Re: [PATCH v6 7/7] target/riscv: Inline unit-stride ld/st and corresponding functions for performance

[Daniel Henrique Barboza]

On 9/18/24 2:14 PM, Max Chou wrote:

In the vector unit-stride load/store helper functions. the vext_ldst_us
& vext_ldst_whole functions corresponding most of the execution time.
Inline the functions can avoid the function call overhead to improve the
helper function performance.

Signed-off-by: Max Chou <max.c...@sifive.com>
Reviewed-by: Richard Henderson <richard.hender...@linaro.org>
---

Reviewed-by: Daniel Henrique Barboza <dbarb...@ventanamicro.com>

  target/riscv/vector_helper.c | 18 +++++++++++-------
  1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 654d5e111f3..0d5ed950486 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -152,14 +152,16 @@ typedef void vext_ldst_elem_fn_tlb(CPURISCVState *env, 
abi_ptr addr,
  typedef void vext_ldst_elem_fn_host(void *vd, uint32_t idx, void *host);

#define GEN_VEXT_LD_ELEM(NAME, ETYPE, H, LDSUF) \

-static void NAME##_tlb(CPURISCVState *env, abi_ptr addr,    \
+static inline QEMU_ALWAYS_INLINE                            \
+void NAME##_tlb(CPURISCVState *env, abi_ptr addr,           \
                  uint32_t idx, void *vd, uintptr_t retaddr)  \
  {                                                           \
      ETYPE *cur = ((ETYPE *)vd + H(idx));                    \
      *cur = cpu_##LDSUF##_data_ra(env, addr, retaddr);       \
  }                                                           \
                                                              \
-static void NAME##_host(void *vd, uint32_t idx, void *host) \
+static inline QEMU_ALWAYS_INLINE                            \
+void NAME##_host(void *vd, uint32_t idx, void *host)        \
  {                                                           \
      ETYPE *cur = ((ETYPE *)vd + H(idx));                    \
      *cur = (ETYPE)LDSUF##_p(host);                          \
@@ -171,14 +173,16 @@ GEN_VEXT_LD_ELEM(lde_w, uint32_t, H4, ldl)
  GEN_VEXT_LD_ELEM(lde_d, uint64_t, H8, ldq)

#define GEN_VEXT_ST_ELEM(NAME, ETYPE, H, STSUF) \

-static void NAME##_tlb(CPURISCVState *env, abi_ptr addr,    \
+static inline QEMU_ALWAYS_INLINE                            \
+void NAME##_tlb(CPURISCVState *env, abi_ptr addr,           \
                  uint32_t idx, void *vd, uintptr_t retaddr)  \
  {                                                           \
      ETYPE data = *((ETYPE *)vd + H(idx));                   \
      cpu_##STSUF##_data_ra(env, addr, data, retaddr);        \
  }                                                           \
                                                              \
-static void NAME##_host(void *vd, uint32_t idx, void *host) \
+static inline QEMU_ALWAYS_INLINE                            \
+void NAME##_host(void *vd, uint32_t idx, void *host)        \
  {                                                           \
      ETYPE data = *((ETYPE *)vd + H(idx));                   \
      STSUF##_p(host, data);                                  \
@@ -317,7 +321,7 @@ GEN_VEXT_ST_STRIDE(vsse64_v, int64_t, ste_d_tlb)
   */

/* unmasked unit-stride load and store operation */

-static void
+static inline QEMU_ALWAYS_INLINE void
  vext_page_ldst_us(CPURISCVState *env, void *vd, target_ulong addr,
                    uint32_t elems, uint32_t nf, uint32_t max_elems,
                    uint32_t log2_esz, bool is_load, int mmu_index,
@@ -369,7 +373,7 @@ vext_page_ldst_us(CPURISCVState *env, void *vd, 
target_ulong addr,
      }
  }

-static void

+static inline QEMU_ALWAYS_INLINE void
  vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
               vext_ldst_elem_fn_tlb *ldst_tlb,
               vext_ldst_elem_fn_host *ldst_host, uint32_t log2_esz,
@@ -756,7 +760,7 @@ GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d_tlb, lde_d_host)
  /*
   * load and store whole register instructions
   */
-static void
+static inline QEMU_ALWAYS_INLINE void
  vext_ldst_whole(void *vd, target_ulong base, CPURISCVState *env, uint32_t 
desc,
                  vext_ldst_elem_fn_tlb *ldst_tlb,
                  vext_ldst_elem_fn_host *ldst_host, uint32_t log2_esz,