[PATCH] D67948: [LV] Interleaving should not exceed estimated loop trip count.

[Craig Topper via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rG18824d25d8aa: [LV] Interleaving should not exceed estimated loop trip count. (authored by craig.topper).

Changed prior to commit:
  https://reviews.llvm.org/D67948?vs=225999&id=226707#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D67948/new/

https://reviews.llvm.org/D67948

Files:
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll


Index: llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll
+++ llvm/test/Transforms/LoopVectorize/X86/no_fpmath_with_hotness.ll
@@ -3,7 +3,7 @@
 
 ; CHECK: remark: no_fpmath.c:6:11: loop not vectorized: cannot prove it is safe to reorder floating-point operations (hotness: 300)
 ; CHECK: remark: no_fpmath.c:6:14: loop not vectorized
-; CHECK: remark: no_fpmath.c:17:14: vectorized loop (vectorization width: 2, interleaved count: 2) (hotness: 300)
+; CHECK: remark: no_fpmath.c:17:14: vectorized loop (vectorization width: 2, interleaved count: 1) (hotness: 300)
 
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.10.0"
Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -200,9 +200,10 @@
     "enable-masked-interleaved-mem-accesses", cl::init(false), cl::Hidden,
     cl::desc("Enable vectorization on masked interleaved memory accesses in a loop"));
 
-/// We don't interleave loops with a known constant trip count below this
-/// number.
-static const unsigned TinyTripCountInterleaveThreshold = 128;
+static cl::opt<unsigned> TinyTripCountInterleaveThreshold(
+    "tiny-trip-count-interleave-threshold", cl::init(128), cl::Hidden,
+    cl::desc("We don't interleave loops with a estimated constant trip count "
+             "below this number"));
 
 static cl::opt<unsigned> ForceTargetNumScalarRegs(
     "force-target-num-scalar-regs", cl::init(0), cl::Hidden,
@@ -5143,9 +5144,10 @@
   if (Legal->getMaxSafeDepDistBytes() != -1U)
     return 1;
 
-  // Do not interleave loops with a relatively small trip count.
-  unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
-  if (TC > 1 && TC < TinyTripCountInterleaveThreshold)
+  // Do not interleave loops with a relatively small known or estimated trip
+  // count.
+  auto BestKnownTC = getSmallBestKnownTC(*PSE.getSE(), TheLoop);
+  if (BestKnownTC && *BestKnownTC < TinyTripCountInterleaveThreshold)
     return 1;
 
   RegisterUsage R = calculateRegisterUsage({VF})[0];
@@ -5208,12 +5210,10 @@
       MaxInterleaveCount = ForceTargetMaxVectorInterleaveFactor;
   }
 
-  // If the trip count is constant, limit the interleave count to be less than
-  // the trip count divided by VF.
-  if (TC > 0) {
-    assert(TC >= VF && "VF exceeds trip count?");
-    if ((TC / VF) < MaxInterleaveCount)
-      MaxInterleaveCount = (TC / VF);
+  // If trip count is known or estimated compile time constant, limit the
+  // interleave count to be less than the trip count divided by VF.
+  if (BestKnownTC) {
+    MaxInterleaveCount = std::min(*BestKnownTC / VF, MaxInterleaveCount);
   }
 
   // If we did not calculate the cost for VF (because the user selected the VF)


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D67948.226707.patch
Type: text/x-patch
Size: 3018 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191028/bd5a929d/attachment-0001.bin>