[llvm-branch-commits] [llvm-branch] r279174 - Merging r279125 and r278343:
Hans Wennborg via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Thu Aug 18 15:38:06 PDT 2016
Author: hans
Date: Thu Aug 18 17:38:06 2016
New Revision: 279174
URL: http://llvm.org/viewvc/llvm-project?rev=279174&view=rev
Log:
Merging r279125 and r278343:
------------------------------------------------------------------------
r279125 | mssimpso | 2016-08-18 12:50:32 -0700 (Thu, 18 Aug 2016) | 14 lines
[SLP] Initialize VectorizedValue when gathering
We abort building vectorizable trees in some cases (e.g., if the maximum
recursion depth is reached, if the region size is too large, etc.). If this
happens for a reduction, we can be left with a root entry that needs to be
gathered. For these cases, we need make sure we actually set VectorizedValue to
the resulting vector.
This patch ensures we properly set VectorizedValue, and it also ensures the
insertelement sequence generated for the gathers is inserted at the correct
location.
Reference: https://llvm.org/bugs/show_bug.cgi?id=28330
Differential Revison: https://reviews.llvm.org/D23410
------------------------------------------------------------------------
------------------------------------------------------------------------
r278343 | mssimpso | 2016-08-11 08:28:45 -0700 (Thu, 11 Aug 2016) | 1 line
[SLP] Make RecursionMaxDepth a command line option (NFC)
------------------------------------------------------------------------
Added:
llvm/branches/release_39/test/Transforms/SLPVectorizer/AArch64/gather-root.ll
- copied unchanged from r279125, llvm/trunk/test/Transforms/SLPVectorizer/AArch64/gather-root.ll
Modified:
llvm/branches/release_39/ (props changed)
llvm/branches/release_39/lib/Transforms/Vectorize/SLPVectorizer.cpp
Propchange: llvm/branches/release_39/
------------------------------------------------------------------------------
--- svn:mergeinfo (original)
+++ svn:mergeinfo Thu Aug 18 17:38:06 2016
@@ -1,3 +1,3 @@
/llvm/branches/Apple/Pertwee:110850,110961
/llvm/branches/type-system-rewrite:133420-134817
-/llvm/trunk:155241,275868-275870,275879,275898,275928,275935,275946,275978,275981,276015,276051,276077,276109,276119,276181,276209,276236-276237,276358,276364,276368,276389,276435,276438,276479,276510,276648,276676,276712,276740,276823,276956,276980,277093,277114,277135,277371,277399,277500,277504,277625,277691,277693,277773,278002,278086,278133,278157,278370,278413,278558-278559,278562,278569,278571,278573,278575,278584,278841,278900,278938,278999
+/llvm/trunk:155241,275868-275870,275879,275898,275928,275935,275946,275978,275981,276015,276051,276077,276109,276119,276181,276209,276236-276237,276358,276364,276368,276389,276435,276438,276479,276510,276648,276676,276712,276740,276823,276956,276980,277093,277114,277135,277371,277399,277500,277504,277625,277691,277693,277773,278002,278086,278133,278157,278343,278370,278413,278558-278559,278562,278569,278571,278573,278575,278584,278841,278900,278938,278999,279125
Modified: llvm/branches/release_39/lib/Transforms/Vectorize/SLPVectorizer.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/branches/release_39/lib/Transforms/Vectorize/SLPVectorizer.cpp?rev=279174&r1=279173&r2=279174&view=diff
==============================================================================
--- llvm/branches/release_39/lib/Transforms/Vectorize/SLPVectorizer.cpp (original)
+++ llvm/branches/release_39/lib/Transforms/Vectorize/SLPVectorizer.cpp Thu Aug 18 17:38:06 2016
@@ -82,8 +82,9 @@ static cl::opt<int> MinVectorRegSizeOpti
"slp-min-reg-size", cl::init(128), cl::Hidden,
cl::desc("Attempt to vectorize for this register size in bits"));
-// FIXME: Set this via cl::opt to allow overriding.
-static const unsigned RecursionMaxDepth = 12;
+static cl::opt<unsigned> RecursionMaxDepth(
+ "slp-recursion-max-depth", cl::init(12), cl::Hidden,
+ cl::desc("Limit the recursion depth when building a vectorizable tree"));
// Limit the number of alias checks. The limit is chosen so that
// it has no negative effect on the llvm benchmarks.
