Fix PR 106601: __builtin_bswap16 code gen could be improved with ZBB enabled

The default expansion for bswap16 is two extractions (shift/and)
followed by an insertation (ior) and then a zero extend. This can be improved
with ZBB enabled to just full byteswap followed by a (logical) shift right.
This patch adds a new pattern for this which does that.

OK? Built and tested on riscv32-linux-gnu and riscv64-linux-gnu.

gcc/ChangeLog:

	PR target/106601
	* config/riscv/bitmanip.md (bswaphi2): New pattern.

gcc/testsuite/ChangeLog:

	PR target/106601
	* gcc.target/riscv/zbb_32_bswap-2.c: New test.
	* gcc.target/riscv/zbb_bswap-2.c: New test.

(cherry picked from commit e5e6983)

Signed-off-by: Stephanos Ioannidis <root@stephanos.io>

Author: apinski-cavium

gcc/config/riscv/bitmanip.md

@@ -232,6 +232,30 @@
   "rev8\t%0,%1"
   [(set_attr "type" "bitmanip")])
 
+;; HI bswap can be emulated using SI/DI bswap followed
+;; by a logical shift right
+;; SI bswap for TARGET_64BIT is already similarly in
+;; the common code.
+(define_expand "bswaphi2"
+  [(set (match_operand:HI 0 "register_operand" "=r")
+        (bswap:HI (match_operand:HI 1 "register_operand" "r")))]
+  "TARGET_ZBB"
+{
+  rtx tmp = gen_reg_rtx (word_mode);
+  rtx newop1 = gen_lowpart (word_mode, operands[1]);
+  if (TARGET_64BIT)
+    emit_insn (gen_bswapdi2 (tmp, newop1));
+  else
+    emit_insn (gen_bswapsi2 (tmp, newop1));
+  rtx tmp1 = gen_reg_rtx (word_mode);
+  if (TARGET_64BIT)
+    emit_insn (gen_lshrdi3 (tmp1, tmp, GEN_INT (64 - 16)));
+  else
+    emit_insn (gen_lshrsi3 (tmp1, tmp, GEN_INT (32 - 16)));
+  emit_move_insn (operands[0], gen_lowpart (HImode, tmp1));
+  DONE;
+})
+
 (define_insn "<bitmanip_optab><mode>3"
   [(set (match_operand:X 0 "register_operand" "=r")
         (bitmanip_minmax:X (match_operand:X 1 "register_operand" "r")

gcc/testsuite/gcc.target/riscv/zbb_32_bswap-2.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gc_zbb -mabi=ilp32" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" } } */
+
+int foo(int n)
+{
+  return __builtin_bswap16(n);
+}
+
+/* { dg-final { scan-assembler "rev8" } } */
+/* { dg-final { scan-assembler "srli" } } */
+

gcc/testsuite/gcc.target/riscv/zbb_bswap-2.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zbb -mabi=lp64" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" } } */
+
+int foo(int n)
+{
+  return __builtin_bswap16(n);
+}
+
+/* { dg-final { scan-assembler "rev8" } } */
+/* { dg-final { scan-assembler "srli" } } */
+