X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=target%2Friscv%2Fvector_helper.c;h=7505f9470a64cda009199347b1b64c770f2aa149;hb=7b945bdc0b10eda16dbeafe6a4dc1480176db38e;hp=b94f809eb38f2785cf231cb78a21abebf90cfd5a;hpb=fe65642bbae13bc8ea2e2498ea7bd2977ed443e5;p=mirror_qemu.git

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index b94f809eb3..7505f9470a 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -50,10 +50,7 @@ target_ulong HELPER(vsetvl)(CPURISCVState *env, target_ulong s1,
         }
     }
 
-    if ((sew > cpu->cfg.elen)
-        || vill
-        || (ediv != 0)
-        || (reserved != 0)) {
+    if ((sew > cpu->cfg.elen) || vill || (ediv != 0) || (reserved != 0)) {
         /* only set vill bit. */
         env->vill = 1;
         env->vtype = 0;
@@ -172,7 +169,7 @@ static inline uint32_t vext_get_total_elems(CPURISCVState *env, uint32_t desc,
 
 static inline target_ulong adjust_addr(CPURISCVState *env, target_ulong addr)
 {
-    return (addr & env->cur_pmmask) | env->cur_pmbase;
+    return (addr & ~env->cur_pmmask) | env->cur_pmbase;
 }
 
 /*
@@ -211,7 +208,7 @@ static void vext_set_elems_1s(void *base, uint32_t is_agnostic, uint32_t cnt,
         return;
     }
     if (tot - cnt == 0) {
-        return ;
+        return;
     }
     memset(base + cnt, -1, tot - cnt);
 }
@@ -267,8 +264,35 @@ GEN_VEXT_ST_ELEM(ste_h, int16_t, H2, stw)
 GEN_VEXT_ST_ELEM(ste_w, int32_t, H4, stl)
 GEN_VEXT_ST_ELEM(ste_d, int64_t, H8, stq)
 
+static void vext_set_tail_elems_1s(CPURISCVState *env, target_ulong vl,
+                                   void *vd, uint32_t desc, uint32_t nf,
+                                   uint32_t esz, uint32_t max_elems)
+{
+    uint32_t total_elems, vlenb, registers_used;
+    uint32_t vta = vext_vta(desc);
+    int k;
+
+    if (vta == 0) {
+        return;
+    }
+
+    total_elems = vext_get_total_elems(env, desc, esz);
+    vlenb = riscv_cpu_cfg(env)->vlen >> 3;
+
+    for (k = 0; k < nf; ++k) {
+        vext_set_elems_1s(vd, vta, (k * max_elems + vl) * esz,
+                          (k * max_elems + max_elems) * esz);
+    }
+
+    if (nf * max_elems % total_elems != 0) {
+        registers_used = ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
+        vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
+                          registers_used * vlenb);
+    }
+}
+
 /*
- *** stride: access vector element from strided memory
+ * stride: access vector element from strided memory
  */
 static void
 vext_ldst_stride(void *vd, void *v0, target_ulong base,
@@ -281,8 +305,6 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
     uint32_t nf = vext_nf(desc);
     uint32_t max_elems = vext_max_elems(desc, log2_esz);
     uint32_t esz = 1 << log2_esz;
-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
-    uint32_t vta = vext_vta(desc);
     uint32_t vma = vext_vma(desc);
 
     for (i = env->vstart; i < env->vl; i++, env->vstart++) {
@@ -301,18 +323,8 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
         }
     }
     env->vstart = 0;
-    /* set tail elements to 1s */
-    for (k = 0; k < nf; ++k) {
-        vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
-                          (k * max_elems + max_elems) * esz);
-    }
-    if (nf * max_elems % total_elems != 0) {
-        uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
-        uint32_t registers_used =
-            ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
-        vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
-                          registers_used * vlenb);
-    }
+
+    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
 }
 
 #define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN)                        \
@@ -346,10 +358,10 @@ 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
+ * unit-stride: access elements stored contiguously in memory
  */
 
-/* unmasked unit-stride load and store operation*/
+/* 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 log2_esz, uint32_t evl,
@@ -359,8 +371,6 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
     uint32_t nf = vext_nf(desc);
     uint32_t max_elems = vext_max_elems(desc, log2_esz);
     uint32_t esz = 1 << log2_esz;
-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
-    uint32_t vta = vext_vta(desc);
 
     /* load bytes from guest memory */
     for (i = env->vstart; i < evl; i++, env->vstart++) {
@@ -372,23 +382,13 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
         }
     }
     env->vstart = 0;
-    /* set tail elements to 1s */
-    for (k = 0; k < nf; ++k) {
-        vext_set_elems_1s(vd, vta, (k * max_elems + evl) * esz,
-                          (k * max_elems + max_elems) * esz);
-    }
-    if (nf * max_elems % total_elems != 0) {
-        uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
-        uint32_t registers_used =
-            ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
-        vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
-                          registers_used * vlenb);
-    }
+
+    vext_set_tail_elems_1s(env, evl, vd, desc, nf, esz, max_elems);
 }
 
 /*
- * masked unit-stride load and store operation will be a special case of stride,
- * stride = NF * sizeof (MTYPE)
+ * masked unit-stride load and store operation will be a special case of
+ * stride, stride = NF * sizeof (MTYPE)
  */
 
 #define GEN_VEXT_LD_US(NAME, ETYPE, LOAD_FN)                            \
@@ -434,7 +434,7 @@ GEN_VEXT_ST_US(vse32_v, int32_t, ste_w)
 GEN_VEXT_ST_US(vse64_v, int64_t, ste_d)
 
 /*
- *** unit stride mask load and store, EEW = 1
+ * unit stride mask load and store, EEW = 1
  */
 void HELPER(vlm_v)(void *vd, void *v0, target_ulong base,
                     CPURISCVState *env, uint32_t desc)
@@ -455,7 +455,7 @@ void HELPER(vsm_v)(void *vd, void *v0, target_ulong base,
 }
 
 /*
- *** index: access vector element from indexed memory
+ * index: access vector element from indexed memory
  */
 typedef target_ulong vext_get_index_addr(target_ulong base,
         uint32_t idx, void *vs2);
@@ -484,8 +484,6 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
     uint32_t vm = vext_vm(desc);
     uint32_t max_elems = vext_max_elems(desc, log2_esz);
     uint32_t esz = 1 << log2_esz;
-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
-    uint32_t vta = vext_vta(desc);
     uint32_t vma = vext_vma(desc);
 
