[RFC PATCH v5 3/5] target/riscv: rvv: Provide a fast path using direct access to host ram for unit-stride whole register load/store

[Max Chou]

The vector unit-stride whole register load/store instructions are
similar to unmasked unit-stride load/store instructions that is suitable
to be optimized by using a direct access to host ram fast path.

Because the vector whole register load/store instructions do not need to
handle the tail agnostic, so remove the vstart early exit checking.

Signed-off-by: Max Chou <max.chou@sifive.com>
---
 target/riscv/vector_helper.c | 123 +++++++++++++++++------------------
 1 file changed, 61 insertions(+), 62 deletions(-)

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 23396a1b750..5343a08e6ad 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -653,81 +653,80 @@ GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d_tlb)
  */
 static void
 vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
-                vext_ldst_elem_fn_tlb *ldst_elem, uint32_t log2_esz,
-                uintptr_t ra)
+                vext_ldst_elem_fn_tlb *ldst_tlb,
+                vext_ldst_elem_fn_host *ldst_host, uint32_t log2_esz,
+                uintptr_t ra, bool is_load)
 {
-    uint32_t i, k, off, pos;
+    target_ulong page_split, elems, addr;
     uint32_t nf = vext_nf(desc);
     uint32_t vlenb = riscv_cpu_cfg(env)->vlenb;
     uint32_t max_elems = vlenb >> log2_esz;
+    uint32_t evl = nf * max_elems;
+    uint32_t esz = 1 << log2_esz;
 
-    if (env->vstart >= ((vlenb * nf) >> log2_esz)) {
-        env->vstart = 0;
-        return;
-    }
-
-    k = env->vstart / max_elems;
-    off = env->vstart % max_elems;
-
-    if (off) {
-        /* 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) << log2_esz, vd, ra);
+    while (env->vstart < evl) {
+        /* Calculate page range */
+        addr = base + (env->vstart << log2_esz);
+        page_split = -(addr | TARGET_PAGE_MASK);
+        /* Get number of elements */
+        elems = page_split / esz;
+        if (unlikely(env->vstart + elems >= evl)) {
+            elems = evl - env->vstart;
         }
-        k++;
-    }
 
-    /* load/store elements for rest of segments */
-    for (; k < nf; k++) {
-        for (i = 0; i < max_elems; i++, env->vstart++) {
-            target_ulong addr = base + ((i + k * max_elems) << log2_esz);
-            ldst_elem(env, adjust_addr(env, addr),
-                      (i + k * max_elems) << log2_esz, vd, ra);
+        /* Load/store elements in page */
+        vext_page_ldst_us(env, vd, addr, elems, 1, max_elems, log2_esz,
+                          is_load, ldst_tlb, ldst_host, ra);
+
+        /* Cross page element */
+        if (unlikely((page_split % esz) != 0 && (env->vstart + 1) < evl)) {
+            addr = base + (env->vstart << log2_esz);
+            ldst_tlb(env, adjust_addr(env, addr), (env->vstart << log2_esz),
+                     vd, ra);
+            env->vstart++;
         }
     }
 
