[v2] target/riscv/vector_helper.c: Remove the check for extra tail elements

Commit 752614cab8e6 ("target/riscv: rvv: Add tail agnostic for vector
load / store instructions") added an extra check for LMUL fragmentation,
intended for setting the "rest tail elements" in the last register for a
segment load insn.

Actually, the max_elements derived in vext_ld*() won't be a fraction of
vector register size, since the lmul encoded in desc is emul, which has
already been adjusted to 1 for LMUL fragmentation case by vext_get_emul()
in trans_rvv.c.inc, for ld_stride(), ld_us(), ld_index() and ldff().

Besides, vext_get_emul() has also taken EEW/SEW into consideration, so no
need to call vext_get_total_elems() which would base on the emul to derive
another emul, the second emul would be incorrect when esz differs from sew.

Thus this patch removes the check for extra tail elements.

Fixes: 752614cab8e6 ("target/riscv: rvv: Add tail agnostic for vector load / store instructions")

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
---
v2:
* Rebased on top of Alistair's riscv-to-apply.next branch.
---
 target/riscv/vector_helper.c | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

On 6/7/23 06:16, Xiao Wang wrote:
> Commit 752614cab8e6 ("target/riscv: rvv: Add tail agnostic for vector
> load / store instructions") added an extra check for LMUL fragmentation,
> intended for setting the "rest tail elements" in the last register for a
> segment load insn.
> 
> Actually, the max_elements derived in vext_ld*() won't be a fraction of
> vector register size, since the lmul encoded in desc is emul, which has
> already been adjusted to 1 for LMUL fragmentation case by vext_get_emul()
> in trans_rvv.c.inc, for ld_stride(), ld_us(), ld_index() and ldff().
> 
> Besides, vext_get_emul() has also taken EEW/SEW into consideration, so no
> need to call vext_get_total_elems() which would base on the emul to derive
> another emul, the second emul would be incorrect when esz differs from sew.
> 
> Thus this patch removes the check for extra tail elements.
> 
> Fixes: 752614cab8e6 ("target/riscv: rvv: Add tail agnostic for vector load / store instructions")
> 
> Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
> ---

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


> v2:
> * Rebased on top of Alistair's riscv-to-apply.next branch.
> ---
>   target/riscv/vector_helper.c | 22 ++++++----------------
>   1 file changed, 6 insertions(+), 16 deletions(-)
> 
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 7505f9470a..f261e726c2 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -264,11 +264,10 @@ 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,
> +static void vext_set_tail_elems_1s(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;
>   
> @@ -276,19 +275,10 @@ static void vext_set_tail_elems_1s(CPURISCVState *env, target_ulong vl,
>           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);
> -    }
>   }
>   
>   /*
> @@ -324,7 +314,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
>       }
>       env->vstart = 0;
>   
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>   }
>   
>   #define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN)                        \
> @@ -383,7 +373,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
>       }
>       env->vstart = 0;
>   
> -    vext_set_tail_elems_1s(env, evl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(evl, vd, desc, nf, esz, max_elems);
>   }
>   
>   /*
> @@ -504,7 +494,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
>       }
>       env->vstart = 0;
>   
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>   }
>   
>   #define GEN_VEXT_LD_INDEX(NAME, ETYPE, INDEX_FN, LOAD_FN)                  \
> @@ -634,7 +624,7 @@ ProbeSuccess:
>       }
>       env->vstart = 0;
>   
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>   }
>   
>   #define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN)               \

On 2023/6/7 17:16, Xiao Wang wrote:
> Commit 752614cab8e6 ("target/riscv: rvv: Add tail agnostic for vector
> load / store instructions") added an extra check for LMUL fragmentation,
> intended for setting the "rest tail elements" in the last register for a
> segment load insn.
>
> Actually, the max_elements derived in vext_ld*() won't be a fraction of
> vector register size, since the lmul encoded in desc is emul, which has
> already been adjusted to 1 for LMUL fragmentation case by vext_get_emul()
> in trans_rvv.c.inc, for ld_stride(), ld_us(), ld_index() and ldff().
>
> Besides, vext_get_emul() has also taken EEW/SEW into consideration, so no
> need to call vext_get_total_elems() which would base on the emul to derive
> another emul, the second emul would be incorrect when esz differs from sew.
>
> Thus this patch removes the check for extra tail elements.
>
> Fixes: 752614cab8e6 ("target/riscv: rvv: Add tail agnostic for vector load / store instructions")
>
> Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
> ---
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>

