From 2aff950822bee20e1398a2a528ad927740f799f8 Mon Sep 17 00:00:00 2001
From: Dale Johannesen <dalej@apple.com>
Date: Mon, 4 Nov 2002 20:06:28 +0000
Subject: [PATCH] Fix bugs that showed up building Spec on ppc darwin.

From-SVN: r58800
---
 gcc/ChangeLog |  6 ++++++
 gcc/doloop.c  | 29 ++++++++++++++++-------------
 gcc/loop.c    |  7 +++++++
 3 files changed, 29 insertions(+), 13 deletions(-)

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index dfda5def0848..0b4cc8e6795f 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2002-11-04  Dale Johannesen  <dalej@apple.com>
+
+        * doloop.c (doloop_modify_runtime):  Fix loop count computation
+        for unrolled loops.
+	* loop.c (loop_invariant_p):  Support calling from unroller.
+
 2002-11-04  Ulrich Weigand  <uweigand@de.ibm.com>
 
 	* config/s390/s390.c (s390_decompose_address): Use arg_pointer_rtx
diff --git a/gcc/doloop.c b/gcc/doloop.c
index 1f7d47ae035c..67b742cde714 100644
--- a/gcc/doloop.c
+++ b/gcc/doloop.c
@@ -599,16 +599,19 @@ doloop_modify_runtime (loop, iterations_max,
 
      If the loop has been unrolled, the full calculation is
 
-       t1 = abs_inc * unroll_number;		increment per loop
-       n = abs (final - initial) / t1;		full loops
-       n += (abs (final - initial) % t1) != 0;	partial loop
+       t1 = abs_inc * unroll_number;		        increment per loop
+       n = (abs (final - initial) + abs_inc - 1) / t1;    full loops
+       n += (abs (final - initial) + abs_inc - 1) % t1) >= abs_inc;
+                                                          partial loop
+     which works out to be equivalent to
 
-     However, in certain cases the unrolled loop will be preconditioned
-     by emitting copies of the loop body with conditional branches,
-     so that the unrolled loop is always a full loop and thus needs
-     no exit tests.  In this case we don't want to add the partial
-     loop count.  As above, when t1 is a power of two we don't need to
-     worry about overflow.
+       n = (abs (final - initial) + t1 - 1) / t1;
+
+     In the case where the loop was preconditioned, a few iterations
+     may have been executed earlier; but 'initial' was adjusted as they
+     were executed, so we don't need anything special for that case here.
+     As above, when t1 is a power of two we don't need to worry about
+     overflow.
 
      The division and modulo operations can be avoided by requiring
      that the increment is a power of 2 (precondition_loop_p enforces
@@ -683,10 +686,10 @@ doloop_modify_runtime (loop, iterations_max,
       if (shift_count < 0)
 	abort ();
 
-      if (!loop_info->preconditioned)
-	diff = expand_simple_binop (GET_MODE (diff), PLUS,
-				    diff, GEN_INT (abs_loop_inc - 1),
-				    diff, 1, OPTAB_LIB_WIDEN);
+      /* (abs (final - initial) + abs_inc * unroll_number - 1) */
+      diff = expand_simple_binop (GET_MODE (diff), PLUS,
+				  diff, GEN_INT (abs_loop_inc - 1),
+				  diff, 1, OPTAB_LIB_WIDEN);
 
       /* (abs (final - initial) + abs_inc * unroll_number - 1)
 	 / (abs_inc * unroll_number)  */
diff --git a/gcc/loop.c b/gcc/loop.c
index 9461530e8946..04f95ab49258 100644
--- a/gcc/loop.c
+++ b/gcc/loop.c
@@ -3273,6 +3273,13 @@ loop_invariant_p (loop, x)
 	  && REGNO (x) < FIRST_PSEUDO_REGISTER && call_used_regs[REGNO (x)])
 	return 0;
 
+      /* Out-of-range regs can occur when we are called from unrolling.
+	 These have always been created by the unroller and are set in
+	 the loop, hence are never invariant. */
+
+      if (REGNO (x) >= regs->num)
+	return 0;
+
       if (regs->array[REGNO (x)].set_in_loop < 0)
 	return 2;