aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Transforms/Vectorize
diff options
context:
space:
mode:
authorChandler Carruth <chandlerc@gmail.com>2013-08-22 12:45:17 +0000
committerChandler Carruth <chandlerc@gmail.com>2013-08-22 12:45:17 +0000
commit474be0d0f83eb6543bd4091946b40bb4967a3c11 (patch)
treec204219411036c5974a32ab64afecd02125a6d87 /lib/Transforms/Vectorize
parentbad8d4ca599024de8fdc6255a4b73bb294f49239 (diff)
downloadexternal_llvm-474be0d0f83eb6543bd4091946b40bb4967a3c11.zip
external_llvm-474be0d0f83eb6543bd4091946b40bb4967a3c11.tar.gz
external_llvm-474be0d0f83eb6543bd4091946b40bb4967a3c11.tar.bz2
Teach the SLP vectorizer the correct way to check for consecutive access
using GEPs. Previously, it used a number of different heuristics for analyzing the GEPs. Several of these were conservatively correct, but failed to fall back to SCEV even when SCEV might have given a reasonable answer. One was simply incorrect in how it was formulated. There was good code already to recursively evaluate the constant offsets in GEPs, look through pointer casts, etc. I gathered this into a form code like the SLP code can use in a previous commit, which allows all of this code to become quite simple. There is some performance (compile time) concern here at first glance as we're directly attempting to walk both pointers constant GEP chains. However, a couple of thoughts: 1) The very common cases where there is a dynamic pointer, and a second pointer at a constant offset (usually a stride) from it, this code will actually not do any unnecessary work. 2) InstCombine and other passes work very hard to collapse constant GEPs, so it will be rare that we iterate here for a long time. That said, if there remain performance problems here, there are some obvious things that can improve the situation immensely. Doing a vectorizer-pass-wide memoizer for each individual layer of pointer values, their base values, and the constant offset is likely to be able to completely remove redundant work and strictly limit the scaling of the work to scrape these GEPs. Since this optimization was not done on the prior version (which would still benefit from it), I've not done it here. But if folks have benchmarks that slow down it should be straight forward for them to add. I've added a test case, but I'm not really confident of the amount of testing done for different access patterns, strides, and pointer manipulation. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189007 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Transforms/Vectorize')
-rw-r--r--lib/Transforms/Vectorize/SLPVectorizer.cpp64
1 files changed, 15 insertions, 49 deletions
diff --git a/lib/Transforms/Vectorize/SLPVectorizer.cpp b/lib/Transforms/Vectorize/SLPVectorizer.cpp
index c9b8e7b..b1f097e 100644
--- a/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -992,63 +992,29 @@ bool BoUpSLP::isConsecutiveAccess(Value *A, Value *B) {
if (PtrA == PtrB || PtrA->getType() != PtrB->getType())
return false;
- // Calculate a constant offset from the base pointer without using SCEV
- // in the supported cases.
- // TODO: Add support for the case where one of the pointers is a GEP that
- // uses the other pointer.
- GetElementPtrInst *GepA = dyn_cast<GetElementPtrInst>(PtrA);
- GetElementPtrInst *GepB = dyn_cast<GetElementPtrInst>(PtrB);
-
- unsigned BW = DL->getPointerSizeInBits(ASA);
+ unsigned PtrBitWidth = DL->getPointerSizeInBits(ASA);
Type *Ty = cast<PointerType>(PtrA->getType())->getElementType();
- int64_t Sz = DL->getTypeStoreSize(Ty);
+ APInt Size(PtrBitWidth, DL->getTypeStoreSize(Ty));
- // Check if PtrA is the base and PtrB is a constant offset.
- if (GepB && GepB->getPointerOperand() == PtrA) {
- APInt Offset(BW, 0);
- if (GepB->accumulateConstantOffset(*DL, Offset))
- return Offset.getSExtValue() == Sz;
- return false;
- }
+ APInt OffsetA(PtrBitWidth, 0), OffsetB(PtrBitWidth, 0);
+ PtrA = PtrA->stripAndAccumulateInBoundsConstantOffsets(*DL, OffsetA);
+ PtrB = PtrB->stripAndAccumulateInBoundsConstantOffsets(*DL, OffsetB);
- // Check if PtrB is the base and PtrA is a constant offset.
- if (GepA && GepA->getPointerOperand() == PtrB) {
- APInt Offset(BW, 0);
- if (GepA->accumulateConstantOffset(*DL, Offset))
- return Offset.getSExtValue() == -Sz;
- return false;
- }
+ APInt OffsetDelta = OffsetB - OffsetA;
- // If both pointers are GEPs:
- if (GepA && GepB) {
- // Check that they have the same base pointer and number of indices.
- if (GepA->getPointerOperand() != GepB->getPointerOperand() ||
- GepA->getNumIndices() != GepB->getNumIndices())
- return false;
+ // Check if they are based on the same pointer. That makes the offsets
+ // sufficient.
+ if (PtrA == PtrB)
+ return OffsetDelta == Size;
- // Try to strip the geps. This makes SCEV faster.
- // Make sure that all of the indices except for the last are identical.
- int LastIdx = GepA->getNumIndices();
- for (int i = 0; i < LastIdx - 1; i++) {
- if (GepA->getOperand(i+1) != GepB->getOperand(i+1))
- return false;
- }
-
- PtrA = GepA->getOperand(LastIdx);
- PtrB = GepB->getOperand(LastIdx);
- Sz = 1;
- }
-
- ConstantInt *CA = dyn_cast<ConstantInt>(PtrA);
- ConstantInt *CB = dyn_cast<ConstantInt>(PtrB);
- if (CA && CB) {
- return (CA->getSExtValue() + Sz == CB->getSExtValue());
- }
+ // Compute the necessary base pointer delta to have the necessary final delta
+ // equal to the size.
+ APInt BaseDelta = Size - OffsetDelta;
- // Calculate the distance.
+ // Otherwise compute the distance with SCEV between the base pointers.
const SCEV *PtrSCEVA = SE->getSCEV(PtrA);
const SCEV *PtrSCEVB = SE->getSCEV(PtrB);
- const SCEV *C = SE->getConstant(PtrSCEVA->getType(), Sz);
+ const SCEV *C = SE->getConstant(BaseDelta);
const SCEV *X = SE->getAddExpr(PtrSCEVA, C);
return X == PtrSCEVB;
}