Looking at PR77308, one of the issues is that the bswap optimization phase doesn...

Looking at PR77308, one of the issues is that the bswap optimization
phase doesn't work on ARM.  This is due to an odd check that uses
SLOW_UNALIGNED_ACCESS (which is always true on ARM).  Since the testcase
in PR77308 generates much better code with this patch (~13% fewer
instructions), it seems best to remove this check.

    gcc/
	* tree-ssa-math-opts.c (bswap_replace): Remove test
	of SLOW_UNALIGNED_ACCESS.

    testsuite/
	* gcc.dg/optimize-bswapdi-3.c: Remove xfail.
	* gcc.dg/optimize-bswaphi-1.c: Likewise.
	* gcc.dg/optimize-bswapsi-2.c: Likewise.

From-SVN: r242506

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index be573a3124b919ef8732a8c68b2545e8e5037ba0..a5290bafc4a7fa8cf940f851f1415d8361c4bd48 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,8 @@
+2015-11-16  Wilco Dijkstra  <wdijkstr@arm.com>
+
+       * tree-ssa-math-opts.c (bswap_replace): Remove test
+       of SLOW_UNALIGNED_ACCESS.
+
 2016-11-16  Alexander Monakov  <amonakov@ispras.ru>
 
        * config/nvptx/mkoffload.c (main): Check that either OpenACC or OpenMP

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index d750f25d328f848986eec79ce92cd17a3499d567..3f8831e066afbc98f110f914367685ec1f60ac6c 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2015-11-16  Wilco Dijkstra  <wdijkstr@arm.com>
+
+       * gcc.dg/optimize-bswapdi-3.c: Remove xfail.
+       * gcc.dg/optimize-bswaphi-1.c: Likewise.        
+       * gcc.dg/optimize-bswapsi-2.c: Likewise.
+
 2016-11-16  Szabolcs Nagy  <szabolcs.nagy@arm.com>
 
        PR libgfortran/78314

diff --git a/gcc/testsuite/gcc.dg/optimize-bswapdi-3.c b/gcc/testsuite/gcc.dg/optimize-bswapdi-3.c
index 273b4bc622cb32564533e1352b5fc8ad52054f8b..6f682014622ab79e541cdf26d13f16a7d87f158d 100644 (file)
--- a/gcc/testsuite/gcc.dg/optimize-bswapdi-3.c
+++ b/gcc/testsuite/gcc.dg/optimize-bswapdi-3.c
@@ -61,4 +61,4 @@ uint64_t read_be64_3 (unsigned char *data)
 }
 
 /* { dg-final { scan-tree-dump-times "64 bit load in target endianness found at" 3 "bswap" } } */
-/* { dg-final { scan-tree-dump-times "64 bit bswap implementation found at" 3 "bswap" { xfail alpha*-*-* arm*-*-* } } } */
+/* { dg-final { scan-tree-dump-times "64 bit bswap implementation found at" 3 "bswap" } } */

diff --git a/gcc/testsuite/gcc.dg/optimize-bswaphi-1.c b/gcc/testsuite/gcc.dg/optimize-bswaphi-1.c
index c18ca6174d12a786a71252dfe47cfe78ca58750a..852ccfe5c1acd519f2cf340cc55f3ea74b1ec21f 100644 (file)
--- a/gcc/testsuite/gcc.dg/optimize-bswaphi-1.c
+++ b/gcc/testsuite/gcc.dg/optimize-bswaphi-1.c
@@ -55,5 +55,4 @@ swap16 (HItype in)
 }
 
 /* { dg-final { scan-tree-dump-times "16 bit load in target endianness found at" 3 "bswap" } } */
-/* { dg-final { scan-tree-dump-times "16 bit bswap implementation found at" 1 "bswap" { target alpha*-*-* arm*-*-* } } } */
-/* { dg-final { scan-tree-dump-times "16 bit bswap implementation found at" 4 "bswap" { xfail alpha*-*-* arm*-*-* } } } */
+/* { dg-final { scan-tree-dump-times "16 bit bswap implementation found at" 4 "bswap" } } */

diff --git a/gcc/testsuite/gcc.dg/optimize-bswapsi-2.c b/gcc/testsuite/gcc.dg/optimize-bswapsi-2.c
index a1558af2cc74adde439d42223b00977d9eeb9639..01ae3776ed3f44fbc300d001f8c67ec11625d03b 100644 (file)
--- a/gcc/testsuite/gcc.dg/optimize-bswapsi-2.c
+++ b/gcc/testsuite/gcc.dg/optimize-bswapsi-2.c
@@ -45,4 +45,4 @@ uint32_t read_be32_3 (unsigned char *data)
 }
 
 /* { dg-final { scan-tree-dump-times "32 bit load in target endianness found at" 3 "bswap" } } */
-/* { dg-final { scan-tree-dump-times "32 bit bswap implementation found at" 3 "bswap" { xfail alpha*-*-* arm*-*-* } } } */
+/* { dg-final { scan-tree-dump-times "32 bit bswap implementation found at" 3 "bswap" } } */

diff --git a/gcc/tree-ssa-math-opts.c b/gcc/tree-ssa-math-opts.c
index b28c808c55489ae1ae16c173d66c561c1897e6ab..a389dfcae14f35e3e5ec9d52c2a5bcf3b76c07e7 100644 (file)
--- a/gcc/tree-ssa-math-opts.c
+++ b/gcc/tree-ssa-math-opts.c
@@ -2649,11 +2649,6 @@ bswap_replace (gimple *cur_stmt, gimple *src_stmt, tree fndecl,
 
       align = get_object_alignment (src);
 
-      if (bswap
-         && align < GET_MODE_ALIGNMENT (TYPE_MODE (load_type))
-         && SLOW_UNALIGNED_ACCESS (TYPE_MODE (load_type), align))
-       return false;
-
       /* Move cur_stmt just before  one of the load of the original
         to ensure it has the same VUSE.  See PR61517 for what could
         go wrong.  */