[PerfMonitor] Fix rdtscp callsites

[ttheodor]

Summary

Update all rdtscp callsites in PerfMonitor so that they conform with the signature changes introduced in r341698.

include/polly/CodeGen/PerfMonitor.h

private:
   llvm::Value *TripCountForCurrentScopPtr;
 
   /// The total number of cycles spent within scops.
   llvm::Value *CyclesInScopsPtr;
 
   /// The value of the cycle counter at the beginning of the last scop.
   llvm::Value *CyclesInScopStartPtr;
 
-  /// A memory location which serves as argument of the RDTSCP function.
-  ///
-  /// The value written to this location is currently not used.
-  llvm::Value *RDTSCPWriteLocation;
-
   /// A global variable, that keeps track if the performance monitor
   /// initialization has already been run.
   llvm::Value *AlreadyInitializedPtr;
 
   llvm::Function *insertInitFunction(llvm::Function *FinalReporting);
 
   /// Add Function @p to list of global constructors
   ///
private:
   void addGlobalVariables();
 
   /// Add per-scop tracking to module.
   ///
   /// Insert the global variable which is used to track the number of cycles
   /// this scop runs.
   void addScopCounter();
 
-  /// Get a reference to the intrinsic "i64 @llvm.x86.rdtscp(i8*)".
+  /// Get a reference to the intrinsic "{ i64, i32 } @llvm.x86.rdtscp()".
   ///
   /// The rdtscp function returns the current value of the processor's
   /// time-stamp counter as well as the current CPU identifier. On modern x86
   /// systems, the returned value is independent of the dynamic clock frequency
   /// and consistent across multiple cores. It can consequently be used to get
   /// accurate and low-overhead timing information. Even though the counter is
   /// wrapping, it can be reliably used even for measuring longer time
   /// intervals, as on a 1 GHz processor the counter only wraps every 545 years.

lib/CodeGen/PerfMonitor.cpp

void PerfMonitor::addGlobalVariables() {
   TryRegisterGlobal(M, "__polly_perf_initialized", Builder.getInt1(0),
                     &AlreadyInitializedPtr);
 
   TryRegisterGlobal(M, "__polly_perf_cycles_in_scops", Builder.getInt64(0),
                     &CyclesInScopsPtr);
 
   TryRegisterGlobal(M, "__polly_perf_cycles_in_scop_start", Builder.getInt64(0),
                     &CyclesInScopStartPtr);
-
-  TryRegisterGlobal(M, "__polly_perf_write_loation", Builder.getInt32(0),
-                    &RDTSCPWriteLocation);
 }
 
 static const char *InitFunctionName = "__polly_perf_init";
 static const char *FinalReportingFunctionName = "__polly_perf_final";
 
 static BasicBlock *FinalStartBB = nullptr;
 static ReturnInst *ReturnFromFinal = nullptr;
 
if (!Supported) {
     RuntimeDebugBuilder::createCPUPrinter(
         Builder, "Polly runtime information generation not supported\n");
     Builder.CreateRetVoid();
     return ExitFn;
   }
 
   // Measure current cycles and compute final timings.
   Function *RDTSCPFn = getRDTSCP();
-  Value *CurrentCycles = Builder.CreateCall(
-      RDTSCPFn,
-      Builder.CreatePointerCast(RDTSCPWriteLocation, Builder.getInt8PtrTy()));
+
+  Value *CurrentCycles =
+      Builder.CreateExtractValue(Builder.CreateCall(RDTSCPFn), {0});
   Value *CyclesStart = Builder.CreateLoad(CyclesTotalStartPtr, true);
   Value *CyclesTotal = Builder.CreateSub(CurrentCycles, CyclesStart);
   Value *CyclesInScops = Builder.CreateLoad(CyclesInScopsPtr, true);
 
