[llvm] cd0c00c - [LV] Move exact FP math check out of Requirements.

[Florian Hahn via llvm-commits]

Author: Florian Hahn
Date: 2021-03-24T11:01:44Z
New Revision: cd0c00c9fe39a5dff9c776e5727fdf38be7e8132

URL: https://github.com/llvm/llvm-project/commit/cd0c00c9fe39a5dff9c776e5727fdf38be7e8132
DIFF: https://github.com/llvm/llvm-project/commit/cd0c00c9fe39a5dff9c776e5727fdf38be7e8132.diff

LOG: [LV] Move exact FP math check out of Requirements.

We know if the loop contains FP instructions preventing vectorization
after we are done with legality checks. This patch updates the code the
check for un-vectorizable FP operations earlier, to avoid unnecessarily
running the cost model and picking a vectorization factor. It also makes
the code more direct and moves the check to a position where similar
checks are done.

I might be missing something, but I don't see any reason to handle this
check differently to other, similar checks.

Reviewed By: lebedev.ri

Differential Revision: https://reviews.llvm.org/D98633

Added: 
    

Modified: 
    llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
    llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
    llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h b/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
index d6b0dcc7b771..f9a8be317bb6 100644
--- a/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
+++ b/llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
@@ -189,6 +189,11 @@ class LoopVectorizationRequirements {
 
   bool doesNotMeet(Function *F, Loop *L, const LoopVectorizeHints &Hints);
 
+  Instruction *getExactFPInst() { return ExactFPMathInst; }
+  bool canVectorizeFPMath(const LoopVectorizeHints &Hints) const {
+    return !ExactFPMathInst || Hints.allowReordering();
+  }
+
 private:
   unsigned NumRuntimePointerChecks = 0;
   Instruction *ExactFPMathInst = nullptr;

diff  --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
index 5091bb03bad0..939fbe3e3601 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
@@ -250,16 +250,6 @@ bool LoopVectorizationRequirements::doesNotMeet(
     Function *F, Loop *L, const LoopVectorizeHints &Hints) {
   const char *PassName = Hints.vectorizeAnalysisPassName();
   bool Failed = false;
-  if (ExactFPMathInst && !Hints.allowReordering()) {
-    ORE.emit([&]() {
-      return OptimizationRemarkAnalysisFPCommute(
-                 PassName, "CantReorderFPOps", ExactFPMathInst->getDebugLoc(),
-                 ExactFPMathInst->getParent())
-             << "loop not vectorized: cannot prove it is safe to reorder "
-                "floating-point operations";
-    });
-    Failed = true;
-  }
 
   // Test if runtime memcheck thresholds are exceeded.
   bool PragmaThresholdReached =

diff  --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index c5611fa0f1be..c60880cc452a 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -9599,6 +9599,21 @@ bool LoopVectorizePass::processLoop(Loop *L) {
     return false;
   }
 
+  if (!Requirements.canVectorizeFPMath(Hints)) {
+    ORE->emit([&]() {
+      auto *ExactFPMathInst = Requirements.getExactFPInst();
+      return OptimizationRemarkAnalysisFPCommute(DEBUG_TYPE, "CantReorderFPOps",
+                                                 ExactFPMathInst->getDebugLoc(),
+                                                 ExactFPMathInst->getParent())
+             << "loop not vectorized: cannot prove it is safe to reorder "
+                "floating-point operations";
+    });
+    LLVM_DEBUG(dbgs() << "LV: loop not vectorized: cannot prove it is safe to "
+                         "reorder floating-point operations\n");
+    Hints.emitRemarkWithHints();
+    return false;
+  }
+
   bool UseInterleaved = TTI->enableInterleavedAccessVectorization();
   InterleavedAccessInfo IAI(PSE, L, DT, LI, LVL.getLAI());