     /* load bytes from guest memory */
@@ -505,18 +503,8 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
         }
     }
     env->vstart = 0;
-    /* set tail elements to 1s */
-    for (k = 0; k < nf; ++k) {
-        vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
-                          (k * max_elems + max_elems) * esz);
-    }
-    if (nf * max_elems % total_elems != 0) {
-        uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
-        uint32_t registers_used =
-            ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
-        vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
-                          registers_used * vlenb);
-    }
+
+    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
 }
 
 #define GEN_VEXT_LD_INDEX(NAME, ETYPE, INDEX_FN, LOAD_FN)                  \
@@ -571,7 +559,7 @@ GEN_VEXT_ST_INDEX(vsxei64_32_v, int32_t, idx_d, ste_w)
 GEN_VEXT_ST_INDEX(vsxei64_64_v, int64_t, idx_d, ste_d)
 
 /*
- *** unit-stride fault-only-fisrt load instructions
+ * unit-stride fault-only-fisrt load instructions
  */
 static inline void
 vext_ldff(void *vd, void *v0, target_ulong base,
@@ -585,12 +573,10 @@ vext_ldff(void *vd, void *v0, target_ulong base,
     uint32_t vm = vext_vm(desc);
     uint32_t max_elems = vext_max_elems(desc, log2_esz);
     uint32_t esz = 1 << log2_esz;
-    uint32_t total_elems = vext_get_total_elems(env, desc, esz);
-    uint32_t vta = vext_vta(desc);
     uint32_t vma = vext_vma(desc);
     target_ulong addr, offset, remain;
 
-    /* probe every access*/
+    /* probe every access */
     for (i = env->vstart; i < env->vl; i++) {
         if (!vm && !vext_elem_mask(v0, i)) {
             continue;
@@ -647,18 +633,8 @@ ProbeSuccess:
         }
     }
     env->vstart = 0;
-    /* set tail elements to 1s */
-    for (k = 0; k < nf; ++k) {
-        vext_set_elems_1s(vd, vta, (k * max_elems + env->vl) * esz,
-                          (k * max_elems + max_elems) * esz);
-    }
-    if (nf * max_elems % total_elems != 0) {
-        uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
-        uint32_t registers_used =
-            ((nf * max_elems) * esz + (vlenb - 1)) / vlenb;
-        vext_set_elems_1s(vd, vta, (nf * max_elems) * esz,
-                          registers_used * vlenb);
-    }
+
+    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
 }
 
 #define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN)               \
@@ -689,7 +665,7 @@ GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d)
 #define DO_MINU(N, M) DO_MIN((UMTYPE)N, (UMTYPE)M)
 
 /*
- *** load and store whole register instructions
+ * load and store whole register instructions
  */
 static void
 vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
@@ -697,7 +673,7 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
 {
     uint32_t i, k, off, pos;
     uint32_t nf = vext_nf(desc);
-    uint32_t vlenb = env_archcpu(env)->cfg.vlen >> 3;
+    uint32_t vlenb = riscv_cpu_cfg(env)->vlen >> 3;
     uint32_t max_elems = vlenb >> log2_esz;
 
     k = env->vstart / max_elems;
@@ -707,7 +683,8 @@ vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
         /* load/store rest of elements of current segment pointed by vstart */
         for (pos = off; pos < max_elems; pos++, env->vstart++) {
             target_ulong addr = base + ((pos + k * max_elems) << log2_esz);
-            ldst_elem(env, adjust_addr(env, addr), pos + k * max_elems, vd, ra);
+            ldst_elem(env, adjust_addr(env, addr), pos + k * max_elems, vd,
+                      ra);
         }
         k++;
     }
@@ -762,7 +739,7 @@ GEN_VEXT_ST_WHOLE(vs4r_v, int8_t, ste_b)
 GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b)
 
 /*
- *** Vector Integer Arithmetic Instructions
+ * Vector Integer Arithmetic Instructions
  */
 
 /* expand macro args before macro */
@@ -1142,7 +1119,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,        \
                                                                          \
         *((ETYPE *)vd + H(i)) = DO_OP(s2, (ETYPE)(target_long)s1, carry);\
     }                                                                    \
-    env->vstart = 0;                                          \
+    env->vstart = 0;                                                     \
     /* set tail elements to 1s */                                        \
     vext_set_elems_1s(vd, vta, vl * esz, total_elems * esz);             \
 }
@@ -1167,7 +1144,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
 {                                                             \
     uint32_t vl = env->vl;                                    \
     uint32_t vm = vext_vm(desc);                              \
-    uint32_t total_elems = env_archcpu(env)->cfg.vlen;        \
+    uint32_t total_elems = riscv_cpu_cfg(env)->vlen;          \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);              \
     uint32_t i;                                               \
                                                               \
@@ -1178,8 +1155,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
         vext_set_elem_mask(vd, i, DO_OP(s2, s1, carry));      \
     }                                                         \
     env->vstart = 0;                                          \
-    /* mask destination register are always tail-agnostic */  \
-    /* set tail elements to 1s */                             \
+    /*
+     * mask destination register are always tail-agnostic
+     * set tail elements to 1s
+     */                                                       \
     if (vta_all_1s) {                                         \
         for (; i < total_elems; i++) {                        \
             vext_set_elem_mask(vd, i, 1);                     \
@@ -1203,7 +1182,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,          \
 {                                                               \
     uint32_t vl = env->vl;                                      \
     uint32_t vm = vext_vm(desc);                                \
-    uint32_t total_elems = env_archcpu(env)->cfg.vlen;          \
+    uint32_t total_elems = riscv_cpu_cfg(env)->vlen;            \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);                \
     uint32_t i;                                                 \
                                                                 \
@@ -1214,8 +1193,10 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,          \
                 DO_OP(s2, (ETYPE)(target_long)s1, carry));      \
     }                                                           \
     env->vstart = 0;                                            \
-    /* mask destination register are always tail-agnostic */    \
-    /* set tail elements to 1s */                               \
+    /*
+     * mask destination register are always tail-agnostic
+     * set tail elements to 1s
+     */                                                         \
     if (vta_all_1s) {                                           \
         for (; i < total_elems; i++) {                          \
             vext_set_elem_mask(vd, i, 1);                       \
@@ -1331,10 +1312,13 @@ GEN_VEXT_SHIFT_VV(vsra_vv_h, uint16_t, int16_t, H2, H2, DO_SRL, 0xf)
 GEN_VEXT_SHIFT_VV(vsra_vv_w, uint32_t, int32_t, H4, H4, DO_SRL, 0x1f)
 GEN_VEXT_SHIFT_VV(vsra_vv_d, uint64_t, int64_t, H8, H8, DO_SRL, 0x3f)
 
