This fixes a missed vectorization with bitwise int-float conversions.
Bootstrapped and tested on x86_64-unknown-linux-gnu, applied to trunk.
Richard.
2011-06-21 Richard Guenther <rguent...@suse.de>
PR tree-optimization/49483
* tree-vect-stmts.c (vectorizable_assignment): Also handle
VIEW_CONVERT_EXPR conversions.
* gcc.dg/vect/vect-120.c: New testcase.
Index: gcc/tree-vect-stmts.c
===================================================================
--- gcc/tree-vect-stmts.c (revision 175205)
+++ gcc/tree-vect-stmts.c (working copy)
@@ -2089,6 +2089,9 @@ vectorizable_assignment (gimple stmt, gi
else
return false;
+ if (code == VIEW_CONVERT_EXPR)
+ op = TREE_OPERAND (op, 0);
+
if (!vect_is_simple_use_1 (op, loop_vinfo, bb_vinfo,
&def_stmt, &def, &dt[0], &vectype_in))
{
@@ -2099,7 +2102,8 @@ vectorizable_assignment (gimple stmt, gi
/* We can handle NOP_EXPR conversions that do not change the number
of elements or the vector size. */
- if (CONVERT_EXPR_CODE_P (code)
+ if ((CONVERT_EXPR_CODE_P (code)
+ || code == VIEW_CONVERT_EXPR)
&& (!vectype_in
|| TYPE_VECTOR_SUBPARTS (vectype_in) != nunits
|| (GET_MODE_SIZE (TYPE_MODE (vectype))
@@ -2134,7 +2138,8 @@ vectorizable_assignment (gimple stmt, gi
/* Arguments are ready. create the new vector stmt. */
FOR_EACH_VEC_ELT (tree, vec_oprnds, i, vop)
{
- if (CONVERT_EXPR_CODE_P (code))
+ if (CONVERT_EXPR_CODE_P (code)
+ || code == VIEW_CONVERT_EXPR)
vop = build1 (VIEW_CONVERT_EXPR, vectype, vop);
new_stmt = gimple_build_assign (vec_dest, vop);
new_temp = make_ssa_name (vec_dest, new_stmt);
Index: gcc/testsuite/gcc.dg/vect/vect-120.c
===================================================================
--- gcc/testsuite/gcc.dg/vect/vect-120.c (revision 0)
+++ gcc/testsuite/gcc.dg/vect/vect-120.c (revision 0)
@@ -0,0 +1,36 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_float } */
+/* { dg-require-effective-target vect_shift } */
+
+static inline float
+i2f(int x)
+{
+ union { float f; int i; } tmp;
+ tmp.i=x;
+ return tmp.f;
+}
+static inline float
+vect_ldexpf(float x, int n)
+{
+ n = (n+0x7f)<<23;
+ return x * i2f(n);
+}
+
+float __attribute__ ((aligned(16))) a[1024];
+float __attribute__ ((aligned(16))) b[1024];
+float __attribute__ ((aligned(16))) c[1024];
+
+void
+tV()
+{
+ int i;
+ for (i=0; i!=1024; ++i)
+ {
+ float z = a[i];
+ int n = b[i];
+ c[i] = vect_ldexpf(z,n);
+ }
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
