[v1,2/2] LoongArch: Add prefetch insns.

  Co-Authored-By: xujiahao <xujiahao@loongson.cn>

gcc/ChangeLog:

	* config/loongarch/loongarch-def.c: Initial number of parallel prefetch.
	* config/loongarch/loongarch-protos.h (loongarch_prefetch_cookie):
	Function declaration.
	* config/loongarch/loongarch-tune.h (struct loongarch_cache):
	Define number of parallel prefetch.
	* config/loongarch/loongarch.cc (loongarch_option_override_internal):
	Set up parameters to be used in prefetching algorithm.
	(loongarch_prefetch_cookie): Select load or store based on the value of write.
	* config/loongarch/loongarch.md (prefetch): New template.
	(*prefetch_indexed_<mode>): New template.
---
 gcc/config/loongarch/loongarch-def.c    |  2 ++
 gcc/config/loongarch/loongarch-protos.h |  1 +
 gcc/config/loongarch/loongarch-tune.h   |  1 +
 gcc/config/loongarch/loongarch.cc       | 48 +++++++++++++++++++++++++
 gcc/config/loongarch/loongarch.md       | 23 ++++++++++++
 5 files changed, 75 insertions(+)
  

Sorry for the problem in this patch. I will send it again after 
modification.

在 2022/10/29 下午3:05, Lulu Cheng 写道:
> Co-Authored-By: xujiahao <xujiahao@loongson.cn>
>
> gcc/ChangeLog:
>
> 	* config/loongarch/loongarch-def.c: Initial number of parallel prefetch.
> 	* config/loongarch/loongarch-protos.h (loongarch_prefetch_cookie):
> 	Function declaration.
> 	* config/loongarch/loongarch-tune.h (struct loongarch_cache):
> 	Define number of parallel prefetch.
> 	* config/loongarch/loongarch.cc (loongarch_option_override_internal):
> 	Set up parameters to be used in prefetching algorithm.
> 	(loongarch_prefetch_cookie): Select load or store based on the value of write.
> 	* config/loongarch/loongarch.md (prefetch): New template.
> 	(*prefetch_indexed_<mode>): New template.
> ---
>   gcc/config/loongarch/loongarch-def.c    |  2 ++
>   gcc/config/loongarch/loongarch-protos.h |  1 +
>   gcc/config/loongarch/loongarch-tune.h   |  1 +
>   gcc/config/loongarch/loongarch.cc       | 48 +++++++++++++++++++++++++
>   gcc/config/loongarch/loongarch.md       | 23 ++++++++++++
>   5 files changed, 75 insertions(+)
>
> diff --git a/gcc/config/loongarch/loongarch-def.c b/gcc/config/loongarch/loongarch-def.c
> index cbf995d81b5..80ab10a52a8 100644
> --- a/gcc/config/loongarch/loongarch-def.c
> +++ b/gcc/config/loongarch/loongarch-def.c
> @@ -62,11 +62,13 @@ loongarch_cpu_cache[N_TUNE_TYPES] = {
>         .l1d_line_size = 64,
>         .l1d_size = 64,
>         .l2d_size = 256,
> +      .simultaneous_prefetches = 4,
>     },
>     [CPU_LA464] = {
>         .l1d_line_size = 64,
>         .l1d_size = 64,
>         .l2d_size = 256,
> +      .simultaneous_prefetches = 4,
>     },
>   };
>   
> diff --git a/gcc/config/loongarch/loongarch-protos.h b/gcc/config/loongarch/loongarch-protos.h
> index 77b2217247d..489525b520e 100644
> --- a/gcc/config/loongarch/loongarch-protos.h
> +++ b/gcc/config/loongarch/loongarch-protos.h
> @@ -179,5 +179,6 @@ extern tree loongarch_builtin_decl (unsigned int, bool);
>   extern rtx loongarch_expand_builtin (tree, rtx, rtx subtarget ATTRIBUTE_UNUSED,
>   				     machine_mode, int);
>   extern tree loongarch_build_builtin_va_list (void);
> +extern rtx loongarch_prefetch_cookie (rtx, rtx);
>   
>   #endif /* ! GCC_LOONGARCH_PROTOS_H */
> diff --git a/gcc/config/loongarch/loongarch-tune.h b/gcc/config/loongarch/loongarch-tune.h
> index 6f3530f5c02..8e3eb29472b 100644
> --- a/gcc/config/loongarch/loongarch-tune.h
> +++ b/gcc/config/loongarch/loongarch-tune.h
> @@ -45,6 +45,7 @@ struct loongarch_cache {
>       int l1d_line_size;  /* bytes */
>       int l1d_size;       /* KiB */
>       int l2d_size;       /* kiB */
> +    int simultaneous_prefetches; /* number of parallel prefetch */
>   };
>   