-/* generate the helpers for shift instructions with one vector and one scalar */
+/*
+ * generate the helpers for shift instructions with one vector and one scalar
+ */
 #define GEN_VEXT_SHIFT_VX(NAME, TD, TS2, HD, HS2, OP, MASK) \
 void HELPER(NAME)(void *vd, void *v0, target_ulong s1,      \
-        void *vs2, CPURISCVState *env, uint32_t desc)       \
+                  void *vs2, CPURISCVState *env,            \
+                  uint32_t desc)                            \
 {                                                           \
     uint32_t vm = vext_vm(desc);                            \
     uint32_t vl = env->vl;                                  \
@@ -1402,7 +1386,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
 {                                                             \
     uint32_t vm = vext_vm(desc);                              \
     uint32_t vl = env->vl;                                    \
-    uint32_t total_elems = env_archcpu(env)->cfg.vlen;        \
+    uint32_t total_elems = riscv_cpu_cfg(env)->vlen;          \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);              \
     uint32_t vma = vext_vma(desc);                            \
     uint32_t i;                                               \
@@ -1420,8 +1404,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
         vext_set_elem_mask(vd, i, DO_OP(s2, s1));             \
     }                                                         \
     env->vstart = 0;                                          \
-    /* mask destination register are always tail-agnostic */  \
-    /* set tail elements to 1s */                             \
+    /*
+     * mask destination register are always tail-agnostic
+     * set tail elements to 1s
+     */                                                       \
     if (vta_all_1s) {                                         \
         for (; i < total_elems; i++) {                        \
             vext_set_elem_mask(vd, i, 1);                     \
@@ -1465,7 +1451,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,   \
 {                                                                   \
     uint32_t vm = vext_vm(desc);                                    \
     uint32_t vl = env->vl;                                          \
-    uint32_t total_elems = env_archcpu(env)->cfg.vlen;              \
+    uint32_t total_elems = riscv_cpu_cfg(env)->vlen;                \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);                    \
     uint32_t vma = vext_vma(desc);                                  \
     uint32_t i;                                                     \
@@ -1483,8 +1469,10 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,   \
                 DO_OP(s2, (ETYPE)(target_long)s1));                 \
     }                                                               \
     env->vstart = 0;                                                \
-    /* mask destination register are always tail-agnostic */        \
-    /* set tail elements to 1s */                                   \
+    /*
+     * mask destination register are always tail-agnostic
+     * set tail elements to 1s
+     */                                                             \
     if (vta_all_1s) {                                               \
         for (; i < total_elems; i++) {                              \
             vext_set_elem_mask(vd, i, 1);                           \
@@ -1761,9 +1749,9 @@ GEN_VEXT_VX(vmulhsu_vx_d, 8)
 /* Vector Integer Divide Instructions */
 #define DO_DIVU(N, M) (unlikely(M == 0) ? (__typeof(N))(-1) : N / M)
 #define DO_REMU(N, M) (unlikely(M == 0) ? N : N % M)
-#define DO_DIV(N, M)  (unlikely(M == 0) ? (__typeof(N))(-1) :\
+#define DO_DIV(N, M)  (unlikely(M == 0) ? (__typeof(N))(-1) : \
         unlikely((N == -N) && (M == (__typeof(N))(-1))) ? N : N / M)
-#define DO_REM(N, M)  (unlikely(M == 0) ? N :\
+#define DO_REM(N, M)  (unlikely(M == 0) ? N : \
         unlikely((N == -N) && (M == (__typeof(N))(-1))) ? 0 : N % M)
 
 RVVCALL(OPIVV2, vdivu_vv_b, OP_UUU_B, H1, H1, H1, DO_DIVU)
@@ -1872,7 +1860,7 @@ GEN_VEXT_VX(vwmulsu_vx_h, 4)
 GEN_VEXT_VX(vwmulsu_vx_w, 8)
 
 /* Vector Single-Width Integer Multiply-Add Instructions */
-#define OPIVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)   \
+#define OPIVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)       \
 static void do_##NAME(void *vd, void *vs1, void *vs2, int i)       \
 {                                                                  \
     TX1 s1 = *((T1 *)vs1 + HS1(i));                                \
@@ -2103,7 +2091,7 @@ GEN_VEXT_VMERGE_VX(vmerge_vxm_w, int32_t, H4)
 GEN_VEXT_VMERGE_VX(vmerge_vxm_d, int64_t, H8)
 
 /*
- *** Vector Fixed-Point Arithmetic Instructions
+ * Vector Fixed-Point Arithmetic Instructions
  */
 
 /* Vector Single-Width Saturating Add and Subtract */
@@ -2185,7 +2173,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,     \
                  do_##NAME, ESZ);                               \
 }
 
-static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
+static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a,
+                             uint8_t b)
 {
     uint8_t res = a + b;
     if (res < a) {
@@ -2303,7 +2292,8 @@ vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
 /* generate helpers for fixed point instructions with OPIVX format */
 #define GEN_VEXT_VX_RM(NAME, ESZ)                         \
 void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
-        void *vs2, CPURISCVState *env, uint32_t desc)     \
+                  void *vs2, CPURISCVState *env,          \
+                  uint32_t desc)                          \
 {                                                         \
     vext_vx_rm_2(vd, v0, s1, vs2, env, desc,              \
                  do_##NAME, ESZ);                         \
@@ -2328,7 +2318,8 @@ static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
     return res;
 }
 
-static inline int16_t sadd16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
+static inline int16_t sadd16(CPURISCVState *env, int vxrm, int16_t a,
+                             int16_t b)
 {
     int16_t res = a + b;
     if ((res ^ a) & (res ^ b) & INT16_MIN) {
@@ -2338,7 +2329,8 @@ static inline int16_t sadd16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
     return res;
 }
 
-static inline int32_t sadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+static inline int32_t sadd32(CPURISCVState *env, int vxrm, int32_t a,
+                             int32_t b)
 {
     int32_t res = a + b;
     if ((res ^ a) & (res ^ b) & INT32_MIN) {
@@ -2348,7 +2340,8 @@ static inline int32_t sadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
     return res;
 }
 
-static inline int64_t sadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+static inline int64_t sadd64(CPURISCVState *env, int vxrm, int64_t a,
+                             int64_t b)
 {
     int64_t res = a + b;
     if ((res ^ a) & (res ^ b) & INT64_MIN) {
@@ -2376,7 +2369,8 @@ GEN_VEXT_VX_RM(vsadd_vx_h, 2)
 GEN_VEXT_VX_RM(vsadd_vx_w, 4)
 GEN_VEXT_VX_RM(vsadd_vx_d, 8)
 
