LoongArch: Use bstrins for "value & (-1u << const)"

A move/bstrins pair is as fast as a (addi.w|lu12i.w|lu32i.d|lu52i.d)/and
pair, and twice fast as a srli/slli pair.  When the src reg and the dst
reg happens to be the same, the move instruction can be optimized away.

gcc/ChangeLog:

	* config/loongarch/predicates.md (high_bitmask_operand): New
	predicate.
	* config/loongarch/constraints.md (Yy): New constriant.
	* config/loongarch/loongarch.md (and<mode>3_align): New
	define_insn_and_split.

gcc/testsuite/ChangeLog:

	* gcc.target/loongarch/bstrins-1.c: New test.
	* gcc.target/loongarch/bstrins-2.c: New test.

gcc/config/loongarch/constraints.md

@@ -94,6 +94,7 @@
 ;;       "A constant @code{move_operand} that can be safely loaded using
 ;;	  @code{la}."
 ;;    "Yx"
+;;    "Yy"
 ;; "Z" -
 ;;    "ZC"
 ;;      "A memory operand whose address is formed by a base register and offset
@@ -291,6 +292,10 @@
    "@internal"
    (match_operand 0 "low_bitmask_operand"))
 
+(define_constraint "Yy"
+   "@internal"
+   (match_operand 0 "high_bitmask_operand"))
+
 (define_constraint "YI"
   "@internal
    A replicated vector const in which the replicated value is in the range

gcc/config/loongarch/loongarch.md

@@ -1542,6 +1542,23 @@
   [(set_attr "move_type" "pick_ins")
    (set_attr "mode" "<MODE>")])
 
+(define_insn_and_split "and<mode>3_align"
+  [(set (match_operand:GPR 0 "register_operand" "=r")
+	(and:GPR (match_operand:GPR 1 "register_operand" "r")
+		 (match_operand:GPR 2 "high_bitmask_operand" "Yy")))]
+  ""
+  "#"
+  ""
+  [(set (match_dup 0) (match_dup 1))
+   (set (zero_extract:GPR (match_dup 0) (match_dup 2) (const_int 0))
+	(const_int 0))]
+{
+  int len;
+
+  len = low_bitmask_len (<MODE>mode, ~INTVAL (operands[2]));
+  operands[2] = GEN_INT (len);
+})
+
 (define_insn_and_split "*bstrins_<mode>_for_mask"
   [(set (match_operand:GPR 0 "register_operand" "=r")
 	(and:GPR (match_operand:GPR 1 "register_operand" "r")

gcc/config/loongarch/predicates.md

@@ -293,6 +293,10 @@
   (and (match_code "const_int")
        (match_test "low_bitmask_len (mode, INTVAL (op)) > 12")))
 
+(define_predicate "high_bitmask_operand"
+  (and (match_code "const_int")
+       (match_test "low_bitmask_len (mode, ~INTVAL (op)) > 0")))
+
 (define_predicate "d_operand"
   (and (match_code "reg")
        (match_test "GP_REG_P (REGNO (op))")))

gcc/testsuite/gcc.target/loongarch/bstrins-1.c

@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=loongarch64 -mabi=lp64d" } */
+/* { dg-final { scan-assembler "bstrins\\.d\t\\\$r4,\\\$r0,4,0" } } */
+
+long
+x (long a)
+{
+  return a & -32;
+}

gcc/testsuite/gcc.target/loongarch/bstrins-2.c

@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=loongarch64 -mabi=lp64d" } */
+/* { dg-final { scan-assembler "bstrins\\.d\t\\\$r\[0-9\]+,\\\$r0,4,0" } } */
+
+struct aligned_buffer {
+  _Alignas(32) char x[1024];
+};
+
+extern int f(char *);
+int g(void)
+{
+  struct aligned_buffer buf;
+  return f(buf.x);
+}