[v4] RISC-V: Rewrite some instructions using ASM targethook

There are some xtheadvector instructions that differ from RVV1.0
apart from simply adding "th." prefix. For example, RVV1.0
load/store instructions will have SEW while xtheadvector not;
RVV1.0 will have "o" for indexed-ordered store instructions while
xtheadvecotr not; xtheadvector and RVV1.0 have different
vnsrl/vnsra/vfncvt suffix (vv/vx/vi vs wv/wx/wi).

To address this issue without duplicating patterns, we use ASM
targethook to rewrite the whole string of the instructions. We
identify different instructions from the corresponding attribute.

gcc/ChangeLog:

	* config/riscv/riscv.cc (riscv_asm_output_opcode):

Co-authored-by: Jin Ma <jinma@linux.alibaba.com>
Co-authored-by: Xianmiao Qu <cooper.qu@linux.alibaba.com>
Co-authored-by: Christoph Müllner <christoph.muellner@vrull.eu>
---
 gcc/config/riscv/riscv.cc | 213 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 210 insertions(+), 3 deletions(-)

Please move those code logic to thead.cc, e.g.

if (TARGET_XTHEADVECTOR)
  return th_asm_output_opcode (asm_out_file, p);

And then implement th_asm_output_opcode in thead.cc.


On Wed, Jan 3, 2024 at 10:39 AM Jun Sha (Joshua)
<cooper.joshua@linux.alibaba.com> wrote:
>
> There are some xtheadvector instructions that differ from RVV1.0
> apart from simply adding "th." prefix. For example, RVV1.0
> load/store instructions will have SEW while xtheadvector not;
> RVV1.0 will have "o" for indexed-ordered store instructions while
> xtheadvecotr not; xtheadvector and RVV1.0 have different
> vnsrl/vnsra/vfncvt suffix (vv/vx/vi vs wv/wx/wi).
>
> To address this issue without duplicating patterns, we use ASM
> targethook to rewrite the whole string of the instructions. We
> identify different instructions from the corresponding attribute.
>
> gcc/ChangeLog:
>
>         * config/riscv/riscv.cc (riscv_asm_output_opcode):
>
> Co-authored-by: Jin Ma <jinma@linux.alibaba.com>
> Co-authored-by: Xianmiao Qu <cooper.qu@linux.alibaba.com>
> Co-authored-by: Christoph Müllner <christoph.muellner@vrull.eu>
> ---
>  gcc/config/riscv/riscv.cc | 213 +++++++++++++++++++++++++++++++++++++-
>  1 file changed, 210 insertions(+), 3 deletions(-)
>
> diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
> index a80bf8d1a74..13cdfc4ee27 100644
> --- a/gcc/config/riscv/riscv.cc
> +++ b/gcc/config/riscv/riscv.cc
> @@ -5646,9 +5646,216 @@ riscv_asm_output_opcode (FILE *asm_out_file, const char *p)
>  {
>    /* We need to add th. prefix to all the xtheadvector
>       insturctions here.*/
> -  if (TARGET_XTHEADVECTOR && current_output_insn != NULL_RTX &&
> -      p[0] == 'v')
> -    fputs ("th.", asm_out_file);
> +  if (TARGET_XTHEADVECTOR && current_output_insn != NULL_RTX)
> +    {
> +      if (get_attr_type (current_output_insn) == TYPE_VLDE ||
> +         get_attr_type (current_output_insn) == TYPE_VSTE ||
> +         get_attr_type (current_output_insn) == TYPE_VLDFF)
> +       {
> +         if (strstr (p, "e8") || strstr (p, "e16") ||
> +             strstr (p, "e32") || strstr (p, "e64"))
> +           {
> +             get_attr_type (current_output_insn) == TYPE_VSTE
> +                                 ? fputs ("th.vse", asm_out_file)
> +                                 : fputs ("th.vle", asm_out_file);
> +             if (strstr (p, "e8"))
> +               return p+4;
> +             else
> +               return p+5;
> +           }
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VLDS ||
> +         get_attr_type (current_output_insn) == TYPE_VSTS)
> +       {
> +         if (strstr (p, "vle8") || strstr (p, "vse8") ||
> +             strstr (p, "vle16") || strstr (p, "vse16") ||
> +             strstr (p, "vle32") || strstr (p, "vse32") ||
> +             strstr (p, "vle64") || strstr (p, "vse64"))
> +           {
> +             get_attr_type (current_output_insn) == TYPE_VSTS
> +                                 ? fputs ("th.vse", asm_out_file)
> +                                 : fputs ("th.vle", asm_out_file);
> +             if (strstr (p, "e8"))
> +               return p+4;
> +             else
> +               return p+5;
> +           }
> +         else if (strstr (p, "vlse8") || strstr (p, "vsse8") ||
> +                  strstr (p, "vlse16") || strstr (p, "vsse16") ||
> +                  strstr (p, "vlse32") || strstr (p, "vsse32") ||
> +                  strstr (p, "vlse64") || strstr (p, "vsse64"))
> +           {
> +             get_attr_type (current_output_insn) == TYPE_VSTS
> +                                 ? fputs ("th.vsse", asm_out_file)
> +                                 : fputs ("th.vlse", asm_out_file);
> +             if (strstr (p, "e8"))
> +               return p+5;
> +             else
> +               return p+6;
> +           }
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VLDUX ||
> +         get_attr_type (current_output_insn) == TYPE_VLDOX)
> +       {
> +         if (strstr (p, "ei"))
> +           {
