Revert "[VectorUtils] Query number of sign bits to allow more truncations"

This was a fairly simple patch but on closer inspection was seriously flawed and caused PR27690.

This reverts commit r268921.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@269051 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Analysis/VectorUtils.cpp b/lib/Analysis/VectorUtils.cpp
index 2c03f1a05ced46dfd29f1ddf477634ac9edbf1f8..23a0de856bcc55f6772fee05f25ca838ecba3ca3 100644 (file)
--- a/lib/Analysis/VectorUtils.cpp
+++ b/lib/Analysis/VectorUtils.cpp
@@ -320,9 +320,6 @@ llvm::computeMinimumValueSizes(ArrayRef<BasicBlock *> Blocks, DemandedBits &DB,
   SmallPtrSet<Instruction *, 4> InstructionSet;
   MapVector<Instruction *, uint64_t> MinBWs;
 
-  assert(Blocks.size() > 0 && "Must have at least one block!");
-  const DataLayout &DL = Blocks[0]->getModule()->getDataLayout();
-  
   // Determine the roots. We work bottom-up, from truncs or icmps.
   bool SeenExtFromIllegalType = false;
   for (auto *BB : Blocks)
@@ -366,19 +363,12 @@ llvm::computeMinimumValueSizes(ArrayRef<BasicBlock *> Blocks, DemandedBits &DB,
 
     // If we encounter a type that is larger than 64 bits, we can't represent
     // it so bail out.
-    APInt NeededBits = DB.getDemandedBits(I);
-    unsigned BW = NeededBits.getBitWidth();
-    if (BW > 64)
+    if (DB.getDemandedBits(I).getBitWidth() > 64)
       return MapVector<Instruction *, uint64_t>();
 
-    auto NSB = ComputeNumSignBits(I, DL);
-
-    // Query demanded bits for the bits required by the instruction. Remove
-    // any bits that are equal to the sign bit, because we can truncate the
-    // instruction without changing their value.
-    NeededBits &= APInt::getLowBitsSet(BW, BW - NSB);
-    DBits[Leader] |= NeededBits.getZExtValue();
-    DBits[I] |= NeededBits.getZExtValue();
+    uint64_t V = DB.getDemandedBits(I).getZExtValue();
+    DBits[Leader] |= V;
+    DBits[I] = V;
 
     // Casts, loads and instructions outside of our range terminate a chain
     // successfully.

diff --git a/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll b/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll
index 729592d6f81106b060d326185adb75d448c0dd50..c7ced757581aa399264f0afe85be0c782a4ae8d1 100644 (file)
--- a/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll
+++ b/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll
@@ -263,41 +263,5 @@ for.body:                                         ; preds = %entry, %for.body
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
 
-; CHECK-LABEL: @add_g
-; CHECK: load <16 x i8>
-; CHECK: xor <16 x i8>
-; CHECK: icmp ult <16 x i8>
-; CHECK: select <16 x i1> {{.*}}, <16 x i8>
-; CHECK: store <16 x i8>
-define void @add_g(i8* noalias nocapture readonly %p, i8* noalias nocapture readonly %q, i8* noalias nocapture
-%r, i8 %arg1, i32 %len) #0 {
-  %1 = icmp sgt i32 %len, 0
-  br i1 %1, label %.lr.ph, label %._crit_edge
-
-.lr.ph:                                           ; preds = %0
-  %2 = sext i8 %arg1 to i64
-  br label %3
-
-._crit_edge:                                      ; preds = %3, %0
-  ret void
-
-; <label>:3                                       ; preds = %3, %.lr.ph
-  %indvars.iv = phi i64 [ 0, %.lr.ph ], [ %indvars.iv.next, %3 ]
-  %x4 = getelementptr inbounds i8, i8* %p, i64 %indvars.iv
-  %x5 = load i8, i8* %x4
-  %x7 = getelementptr inbounds i8, i8* %q, i64 %indvars.iv
-  %x8 = load i8, i8* %x7
-  %x9 = zext i8 %x5 to i32
-  %x10 = xor i32 %x9, 255
-  %x11 = icmp ult i32 %x10, 24
-  %x12 = select i1 %x11, i32 %x10, i32 24
-  %x13 = trunc i32 %x12 to i8
-  store i8 %x13, i8* %x4
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
-  %exitcond = icmp eq i32 %lftr.wideiv, %len
-  br i1 %exitcond, label %._crit_edge, label %3
-}
-
 attributes #0 = { nounwind }