-static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
+static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a,
+                             uint8_t b)
 {
     uint8_t res = a - b;
     if (res > a) {
@@ -2447,7 +2441,8 @@ static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
     return res;
 }
 
-static inline int16_t ssub16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
+static inline int16_t ssub16(CPURISCVState *env, int vxrm, int16_t a,
+                             int16_t b)
 {
     int16_t res = a - b;
     if ((res ^ a) & (a ^ b) & INT16_MIN) {
@@ -2457,7 +2452,8 @@ static inline int16_t ssub16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
     return res;
 }
 
-static inline int32_t ssub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+static inline int32_t ssub32(CPURISCVState *env, int vxrm, int32_t a,
+                             int32_t b)
 {
     int32_t res = a - b;
     if ((res ^ a) & (a ^ b) & INT32_MIN) {
@@ -2467,7 +2463,8 @@ static inline int32_t ssub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
     return res;
 }
 
-static inline int64_t ssub64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+static inline int64_t ssub64(CPURISCVState *env, int vxrm, int64_t a,
+                             int64_t b)
 {
     int64_t res = a - b;
     if ((res ^ a) & (a ^ b) & INT64_MIN) {
@@ -2523,7 +2520,8 @@ static inline uint8_t get_round(int vxrm, uint64_t v, uint8_t shift)
     return 0; /* round-down (truncate) */
 }
 
-static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a,
+                             int32_t b)
 {
     int64_t res = (int64_t)a + b;
     uint8_t round = get_round(vxrm, res, 1);
@@ -2531,7 +2529,8 @@ static inline int32_t aadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
     return (res >> 1) + round;
 }
 
-static inline int64_t aadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+static inline int64_t aadd64(CPURISCVState *env, int vxrm, int64_t a,
+                             int64_t b)
 {
     int64_t res = a + b;
     uint8_t round = get_round(vxrm, res, 1);
@@ -2596,7 +2595,8 @@ GEN_VEXT_VX_RM(vaaddu_vx_h, 2)
 GEN_VEXT_VX_RM(vaaddu_vx_w, 4)
 GEN_VEXT_VX_RM(vaaddu_vx_d, 8)
 
-static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a,
+                             int32_t b)
 {
     int64_t res = (int64_t)a - b;
     uint8_t round = get_round(vxrm, res, 1);
@@ -2604,7 +2604,8 @@ static inline int32_t asub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
     return (res >> 1) + round;
 }
 
-static inline int64_t asub64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+static inline int64_t asub64(CPURISCVState *env, int vxrm, int64_t a,
+                             int64_t b)
 {
     int64_t res = (int64_t)a - b;
     uint8_t round = get_round(vxrm, res, 1);
@@ -2677,7 +2678,7 @@ static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
 
     res = (int16_t)a * (int16_t)b;
     round = get_round(vxrm, res, 7);
-    res   = (res >> 7) + round;
+    res = (res >> 7) + round;
 
     if (res > INT8_MAX) {
         env->vxsat = 0x1;
@@ -2697,7 +2698,7 @@ static int16_t vsmul16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
 
     res = (int32_t)a * (int32_t)b;
     round = get_round(vxrm, res, 15);
-    res   = (res >> 15) + round;
+    res = (res >> 15) + round;
 
     if (res > INT16_MAX) {
         env->vxsat = 0x1;
@@ -2717,7 +2718,7 @@ static int32_t vsmul32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
 
     res = (int64_t)a * (int64_t)b;
     round = get_round(vxrm, res, 31);
-    res   = (res >> 31) + round;
+    res = (res >> 31) + round;
 
     if (res > INT32_MAX) {
         env->vxsat = 0x1;
@@ -2784,38 +2785,32 @@ vssrl8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
     uint8_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
+    res = (a >> shift) + round;
     return res;
 }
 static inline uint16_t
 vssrl16(CPURISCVState *env, int vxrm, uint16_t a, uint16_t b)
 {
     uint8_t round, shift = b & 0xf;
-    uint16_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
-    return res;
+    return (a >> shift) + round;
 }
 static inline uint32_t
 vssrl32(CPURISCVState *env, int vxrm, uint32_t a, uint32_t b)
 {
     uint8_t round, shift = b & 0x1f;
-    uint32_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
-    return res;
+    return (a >> shift) + round;
 }
 static inline uint64_t
 vssrl64(CPURISCVState *env, int vxrm, uint64_t a, uint64_t b)
 {
     uint8_t round, shift = b & 0x3f;
-    uint64_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
-    return res;
+    return (a >> shift) + round;
 }
 RVVCALL(OPIVV2_RM, vssrl_vv_b, OP_UUU_B, H1, H1, H1, vssrl8)
 RVVCALL(OPIVV2_RM, vssrl_vv_h, OP_UUU_H, H2, H2, H2, vssrl16)
@@ -2839,41 +2834,33 @@ static inline int8_t
 vssra8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
 {
     uint8_t round, shift = b & 0x7;
-    int8_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
-    return res;
+    return (a >> shift) + round;
 }
 static inline int16_t
 vssra16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
 {
     uint8_t round, shift = b & 0xf;
-    int16_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
-    return res;
+    return (a >> shift) + round;
 }
 static inline int32_t
 vssra32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
 {
     uint8_t round, shift = b & 0x1f;
-    int32_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
-    return res;
+    return (a >> shift) + round;
 }
 static inline int64_t
 vssra64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
 {
     uint8_t round, shift = b & 0x3f;
-    int64_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
-    return res;
+    return (a >> shift) + round;
 }
 
 RVVCALL(OPIVV2_RM, vssra_vv_b, OP_SSS_B, H1, H1, H1, vssra8)
@@ -2902,7 +2889,7 @@ vnclip8(CPURISCVState *env, int vxrm, int16_t a, int8_t b)
     int16_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
+    res = (a >> shift) + round;
     if (res > INT8_MAX) {
         env->vxsat = 0x1;
         return INT8_MAX;
@@ -2921,7 +2908,7 @@ vnclip16(CPURISCVState *env, int vxrm, int32_t a, int16_t b)
     int32_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
+    res = (a >> shift) + round;
     if (res > INT16_MAX) {
         env->vxsat = 0x1;
         return INT16_MAX;
@@ -2940,7 +2927,7 @@ vnclip32(CPURISCVState *env, int vxrm, int64_t a, int32_t b)
     int64_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
+    res = (a >> shift) + round;
     if (res > INT32_MAX) {
         env->vxsat = 0x1;
         return INT32_MAX;
@@ -2973,7 +2960,7 @@ vnclipu8(CPURISCVState *env, int vxrm, uint16_t a, uint8_t b)
     uint16_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
+    res = (a >> shift) + round;
     if (res > UINT8_MAX) {
         env->vxsat = 0x1;
         return UINT8_MAX;
@@ -2989,7 +2976,7 @@ vnclipu16(CPURISCVState *env, int vxrm, uint32_t a, uint16_t b)
     uint32_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
+    res = (a >> shift) + round;
     if (res > UINT16_MAX) {
         env->vxsat = 0x1;
         return UINT16_MAX;
@@ -3005,7 +2992,7 @@ vnclipu32(CPURISCVState *env, int vxrm, uint64_t a, uint32_t b)
     uint64_t res;
 