   // Print the runtime information.
   RuntimeDebugBuilder::createCPUPrinter(Builder, "Polly runtime information\n");
   RuntimeDebugBuilder::createCPUPrinter(Builder, "-------------------------\n");
   RuntimeDebugBuilder::createCPUPrinter(Builder, "Total: ", CyclesTotal, "\n");
Function *PerfMonitor::insertInitFunction(Function *FinalReporting) {
   Value *FinalReportingPtr =
       Builder.CreatePointerCast(FinalReporting, Builder.getInt8PtrTy());
   Function *AtExitFn = getAtExit();
   Builder.CreateCall(AtExitFn, {FinalReportingPtr});
 
   if (Supported) {
     // Read the currently cycle counter and store the result for later.
     Function *RDTSCPFn = getRDTSCP();
-    Value *CurrentCycles = Builder.CreateCall(
-        RDTSCPFn,
-        Builder.CreatePointerCast(RDTSCPWriteLocation, Builder.getInt8PtrTy()));
+    Value *CurrentCycles =
+        Builder.CreateExtractValue(Builder.CreateCall(RDTSCPFn), {0});
     Builder.CreateStore(CurrentCycles, CyclesTotalStartPtr, true);
   }
   Builder.CreateRetVoid();
 
   return InitFn;
 }
 
 void PerfMonitor::insertRegionStart(Instruction *InsertBefore) {
   if (!Supported)
     return;
 
   Builder.SetInsertPoint(InsertBefore);
   Function *RDTSCPFn = getRDTSCP();
-  Value *CurrentCycles = Builder.CreateCall(
-      RDTSCPFn,
-      Builder.CreatePointerCast(RDTSCPWriteLocation, Builder.getInt8PtrTy()));
+  Value *CurrentCycles =
+      Builder.CreateExtractValue(Builder.CreateCall(RDTSCPFn), {0});
   Builder.CreateStore(CurrentCycles, CyclesInScopStartPtr, true);
 }
 
 void PerfMonitor::insertRegionEnd(Instruction *InsertBefore) {
   if (!Supported)
     return;
 
   Builder.SetInsertPoint(InsertBefore);
   Function *RDTSCPFn = getRDTSCP();
   LoadInst *CyclesStart = Builder.CreateLoad(CyclesInScopStartPtr, true);
-  Value *CurrentCycles = Builder.CreateCall(
-      RDTSCPFn,
-      Builder.CreatePointerCast(RDTSCPWriteLocation, Builder.getInt8PtrTy()));
+  Value *CurrentCycles =
+      Builder.CreateExtractValue(Builder.CreateCall(RDTSCPFn), {0});
   Value *CyclesInScop = Builder.CreateSub(CurrentCycles, CyclesStart);
   Value *CyclesInScops = Builder.CreateLoad(CyclesInScopsPtr, true);
   CyclesInScops = Builder.CreateAdd(CyclesInScops, CyclesInScop);
   Builder.CreateStore(CyclesInScops, CyclesInScopsPtr, true);
 
   Value *CyclesInCurrentScop = Builder.CreateLoad(CyclesInCurrentScopPtr, true);
   CyclesInCurrentScop = Builder.CreateAdd(CyclesInCurrentScop, CyclesInScop);
   Builder.CreateStore(CyclesInCurrentScop, CyclesInCurrentScopPtr, true);
 
   Value *TripCountForCurrentScop =
       Builder.CreateLoad(TripCountForCurrentScopPtr, true);
   TripCountForCurrentScop =
       Builder.CreateAdd(TripCountForCurrentScop, Builder.getInt64(1));
   Builder.CreateStore(TripCountForCurrentScop, TripCountForCurrentScopPtr,
                       true);
 }

test/Isl/CodeGen/perf_monitoring.ll

return:
   fence seq_cst
   ret void
 }
 
 ; CHECK:      @__polly_perf_cycles_total_start = weak thread_local(initialexec) constant i64 0
 ; CHECK-NEXT: @__polly_perf_initialized = weak thread_local(initialexec) constant i1 false
 ; CHECK-NEXT: @__polly_perf_cycles_in_scops = weak thread_local(initialexec) constant i64 0
 ; CHECK-NEXT: @__polly_perf_cycles_in_scop_start = weak thread_local(initialexec) constant i64 0
-; CHECK-NEXT: @__polly_perf_write_loation = weak thread_local(initialexec) constant i32 0
 