Weiwei Li
> v2:
> * Rebased on top of Alistair's riscv-to-apply.next branch.
> ---
>   target/riscv/vector_helper.c | 22 ++++++----------------
>   1 file changed, 6 insertions(+), 16 deletions(-)
>
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 7505f9470a..f261e726c2 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -264,11 +264,10 @@ 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,
> +static void vext_set_tail_elems_1s(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;
>   
> @@ -276,19 +275,10 @@ static void vext_set_tail_elems_1s(CPURISCVState *env, target_ulong vl,
>           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);
> -    }
>   }
>   
>   /*
> @@ -324,7 +314,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
>       }
>       env->vstart = 0;
>   
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>   }
>   
>   #define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN)                        \
> @@ -383,7 +373,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
>       }
>       env->vstart = 0;
>   
> -    vext_set_tail_elems_1s(env, evl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(evl, vd, desc, nf, esz, max_elems);
>   }
>   
>   /*
> @@ -504,7 +494,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
>       }
>       env->vstart = 0;
>   
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>   }
>   
>   #define GEN_VEXT_LD_INDEX(NAME, ETYPE, INDEX_FN, LOAD_FN)                  \
> @@ -634,7 +624,7 @@ ProbeSuccess:
>       }
>       env->vstart = 0;
>   
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>   }
>   
>   #define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN)               \

On Wed, Jun 7, 2023 at 7:13 PM Xiao Wang <xiao.w.wang@intel.com> wrote:
>
> Commit 752614cab8e6 ("target/riscv: rvv: Add tail agnostic for vector
> load / store instructions") added an extra check for LMUL fragmentation,
> intended for setting the "rest tail elements" in the last register for a
> segment load insn.
>
> Actually, the max_elements derived in vext_ld*() won't be a fraction of
> vector register size, since the lmul encoded in desc is emul, which has
> already been adjusted to 1 for LMUL fragmentation case by vext_get_emul()
> in trans_rvv.c.inc, for ld_stride(), ld_us(), ld_index() and ldff().
>
> Besides, vext_get_emul() has also taken EEW/SEW into consideration, so no
> need to call vext_get_total_elems() which would base on the emul to derive
> another emul, the second emul would be incorrect when esz differs from sew.
>
> Thus this patch removes the check for extra tail elements.
>
> Fixes: 752614cab8e6 ("target/riscv: rvv: Add tail agnostic for vector load / store instructions")
>
> Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>

Thanks!

Applied to riscv-to-apply.next

Alistair

> ---
> v2:
> * Rebased on top of Alistair's riscv-to-apply.next branch.
> ---
>  target/riscv/vector_helper.c | 22 ++++++----------------
>  1 file changed, 6 insertions(+), 16 deletions(-)
>
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 7505f9470a..f261e726c2 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -264,11 +264,10 @@ 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,
> +static void vext_set_tail_elems_1s(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;
>
> @@ -276,19 +275,10 @@ static void vext_set_tail_elems_1s(CPURISCVState *env, target_ulong vl,
>          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);
> -    }
>  }
>
>  /*
> @@ -324,7 +314,7 @@ vext_ldst_stride(void *vd, void *v0, target_ulong base,
>      }
>      env->vstart = 0;
>
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>  }
>
>  #define GEN_VEXT_LD_STRIDE(NAME, ETYPE, LOAD_FN)                        \
> @@ -383,7 +373,7 @@ vext_ldst_us(void *vd, target_ulong base, CPURISCVState *env, uint32_t desc,
>      }
>      env->vstart = 0;
>
> -    vext_set_tail_elems_1s(env, evl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(evl, vd, desc, nf, esz, max_elems);
>  }
>
>  /*
> @@ -504,7 +494,7 @@ vext_ldst_index(void *vd, void *v0, target_ulong base,
>      }
>      env->vstart = 0;
>
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>  }
>
>  #define GEN_VEXT_LD_INDEX(NAME, ETYPE, INDEX_FN, LOAD_FN)                  \
> @@ -634,7 +624,7 @@ ProbeSuccess:
>      }
>      env->vstart = 0;
>
> -    vext_set_tail_elems_1s(env, env->vl, vd, desc, nf, esz, max_elems);
> +    vext_set_tail_elems_1s(env->vl, vd, desc, nf, esz, max_elems);
>  }
>
>  #define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN)               \
> --
> 2.25.1
>
>