diff mbox series

[RFC,v4,5/5] target/riscv: Inline unit-stride ld/st and corresponding functions for performance

Message ID 20240613175122.1299212-6-max.chou@sifive.com
State New
Headers show
Series Improve the performance of RISC-V vector unit-stride/whole register ld/st instructions | expand

Commit Message

Max Chou June 13, 2024, 5:51 p.m. UTC
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.chou@sifive.com>
---
 target/riscv/vector_helper.c | 64 +++++++++++++++++++-----------------
 1 file changed, 34 insertions(+), 30 deletions(-)

Comments

Richard Henderson June 20, 2024, 4:44 a.m. UTC | #1
On 6/13/24 10:51, 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.chou@sifive.com>
> ---
>   target/riscv/vector_helper.c | 64 +++++++++++++++++++-----------------
>   1 file changed, 34 insertions(+), 30 deletions(-)


Reviewed-by: Richard Henderson <richard.henderson@linaro.org>


r~
diff mbox series

Patch

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index cba46ef16a5..29849a8b66f 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -415,20 +415,22 @@  typedef void vext_ldst_elem_fn_tlb(CPURISCVState *env, abi_ptr addr,
                                    uint32_t idx, void *vd, uintptr_t retaddr);
 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,                \
-                       uint32_t byte_off, void *vd, uintptr_t retaddr)  \
-{                                                                       \
-    uint8_t *reg = ((uint8_t *)vd + byte_off);                          \
-    ETYPE *cur = ((ETYPE *)reg);                                        \
-    *cur = cpu_##LDSUF##_data_ra(env, addr, retaddr);                   \
-}                                                                       \
-                                                                        \
-static void NAME##_host(void *vd, uint32_t byte_off, void *host)        \
-{                                                                       \
-    ETYPE val = LDSUF##_p(host);                                        \
-    uint8_t *reg = (uint8_t *)(vd + byte_off);                          \
-    *(ETYPE *)(reg) = val;                                              \
+#define GEN_VEXT_LD_ELEM(NAME, ETYPE, H, LDSUF)                 \
+static inline QEMU_ALWAYS_INLINE                                \
+void NAME##_tlb(CPURISCVState *env, abi_ptr addr,               \
+                uint32_t byte_off, void *vd, uintptr_t retaddr) \
+{                                                               \
+    uint8_t *reg = ((uint8_t *)vd + byte_off);                  \
+    ETYPE *cur = ((ETYPE *)reg);                                \
+    *cur = cpu_##LDSUF##_data_ra(env, addr, retaddr);           \
+}                                                               \
+                                                                \
+static inline QEMU_ALWAYS_INLINE                                \
+void NAME##_host(void *vd, uint32_t byte_off, void *host)       \
+{                                                               \
+    ETYPE val = LDSUF##_p(host);                                \
+    uint8_t *reg = (uint8_t *)(vd + byte_off);                  \
+    *(ETYPE *)(reg) = val;                                      \
 }
 
 GEN_VEXT_LD_ELEM(lde_b, uint8_t,  H1, ldub)
@@ -436,20 +438,22 @@  GEN_VEXT_LD_ELEM(lde_h, uint16_t, H2, lduw)
 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,                \
-                       uint32_t byte_off, void *vd, uintptr_t retaddr)  \
-{                                                                       \
-    uint8_t *reg = ((uint8_t *)vd + byte_off);                          \
-    ETYPE data = *((ETYPE *)reg);                                       \
-    cpu_##STSUF##_data_ra(env, addr, data, retaddr);                    \
-}                                                                       \
-                                                                        \
-static void NAME##_host(void *vd, uint32_t byte_off, void *host)        \
-{                                                                       \
-    uint8_t *reg = ((uint8_t *)vd + byte_off);                          \
-    ETYPE val = *(ETYPE *)(reg);                                        \
-    STSUF##_p(host, val);                                               \
+#define GEN_VEXT_ST_ELEM(NAME, ETYPE, H, STSUF)                 \
+static inline QEMU_ALWAYS_INLINE                                \
+void NAME##_tlb(CPURISCVState *env, abi_ptr addr,               \
+                uint32_t byte_off, void *vd, uintptr_t retaddr) \
+{                                                               \
+    uint8_t *reg = ((uint8_t *)vd + byte_off);                  \
+    ETYPE data = *((ETYPE *)reg);                               \
+    cpu_##STSUF##_data_ra(env, addr, data, retaddr);            \
+}                                                               \
+                                                                \
+static inline QEMU_ALWAYS_INLINE                                \
+void NAME##_host(void *vd, uint32_t byte_off, void *host)       \
+{                                                               \
+    uint8_t *reg = ((uint8_t *)vd + byte_off);                  \
+    ETYPE val = *(ETYPE *)(reg);                                \
+    STSUF##_p(host, val);                                       \
 }
 
 GEN_VEXT_ST_ELEM(ste_b, uint8_t,  H1, stb)
@@ -611,7 +615,7 @@  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_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,
@@ -1013,7 +1017,7 @@  GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d_tlb)
 /*
  * 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,