On 19/10/15 12:49, Richard Biener wrote:
> Err, you should always do the shift in the type of rhs1. You should also
> avoid the chrec_convert of rhs2 above for shifts.
Err, yes, indeed. Needed to keep the chrec_convert before the
chrec_fold_multiply, and the rest followed. How's this?
Bootstrapped+check-gcc,g++ on x86, ARM, AArch64.
gcc/ChangeLog (as before):
PR tree-optimization/65963
* tree-scalar-evolution.c (interpret_rhs_expr): Handle some LSHIFT_EXPRs
as equivalent MULT_EXPRs.
gcc/testsuite/ChangeLog:
* gcc.dg/vect/vect-strided-shift-1.c: New.
---
gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c | 33 ++++++++++++++++++++++++
gcc/tree-scalar-evolution.c | 15 +++++++++++
2 files changed, 48 insertions(+)
create mode 100644 gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
diff --git a/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
new file mode 100644
index 0000000..b1ce2ec
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-strided-shift-1.c
@@ -0,0 +1,33 @@
+/* PR tree-optimization/65963. */
+#include "tree-vect.h"
+
+#define N 512
+
+int in[2*N], out[N];
+
+__attribute__ ((noinline)) void
+loop (void)
+{
+ for (int i = 0; i < N; i++)
+ out[i] = in[i << 1] + 7;
+}
+
+int
+main (int argc, char **argv)
+{
+ check_vect ();
+ for (int i = 0; i < 2*N; i++)
+ {
+ in[i] = i;
+ __asm__ volatile ("" : : : "memory");
+ }
+ loop ();
+ __asm__ volatile ("" : : : "memory");
+ for (int i = 0; i < N; i++)
+ {
+ if (out[i] != i*2 + 7)
+ abort ();
+ }
+ return 0;
+}
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 1 "vect"
{ target { vect_strided2 } } } } */
diff --git a/gcc/tree-scalar-evolution.c b/gcc/tree-scalar-evolution.c
index 0753bf3..129682f 100644
--- a/gcc/tree-scalar-evolution.c
+++ b/gcc/tree-scalar-evolution.c
@@ -1840,6 +1840,21 @@ interpret_rhs_expr (struct loop *loop, gimple *at_stmt,
res = chrec_fold_multiply (type, chrec1, chrec2);
break;
+ case LSHIFT_EXPR:
+ /* Handle A<<B as A * (1<<B). */
+ chrec1 = analyze_scalar_evolution (loop, rhs1);
+ chrec2 = analyze_scalar_evolution (loop, rhs2);
+ chrec1 = chrec_convert (type, chrec1, at_stmt);
+ chrec1 = instantiate_parameters (loop, chrec1);
+ chrec2 = instantiate_parameters (loop, chrec2);
+
+ chrec2 = fold_build2 (LSHIFT_EXPR, TREE_TYPE (rhs1),
+ build_int_cst (TREE_TYPE (rhs1), 1),
+ chrec2);
+ chrec2 = chrec_convert (type, chrec2, at_stmt);
+ res = chrec_fold_multiply (type, chrec1, chrec2);
+ break;
+
CASE_CONVERT:
/* In case we have a truncation of a widened operation that in
the truncated type has undefined overflow behavior analyze
--
1.9.1
