[PATCH] D69470: [ExpandReductions] Don't push all intrinsics to the worklist. Just push reductions.

[Craig Topper via Phabricator via llvm-commits]

craig.topper created this revision.
craig.topper added reviewers: RKSimon, spatel, aemerson.
Herald added a subscriber: hiraditya.
Herald added a project: LLVM.

We were previously pushing all intrinsics used in a function to the
worklist. This is wasteful for memory in a function with a lot of
intrinsics.

We also ask TTI if we should expand every intrinsic, but we only
have expansion support for the reduction intrinsics. This just
wastes time for the non-reduction intrinsics.

This patch only pushes reduction intrinsics into the worklist and
skips other intrinsics.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D69470

Files:
  llvm/lib/CodeGen/ExpandReductions.cpp


Index: llvm/lib/CodeGen/ExpandReductions.cpp
===================================================================
--- llvm/lib/CodeGen/ExpandReductions.cpp
+++ llvm/lib/CodeGen/ExpandReductions.cpp
@@ -78,9 +78,28 @@
 bool expandReductions(Function &F, const TargetTransformInfo *TTI) {
   bool Changed = false;
   SmallVector<IntrinsicInst *, 4> Worklist;
-  for (inst_iterator I = inst_begin(F), E = inst_end(F); I != E; ++I)
-    if (auto II = dyn_cast<IntrinsicInst>(&*I))
-      Worklist.push_back(II);
+  for (inst_iterator I = inst_begin(F), E = inst_end(F); I != E; ++I) {
+    if (auto II = dyn_cast<IntrinsicInst>(&*I)) {
+      switch (II->getIntrinsicID()) {
+      default: break;
+      case Intrinsic::experimental_vector_reduce_v2_fadd:
+      case Intrinsic::experimental_vector_reduce_v2_fmul:
+      case Intrinsic::experimental_vector_reduce_add:
+      case Intrinsic::experimental_vector_reduce_mul:
+      case Intrinsic::experimental_vector_reduce_and:
+      case Intrinsic::experimental_vector_reduce_or:
+      case Intrinsic::experimental_vector_reduce_xor:
+      case Intrinsic::experimental_vector_reduce_smax:
+      case Intrinsic::experimental_vector_reduce_smin:
+      case Intrinsic::experimental_vector_reduce_umax:
+      case Intrinsic::experimental_vector_reduce_umin:
+      case Intrinsic::experimental_vector_reduce_fmax:
+      case Intrinsic::experimental_vector_reduce_fmin:
+        Worklist.push_back(II);
+        break;
+      }
+    }
+  }
 
   for (auto *II : Worklist) {
     if (!TTI->shouldExpandReduction(II))
@@ -96,6 +115,7 @@
     IRBuilder<>::FastMathFlagGuard FMFGuard(Builder);
     Builder.setFastMathFlags(FMF);
     switch (ID) {
+    default: llvm_unreachable("Unexpected intrinsic!");
     case Intrinsic::experimental_vector_reduce_v2_fadd:
     case Intrinsic::experimental_vector_reduce_v2_fmul: {
       // FMFs must be attached to the call, otherwise it's an ordered reduction
@@ -109,7 +129,8 @@
         Rdx = Builder.CreateBinOp((Instruction::BinaryOps)getOpcode(ID),
                                   Acc, Rdx, "bin.rdx");
       }
-    } break;
+      break;
+    }
     case Intrinsic::experimental_vector_reduce_add:
     case Intrinsic::experimental_vector_reduce_mul:
     case Intrinsic::experimental_vector_reduce_and:
@@ -123,9 +144,8 @@
     case Intrinsic::experimental_vector_reduce_fmin: {
       Value *Vec = II->getArgOperand(0);
       Rdx = getShuffleReduction(Builder, Vec, getOpcode(ID), MRK);
-    } break;
-    default:
-      continue;
+      break;
+    }
     }
     II->replaceAllUsesWith(Rdx);
     II->eraseFromParent();


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D69470.226558.patch
Type: text/x-patch
Size: 2624 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191027/2026c039/attachment.bin>