LoongArch: Add prefetch instructions.

Enable sw prefetching at -O3 and higher.

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

gcc/ChangeLog:

	* config/loongarch/constraints.md (ZD): New constraint.
	* config/loongarch/loongarch-def.c: Initial number of parallel prefetch.
	* 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.
	* config/loongarch/loongarch.md (prefetch): New template.

gcc/config/loongarch/constraints.md

@@ -86,6 +86,10 @@
 ;;    "ZB"
 ;;      "An address that is held in a general-purpose register.
 ;;      The offset is zero"
+;;    "ZD"
+;;	"An address operand whose address is formed by a base register
+;;	 and offset that is suitable for use in instructions with the same
+;;	 addressing mode as @code{preld}."
 ;; "<" "Matches a pre-dec or post-dec operand." (Global non-architectural)
 ;; ">" "Matches a pre-inc or post-inc operand." (Global non-architectural)
 
@@ -190,3 +194,9 @@
   The offset is zero"
   (and (match_code "mem")
        (match_test "REG_P (XEXP (op, 0))")))
+
+(define_address_constraint "ZD"
+  "An address operand whose address is formed by a base register
+   and offset that is suitable for use in instructions with the same
+   addressing mode as @code{preld}."
+   (match_test "loongarch_12bit_offset_address_p (op, mode)"))

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,
   },
 };
 

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 */

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 "opts.h"
 
 /* This file should be included last.  */
 #include "target-def.h"
@@ -6100,6 +6101,33 @@ 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.  */
+  int simultaneous_prefetches
+    = loongarch_cpu_cache[LARCH_ACTUAL_TUNE].simultaneous_prefetches;
+
+  SET_OPTION_IF_UNSET (opts, &global_options_set,
+		       param_simultaneous_prefetches,
+		       simultaneous_prefetches);
+
+  SET_OPTION_IF_UNSET (opts, &global_options_set,
+		       param_l1_cache_line_size,
+		       loongarch_cpu_cache[LARCH_ACTUAL_TUNE].l1d_line_size);
+
+  SET_OPTION_IF_UNSET (opts, &global_options_set,
+		       param_l1_cache_size,
+		       loongarch_cpu_cache[LARCH_ACTUAL_TUNE].l1d_size);
+
+  SET_OPTION_IF_UNSET (opts, &global_options_set,
+		       param_l2_cache_size,
+		       loongarch_cpu_cache[LARCH_ACTUAL_TUNE].l2d_size);
+
+
+  /* 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");

gcc/config/loongarch/loongarch.md

@@ -3282,6 +3282,20 @@
 ;;  ....................
 ;;
 
+(define_insn "prefetch"
+  [(prefetch (match_operand 0 "address_operand" "ZD")
+	     (match_operand 1 "const_int_operand" "n")
+	     (match_operand 2 "const_int_operand" "n"))]
+  ""
+{
+  switch (INTVAL (operands[1]))
+  {
+    case 0: return "preld\t0,%a0";
+    case 1: return "preld\t8,%a0";
+    default: gcc_unreachable ();
+  }
+})
+
 (define_insn "nop"
   [(const_int 0)]
   ""