> +             fputs ("th.vlxe", asm_out_file);
> +             if (strstr (p, "ei8"))
> +               return p+7;
> +             else
> +               return p+8;
> +           }
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VSTUX ||
> +         get_attr_type (current_output_insn) == TYPE_VSTOX)
> +       {
> +         if (strstr (p, "ei"))
> +           {
> +             get_attr_type (current_output_insn) == TYPE_VSTUX
> +                               ? fputs ("th.vsuxe", asm_out_file)
> +                               : fputs ("th.vsxe", asm_out_file);
> +             if (strstr (p, "ei8"))
> +               return p+7;
> +             else
> +               return p+8;
> +           }
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VLSEGDE ||
> +         get_attr_type (current_output_insn) == TYPE_VSSEGTE ||
> +         get_attr_type (current_output_insn) == TYPE_VLSEGDFF)
> +       {
> +         get_attr_type (current_output_insn) == TYPE_VSSEGTE
> +                               ? fputs ("th.vsseg", asm_out_file)
> +                               : fputs ("th.vlseg", asm_out_file);
> +         asm_fprintf (asm_out_file, "%c", p[5]);
> +         fputs ("e", asm_out_file);
> +         if (strstr (p, "e8"))
> +           return p+8;
> +         else
> +           return p+9;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VLSEGDS ||
> +         get_attr_type (current_output_insn) == TYPE_VSSEGTS)
> +       {
> +         get_attr_type (current_output_insn) == TYPE_VSSEGTS
> +                               ? fputs ("th.vssseg", asm_out_file)
> +                               : fputs ("th.vlsseg", asm_out_file);
> +         asm_fprintf (asm_out_file, "%c", p[6]);
> +         fputs ("e", asm_out_file);
> +         if (strstr (p, "e8"))
> +           return p+9;
> +         else
> +           return p+10;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VLSEGDUX ||
> +         get_attr_type (current_output_insn) == TYPE_VLSEGDOX)
> +       {
> +         fputs ("th.vlxseg", asm_out_file);
> +         asm_fprintf (asm_out_file, "%c", p[7]);
> +         fputs ("e", asm_out_file);
> +         if (strstr (p, "e8"))
> +           return p+10;
> +         else
> +           return p+11;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VSSEGTUX ||
> +         get_attr_type (current_output_insn) == TYPE_VSSEGTOX)
> +       {
> +         fputs ("th.vsxseg", asm_out_file);
> +         asm_fprintf (asm_out_file, "%c", p[7]);
> +         fputs ("e", asm_out_file);
> +         if (strstr (p, "e8"))
> +           return p+10;
> +         else
> +           return p+11;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VNSHIFT)
> +       {
> +         if (strstr (p, "vncvt"))
> +           {
> +             fputs ("th.vncvt.x.x.v", asm_out_file);
> +             return p+11;
> +           }
> +
> +         strstr (p, "vnsrl") ? fputs ("th.vnsrl.v", asm_out_file)
> +                             : fputs ("th.vnsra.v", asm_out_file);
> +         return p+7;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VNCLIP)
> +       {
> +         if (strstr (p, "vnclipu"))
> +           {
> +             fputs ("th.vnclipu.v", asm_out_file);
> +             return p+9;
> +           }
> +         else
> +           {
> +             fputs ("th.vnclip.v", asm_out_file);
> +             return p+8;
> +           }
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VMPOP)
> +       {
> +         fputs ("th.vmpopc", asm_out_file);
> +         return p+5;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VMFFS)
> +       {
> +         fputs ("th.vmfirst", asm_out_file);
> +         return p+6;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VFNCVTFTOI ||
> +         get_attr_type (current_output_insn) == TYPE_VFNCVTITOF)
> +       {
> +         if (strstr (p, "xu"))
> +           {
> +             get_attr_type (current_output_insn) == TYPE_VFNCVTFTOI
> +                          ? fputs ("th.vfncvt.xu.f.v", asm_out_file)
> +                          : fputs ("th.vfncvt.f.xu.v", asm_out_file);
> +         return p+13;
> +       }
> +         else
> +           {
> +             get_attr_type (current_output_insn) == TYPE_VFNCVTFTOI
> +                          ? fputs ("th.vfncvt.x.f.v", asm_out_file)
> +                          : fputs ("th.vfncvt.f.x.v", asm_out_file);
> +             return p+12;
> +           }
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VFNCVTFTOF)
> +       {
> +         fputs ("th.vfncvt.f.f.v", asm_out_file);
> +         return p+12;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VFREDU)
> +       {
> +         fputs ("th.vfredsum", asm_out_file);
> +         return p+9;
> +       }
> +
> +      if (get_attr_type (current_output_insn) == TYPE_VFWREDU)
> +       {
> +         fputs ("th.vfwredsum", asm_out_file);
> +         return p+10;
> +       }
> +
> +      if (p[0] == 'v')
> +       fputs ("th.", asm_out_file);
> +    }
>
>    return p;
>  }
> --
> 2.17.1
>