[PATCH] D57779: [SLP] Add support for throttling.

[Dinar Temirbulatov via Phabricator via llvm-commits]

dtemirbulatov marked 2 inline comments as done.
dtemirbulatov added inline comments.


================
Comment at: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp:6680-6681
         Changed = true;
-      }
+      } else if (SLPThrottleBudget > 0 &&
+                 R.getTreeCost(true, UserCost) < -SLPCostThreshold) {
+        R.vectorizeTree();
----------------
ABataev wrote:
> ABataev wrote:
> > Why `SLPThrottleBudget > 0`? What if `SLPThrottleBudget` equals 0?
> Why we can't do something like this:
> ```
> int NumAttempts = 0;
> do {
>       if (R.isTreeTinyAndNotFullyVectorizable())
>         break;
> 
>       R.computeMinimumValueSizes();
>       InstructionCost Cost = R.getTreeCost();
>       InstructionCost UserCost = 0;
>       ....
>       if (Cost < -SLPCostThreshold) {
>         LLVM_DEBUG(dbgs() << "SLP: Vectorizing list at cost:" << Cost << ".\n");
>         R.getORE()->emit(OptimizationRemark(SV_NAME, "VectorizedList",
>                                                     cast<Instruction>(Ops[0]))
>                                  << "SLP vectorized with cost " << ore::NV("Cost", Cost)
>                                  << " and with tree size "
>                                  << ore::NV("TreeSize", R.getTreeSize()));
> 
>         R.vectorizeTree();
>         // Move to the next bundle.
>         I += VF - 1;
>         NextInst = I + 1;
>         Changed = true;
>         break;
>       }
>    ...
>    /// Do throttling here.
>    ++NumAttempts;
> } while (NumAttempts < SLPThrottleBudget);
> ```
We are doing partial vectorization and we have to know UserCost to make the correct partial tree cut.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57779/new/

https://reviews.llvm.org/D57779