1 files changed, 42 insertions, 16 deletions

diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
index 5314a8219b1e..9c992830879a 100644
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -147,6 +147,10 @@ cl::opt<bool> EnableOrderFileInstrumentation(
     "enable-order-file-instrumentation", cl::init(false), cl::Hidden,
     cl::desc("Enable order file instrumentation (default = off)"));
 
+static cl::opt<bool>
+    EnableMatrix("enable-matrix", cl::init(false), cl::Hidden,
+                 cl::desc("Enable lowering of the matrix intrinsics"));
+
 PassManagerBuilder::PassManagerBuilder() {
     OptLevel = 2;
     SizeLevel = 0;
@@ -320,19 +324,26 @@ void PassManagerBuilder::addFunctionSimplificationPasses(
     legacy::PassManagerBase &MPM) {
   // Start of function pass.
   // Break up aggregate allocas, using SSAUpdater.
+  assert(OptLevel >= 1 && "Calling function optimizer with no optimization level!");
   MPM.add(createSROAPass());
   MPM.add(createEarlyCSEPass(true /* Enable mem-ssa. */)); // Catch trivial redundancies
-  if (EnableGVNHoist)
-    MPM.add(createGVNHoistPass());
-  if (EnableGVNSink) {
-    MPM.add(createGVNSinkPass());
-    MPM.add(createCFGSimplificationPass());
+
+  if (OptLevel > 1) {
+    if (EnableGVNHoist)
+      MPM.add(createGVNHoistPass());
+    if (EnableGVNSink) {
+      MPM.add(createGVNSinkPass());
+      MPM.add(createCFGSimplificationPass());
+    }
   }
 
-  // Speculative execution if the target has divergent branches; otherwise nop.
-  MPM.add(createSpeculativeExecutionIfHasBranchDivergencePass());
-  MPM.add(createJumpThreadingPass());         // Thread jumps.
-  MPM.add(createCorrelatedValuePropagationPass()); // Propagate conditionals
+  if (OptLevel > 1) {
+    // Speculative execution if the target has divergent branches; otherwise nop.
+    MPM.add(createSpeculativeExecutionIfHasBranchDivergencePass());
+
+    MPM.add(createJumpThreadingPass());         // Thread jumps.
+    MPM.add(createCorrelatedValuePropagationPass()); // Propagate conditionals
+  }
   MPM.add(createCFGSimplificationPass());     // Merge & remove BBs
   // Combine silly seq's
   if (OptLevel > 2)
@@ -346,8 +357,10 @@ void PassManagerBuilder::addFunctionSimplificationPasses(
   if (SizeLevel == 0)
     MPM.add(createPGOMemOPSizeOptLegacyPass());
 
-  MPM.add(createTailCallEliminationPass()); // Eliminate tail calls
-  MPM.add(createCFGSimplificationPass());     // Merge & remove BBs
+  // TODO: Investigate the cost/benefit of tail call elimination on debugging.
+  if (OptLevel > 1)
+    MPM.add(createTailCallEliminationPass()); // Eliminate tail calls
+  MPM.add(createCFGSimplificationPass());      // Merge & remove BBs
   MPM.add(createReassociatePass());           // Reassociate expressions
 
   // Begin the loop pass pipeline.
@@ -360,6 +373,7 @@ void PassManagerBuilder::addFunctionSimplificationPasses(
   }
   // Rotate Loop - disable header duplication at -Oz
   MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1));
+  // TODO: Investigate promotion cap for O1.
   MPM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
   if (EnableSimpleLoopUnswitch)
     MPM.add(createSimpleLoopUnswitchLegacyPass());
@@ -402,16 +416,19 @@ void PassManagerBuilder::addFunctionSimplificationPasses(
   // opened up by them.
   addInstructionCombiningPass(MPM);
   addExtensionsToPM(EP_Peephole, MPM);
-  MPM.add(createJumpThreadingPass());         // Thread jumps
-  MPM.add(createCorrelatedValuePropagationPass());
-  MPM.add(createDeadStoreEliminationPass());  // Delete dead stores
-  MPM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
+  if (OptLevel > 1) {
+    MPM.add(createJumpThreadingPass());         // Thread jumps
+    MPM.add(createCorrelatedValuePropagationPass());
+    MPM.add(createDeadStoreEliminationPass());  // Delete dead stores
+    MPM.add(createLICMPass(LicmMssaOptCap, LicmMssaNoAccForPromotionCap));
+  }
 
   addExtensionsToPM(EP_ScalarOptimizerLate, MPM);
 
   if (RerollLoops)
     MPM.add(createLoopRerollPass());
 
+  // TODO: Investigate if this is too expensive at O1.
   MPM.add(createAggressiveDCEPass());         // Delete dead instructions
   MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
   // Clean up after everything.
@@ -656,6 +673,14 @@ void PassManagerBuilder::populateModulePassManager(
   MPM.add(createFloat2IntPass());
   MPM.add(createLowerConstantIntrinsicsPass());
 
+  if (EnableMatrix) {
+    MPM.add(createLowerMatrixIntrinsicsPass());
+    // CSE the pointer arithmetic of the column vectors.  This allows alias
+    // analysis to establish no-aliasing between loads and stores of different
+    // columns of the same matrix.
+    MPM.add(createEarlyCSEPass(false));
+  }
+
   addExtensionsToPM(EP_VectorizerStart, MPM);
 
   // Re-rotate loops in all our loop nests. These may have fallout out of
@@ -899,7 +924,8 @@ void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
 
   // LTO provides additional opportunities for tailcall elimination due to
   // link-time inlining, and visibility of nocapture attribute.
-  PM.add(createTailCallEliminationPass());
+  if (OptLevel > 1)
+    PM.add(createTailCallEliminationPass());
 
   // Infer attributes on declarations, call sites, arguments, etc.
   PM.add(createPostOrderFunctionAttrsLegacyPass()); // Add nocapture.