Add support for lowering simd if clause to LLVM IR

Scope of changes:
  1) Added new function to generate loop versioning
  2) Added support for if clause to applySimd function
  2) Added tests which confirm that lowering is successful

If ifCond is specified, then collapsed loop is duplicated and if branch
is added. Duplicated loop is executed if simd ifCond is evaluated to false.

Reviewed By: Meinersbur

Differential Revision: https://reviews.llvm.org/D129368

Signed-off-by: Dominik Adamski <dominik.adamski@amd.com>

1 files changed, 51 insertions, 2 deletions

diff --git a/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp b/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
index 55afea6..7e3b548 100644
--- a/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
+++ b/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
@@ -1771,7 +1771,7 @@ TEST_F(OpenMPIRBuilderTest, ApplySimd) {
   CanonicalLoopInfo *CLI = buildSingleLoopFunction(DL, OMPBuilder, 32);
 
   // Simd-ize the loop.
-  OMPBuilder.applySimd(CLI, nullptr);
+  OMPBuilder.applySimd(CLI, /* IfCond */ nullptr, /* Simdlen */ nullptr);
 
   OMPBuilder.finalize();
   EXPECT_FALSE(verifyModule(*M, &errs()));
@@ -1802,7 +1802,8 @@ TEST_F(OpenMPIRBuilderTest, ApplySimdlen) {
   CanonicalLoopInfo *CLI = buildSingleLoopFunction(DL, OMPBuilder, 32);
 
   // Simd-ize the loop.
-  OMPBuilder.applySimd(CLI, ConstantInt::get(Type::getInt32Ty(Ctx), 3));
+  OMPBuilder.applySimd(CLI, /*IfCond */ nullptr,
+                       ConstantInt::get(Type::getInt32Ty(Ctx), 3));
 
   OMPBuilder.finalize();
   EXPECT_FALSE(verifyModule(*M, &errs()));
@@ -1828,6 +1829,54 @@ TEST_F(OpenMPIRBuilderTest, ApplySimdlen) {
   }));
 }
 
+TEST_F(OpenMPIRBuilderTest, ApplySimdLoopIf) {
+  OpenMPIRBuilder OMPBuilder(*M);
+  IRBuilder<> Builder(BB);
+  AllocaInst *Alloc1 = Builder.CreateAlloca(Builder.getInt32Ty());
+  AllocaInst *Alloc2 = Builder.CreateAlloca(Builder.getInt32Ty());
+
+  // Generation of if condition
+  Builder.CreateStore(ConstantInt::get(Type::getInt32Ty(Ctx), 0U), Alloc1);
+  Builder.CreateStore(ConstantInt::get(Type::getInt32Ty(Ctx), 1U), Alloc2);
+  LoadInst *Load1 = Builder.CreateLoad(Alloc1->getAllocatedType(), Alloc1);
+  LoadInst *Load2 = Builder.CreateLoad(Alloc2->getAllocatedType(), Alloc2);
+
+  Value *IfCmp = Builder.CreateICmpNE(Load1, Load2);
+
+  CanonicalLoopInfo *CLI = buildSingleLoopFunction(DL, OMPBuilder, 32);
+
+  // Simd-ize the loop with if condition
+  OMPBuilder.applySimd(CLI, IfCmp, ConstantInt::get(Type::getInt32Ty(Ctx), 3));
+
+  OMPBuilder.finalize();
+  EXPECT_FALSE(verifyModule(*M, &errs()));
+
+  PassBuilder PB;
+  FunctionAnalysisManager FAM;
+  PB.registerFunctionAnalyses(FAM);
+  LoopInfo &LI = FAM.getResult<LoopAnalysis>(*F);
+
+  // Check if there are two loops (one with enabled vectorization)
+  const std::vector<Loop *> &TopLvl = LI.getTopLevelLoops();
+  EXPECT_EQ(TopLvl.size(), 2u);
+
+  Loop *L = TopLvl[0];
+  EXPECT_TRUE(findStringMetadataForLoop(L, "llvm.loop.parallel_accesses"));
+  EXPECT_TRUE(getBooleanLoopAttribute(L, "llvm.loop.vectorize.enable"));
+  EXPECT_EQ(getIntLoopAttribute(L, "llvm.loop.vectorize.width"), 3);
+
+  // The second loop should have disabled vectorization
+  L = TopLvl[1];
+  EXPECT_FALSE(findStringMetadataForLoop(L, "llvm.loop.parallel_accesses"));
+  EXPECT_FALSE(getBooleanLoopAttribute(L, "llvm.loop.vectorize.enable"));
+  // Check for llvm.access.group metadata attached to the printf
+  // function in the loop body.
+  BasicBlock *LoopBody = CLI->getBody();
+  EXPECT_TRUE(any_of(*LoopBody, [](Instruction &I) {
+    return I.getMetadata("llvm.access.group") != nullptr;
+  }));
+}
+
 TEST_F(OpenMPIRBuilderTest, UnrollLoopFull) {
   OpenMPIRBuilder OMPBuilder(*M);