RISC-V: Implement locality for __builtin_prefetch

The patch add the Zihintntl instructions in the prefetch pattern.
Zicbop has prefetch instructions. Zihintntl has NTL instructions.
Insert NTL instructions before prefetch instruction, if target
has Zihintntl extension.

gcc/ChangeLog:

	* config/riscv/riscv.cc (riscv_print_operand): Add 'L' letter
	to print zihintntl instructions string.
	* config/riscv/riscv.md (prefetch): Add zihintntl instructions.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/prefetch-zicbop.c: New test.
	* gcc.target/riscv/prefetch-zihintntl.c: New test.

4 files changed, 69 insertions, 3 deletions

diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index 53ab2f1..084a592 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -6488,6 +6488,7 @@ riscv_asm_output_opcode (FILE *asm_out_file, const char *p)
    'A'	Print the atomic operation suffix for memory model OP.
    'I'	Print the LR suffix for memory model OP.
    'J'	Print the SC suffix for memory model OP.
+   'L'	Print a non-temporal locality hints instruction.
    'z'	Print x0 if OP is zero, otherwise print OP normally.
    'i'	Print i if the operand is not a register.
    'S'	Print shift-index of single-bit mask OP.
@@ -6682,6 +6683,27 @@ riscv_print_operand (FILE *file, rtx op, int letter)
       break;
     }
 
+    case 'L':
+      {
+	const char *ntl_hint = NULL;
+	switch (INTVAL (op))
+	  {
+	  case 0:
+	    ntl_hint = "ntl.all";
+	    break;
+	  case 1:
+	    ntl_hint = "ntl.pall";
+	    break;
+	  case 2:
+	    ntl_hint = "ntl.p1";
+	    break;
+	  }
+
+      if (ntl_hint)
+	asm_fprintf (file, "%s\n\t", ntl_hint);
+      break;
+      }
+
     case 'i':
       if (code != REG)
         fputs ("i", file);
diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index 379015c..46c4603 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -4113,12 +4113,16 @@
 {
   switch (INTVAL (operands[1]))
   {
-    case 0: return "prefetch.r\t%a0";
-    case 1: return "prefetch.w\t%a0";
+    case 0: return TARGET_ZIHINTNTL ? "%L2prefetch.r\t%a0" : "prefetch.r\t%a0";
+    case 1: return TARGET_ZIHINTNTL ? "%L2prefetch.w\t%a0" : "prefetch.w\t%a0";
     default: gcc_unreachable ();
   }
 }
-  [(set_attr "type" "store")])
+  [(set_attr "type" "store")
+   (set (attr "length") (if_then_else (and (match_test "TARGET_ZIHINTNTL")
+					   (match_test "IN_RANGE (INTVAL (operands[2]), 0, 2)"))
+				      (const_string "8")
+				      (const_string "4")))])
 
 (define_insn "riscv_prefetchi_<mode>"
   [(unspec_volatile:X [(match_operand:X 0 "address_operand" "r")
diff --git a/gcc/testsuite/gcc.target/riscv/prefetch-zicbop.c b/gcc/testsuite/gcc.target/riscv/prefetch-zicbop.c
new file mode 100644
index 0000000..0faa120
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/prefetch-zicbop.c
@@ -0,0 +1,20 @@
+/* { dg-do compile target { { rv64-*-*}}} */
+/* { dg-options "-march=rv64gc_zicbop -mabi=lp64" } */
+
+void foo (char *p)
+{
+  __builtin_prefetch (p, 0, 0);
+  __builtin_prefetch (p, 0, 1);
+  __builtin_prefetch (p, 0, 2);
+  __builtin_prefetch (p, 0, 3);
+  __builtin_prefetch (p, 1, 0);
+  __builtin_prefetch (p, 1, 1);
+  __builtin_prefetch (p, 1, 2);
+  __builtin_prefetch (p, 1, 3);
+}
+
+/* { dg-final { scan-assembler-not "ntl.all\t" } } */
+/* { dg-final { scan-assembler-not "ntl.pall\t" } } */
+/* { dg-final { scan-assembler-not "ntl.p1\t" } } */
+/* { dg-final { scan-assembler-times "prefetch.r" 4 } } */
+/* { dg-final { scan-assembler-times "prefetch.w" 4 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/prefetch-zihintntl.c b/gcc/testsuite/gcc.target/riscv/prefetch-zihintntl.c
new file mode 100644
index 0000000..78a3afe
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/prefetch-zihintntl.c
@@ -0,0 +1,20 @@
+/* { dg-do compile target { { rv64-*-*}}} */
+/* { dg-options "-march=rv64gc_zicbop_zihintntl -mabi=lp64" } */
+
+void foo (char *p)
+{
+  __builtin_prefetch (p, 0, 0);
+  __builtin_prefetch (p, 0, 1);
+  __builtin_prefetch (p, 0, 2);
+  __builtin_prefetch (p, 0, 3);
+  __builtin_prefetch (p, 1, 0);
+  __builtin_prefetch (p, 1, 1);
+  __builtin_prefetch (p, 1, 2);
+  __builtin_prefetch (p, 1, 3);
+}
+
+/* { dg-final { scan-assembler-times "ntl.all" 2 } } */
+/* { dg-final { scan-assembler-times "ntl.pall" 2 } } */
+/* { dg-final { scan-assembler-times "ntl.p1" 2 } } */
+/* { dg-final { scan-assembler-times "prefetch.r" 4 } } */
+/* { dg-final { scan-assembler-times "prefetch.w" 4 } } */