[PATCH] D23646: Generalize strided store pattern in interleave access pass

[Matthew Simpson via llvm-commits]

mssimpso added inline comments.

================
Comment at: lib/CodeGen/InterleavedAccessPass.cpp:159-164
@@ -158,8 +158,8 @@
 
 /// \brief Check if the mask is RE-interleave mask for an interleaved store.
 ///
 /// I.e. <0, NumSubElts, ... , NumSubElts*(Factor - 1), 1, NumSubElts + 1, ...>
 ///
 /// E.g. The RE-interleave mask (Factor = 2) could be:
 ///     <0, 4, 1, 5, 2, 6, 3, 7>
 static bool isReInterleaveMask(ArrayRef<int> Mask, unsigned &Factor) {
----------------
You should probably update this to define the more general pattern.

================
Comment at: lib/CodeGen/InterleavedAccessPass.cpp:181-207
@@ -180,8 +180,29 @@
     // elements.
-    unsigned i = 0;
-    for (; i < NumElts; i++)
-      if (Mask[i] >= 0 &&
-          static_cast<unsigned>(Mask[i]) !=
-              (i % Factor) * NumSubElts + i / Factor)
+    unsigned i = 0, j;
+    for (; i < Factor; i++) {
+      int PreviousMask = -1;
+      int PreviousPos = -1;
+      //TODO: check that Mask[i] (if it exists) is aligned (TLI).
+      //TODO: add additional tests (+ARM)
+      for (j = 0; j < NumSubElts-1; j++) {
+        unsigned ij = j*Factor + i;
+        if (Mask[ij] >= 0 && Mask[ij + Factor] >= 0 &&
+          static_cast<unsigned>(Mask[ij]) + 1  !=
+            static_cast<unsigned>(Mask[ij + Factor]))
+          break;
+
+        // With undefined mask, we can have: 2, undef, 7, undef, 32.
+        // Compare the next mask, with value from further back to avoid this.
+        if (PreviousMask > 0 && Mask[ij] < 0 && Mask[ij + Factor] >= 0 &&
+            static_cast<unsigned>(PreviousMask) + (j - PreviousPos) + 1  !=
+              static_cast<unsigned>(Mask[ij + Factor]))
+            break;
+        if (Mask[ij] >= 0 && Mask[ij + Factor] < 0) {
+          PreviousMask = Mask[ij];
+          PreviousPos = j;
+        }
+      }
+      if (j < NumSubElts-1)
         break;
+    }
 
----------------
This looks fairly reasonable to me, but the parts dealing with undef are pretty difficult to follow. I think some more high-level comments would help people better understand what's going on here.


https://reviews.llvm.org/D23646