[PATCH] D61237: [SimplifyCFG] ReduceSwitchRange: Improve on the case where the SubThreshold doesn't trigger

[Shawn Landden via Phabricator via llvm-commits]

shawnl updated this revision to Diff 197603.
shawnl edited the summary of this revision.
shawnl added a comment.

no longer depends on cttz transform


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61237/new/

https://reviews.llvm.org/D61237

Files:
  lib/Transforms/Utils/SimplifyCFG.cpp
  test/Transforms/SimplifyCFG/rangereduce.ll


Index: test/Transforms/SimplifyCFG/rangereduce.ll
===================================================================
--- test/Transforms/SimplifyCFG/rangereduce.ll
+++ test/Transforms/SimplifyCFG/rangereduce.ll
@@ -234,10 +234,10 @@
 
 define i8 @test7(i8 %a) optsize {
 ; CHECK-LABEL: @test7(
-; CHECK-NEXT:    [[TMP1:%.*]] = sub i8 [[A:%.*]], -36
-; CHECK-NEXT:    [[TMP2:%.*]] = lshr i8 [[TMP1]], 2
-; CHECK-NEXT:    [[TMP3:%.*]] = shl i8 [[TMP1]], 6
-; CHECK-NEXT:    [[TMP4:%.*]] = or i8 [[TMP2]], [[TMP3]]
+; CHECK-NEXT:    [[TMP1:%.*]] = lshr i8 [[A:%.*]], 2
+; CHECK-NEXT:    [[TMP2:%.*]] = shl i8 [[A]], 6
+; CHECK-NEXT:    [[TMP3:%.*]] = or i8 [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    [[TMP4:%.*]] = sub i8 [[TMP3]], 55
 ; CHECK-NEXT:    [[TMP5:%.*]] = icmp ult i8 [[TMP4]], 4
 ; CHECK-NEXT:    br i1 [[TMP5]], label [[SWITCH_LOOKUP:%.*]], label [[DEF:%.*]]
 ; CHECK:       switch.lookup:
Index: lib/Transforms/Utils/SimplifyCFG.cpp
===================================================================
--- lib/Transforms/Utils/SimplifyCFG.cpp
+++ lib/Transforms/Utils/SimplifyCFG.cpp
@@ -5536,18 +5536,6 @@
       BestDistance = Values[I] - Values[I - 1];
     }
   }
-  uint64_t Base = 0;
-  // Now transform the values such that they start at zero and ascend.
-  if (Values[BestIndex] >= SubThreshold) {
-    Base = Values[BestIndex];
-    MadeChanges = true;
-    for (auto &V : Values)
-      V = (APInt(BitWidth, V) - Base).getLimitedValue();
-  }
-
-  // Now we have signed numbers that have been shifted so that, given enough
-  // precision, there are no negative values. Since the rest of the transform
-  // is bitwise only, we switch now to an unsigned representation.
 
   // This transform can be done speculatively because it is so cheap - it
   // results in a single rotate operation being inserted.
@@ -5559,8 +5547,10 @@
   // one element and LLVM disallows duplicate cases, Shift is guaranteed to be
   // less than 64.
   unsigned Shift = 64;
+  // We need to store this from _before_ the transform
+  uint64_t BestIndexXor = Values[BestIndex];
   for (auto &V : Values)
-    Shift = std::min(Shift, countTrailingZeros(V));
+    Shift = std::min(Shift, countTrailingZeros(V ^ BestIndexXor));
   assert(Shift < 64);
   if (Shift > 0) {
     MadeChanges = true;
@@ -5568,6 +5558,26 @@
       V >>= Shift;
   }
 
+  // We Xor against Values[] (any element will do) because the if we do not
+  // start at zero, but also don't meet the SubThreshold, then we still might
+  // share common rights bits, and if this transform succeeds
+  // then we should insert the subtraction anyways, because the rotate trick
+  // below to avoid a branch needs the shifted away bits to be zero.
+
+  // Now transform the values such that they start at zero and ascend. Do not
+  // do this if the shift reduces the lowest value to less than SubThreshold,
+  // or if the subtraction is less than SubThreshold and it does not enable a
+  // rotate.
+  uint64_t Base = 0;
+  if ((BestIndexXor >= SubThreshold && Shift == 0) ||
+      (Shift > countTrailingZeros(BestIndexXor) &&
+       Values[BestIndex] >= SubThreshold)) {
+    Base = BestIndexXor;
+    MadeChanges = true;
+    for (auto &V : Values)
+      V = (APInt(BitWidth, V) - Base).getLimitedValue();
+  }
+
   if (!MadeChanges)
     // We didn't do anything.
     return false;
@@ -5598,7 +5608,7 @@
 
   for (auto Case : SI->cases()) {
     auto *Orig = Case.getCaseValue();
-    auto Sub = Orig->getValue() - APInt(Ty->getBitWidth(), Base);
+    auto Sub = Orig->getValue() - Base;
     Case.setValue(cast<ConstantInt>(ConstantInt::get(Ty, Sub.lshr(Shift))));
   }
   return true;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D61237.197603.patch
Type: text/x-patch
Size: 3651 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190501/d2c85f24/attachment.bin>