From: Richard Biener <rguenther@suse.de>
Date: Thu, 3 Aug 2023 08:59:52 +0000 (+0200)
Subject: Swap loop splitting and final value replacement
X-Git-Tag: basepoints/gcc-15~7195
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=3d48c11ad082def8ee237e5778d8a5d569bff96d;p=thirdparty%2Fgcc.git

Swap loop splitting and final value replacement

The following swaps the loop splitting pass and the final value
replacement pass to avoid keeping the IV of the earlier loop
live when not necessary.  The existing gcc.target/i386/pr87007-5.c
testcase shows that we otherwise fail to elide an empty loop
later.  I don't see any good reason why loop splitting would need
final value replacement, all exit values honor the constraints
we place on loop header PHIs automatically.

	* passes.def: Exchange loop splitting and final value
	replacement passes.

	* gcc.target/i386/pr87007-5.c: Make sure we split the loop
	and eliminate both in the end.
---

diff --git a/gcc/passes.def b/gcc/passes.def
index f2893ae8a8b2..ef5a21afe497 100644
--- a/gcc/passes.def
+++ b/gcc/passes.def
@@ -282,8 +282,8 @@ along with GCC; see the file COPYING3.  If not see
 	     form if possible.  */
 	  NEXT_PASS (pass_tree_loop_init);
 	  NEXT_PASS (pass_tree_unswitch);
-	  NEXT_PASS (pass_scev_cprop);
 	  NEXT_PASS (pass_loop_split);
+	  NEXT_PASS (pass_scev_cprop);
 	  NEXT_PASS (pass_loop_versioning);
 	  NEXT_PASS (pass_loop_jam);
 	  /* All unswitching, final value replacement and splitting can expose
diff --git a/gcc/testsuite/gcc.target/i386/pr87007-5.c b/gcc/testsuite/gcc.target/i386/pr87007-5.c
index b36e81c270c9..a6cdf11522e5 100644
--- a/gcc/testsuite/gcc.target/i386/pr87007-5.c
+++ b/gcc/testsuite/gcc.target/i386/pr87007-5.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-Ofast -march=skylake-avx512 -mfpmath=sse -fno-tree-vectorize" } */
+/* { dg-options "-Ofast -march=skylake-avx512 -mfpmath=sse -fno-tree-vectorize -fdump-tree-cddce3-details -fdump-tree-lsplit-optimized" } */
 /* Load of d2/d3 is hoisted out, vrndscalesd will reuse loades register to avoid partial dependence.  */
 
 #include<math.h>
@@ -15,4 +15,6 @@ foo (int n, int k)
       d1 = sqrt (d3);
 }
 
+/* { dg-final { scan-tree-dump "optimized: loop split" "lsplit" } } */
+/* { dg-final { scan-tree-dump-times "removing loop" 2 "cddce3" } } */
 /* { dg-final { scan-assembler-times "vxorps\[^\n\r\]*xmm\[0-9\]" 0 } } */