>   #endif /* LOONGARCH_TUNE_H */
> diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
> index 5e8cd293645..d663afe434d 100644
> --- a/gcc/config/loongarch/loongarch.cc
> +++ b/gcc/config/loongarch/loongarch.cc
> @@ -63,6 +63,7 @@ along with GCC; see the file COPYING3.  If not see
>   #include "context.h"
>   #include "builtins.h"
>   #include "rtl-iter.h"
> +#include "params.h"
>   
>   /* This file should be included last.  */
>   #include "target-def.h"
> @@ -6126,6 +6127,33 @@ loongarch_option_override_internal (struct gcc_options *opts)
>     if (loongarch_branch_cost == 0)
>       loongarch_branch_cost = loongarch_cost->branch_cost;
>   
> +  /* Set up parameters to be used in prefetching algorithm. */
> +  maybe_set_param_value (PARAM_SIMULTANEOUS_PREFETCHES,
> +			 loongarch_cpu_cache[LARCH_ACTUAL_TUNE].simultaneous_prefetches,
> +			 opts->x_param_values,
> +			 opts_set->x_param_values);
> +
> +  maybe_set_param_value (PARAM_L1_CACHE_LINE_SIZE,
> +			 loongarch_cpu_cache[LARCH_ACTUAL_TUNE].l1d_line_size,
> +			 opts->x_param_values,
> +			 opts_set->x_param_values);
> +
> +  maybe_set_param_value (PARAM_L1_CACHE_SIZE,
> +			 loongarch_cpu_cache[LARCH_ACTUAL_TUNE].l1d_size,
> +			 opts->x_param_values,
> +			 opts_set->x_param_values);
> +
> +  maybe_set_param_value (PARAM_L2_CACHE_SIZE,
> +			 loongarch_cpu_cache[LARCH_ACTUAL_TUNE].l2d_size,
> +			 opts->x_param_values,
> +			 opts_set->x_param_values);
> +
> +  /* Enable sw prefetching at -O3 and higher. */
> +  if (opts->x_flag_prefetch_loop_arrays < 0
> +      && (opts->x_optimize >= 3 || opts->x_flag_profile_use)
> +      && !opts->x_optimize_size)
> +    opts->x_flag_prefetch_loop_arrays = 1;
> +
>     if (TARGET_DIRECT_EXTERN_ACCESS && flag_shlib)
>       error ("%qs cannot be used for compiling a shared library",
>   	   "-mdirect-extern-access");
> @@ -6506,6 +6534,26 @@ loongarch_asan_shadow_offset (void)
>     return TARGET_64BIT ? (HOST_WIDE_INT_1 << 46) : 0;
>   }
>   
> +/* LoongArch only implements preld hint=0 (prefetch for load) and hint=8
> +   (prefetch for store), other hint just scale to hint = 0 and hint = 1. */
> +
> +rtx
> +loongarch_prefetch_cookie (rtx write, rtx locality)
> +{
> +  if (INTVAL (locality) == 1 && INTVAL (write) == 0)
> +    return GEN_INT (INTVAL (write) + 2);
> +
> +  /* store.  */
> +  if (INTVAL (write) == 1)
> +    return GEN_INT (INTVAL (write) + 7);
> +
> +  /* load.  */
> +  if (INTVAL (write) == 0)
> +    return GEN_INT (INTVAL (write));
> +
> +  gcc_unreachable ();
> +}
> +
>   /* Initialize the GCC target structure.  */
>   #undef TARGET_ASM_ALIGNED_HI_OP
>   #define TARGET_ASM_ALIGNED_HI_OP "\t.half\t"
> diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
> index 7eaa9ab66e3..be247164eb4 100644
> --- a/gcc/config/loongarch/loongarch.md
> +++ b/gcc/config/loongarch/loongarch.md
> @@ -3201,6 +3201,29 @@ (define_expand "untyped_call"
>   ;;  ....................
>   ;;
>   
> +(define_insn "prefetch"
> +  [(prefetch (match_operand 0 "address_operand" "p")
> +	     (match_operand 1 "const_int_operand" "n")
> +	     (match_operand 2 "const_int_operand" "n"))]
> +  ""
> +{
> +  operands[1] = loongarch_prefetch_cookie (operands[1], operands[2]);
> +  return "preld\t%1,%a0";
> +}
> +  [(set_attr "type" "prefetch")])
> +
> +(define_insn "*prefetch_indexed_<mode>"
> +  [(prefetch (plus:P (match_operand 0 "register_operand" "r")
> +		     (match_operand 1 "register_operand" "r"))
> +	     (match_operand 2 "const_int_operand" "n")
> +	     (match_operand 3 "const_int_operand" "n"))]
> +  ""
> +{
> +  operands[2] = loongarch_prefetch_cookie (operands[2], operands[3]);
> +  return "preldx\t%2,%1,%0";
> +}
> +  [(set_attr "type" "prefetchx")])
> +
>   (define_insn "nop"
>     [(const_int 0)]
>     ""