[xstormy16] Improved SImode shifts by two bits.

Currently on xstormy16 SImode shifts by a single bit require two
instructions, and shifts by other non-zero integer immediate constants
require five instructions.  This patch implements the obvious optimization
that shifts by two bits can be done in four instructions, by using two
single-bit sequences.

Hence, ashift_2 was previously generated as:
        mov r7,r2 | shl r2,#2 | shl r3,#2 | shr r7,#14 | or r3,r7
        ret
and with this patch we now generate:
        shl r2,#1 | rlc r3,#1 | shl r2,#1 | rlc r3,#1
        ret

2023-04-23  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	* config/stormy16/stormy16.cc (xstormy16_output_shift): Implement
	SImode shifts by two by performing a single bit SImode shift twice.

gcc/testsuite/ChangeLog
	* gcc.target/xstormy16/shiftsi.c: New test case.

gcc/config/stormy16/stormy16.cc

@@ -2105,6 +2105,29 @@ xstormy16_output_shift (machine_mode mode, enum rtx_code code,
       return r;
     }
 
+  /* For shifts of size 2, we can use two shifts of size 1.  */
+  if (size == 2)
+    {
+      switch (code)
+	{
+	case ASHIFT:
+	  sprintf (r, "shl %s,#1 | rlc %s,#1 | shl %s,#1 | rlc %s,#1",
+		   r0, r1, r0, r1);
+	  break;
+	case ASHIFTRT:
+	  sprintf (r, "asr %s,#1 | rrc %s,#1 | asr %s,#1 | rrc %s,#1",
+		   r1, r0, r1, r0);
+	  break;
+	case LSHIFTRT:
+	  sprintf (r, "shr %s,#1 | rrc %s,#1 | shr %s,#1 | rrc %s,#1",
+		   r1, r0, r1, r0);
+	  break;
+	default:
+	  gcc_unreachable ();
+	}
+      return r;
+    }
+
   /* For large shifts, there are easy special cases.  */
   if (size == 16)
     {

gcc/testsuite/gcc.target/xstormy16/shiftsi.c

@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+unsigned long ashift_1(unsigned long x) { return x << 1; }
+unsigned long ashift_2(unsigned long x) { return x << 2; }
+unsigned long lshiftrt_1(unsigned long x) { return x >> 1; }
+unsigned long lshiftrt_2(unsigned long x) { return x >> 2; }
+long ashiftrt_1(long x) { return x >> 1; }
+long ashiftrt_2(long x) { return x >> 2; }
+
+/* { dg-final { scan-assembler-not "mov " } } */
+/* { dg-final { scan-assembler-not "or " } } */