 ; CHECK:      polly.split_new_and_old:                          ; preds = %entry
-; CHECK-NEXT:   %0 = call i64 @llvm.x86.rdtscp(i8* bitcast (i32* @__polly_perf_write_loation to i8*))
-; CHECK-NEXT:   store volatile i64 %0, i64* @__polly_perf_cycles_in_scop_start
+; CHECK-NEXT:   %0 = call { i64, i32 } @llvm.x86.rdtscp()
+; CHECK-NEXT:   %1 = extractvalue { i64, i32 } %0, 0
+; CHECK-NEXT:   store volatile i64 %1, i64* @__polly_perf_cycles_in_scop_start
 
 ; CHECK:      polly.merge_new_and_old:                          ; preds = %polly.exiting, %return.region_exiting
-; CHECK-NEXT:   %5 = load volatile i64, i64* @__polly_perf_cycles_in_scop_start
-; CHECK-NEXT:   %6 = call i64 @llvm.x86.rdtscp(i8* bitcast (i32* @__polly_perf_write_loation to i8*))
-; CHECK-NEXT:   %7 = sub i64 %6, %5
-; CHECK-NEXT:   %8 = load volatile i64, i64* @__polly_perf_cycles_in_scops
-; CHECK-NEXT:   %9 = add i64 %8, %7
-; CHECK-NEXT:   store volatile i64 %9, i64* @__polly_perf_cycles_in_scops
+; CHECK-NEXT:   %6 = load volatile i64, i64* @__polly_perf_cycles_in_scop_start
+; CHECK-NEXT:   %7 = call { i64, i32 } @llvm.x86.rdtscp()
+; CHECK-NEXT:   %8 = extractvalue { i64, i32 } %7, 0
+; CHECK-NEXT:   %9 = sub i64 %8, %6
+; CHECK-NEXT:   %10 = load volatile i64, i64* @__polly_perf_cycles_in_scops
+; CHECK-NEXT:   %11 = add i64 %10, %9
+; CHECK-NEXT:   store volatile i64 %11, i64* @__polly_perf_cycles_in_scops
 
