Fold (add -1; zero_ext; add +1) operations to zero_ext when not overflow(PR37451, PR61837)

This "subtract/extend/add" existed for a long time and still annoying us
(PR37451, part of PR61837) when converting from 32bits to 64bits, as the ctr
register is used as 64bits on powerpc64, Andraw Pinski had a patch but
caused some issue and reverted by Joseph S. Myers(PR37451, PR37782).

Andraw:
http://gcc.gnu.org/ml/gcc-patches/2008-09/msg01070.html
http://gcc.gnu.org/ml/gcc-patches/2008-10/msg01321.html
Joseph:
https://gcc.gnu.org/legacy-ml/gcc-patches/2011-11/msg02405.html

We still can do the simplification from "subtract/zero_ext/add" to "zero_ext"
when loop iterations is known to be LT than MODE_MAX (only do simplify
when counter+0x1 NOT overflow).

Bootstrap and regression tested pass on Power8-LE.

gcc/ChangeLog

	2020-05-15  Xiong Hu Luo  <luoxhu@linux.ibm.com>

	PR rtl-optimization/37451, part of PR target/61837
	* loop-doloop.c (doloop_simplify_count): New function.  Simplify
	(add -1; zero_ext; add +1) to zero_ext when not wrapping.
	(doloop_modify): Call doloop_simplify_count.

gcc/testsuite/ChangeLog

	2020-05-15  Xiong Hu Luo  <luoxhu@linux.ibm.com>

	PR rtl-optimization/37451, part of PR target/61837
	* gcc.target/powerpc/doloop-2.c: New test.

gcc/ChangeLog

@@ -1,3 +1,10 @@
+2020-05-14  Xiong Hu Luo  <luoxhu@linux.ibm.com>
+
+	PR rtl-optimization/37451, part of PR target/61837
+	* loop-doloop.c (doloop_simplify_count): New function.  Simplify
+	(add -1; zero_ext; add +1) to zero_ext when not wrapping.
+	(doloop_modify): Call doloop_simplify_count.
+
 2020-05-14  H.J. Lu  <hongjiu.lu@intel.com>
 
 	PR jit/94778

gcc/loop-doloop.c

@@ -397,6 +397,42 @@ add_test (rtx cond, edge *e, basic_block dest)
   return true;
 }
 
+/* Fold (add -1; zero_ext; add +1) operations to zero_ext if not wrapping. i.e:
+
+   73: r145:SI=r123:DI#0-0x1
+   74: r144:DI=zero_extend (r145:SI)
+   75: r143:DI=r144:DI+0x1
+   ...
+   31: r135:CC=cmp (r123:DI,0)
+   72: {pc={(r143:DI!=0x1)?L70:pc};r143:DI=r143:DI-0x1;...}
+
+   r123:DI#0-0x1 is param count derived from loop->niter_expr equal to number of
+   loop iterations, if loop iterations expression doesn't overflow, then
+   (zero_extend (r123:DI#0-1))+1 can be simplified to zero_extend.  */
+
+static rtx
+doloop_simplify_count (class loop *loop, scalar_int_mode mode, rtx count)
+{
+  widest_int iterations;
+  if (GET_CODE (count) == ZERO_EXTEND)
+    {
+      rtx extop0 = XEXP (count, 0);
+      if (GET_CODE (extop0) == PLUS)
+	{
+	  rtx addop0 = XEXP (extop0, 0);
+	  rtx addop1 = XEXP (extop0, 1);
+
+	  if (get_max_loop_iterations (loop, &iterations)
+	      && wi::ltu_p (iterations, GET_MODE_MASK (GET_MODE (addop0)))
+	      && addop1 == constm1_rtx)
+	    return simplify_gen_unary (ZERO_EXTEND, mode, addop0,
+				       GET_MODE (addop0));
+	}
+    }
+
+  return simplify_gen_binary (PLUS, mode, count, const1_rtx);
+}
+
 /* Modify the loop to use the low-overhead looping insn where LOOP
    describes the loop, DESC describes the number of iterations of the
    loop, and DOLOOP_INSN is the low-overhead looping insn to emit at the
@@ -477,7 +513,7 @@ doloop_modify (class loop *loop, class niter_desc *desc,
     }
 
   if (increment_count)
-    count = simplify_gen_binary (PLUS, mode, count, const1_rtx);
+    count = doloop_simplify_count (loop, mode, count);
 
   /* Insert initialization of the count register into the loop header.  */
   start_sequence ();

gcc/testsuite/ChangeLog

@@ -1,3 +1,8 @@
+2020-05-14  Xiong Hu Luo  <luoxhu@linux.ibm.com>
+
+	PR rtl-optimization/37451, part of PR target/61837
+	* gcc.target/powerpc/doloop-2.c: New test.
+
 2020-05-14  H.J. Lu  <hongjiu.lu@intel.com>
 
 	PR jit/94778

gcc/testsuite/gcc.target/powerpc/doloop-2.c

@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-unroll-loops" } */
+
+unsigned int
+foo1 (unsigned int l, int *a)
+{
+  unsigned int i;
+  for(i = 0;i < l; i++)
+    a[i] = i;
+  return l;
+}
+
+int
+foo2 (int l, int *a)
+{
+  int i;
+  for(i = 0;i < l; i++)
+    a[i] = i;
+  return l;
+}
+
+/* The place where we were getting an extra -1 is when converting from 32bits
+   to 64bits as the ctr register is used as 64bits on powerpc64.  We should be
+   able to do this loop without "add -1/zero_ext/add 1" to the l to get the
+   number of iterations of this loop still doing a do-loop.  */
+
+/* { dg-final { scan-assembler-not {(?n)\maddi .*,.*,-1$} } } */
+/* { dg-final { scan-assembler-times "bdnz" 2 } } */
+/* { dg-final { scan-assembler-times "mtctr" 2 } } */