     round = get_round(vxrm, a, shift);
-    res   = (a >> shift)  + round;
+    res = (a >> shift) + round;
     if (res > UINT32_MAX) {
         env->vxsat = 0x1;
         return UINT32_MAX;
@@ -3029,7 +3016,7 @@ GEN_VEXT_VX_RM(vnclipu_wx_h, 2)
 GEN_VEXT_VX_RM(vnclipu_wx_w, 4)
 
 /*
- *** Vector Float Point Arithmetic Instructions
+ * Vector Float Point Arithmetic Instructions
  */
 /* Vector Single-Width Floating-Point Add/Subtract Instructions */
 #define OPFVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)   \
@@ -3092,7 +3079,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1,        \
     uint32_t vm = vext_vm(desc);                          \
     uint32_t vl = env->vl;                                \
     uint32_t total_elems =                                \
-        vext_get_total_elems(env, desc, ESZ);              \
+        vext_get_total_elems(env, desc, ESZ);             \
     uint32_t vta = vext_vta(desc);                        \
     uint32_t vma = vext_vma(desc);                        \
     uint32_t i;                                           \
@@ -3158,13 +3145,13 @@ GEN_VEXT_VF(vfrsub_vf_d, 8)
 static uint32_t vfwadd16(uint16_t a, uint16_t b, float_status *s)
 {
     return float32_add(float16_to_float32(a, true, s),
-            float16_to_float32(b, true, s), s);
+                       float16_to_float32(b, true, s), s);
 }
 
 static uint64_t vfwadd32(uint32_t a, uint32_t b, float_status *s)
 {
     return float64_add(float32_to_float64(a, s),
-            float32_to_float64(b, s), s);
+                       float32_to_float64(b, s), s);
 
 }
 
@@ -3180,13 +3167,13 @@ GEN_VEXT_VF(vfwadd_vf_w, 8)
 static uint32_t vfwsub16(uint16_t a, uint16_t b, float_status *s)
 {
     return float32_sub(float16_to_float32(a, true, s),
-            float16_to_float32(b, true, s), s);
+                       float16_to_float32(b, true, s), s);
 }
 
 static uint64_t vfwsub32(uint32_t a, uint32_t b, float_status *s)
 {
     return float64_sub(float32_to_float64(a, s),
-            float32_to_float64(b, s), s);
+                       float32_to_float64(b, s), s);
 
 }
 
@@ -3290,13 +3277,13 @@ GEN_VEXT_VF(vfrdiv_vf_d, 8)
 static uint32_t vfwmul16(uint16_t a, uint16_t b, float_status *s)
 {
     return float32_mul(float16_to_float32(a, true, s),
-            float16_to_float32(b, true, s), s);
+                       float16_to_float32(b, true, s), s);
 }
 
 static uint64_t vfwmul32(uint32_t a, uint32_t b, float_status *s)
 {
     return float64_mul(float32_to_float64(a, s),
-            float32_to_float64(b, s), s);
+                       float32_to_float64(b, s), s);
 
 }
 RVVCALL(OPFVV2, vfwmul_vv_h, WOP_UUU_H, H4, H2, H2, vfwmul16)
@@ -3311,7 +3298,7 @@ GEN_VEXT_VF(vfwmul_vf_w, 8)
 /* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */
 #define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)       \
 static void do_##NAME(void *vd, void *vs1, void *vs2, int i,       \
-        CPURISCVState *env)                                        \
+                      CPURISCVState *env)                          \
 {                                                                  \
     TX1 s1 = *((T1 *)vs1 + HS1(i));                                \
     TX2 s2 = *((T2 *)vs2 + HS2(i));                                \
@@ -3343,7 +3330,7 @@ GEN_VEXT_VV_ENV(vfmacc_vv_d, 8)
 
 #define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP)           \
 static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i,    \
-        CPURISCVState *env)                                       \
+                      CPURISCVState *env)                         \
 {                                                                 \
     TX2 s2 = *((T2 *)vs2 + HS2(i));                               \
     TD d = *((TD *)vd + HD(i));                                   \
@@ -3359,20 +3346,20 @@ GEN_VEXT_VF(vfmacc_vf_d, 8)
 
 static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
 {
-    return float16_muladd(a, b, d,
-            float_muladd_negate_c | float_muladd_negate_product, s);
+    return float16_muladd(a, b, d, float_muladd_negate_c |
+                                   float_muladd_negate_product, s);
 }
 
 static uint32_t fnmacc32(uint32_t a, uint32_t b, uint32_t d, float_status *s)
 {
-    return float32_muladd(a, b, d,
-            float_muladd_negate_c | float_muladd_negate_product, s);
+    return float32_muladd(a, b, d, float_muladd_negate_c |
+                                   float_muladd_negate_product, s);
 }
 
 static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
 {
-    return float64_muladd(a, b, d,
-            float_muladd_negate_c | float_muladd_negate_product, s);
+    return float64_muladd(a, b, d, float_muladd_negate_c |
+                                   float_muladd_negate_product, s);
 }
 
 RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16)
@@ -3474,20 +3461,20 @@ GEN_VEXT_VF(vfmadd_vf_d, 8)
 
 static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s)
 {
-    return float16_muladd(d, b, a,
-            float_muladd_negate_c | float_muladd_negate_product, s);
+    return float16_muladd(d, b, a, float_muladd_negate_c |
+                                   float_muladd_negate_product, s);
 }
 
 static uint32_t fnmadd32(uint32_t a, uint32_t b, uint32_t d, float_status *s)
 {
-    return float32_muladd(d, b, a,
-            float_muladd_negate_c | float_muladd_negate_product, s);
+    return float32_muladd(d, b, a, float_muladd_negate_c |
+                                   float_muladd_negate_product, s);
 }
 
 static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s)
 {
-    return float64_muladd(d, b, a,
-            float_muladd_negate_c | float_muladd_negate_product, s);
+    return float64_muladd(d, b, a, float_muladd_negate_c |
+                                   float_muladd_negate_product, s);
 }
 
 RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16)
@@ -3563,13 +3550,13 @@ GEN_VEXT_VF(vfnmsub_vf_d, 8)
 static uint32_t fwmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
 {
     return float32_muladd(float16_to_float32(a, true, s),
-                        float16_to_float32(b, true, s), d, 0, s);
+                          float16_to_float32(b, true, s), d, 0, s);
 }
 
 static uint64_t fwmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
 {
     return float64_muladd(float32_to_float64(a, s),
-                        float32_to_float64(b, s), d, 0, s);
+                          float32_to_float64(b, s), d, 0, s);
 }
 
 RVVCALL(OPFVV3, vfwmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwmacc16)
@@ -3584,15 +3571,16 @@ GEN_VEXT_VF(vfwmacc_vf_w, 8)
 static uint32_t fwnmacc16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
 {
     return float32_muladd(float16_to_float32(a, true, s),
-                        float16_to_float32(b, true, s), d,
-                        float_muladd_negate_c | float_muladd_negate_product, s);
+                          float16_to_float32(b, true, s), d,
+                          float_muladd_negate_c | float_muladd_negate_product,
+                          s);
 }
 
 static uint64_t fwnmacc32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
 {
-    return float64_muladd(float32_to_float64(a, s),
-                        float32_to_float64(b, s), d,
-                        float_muladd_negate_c | float_muladd_negate_product, s);
+    return float64_muladd(float32_to_float64(a, s), float32_to_float64(b, s),
+                          d, float_muladd_negate_c |
+                             float_muladd_negate_product, s);
 }
 
 RVVCALL(OPFVV3, vfwnmacc_vv_h, WOP_UUU_H, H4, H2, H2, fwnmacc16)
@@ -3607,15 +3595,15 @@ GEN_VEXT_VF(vfwnmacc_vf_w, 8)
 static uint32_t fwmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
 {
     return float32_muladd(float16_to_float32(a, true, s),
-                        float16_to_float32(b, true, s), d,
-                        float_muladd_negate_c, s);
+                          float16_to_float32(b, true, s), d,
+                          float_muladd_negate_c, s);
 }
 
 static uint64_t fwmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
 {
     return float64_muladd(float32_to_float64(a, s),
-                        float32_to_float64(b, s), d,
-                        float_muladd_negate_c, s);
+                          float32_to_float64(b, s), d,
+                          float_muladd_negate_c, s);
 }
 
 RVVCALL(OPFVV3, vfwmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwmsac16)
@@ -3630,15 +3618,15 @@ GEN_VEXT_VF(vfwmsac_vf_w, 8)
 static uint32_t fwnmsac16(uint16_t a, uint16_t b, uint32_t d, float_status *s)
 {
     return float32_muladd(float16_to_float32(a, true, s),
-                        float16_to_float32(b, true, s), d,
-                        float_muladd_negate_product, s);
+                          float16_to_float32(b, true, s), d,
+                          float_muladd_negate_product, s);
 }
 
 static uint64_t fwnmsac32(uint32_t a, uint32_t b, uint64_t d, float_status *s)
 {
     return float64_muladd(float32_to_float64(a, s),
-                        float32_to_float64(b, s), d,
-                        float_muladd_negate_product, s);
+                          float32_to_float64(b, s), d,
+                          float_muladd_negate_product, s);
 }
 
 RVVCALL(OPFVV3, vfwnmsac_vv_h, WOP_UUU_H, H4, H2, H2, fwnmsac16)
@@ -3656,9 +3644,9 @@ GEN_VEXT_VF(vfwnmsac_vf_w, 8)
 #define OP_UU_W uint32_t, uint32_t, uint32_t
 #define OP_UU_D uint64_t, uint64_t, uint64_t
 
-#define OPFVV1(NAME, TD, T2, TX2, HD, HS2, OP)        \
+#define OPFVV1(NAME, TD, T2, TX2, HD, HS2, OP)         \
 static void do_##NAME(void *vd, void *vs2, int i,      \
-        CPURISCVState *env)                            \
+                      CPURISCVState *env)              \
 {                                                      \
     TX2 s2 = *((T2 *)vs2 + HS2(i));                    \
     *((TD *)vd + HD(i)) = OP(s2, &env->fp_status);     \
@@ -3666,7 +3654,7 @@ static void do_##NAME(void *vd, void *vs2, int i,      \
 
 #define GEN_VEXT_V_ENV(NAME, ESZ)                      \
 void HELPER(NAME)(void *vd, void *v0, void *vs2,       \
-        CPURISCVState *env, uint32_t desc)             \
+                  CPURISCVState *env, uint32_t desc)   \
 {                                                      \
     uint32_t vm = vext_vm(desc);                       \
     uint32_t vl = env->vl;                             \
@@ -3743,9 +3731,9 @@ static uint64_t frsqrt7(uint64_t f, int exp_size, int frac_size)
     }
 
     int idx = ((exp & 1) << (precision - 1)) |
-                (frac >> (frac_size - precision + 1));
+              (frac >> (frac_size - precision + 1));
     uint64_t out_frac = (uint64_t)(lookup_table[idx]) <<
-                            (frac_size - precision);
+                        (frac_size - precision);
     uint64_t out_exp = (3 * MAKE_64BIT_MASK(0, exp_size - 1) + ~exp) / 2;
 
