[llvm] [VPlan] Dispatch to multiple exit blocks via middle blocks. (PR #112138)

David Sherwood via llvm-commits llvm-commits at lists.llvm.org
Thu Oct 24 04:06:46 PDT 2024


================
@@ -1696,3 +1702,79 @@ void VPlanTransforms::createInterleaveGroups(
       }
   }
 }
+
+void VPlanTransforms::convertToMultiCond(VPlan &Plan, ScalarEvolution &SE,
+                                         Loop *OrigLoop,
+                                         VPRecipeBuilder &RecipeBuilder) {
+  auto *LatchVPBB =
+      cast<VPBasicBlock>(Plan.getVectorLoopRegion()->getExiting());
+  VPBuilder Builder(LatchVPBB->getTerminator());
+  auto *MiddleVPBB =
+      cast<VPBasicBlock>(Plan.getVectorLoopRegion()->getSingleSuccessor());
+
+  VPRegionBlock *LoopRegion = Plan.getVectorLoopRegion();
+
+  const SCEV *BackedgeTakenCount =
+      SE.getExitCount(OrigLoop, OrigLoop->getLoopLatch());
+  const SCEV *TripCount = SE.getTripCountFromExitCount(
+      BackedgeTakenCount, Plan.getCanonicalIV()->getScalarType(), OrigLoop);
+  VPValue *NewTC = vputils::getOrCreateVPValueForSCEVExpr(Plan, TripCount, SE);
+  Plan.getTripCount()->replaceAllUsesWith(NewTC);
+  Plan.resetTripCount(NewTC);
+
+  VPValue *EarlyExitTaken = nullptr;
+  SmallVector<BasicBlock *> ExitingBBs;
+  OrigLoop->getExitingBlocks(ExitingBBs);
+  for (BasicBlock *Exiting : ExitingBBs) {
+    auto *ExitingTerm = cast<BranchInst>(Exiting->getTerminator());
+    BasicBlock *TrueSucc = ExitingTerm->getSuccessor(0);
+    BasicBlock *FalseSucc = ExitingTerm->getSuccessor(1);
+    VPIRBasicBlock *VPExitBlock;
+    if (OrigLoop->getUniqueExitBlock())
----------------
david-arm wrote:

Hmm, I think I understand what you're trying to do with this a bit more now. Essentially, this patch is trying to take an existing supported vectorisation case (early countable exits) and apply a new vectorisation style. This permits you to test the new code you're adding without having to worry about the legality of vectorising loops with uncountable exits. I guess it's just the new flag I'm worried about since it conflicts with my existing PR #88385. It's almost like you want a flag to control the flavour of vectorisation for an already support case, i.e. something like `-prefer-multi-exit`.

https://github.com/llvm/llvm-project/pull/112138


More information about the llvm-commits mailing list