@@ -2124,11 +2125,61 @@ void BoUpSLP::reorderInputsAccordingToOp
}
void BoUpSLP::setInsertPointAfterBundle(ArrayRef<Value *> VL) {
- Instruction *VL0 = cast<Instruction>(VL[0]);
- BasicBlock::iterator NextInst(VL0);
- ++NextInst;
- Builder.SetInsertPoint(VL0->getParent(), NextInst);
- Builder.SetCurrentDebugLocation(VL0->getDebugLoc());
+
+ // Get the basic block this bundle is in. All instructions in the bundle
+ // should be in this block.
+ auto *Front = cast<Instruction>(VL.front());
+ auto *BB = Front->getParent();
+ assert(all_of(make_range(VL.begin(), VL.end()), [&](Value *V) -> bool {
+ return cast<Instruction>(V)->getParent() == BB;
+ }));
+
+ // The last instruction in the bundle in program order.
+ Instruction *LastInst = nullptr;
+
+ // Find the last instruction. The common case should be that BB has been
+ // scheduled, and the last instruction is VL.back(). So we start with
+ // VL.back() and iterate over schedule data until we reach the end of the
+ // bundle. The end of the bundle is marked by null ScheduleData.
+ if (BlocksSchedules.count(BB)) {
+ auto *Bundle = BlocksSchedules[BB]->getScheduleData(VL.back());
+ if (Bundle && Bundle->isPartOfBundle())
+ for (; Bundle; Bundle = Bundle->NextInBundle)
+ LastInst = Bundle->Inst;
+ }
+
+ // LastInst can still be null at this point if there's either not an entry
+ // for BB in BlocksSchedules or there's no ScheduleData available for
+ // VL.back(). This can be the case if buildTree_rec aborts for various
+ // reasons (e.g., the maximum recursion depth is reached, the maximum region
+ // size is reached, etc.). ScheduleData is initialized in the scheduling
+ // "dry-run".
+ //
+ // If this happens, we can still find the last instruction by brute force. We
+ // iterate forwards from Front (inclusive) until we either see all
+ // instructions in the bundle or reach the end of the block. If Front is the
+ // last instruction in program order, LastInst will be set to Front, and we
+ // will visit all the remaining instructions in the block.
+ //
+ // One of the reasons we exit early from buildTree_rec is to place an upper
+ // bound on compile-time. Thus, taking an additional compile-time hit here is
+ // not ideal. However, this should be exceedingly rare since it requires that
+ // we both exit early from buildTree_rec and that the bundle be out-of-order
+ // (causing us to iterate all the way to the end of the block).
+ if (!LastInst) {
+ SmallPtrSet<Value *, 16> Bundle(VL.begin(), VL.end());
+ for (auto &I : make_range(BasicBlock::iterator(Front), BB->end())) {
+ if (Bundle.erase(&I))
+ LastInst = &I;
+ if (Bundle.empty())
+ break;
+ }
+ }
+
+ // Set the insertion point after the last instruction in the bundle. Set the
+ // debug location to Front.
+ Builder.SetInsertPoint(BB, next(BasicBlock::iterator(LastInst)));
+ Builder.SetCurrentDebugLocation(Front->getDebugLoc());
}
Value *BoUpSLP::Gather(ArrayRef<Value *> VL, VectorType *Ty) {
@@ -2206,7 +2257,9 @@ Value *BoUpSLP::vectorizeTree(TreeEntry
if (E->NeedToGather) {
setInsertPointAfterBundle(E->Scalars);
- return Gather(E->Scalars, VecTy);
+ auto *V = Gather(E->Scalars, VecTy);
+ E->VectorizedValue = V;
+ return V;
}
unsigned Opcode = getSameOpcode(E->Scalars);
@@ -2253,7 +2306,10 @@ Value *BoUpSLP::vectorizeTree(TreeEntry
E->VectorizedValue = V;
return V;
}
- return Gather(E->Scalars, VecTy);
+ setInsertPointAfterBundle(E->Scalars);
+ auto *V = Gather(E->Scalars, VecTy);
+ E->VectorizedValue = V;
+ return V;
}
case Instruction::ExtractValue: {
if (canReuseExtract(E->Scalars, Instruction::ExtractValue)) {
@@ -2265,7 +2321,10 @@ Value *BoUpSLP::vectorizeTree(TreeEntry
E->VectorizedValue = V;
return propagateMetadata(V, E->Scalars);
}
- return Gather(E->Scalars, VecTy);
+ setInsertPointAfterBundle(E->Scalars);
+ auto *V = Gather(E->Scalars, VecTy);
+ E->VectorizedValue = V;
+ return V;
}
case Instruction::ZExt:
case Instruction::SExt:
More information about the llvm-branch-commits
mailing list