[middle-end PATCH] Prefer PLUS over IOR in RTL expansion of multi-word shifts/rotates.

This patch tweaks RTL expansion of multi-word shifts and rotates to use
PLUS rather than IOR for disjunctive operations.  During expansion of
these operations, the middle-end creates RTL like (X<<C1) | (Y>>C2)
where the constants C1 and C2 guarantee that bits don't overlap.
Hence the IOR can be performed by any any_or_plus operation, such as
IOR, XOR or PLUS; for word-size operations where carry chains aren't
an issue these should all be equally fast (single-cycle) instructions.
The benefit of this change is that targets with shift-and-add insns,
like x86's lea, can benefit from the LSHIFT-ADD form.

An example of a backend that benefits is ARC, which is demonstrated
by these two simple functions:

unsigned long long foo(unsigned long long x) { return x<<2; }

which with -O2 is currently compiled to:

foo:    lsr     r2,r0,30
        asl_s   r1,r1,2
        asl_s   r0,r0,2
        j_s.d   [blink]
        or_s    r1,r1,r2

with this patch becomes:

foo:    lsr     r2,r0,30
        add2    r1,r2,r1
        j_s.d   [blink]
        asl_s   r0,r0,2

unsigned long long bar(unsigned long long x) { return (x<<2)|(x>>62); }

which with -O2 is currently compiled to 6 insns + return:

bar:    lsr     r12,r0,30
        asl_s   r3,r1,2
        asl_s   r0,r0,2
        lsr_s   r1,r1,30
        or_s    r0,r0,r1
        j_s.d   [blink]
        or      r1,r12,r3

with this patch becomes 4 insns + return:

bar:    lsr     r3,r1,30
        lsr     r2,r0,30
        add2    r1,r2,r1
        j_s.d   [blink]
        add2    r0,r3,r0

This patch has been tested on x86_64-pc-linux-gnu with make bootstrap
and make -k check, both with and without --target_board=unix{-m32}
with no new failures.  Ok for mainline?

gcc/ChangeLog
	* expmed.cc (expand_shift_1): Use add_optab instead of ior_optab
	to generate PLUS instead or IOR when unioning disjoint bitfields.
	* optabs.cc (expand_subword_shift): Likewise.
	(expand_binop): Likewise for double-word rotate.

2 files changed, 11 insertions, 9 deletions

diff --git a/gcc/expmed.cc b/gcc/expmed.cc
index 50d2276..9ba0169 100644
--- a/gcc/expmed.cc
+++ b/gcc/expmed.cc
@@ -2616,10 +2616,11 @@ expand_shift_1 (enum tree_code code, machine_mode mode, rtx shifted,
 	  else if (methods == OPTAB_LIB_WIDEN)
 	    {
 	      /* If we have been unable to open-code this by a rotation,
-		 do it as the IOR of two shifts.  I.e., to rotate A
-		 by N bits, compute
+		 do it as the IOR or PLUS of two shifts.  I.e., to rotate
+		 A by N bits, compute
 		 (A << N) | ((unsigned) A >> ((-N) & (C - 1)))
-		 where C is the bitsize of A.
+		 where C is the bitsize of A.  If N cannot be zero,
+		 use PLUS instead of IOR.
 
 		 It is theoretically possible that the target machine might
 		 not be able to perform either shift and hence we would
@@ -2656,8 +2657,9 @@ expand_shift_1 (enum tree_code code, machine_mode mode, rtx shifted,
 	      temp1 = expand_shift_1 (left ? RSHIFT_EXPR : LSHIFT_EXPR,
 				      mode, shifted, other_amount,
 				      subtarget, 1);
-	      return expand_binop (mode, ior_optab, temp, temp1, target,
-				   unsignedp, methods);
+	      return expand_binop (mode,
+				   CONST_INT_P (op1) ? add_optab : ior_optab,
+				   temp, temp1, target, unsignedp, methods);
 	    }
 
 	  temp = expand_binop (mode,
diff --git a/gcc/optabs.cc b/gcc/optabs.cc
index e791388..78cd9ef 100644
--- a/gcc/optabs.cc
+++ b/gcc/optabs.cc
@@ -566,8 +566,8 @@ expand_subword_shift (scalar_int_mode op1_mode, optab binoptab,
       if (tmp == 0)
 	return false;
 
-      /* Now OR in the bits carried over from OUTOF_INPUT.  */
-      if (!force_expand_binop (word_mode, ior_optab, tmp, carries,
+      /* Now OR/PLUS in the bits carried over from OUTOF_INPUT.  */
+      if (!force_expand_binop (word_mode, add_optab, tmp, carries,
 			       into_target, unsignedp, methods))
 	return false;
     }
@@ -1937,7 +1937,7 @@ expand_binop (machine_mode mode, optab binoptab, rtx op0, rtx op1,
 				     NULL_RTX, unsignedp, next_methods);
 
 	  if (into_temp1 != 0 && into_temp2 != 0)
-	    inter = expand_binop (word_mode, ior_optab, into_temp1, into_temp2,
+	    inter = expand_binop (word_mode, add_optab, into_temp1, into_temp2,
 				  into_target, unsignedp, next_methods);
 	  else
 	    inter = 0;
@@ -1953,7 +1953,7 @@ expand_binop (machine_mode mode, optab binoptab, rtx op0, rtx op1,
 				      NULL_RTX, unsignedp, next_methods);
 
 	  if (inter != 0 && outof_temp1 != 0 && outof_temp2 != 0)
-	    inter = expand_binop (word_mode, ior_optab,
+	    inter = expand_binop (word_mode, add_optab,
 				  outof_temp1, outof_temp2,
 				  outof_target, unsignedp, next_methods);