h, uint16_t, uint16_t, ldhu_h)
-GEN_VEXT_LD_US(vlhu_v_w, uint16_t, uint32_t, ldhu_w)
-GEN_VEXT_LD_US(vlhu_v_d, uint16_t, uint64_t, ldhu_d)
-GEN_VEXT_LD_US(vlwu_v_w, uint32_t, uint32_t, ldwu_w)
-GEN_VEXT_LD_US(vlwu_v_d, uint32_t, uint64_t, ldwu_d)
-
-#define GEN_VEXT_ST_US(NAME, MTYPE, ETYPE, STORE_FN)                    \
+                 sizeof(ETYPE), GETPC(), MMU_DATA_LOAD);                \
+}
+
+GEN_VEXT_LD_US(vle8_v,  int8_t,  lde_b)
+GEN_VEXT_LD_US(vle16_v, int16_t, lde_h)
+GEN_VEXT_LD_US(vle32_v, int32_t, lde_w)
+GEN_VEXT_LD_US(vle64_v, int64_t, lde_d)
+
+#define GEN_VEXT_ST_US(NAME, ETYPE, STORE_FN)                           \
 void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base,         \
                          CPURISCVState *env, uint32_t desc)             \
 {                                                                       \
-    uint32_t stride = vext_nf(desc) * sizeof(MTYPE);                    \
+    uint32_t stride = vext_nf(desc) * sizeof(ETYPE);                    \
     vext_ldst_stride(vd, v0, base, stride, env, desc, false, STORE_FN,  \
-                     sizeof(ETYPE), sizeof(MTYPE),                      \
-                     GETPC(), MMU_DATA_STORE);                          \
+                     sizeof(ETYPE), GETPC(), MMU_DATA_STORE);           \
 }                                                                       \
                                                                         \
 void HELPER(NAME)(void *vd, void *v0, target_ulong base,                \
                   CPURISCVState *env, uint32_t desc)                    \
 {                                                                       \
     vext_ldst_us(vd, base, env, desc, STORE_FN,                         \
-                 sizeof(ETYPE), sizeof(MTYPE), GETPC(), MMU_DATA_STORE);\
-}
-
-GEN_VEXT_ST_US(vsb_v_b, int8_t,  int8_t , stb_b)
-GEN_VEXT_ST_US(vsb_v_h, int8_t,  int16_t, stb_h)
-GEN_VEXT_ST_US(vsb_v_w, int8_t,  int32_t, stb_w)
-GEN_VEXT_ST_US(vsb_v_d, int8_t,  int64_t, stb_d)
-GEN_VEXT_ST_US(vsh_v_h, int16_t, int16_t, sth_h)
-GEN_VEXT_ST_US(vsh_v_w, int16_t, int32_t, sth_w)
-GEN_VEXT_ST_US(vsh_v_d, int16_t, int64_t, sth_d)
-GEN_VEXT_ST_US(vsw_v_w, int32_t, int32_t, stw_w)
-GEN_VEXT_ST_US(vsw_v_d, int32_t, int64_t, stw_d)
-GEN_VEXT_ST_US(vse_v_b, int8_t,  int8_t , ste_b)
-GEN_VEXT_ST_US(vse_v_h, int16_t, int16_t, ste_h)
-GEN_VEXT_ST_US(vse_v_w, int32_t, int32_t, ste_w)
-GEN_VEXT_ST_US(vse_v_d, int64_t, int64_t, ste_d)
+                 sizeof(ETYPE), GETPC(), MMU_DATA_STORE);               \
+}
+
+GEN_VEXT_ST_US(vse8_v,  int8_t,  ste_b)
+GEN_VEXT_ST_US(vse16_v, int16_t, ste_h)
+GEN_VEXT_ST_US(vse32_v, int32_t, ste_w)
+GEN_VEXT_ST_US(vse64_v, int64_t, ste_d)
 
 /*
  *** index: access vector element from indexed memory