     uint64_t val = 0;
@@ -3767,9 +3755,9 @@ static float16 frsqrt7_h(float16 f, float_status *s)
      * frsqrt7(-subnormal) = canonical NaN
      */
     if (float16_is_signaling_nan(f, s) ||
-            (float16_is_infinity(f) && sign) ||
-            (float16_is_normal(f) && sign) ||
-            (float16_is_zero_or_denormal(f) && !float16_is_zero(f) && sign)) {
+        (float16_is_infinity(f) && sign) ||
+        (float16_is_normal(f) && sign) ||
+        (float16_is_zero_or_denormal(f) && !float16_is_zero(f) && sign)) {
         s->float_exception_flags |= float_flag_invalid;
         return float16_default_nan(s);
     }
@@ -3807,9 +3795,9 @@ static float32 frsqrt7_s(float32 f, float_status *s)
      * frsqrt7(-subnormal) = canonical NaN
      */
     if (float32_is_signaling_nan(f, s) ||
-            (float32_is_infinity(f) && sign) ||
-            (float32_is_normal(f) && sign) ||
-            (float32_is_zero_or_denormal(f) && !float32_is_zero(f) && sign)) {
+        (float32_is_infinity(f) && sign) ||
+        (float32_is_normal(f) && sign) ||
+        (float32_is_zero_or_denormal(f) && !float32_is_zero(f) && sign)) {
         s->float_exception_flags |= float_flag_invalid;
         return float32_default_nan(s);
     }
@@ -3847,9 +3835,9 @@ static float64 frsqrt7_d(float64 f, float_status *s)
      * frsqrt7(-subnormal) = canonical NaN
      */
     if (float64_is_signaling_nan(f, s) ||
-            (float64_is_infinity(f) && sign) ||
-            (float64_is_normal(f) && sign) ||
-            (float64_is_zero_or_denormal(f) && !float64_is_zero(f) && sign)) {
+        (float64_is_infinity(f) && sign) ||
+        (float64_is_normal(f) && sign) ||
+        (float64_is_zero_or_denormal(f) && !float64_is_zero(f) && sign)) {
         s->float_exception_flags |= float_flag_invalid;
         return float64_default_nan(s);
     }
@@ -3937,18 +3925,18 @@ static uint64_t frec7(uint64_t f, int exp_size, int frac_size,
                 ((s->float_rounding_mode == float_round_up) && sign)) {
                 /* Return greatest/negative finite value. */
                 return (sign << (exp_size + frac_size)) |
-                    (MAKE_64BIT_MASK(frac_size, exp_size) - 1);
+                       (MAKE_64BIT_MASK(frac_size, exp_size) - 1);
             } else {
                 /* Return +-inf. */
                 return (sign << (exp_size + frac_size)) |
-                    MAKE_64BIT_MASK(frac_size, exp_size);
+                       MAKE_64BIT_MASK(frac_size, exp_size);
             }
         }
     }
 
     int idx = frac >> (frac_size - precision);
     uint64_t out_frac = (uint64_t)(lookup_table[idx]) <<
-                            (frac_size - precision);
+                        (frac_size - precision);
     uint64_t out_exp = 2 * MAKE_64BIT_MASK(0, exp_size - 1) + ~exp;
 
     if (out_exp == 0 || out_exp == UINT64_MAX) {
@@ -4192,7 +4180,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
 {                                                             \
     uint32_t vm = vext_vm(desc);                              \
     uint32_t vl = env->vl;                                    \
-    uint32_t total_elems = env_archcpu(env)->cfg.vlen;        \
+    uint32_t total_elems = riscv_cpu_cfg(env)->vlen;          \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);              \
     uint32_t vma = vext_vma(desc);                            \
     uint32_t i;                                               \
@@ -4211,8 +4199,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,   \
                            DO_OP(s2, s1, &env->fp_status));   \
     }                                                         \
     env->vstart = 0;                                          \
-    /* mask destination register are always tail-agnostic */  \
-    /* set tail elements to 1s */                             \
+    /*
+     * mask destination register are always tail-agnostic
+     * set tail elements to 1s
+     */                                                       \
     if (vta_all_1s) {                                         \
         for (; i < total_elems; i++) {                        \
             vext_set_elem_mask(vd, i, 1);                     \
@@ -4230,7 +4220,7 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2,       \
 {                                                                   \
     uint32_t vm = vext_vm(desc);                                    \
     uint32_t vl = env->vl;                                          \
-    uint32_t total_elems = env_archcpu(env)->cfg.vlen;              \
+    uint32_t total_elems = riscv_cpu_cfg(env)->vlen;                \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);                    \
     uint32_t vma = vext_vma(desc);                                  \
     uint32_t i;                                                     \
@@ -4248,8 +4238,10 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2,       \
                            DO_OP(s2, (ETYPE)s1, &env->fp_status));  \
     }                                                               \
     env->vstart = 0;                                                \
-    /* mask destination register are always tail-agnostic */        \
-    /* set tail elements to 1s */                                   \
+    /*
+     * mask destination register are always tail-agnostic
+     * set tail elements to 1s
+     */                                                             \
     if (vta_all_1s) {                                               \
         for (; i < total_elems; i++) {                              \
             vext_set_elem_mask(vd, i, 1);                           \
@@ -4462,8 +4454,8 @@ void HELPER(NAME)(void *vd, void *v0, uint64_t s1, void *vs2, \
                                                               \
     for (i = env->vstart; i < vl; i++) {                      \
         ETYPE s2 = *((ETYPE *)vs2 + H(i));                    \
-        *((ETYPE *)vd + H(i))                                 \
-          = (!vm && !vext_elem_mask(v0, i) ? s2 : s1);        \
+        *((ETYPE *)vd + H(i)) =                               \
+            (!vm && !vext_elem_mask(v0, i) ? s2 : s1);        \
     }                                                         \
     env->vstart = 0;                                          \
     /* set tail elements to 1s */                             \
@@ -4512,7 +4504,9 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8)
 #define WOP_UU_B uint16_t, uint8_t,  uint8_t
 #define WOP_UU_H uint32_t, uint16_t, uint16_t
 #define WOP_UU_W uint64_t, uint32_t, uint32_t
-/* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/
+/*
+ * vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.
+ */
 RVVCALL(OPFVV1, vfwcvt_xu_f_v_h, WOP_UU_H, H4, H2, float16_to_uint32)
 RVVCALL(OPFVV1, vfwcvt_xu_f_v_w, WOP_UU_W, H8, H4, float32_to_uint64)
 GEN_VEXT_V_ENV(vfwcvt_xu_f_v_h, 4)
@@ -4524,7 +4518,9 @@ RVVCALL(OPFVV1, vfwcvt_x_f_v_w, WOP_UU_W, H8, H4, float32_to_int64)
 GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 4)
 GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 8)
 
-/* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */
+/*
+ * vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float.
+ */
 RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16)
 RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32)
 RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64)
@@ -4541,8 +4537,7 @@ GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 4)
 GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 8)
 
 /*
- * vfwcvt.f.f.v vd, vs2, vm
- * Convert single-width float to double-width float.
+ * vfwcvt.f.f.v vd, vs2, vm # Convert single-width float to double-width float.
  */
 static uint32_t vfwcvtffv16(uint16_t a, float_status *s)
 {
@@ -4575,7 +4570,9 @@ GEN_VEXT_V_ENV(vfncvt_x_f_w_b, 1)
 GEN_VEXT_V_ENV(vfncvt_x_f_w_h, 2)
 GEN_VEXT_V_ENV(vfncvt_x_f_w_w, 4)
 