     env->vstart = 0;
 }
 
-#define GEN_VEXT_LD_WHOLE(NAME, ETYPE, LOAD_FN)      \
-void HELPER(NAME)(void *vd, target_ulong base,       \
-                  CPURISCVState *env, uint32_t desc) \
-{                                                    \
-    vext_ldst_whole(vd, base, env, desc, LOAD_FN,    \
-                    ctzl(sizeof(ETYPE)), GETPC());   \
-}
-
-GEN_VEXT_LD_WHOLE(vl1re8_v,  int8_t,  lde_b_tlb)
-GEN_VEXT_LD_WHOLE(vl1re16_v, int16_t, lde_h_tlb)
-GEN_VEXT_LD_WHOLE(vl1re32_v, int32_t, lde_w_tlb)
-GEN_VEXT_LD_WHOLE(vl1re64_v, int64_t, lde_d_tlb)
-GEN_VEXT_LD_WHOLE(vl2re8_v,  int8_t,  lde_b_tlb)
-GEN_VEXT_LD_WHOLE(vl2re16_v, int16_t, lde_h_tlb)
-GEN_VEXT_LD_WHOLE(vl2re32_v, int32_t, lde_w_tlb)
-GEN_VEXT_LD_WHOLE(vl2re64_v, int64_t, lde_d_tlb)
-GEN_VEXT_LD_WHOLE(vl4re8_v,  int8_t,  lde_b_tlb)
-GEN_VEXT_LD_WHOLE(vl4re16_v, int16_t, lde_h_tlb)
-GEN_VEXT_LD_WHOLE(vl4re32_v, int32_t, lde_w_tlb)
-GEN_VEXT_LD_WHOLE(vl4re64_v, int64_t, lde_d_tlb)
-GEN_VEXT_LD_WHOLE(vl8re8_v,  int8_t,  lde_b_tlb)
-GEN_VEXT_LD_WHOLE(vl8re16_v, int16_t, lde_h_tlb)
-GEN_VEXT_LD_WHOLE(vl8re32_v, int32_t, lde_w_tlb)
-GEN_VEXT_LD_WHOLE(vl8re64_v, int64_t, lde_d_tlb)
-
-#define GEN_VEXT_ST_WHOLE(NAME, ETYPE, STORE_FN)     \
-void HELPER(NAME)(void *vd, target_ulong base,       \
-                  CPURISCVState *env, uint32_t desc) \
-{                                                    \
-    vext_ldst_whole(vd, base, env, desc, STORE_FN,   \
-                    ctzl(sizeof(ETYPE)), GETPC());   \
-}
-
-GEN_VEXT_ST_WHOLE(vs1r_v, int8_t, ste_b_tlb)
-GEN_VEXT_ST_WHOLE(vs2r_v, int8_t, ste_b_tlb)
-GEN_VEXT_ST_WHOLE(vs4r_v, int8_t, ste_b_tlb)
-GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b_tlb)
+#define GEN_VEXT_LD_WHOLE(NAME, ETYPE, LOAD_FN_TLB, LOAD_FN_HOST)   \
+void HELPER(NAME)(void *vd, target_ulong base, CPURISCVState *env,  \
+                  uint32_t desc)                                    \
+{                                                                   \
+    vext_ldst_whole(vd, base, env, desc, LOAD_FN_TLB, LOAD_FN_HOST, \
+                    ctzl(sizeof(ETYPE)), GETPC(), true);            \
+}
+
+GEN_VEXT_LD_WHOLE(vl1re8_v,  int8_t,  lde_b_tlb, lde_b_host)
+GEN_VEXT_LD_WHOLE(vl1re16_v, int16_t, lde_h_tlb, lde_h_host)
+GEN_VEXT_LD_WHOLE(vl1re32_v, int32_t, lde_w_tlb, lde_w_host)
+GEN_VEXT_LD_WHOLE(vl1re64_v, int64_t, lde_d_tlb, lde_d_host)
+GEN_VEXT_LD_WHOLE(vl2re8_v,  int8_t,  lde_b_tlb, lde_b_host)
+GEN_VEXT_LD_WHOLE(vl2re16_v, int16_t, lde_h_tlb, lde_h_host)
+GEN_VEXT_LD_WHOLE(vl2re32_v, int32_t, lde_w_tlb, lde_w_host)
+GEN_VEXT_LD_WHOLE(vl2re64_v, int64_t, lde_d_tlb, lde_d_host)
+GEN_VEXT_LD_WHOLE(vl4re8_v,  int8_t,  lde_b_tlb, lde_b_host)
+GEN_VEXT_LD_WHOLE(vl4re16_v, int16_t, lde_h_tlb, lde_h_host)
+GEN_VEXT_LD_WHOLE(vl4re32_v, int32_t, lde_w_tlb, lde_w_host)
+GEN_VEXT_LD_WHOLE(vl4re64_v, int64_t, lde_d_tlb, lde_d_host)
+GEN_VEXT_LD_WHOLE(vl8re8_v,  int8_t,  lde_b_tlb, lde_b_host)
+GEN_VEXT_LD_WHOLE(vl8re16_v, int16_t, lde_h_tlb, lde_h_host)
+GEN_VEXT_LD_WHOLE(vl8re32_v, int32_t, lde_w_tlb, lde_w_host)
+GEN_VEXT_LD_WHOLE(vl8re64_v, int64_t, lde_d_tlb, lde_d_host)
+
+#define GEN_VEXT_ST_WHOLE(NAME, ETYPE, STORE_FN_TLB, STORE_FN_HOST)     \
+void HELPER(NAME)(void *vd, target_ulong base, CPURISCVState *env,      \
+                  uint32_t desc)                                        \
+{                                                                       \
+    vext_ldst_whole(vd, base, env, desc, STORE_FN_TLB, STORE_FN_HOST,   \
+                    ctzl(sizeof(ETYPE)), GETPC(), false);               \
+}
+
+GEN_VEXT_ST_WHOLE(vs1r_v, int8_t, ste_b_tlb, ste_b_host)
+GEN_VEXT_ST_WHOLE(vs2r_v, int8_t, ste_b_tlb, ste_b_host)
+GEN_VEXT_ST_WHOLE(vs4r_v, int8_t, ste_b_tlb, ste_b_host)
+GEN_VEXT_ST_WHOLE(vs8r_v, int8_t, ste_b_tlb, ste_b_host)
 
 /*
  * Vector Integer Arithmetic Instructions
-- 
2.34.1