[PPCGCodeGeneration] Enable `polly-codegen-perf-monitoring` for PPCGCodegen.

This feature was not enabled for `PPCGCodeGeneration`. Now that this is
enabled, we can benchmark Scops that have been optimised with
`-polly-codegen-ppcg` with the `-polly-codegen-perf-monitoring` option.

Differential Revision: https://reviews.llvm.org/D36934

llvm-svn: 311328

2 files changed, 25 insertions, 4 deletions

diff --git a/polly/lib/CodeGen/CodeGeneration.cpp b/polly/lib/CodeGen/CodeGeneration.cpp
index 76022d7b594..d362ffbfaf1 100644
--- a/polly/lib/CodeGen/CodeGeneration.cpp
+++ b/polly/lib/CodeGen/CodeGeneration.cpp
@@ -49,10 +49,12 @@ static cl::opt<bool> Verify("polly-codegen-verify",
                             cl::Hidden, cl::init(false), cl::ZeroOrMore,
                             cl::cat(PollyCategory));
 
-static cl::opt<bool>
-    PerfMonitoring("polly-codegen-perf-monitoring",
-                   cl::desc("Add run-time performance monitoring"), cl::Hidden,
-                   cl::init(false), cl::ZeroOrMore, cl::cat(PollyCategory));
+bool polly::PerfMonitoring;
+static cl::opt<bool, true>
+    XPerfMonitoring("polly-codegen-perf-monitoring",
+                    cl::desc("Add run-time performance monitoring"), cl::Hidden,
+                    cl::location(polly::PerfMonitoring), cl::init(false),
+                    cl::ZeroOrMore, cl::cat(PollyCategory));
 
 namespace polly {
 /// Mark a basic block unreachable.
diff --git a/polly/lib/CodeGen/PPCGCodeGeneration.cpp b/polly/lib/CodeGen/PPCGCodeGeneration.cpp
index aa4886dc070..28fa9e6b553 100644
--- a/polly/lib/CodeGen/PPCGCodeGeneration.cpp
+++ b/polly/lib/CodeGen/PPCGCodeGeneration.cpp
@@ -16,6 +16,7 @@
 #include "polly/CodeGen/CodeGeneration.h"
 #include "polly/CodeGen/IslAst.h"
 #include "polly/CodeGen/IslNodeBuilder.h"
+#include "polly/CodeGen/PerfMonitor.h"
 #include "polly/CodeGen/Utils.h"
 #include "polly/DependenceInfo.h"
 #include "polly/LinkAllPasses.h"
@@ -122,6 +123,8 @@ static cl::opt<int>
                cl::desc("Minimal number of compute statements to run on GPU."),
                cl::Hidden, cl::init(10 * 512 * 512));
 
+extern bool polly::PerfMonitoring;
+
 /// Return  a unique name for a Scop, which is the scop region with the
 /// function name.
 std::string getUniqueScopName(const Scop *S) {
@@ -3433,6 +3436,22 @@ public:
       isl_ast_node_free(Root);
     } else {
 
+      if (polly::PerfMonitoring) {
+        PerfMonitor P(*S, EnteringBB->getParent()->getParent());
+        P.initialize();
+        P.insertRegionStart(SplitBlock->getTerminator());
+
+        // TODO: actually think if this is the correct exiting block to place
+        // the `end` performance marker. Invariant load hoisting changes
+        // the CFG in a way that I do not precisely understand, so I
+        // (Siddharth<siddu.druid@gmail.com>) should come back to this and
+        // think about which exiting block to use.
+        auto *ExitingBlock = StartBlock->getUniqueSuccessor();
+        assert(ExitingBlock);
+        BasicBlock *MergeBlock = ExitingBlock->getUniqueSuccessor();
+        P.insertRegionEnd(MergeBlock->getTerminator());
+      }
+
       NodeBuilder.addParameters(S->getContext().release());
       Value *RTC = NodeBuilder.createRTC(Condition);
       Builder.GetInsertBlock()->getTerminator()->setOperand(0, RTC);