[gcc(refs/vendors/redhat/heads/gcc-10-branch)] i386: Fix ix86_fold_builtin shift folding [PR93418]

[Jakub Jelinek]

https://gcc.gnu.org/g:bff948aa337807260344c83ac9079d6386410094

commit bff948aa337807260344c83ac9079d6386410094
Author: Jakub Jelinek <jakub@redhat.com>
Date:   Tue Jan 28 08:46:23 2020 +0100

    i386: Fix ix86_fold_builtin shift folding [PR93418]
    
    The following testcase is miscompiled, because the variable shift left
    operand, { -1, -1, -1, -1 } is represented as a VECTOR_CST with
    VECTOR_CST_NPATTERNS 1 and VECTOR_CST_NELTS_PER_PATTERN 1, so when
    we call builder.new_unary_operation, builder.encoded_nelts () will be just 1
    and thus we encode the resulting vector as if all the elements were the
    same.
    For non-masked is_vshift, we could perhaps call builder.new_binary_operation
    (TREE_TYPE (args[0]), args[0], args[1], false), but then there are masked
    shifts, for non-is_vshift we could perhaps call it too but with args[2]
    instead of args[1], but there is no builder.new_ternary_operation.
    All this stuff is primarily for aarch64 anyway, on x86 we don't have any
    variable length vectors, and it is not a big deal to compute all elements
    and just let builder.finalize () find the most efficient VECTOR_CST
    representation of the vector.  So, instead of doing too much, this just
    keeps using new_unary_operation only if only one VECTOR_CST is involved
    (i.e. non-masked shift by constant) and for the rest just compute all elts.
    
    2020-01-28  Jakub Jelinek  <jakub@redhat.com>
    
    	PR target/93418
    	* config/i386/i386.c (ix86_fold_builtin) <do_shift>: If mask is not
    	-1 or is_vshift is true, use new_vector with number of elts npatterns
    	rather than new_unary_operation.
    
    	* gcc.target/i386/avx2-pr93418.c: New test.

Diff:
---
 gcc/ChangeLog                                |  5 +++++
 gcc/config/i386/i386.c                       |  9 +++++++--
 gcc/testsuite/ChangeLog                      |  3 +++
 gcc/testsuite/gcc.target/i386/avx2-pr93418.c | 20 ++++++++++++++++++++
 4 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 6db98ed..3489428 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,10 @@
 2020-01-28  Jakub Jelinek  <jakub@redhat.com>
 
+	PR target/93418
+	* config/i386/i386.c (ix86_fold_builtin) <do_shift>: If mask is not
+	-1 or is_vshift is true, use new_vector with number of elts npatterns
+	rather than new_unary_operation.
+
 	PR tree-optimization/93454
 	* gimple-fold.c (fold_array_ctor_reference): Perform
 	elt_size.to_uhwi () just once, instead of calling it in every
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index ffe60ba..ffda3e8 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -17278,8 +17278,13 @@ ix86_fold_builtin (tree fndecl, int n_args,
 		    countt = build_int_cst (integer_type_node, count);
 		}
 	      tree_vector_builder builder;
-	      builder.new_unary_operation (TREE_TYPE (args[0]), args[0],
-					   false);
+	      if (mask != HOST_WIDE_INT_M1U || is_vshift)
+		builder.new_vector (TREE_TYPE (args[0]),
+				    TYPE_VECTOR_SUBPARTS (TREE_TYPE (args[0])),
+				    1);
+	      else
+		builder.new_unary_operation (TREE_TYPE (args[0]), args[0],
+					     false);
 	      unsigned int cnt = builder.encoded_nelts ();
 	      for (unsigned int i = 0; i < cnt; ++i)
 		{
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 44d8e67..6518f7f 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,8 @@
 2020-01-28  Jakub Jelinek  <jakub@redhat.com>
 
+	PR target/93418
+	* gcc.target/i386/avx2-pr93418.c: New test.
+
 	PR tree-optimization/93454
 	* gcc.dg/pr93454.c: New test.
 
diff --git a/gcc/testsuite/gcc.target/i386/avx2-pr93418.c b/gcc/testsuite/gcc.target/i386/avx2-pr93418.c
new file mode 100644
index 0000000..67ed33d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx2-pr93418.c
@@ -0,0 +1,20 @@
+/* PR target/93418 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx2 -fdump-tree-optimized" } */
+/* { dg-final { scan-tree-dump-not "link_error" "optimized" } } */
+
+#include <x86intrin.h>
+
+void link_error (void);
+
+void
+foo (void)
+{
+  __m128i a = _mm_set1_epi32 (0xffffffffU);
+  __m128i b = _mm_setr_epi32 (16, 31, -34, 3);
+  __m128i c = _mm_sllv_epi32 (a, b);
+  __v4su d = (__v4su) c;
+  if (d[0] != 0xffff0000U || d[1] != 0x80000000U
+      || d[2] != 0 || d[3] != 0xfffffff8U)
+    link_error ();
+}