Support accesses with differently sized types to the same array

This allows code such as:

void multiple_types(char *Short, char *Float, char *Double) {
  for (long i = 0; i < 100; i++) {
    Short[i] = *(short *)&Short[2 * i];
    Float[i] = *(float *)&Float[4 * i];
    Double[i] = *(double *)&Double[8 * i];
  }
}

To model such code we use as canonical element type of the modeled array the
smallest element type of all original array accesses, if type allocation sizes
are multiples of each other. Otherwise, we use a newly created iN type, where N
is the gcd of the allocation size of the types used in the accesses to this
array. Accesses with types larger as the canonical element type are modeled as
multiple accesses with the smaller type.

For example the second load access is modeled as:

  { Stmt_bb2[i0] -> MemRef_Float[o0] : 4i0 <= o0 <= 3 + 4i0 }

To support code-generating these memory accesses, we introduce a new method
getAccessAddressFunction that assigns each statement instance a single memory
location, the address we load from/store to. Currently we obtain this address by
taking the lexmin of the access function. We may consider keeping track of the
memory location more explicitly in the future.

We currently do _not_ handle multi-dimensional arrays and also keep the
restriction of not supporting accesses where the offset expression is not a
multiple of the access element type size. This patch adds tests that ensure
we correctly invalidate a scop in case these accesses are found. Both types of
accesses can be handled using the very same model, but are left to be added in
the future.

We also move the initialization of the scop-context into the constructor to
ensure it is already available when invalidating the scop.

Finally, we add this as a new item to the 2.9 release notes

Reviewers: jdoerfert, Meinersbur

Differential Revision: http://reviews.llvm.org/D16878

llvm-svn: 259784

1 files changed, 21 insertions, 0 deletions

diff --git a/polly/docs/ReleaseNotes.rst b/polly/docs/ReleaseNotes.rst
index d6eb1c81525..1f75ead6a4e 100644
--- a/polly/docs/ReleaseNotes.rst
+++ b/polly/docs/ReleaseNotes.rst
@@ -4,6 +4,27 @@ Release Notes
 
 In Polly 3.9 the following important changes have been incorporated.
 
+Increased analysis coverage
+---------------------------
+
+Polly's modeling has been improved to increase the applicability of Polly. The
+following code pieces are newly supported:
+
+Arrays accessed through different types
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+It is not uncommon that one array stores elements of different types. Polly now
+can model and optimize such code.
+
+.. code-block:: c
+
+    void multiple_types(char *Short, char *Float, char *Double) {
+      for (long i = 0; i < 100; i++) {
+        Short[i] = *(short *)&Short[2 * i];
+        Float[i] = *(float *)&Float[4 * i];
+        Double[i] = *(double *)&Double[8 * i];
+      }
+    }
 
 Update of the isl math library
 ------------------------------