-/* vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float */
+/*
+ * vfncvt.f.xu.v vd, vs2, vm # Convert double-width unsigned integer to float.
+ */
 RVVCALL(OPFVV1, vfncvt_f_xu_w_h, NOP_UU_H, H2, H4, uint32_to_float16)
 RVVCALL(OPFVV1, vfncvt_f_xu_w_w, NOP_UU_W, H4, H8, uint64_to_float32)
 GEN_VEXT_V_ENV(vfncvt_f_xu_w_h, 2)
@@ -4599,12 +4596,13 @@ GEN_VEXT_V_ENV(vfncvt_f_f_w_h, 2)
 GEN_VEXT_V_ENV(vfncvt_f_f_w_w, 4)
 
 /*
- *** Vector Reduction Operations
+ * Vector Reduction Operations
  */
 /* Vector Single-Width Integer Reduction Instructions */
 #define GEN_VEXT_RED(NAME, TD, TS2, HD, HS2, OP)          \
 void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
-        void *vs2, CPURISCVState *env, uint32_t desc)     \
+                  void *vs2, CPURISCVState *env,          \
+                  uint32_t desc)                          \
 {                                                         \
     uint32_t vm = vext_vm(desc);                          \
     uint32_t vl = env->vl;                                \
@@ -4724,14 +4722,20 @@ GEN_VEXT_FRED(vfredosum_vs_w, uint32_t, uint32_t, H4, H4, float32_add)
 GEN_VEXT_FRED(vfredosum_vs_d, uint64_t, uint64_t, H8, H8, float64_add)
 
 /* Maximum value */
-GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2, float16_maximum_number)
-GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4, float32_maximum_number)
-GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maximum_number)
+GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2,
+              float16_maximum_number)
+GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4,
+              float32_maximum_number)
+GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8,
+              float64_maximum_number)
 
 /* Minimum value */
-GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minimum_number)
-GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minimum_number)
-GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minimum_number)
+GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2,
+              float16_minimum_number)
+GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4,
+              float32_minimum_number)
+GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8,
+              float64_minimum_number)
 
 /* Vector Widening Floating-Point Add Instructions */
 static uint32_t fwadd16(uint32_t a, uint16_t b, float_status *s)
@@ -4752,7 +4756,7 @@ GEN_VEXT_FRED(vfwredosum_vs_h, uint32_t, uint16_t, H4, H2, fwadd16)
 GEN_VEXT_FRED(vfwredosum_vs_w, uint64_t, uint32_t, H8, H4, fwadd32)
 
 /*
- *** Vector Mask Operations
+ * Vector Mask Operations
  */
 /* Vector Mask-Register Logical Instructions */
 #define GEN_VEXT_MASK_VV(NAME, OP)                        \
@@ -4761,7 +4765,7 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
                   uint32_t desc)                          \
 {                                                         \
     uint32_t vl = env->vl;                                \
-    uint32_t total_elems = env_archcpu(env)->cfg.vlen;    \
+    uint32_t total_elems = riscv_cpu_cfg(env)->vlen;      \
     uint32_t vta_all_1s = vext_vta_all_1s(desc);          \
     uint32_t i;                                           \
     int a, b;                                             \
@@ -4772,10 +4776,10 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
         vext_set_elem_mask(vd, i, OP(b, a));              \
     }                                                     \
     env->vstart = 0;                                      \
-    /* mask destination register are always tail-         \
-     * agnostic                                           \
+    /*
+     * mask destination register are always tail-agnostic
+     * set tail elements to 1s
      */                                                   \
-    /* set tail elements to 1s */                         \
     if (vta_all_1s) {                                     \
         for (; i < total_elems; i++) {                    \
             vext_set_elem_mask(vd, i, 1);                 \
@@ -4818,7 +4822,7 @@ target_ulong HELPER(vcpop_m)(void *v0, void *vs2, CPURISCVState *env,
     return cnt;
 }
 
-/* vfirst find-first-set mask bit*/
+/* vfirst find-first-set mask bit */
 target_ulong HELPER(vfirst_m)(void *v0, void *vs2, CPURISCVState *env,
                               uint32_t desc)
 {
@@ -4848,7 +4852,7 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
 {
     uint32_t vm = vext_vm(desc);
     uint32_t vl = env->vl;
-    uint32_t total_elems = env_archcpu(env)->cfg.vlen;
+    uint32_t total_elems = riscv_cpu_cfg(env)->vlen;
     uint32_t vta_all_1s = vext_vta_all_1s(desc);
     uint32_t vma = vext_vma(desc);
     int i;
@@ -4883,8 +4887,10 @@ static void vmsetm(void *vd, void *v0, void *vs2, CPURISCVState *env,
         }
     }
     env->vstart = 0;
-    /* mask destination register are always tail-agnostic */
-    /* set tail elements to 1s */
+    /*
+     * mask destination register are always tail-agnostic
+     * set tail elements to 1s
+     */
     if (vta_all_1s) {
         for (; i < total_elems; i++) {
             vext_set_elem_mask(vd, i, 1);
@@ -4976,7 +4982,7 @@ GEN_VEXT_VID_V(vid_v_w, uint32_t, H4)
 GEN_VEXT_VID_V(vid_v_d, uint64_t, H8)
 
 /*
- *** Vector Permutation Instructions
+ * Vector Permutation Instructions
  */
 
 /* Vector Slide Instructions */
@@ -5052,8 +5058,9 @@ GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_w, uint32_t, H4)
 GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8)
 
 #define GEN_VEXT_VSLIE1UP(BITWIDTH, H)                                      \
-static void vslide1up_##BITWIDTH(void *vd, void *v0, target_ulong s1,       \
-                     void *vs2, CPURISCVState *env, uint32_t desc)          \
+static void vslide1up_##BITWIDTH(void *vd, void *v0, uint64_t s1,           \
+                                 void *vs2, CPURISCVState *env,             \
+                                 uint32_t desc)                             \
 {                                                                           \
     typedef uint##BITWIDTH##_t ETYPE;                                       \
     uint32_t vm = vext_vm(desc);                                            \
@@ -5100,8 +5107,9 @@ GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_w, 32)
 GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, 64)
 
 #define GEN_VEXT_VSLIDE1DOWN(BITWIDTH, H)                                     \
-static void vslide1down_##BITWIDTH(void *vd, void *v0, target_ulong s1,       \
-                       void *vs2, CPURISCVState *env, uint32_t desc)          \
+static void vslide1down_##BITWIDTH(void *vd, void *v0, uint64_t s1,           \
+                                   void *vs2, CPURISCVState *env,             \
+                                   uint32_t desc)                             \
 {                                                                             \
     typedef uint##BITWIDTH##_t ETYPE;                                         \
     uint32_t vm = vext_vm(desc);                                              \