maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

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

When deciding if a vector calculation can be done in a smaller bitwidth, use sign bit information from ValueTracking to add more information and allow more truncations.

llvm-svn: 268921
This commit is contained in:
James Molloy 2016-05-09 14:32:30 +00:00
parent b6aed5f441
commit 5c20e27b7f
2 changed files with 50 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
llvm/lib/Analysis/VectorUtils.cpp
View File

@ -320,6 +320,9 @@ 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)
@ -363,12 +366,19 @@ 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.
if (DB.getDemandedBits(I).getBitWidth() > 64)
APInt NeededBits = DB.getDemandedBits(I);
unsigned BW = NeededBits.getBitWidth();
if (BW > 64)
return MapVector<Instruction *, uint64_t>();
uint64_t V = DB.getDemandedBits(I).getZExtValue();
DBits[Leader] |= V;
DBits[I] = V;
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();
// Casts, loads and instructions outside of our range terminate a chain
// successfully.

36
llvm/test/Transforms/LoopVectorize/AArch64/loop-vectorization-factors.ll
View File

@ -263,5 +263,41 @@ 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 }