 
 ; CHECK:      define weak_odr void @__polly_perf_final() {
 ; CHECK-NEXT: start:
-; CHECK-NEXT:   %0 = call i64 @llvm.x86.rdtscp(i8* bitcast (i32* @__polly_perf_write_loation to i8*))
-; CHECK-NEXT:   %1 = load volatile i64, i64* @__polly_perf_cycles_total_start
-; CHECK-NEXT:   %2 = sub i64 %0, %1
-; CHECK-NEXT:   %3 = load volatile i64, i64* @__polly_perf_cycles_in_scops
-; CHECK-NEXT:   %4 = call i32 (...) @printf(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @1, i32 0, i32 0), i8 addrspace(4)* getelementptr inbounds ([27 x i8], [27 x i8] addrspace(4)* @0, i32 0, i32 0))
-; CHECK-NEXT:   %5 = call i32 @fflush(i8* null)
-; CHECK-NEXT:   %6 = call i32 (...) @printf(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @3, i32 0, i32 0), i8 addrspace(4)* getelementptr inbounds ([27 x i8], [27 x i8] addrspace(4)* @2, i32 0, i32 0))
-; CHECK-NEXT:   %7 = call i32 @fflush(i8* null)
-; CHECK-NEXT:   %8 = call i32 (...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @6, i32 0, i32 0), i8 addrspace(4)* getelementptr inbounds ([8 x i8], [8 x i8] addrspace(4)* @4, i32 0, i32 0), i64 %2, i8 addrspace(4)* getelementptr inbounds ([2 x i8], [2 x i8] addrspace(4)* @5, i32 0, i32 0))
-; CHECK-NEXT:   %9 = call i32 @fflush(i8* null)
-; CHECK-NEXT:   %10 = call i32 (...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @9, i32 0, i32 0), i8 addrspace(4)* getelementptr inbounds ([8 x i8], [8 x i8] addrspace(4)* @7, i32 0, i32 0), i64 %3, i8 addrspace(4)* getelementptr inbounds ([2 x i8], [2 x i8] addrspace(4)* @8, i32 0, i32 0))
-; CHECK-NEXT:   %11 = call i32 @fflush(i8* null)
+; CHECK-NEXT:   %0 = call { i64, i32 } @llvm.x86.rdtscp()
+; CHECK-NEXT:   %1 = extractvalue { i64, i32 } %0, 0
+; CHECK-NEXT:   %2 = load volatile i64, i64* @__polly_perf_cycles_total_start
+; CHECK-NEXT:   %3 = sub i64 %1, %2
+; CHECK-NEXT:   %4 = load volatile i64, i64* @__polly_perf_cycles_in_scops
+; CHECK-NEXT:   %5 = call i32 (...) @printf(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @1, i32 0, i32 0), i8 addrspace(4)* getelementptr inbounds ([27 x i8], [27 x i8] addrspace(4)* @0, i32 0, i32 0))
+; CHECK-NEXT:   %6 = call i32 @fflush(i8* null)
+; CHECK-NEXT:   %7 = call i32 (...) @printf(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @3, i32 0, i32 0), i8 addrspace(4)* getelementptr inbounds ([27 x i8], [27 x i8] addrspace(4)* @2, i32 0, i32 0))
+; CHECK-NEXT:   %8 = call i32 @fflush(i8* null)
+; CHECK-NEXT:   %9 = call i32 (...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @6, i32 0, i32 0), i8 addrspace(4)* getelementptr inbounds ([8 x i8], [8 x i8] addrspace(4)* @4, i32 0, i32 0), i64 %3, i8 addrspace(4)* getelementptr inbounds ([2 x i8], [2 x i8] addrspace(4)* @5, i32 0, i32 0))
+; CHECK-NEXT:   %10 = call i32 @fflush(i8* null)
+; CHECK-NEXT:   %11 = call i32 (...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @9, i32 0, i32 0), i8 addrspace(4)* getelementptr inbounds ([8 x i8], [8 x i8] addrspace(4)* @7, i32 0, i32 0), i64 %4, i8 addrspace(4)* getelementptr inbounds ([2 x i8], [2 x i8] addrspace(4)* @8, i32 0, i32 0))
+; CHECK-NEXT:   %12 = call i32 @fflush(i8* null)
 
 
 ; CHECK:      define weak_odr void @__polly_perf_init() {
 ; CHECK-NEXT: start:
 ; CHECK-NEXT:   %0 = load i1, i1* @__polly_perf_initialized
 ; CHECK-NEXT:   br i1 %0, label %earlyreturn, label %initbb
 
 ; CHECK:      earlyreturn:                                      ; preds = %start
 ; CHECK-NEXT:   ret void
 
 ; CHECK:      initbb:                                           ; preds = %start
 ; CHECK-NEXT:   store i1 true, i1* @__polly_perf_initialized
 ; CHECK-NEXT:   %1 = call i32 @atexit(i8* bitcast (void ()* @__polly_perf_final to i8*))
-; CHECK-NEXT:   %2 = call i64 @llvm.x86.rdtscp(i8* bitcast (i32* @__polly_perf_write_loation to i8*))
-; CHECK-NEXT:   store volatile i64 %2, i64* @__polly_perf_cycles_total_start
+; CHECK-NEXT:   %2 = call { i64, i32 } @llvm.x86.rdtscp()
+; CHECK-NEXT:   %3 = extractvalue { i64, i32 } %2, 0
+; CHECK-NEXT:   store volatile i64 %3, i64* @__polly_perf_cycles_total_start
 ; CHECK-NEXT:   ret void
 ; CHECK-NEXT: }

test/Isl/CodeGen/perf_monitoring_cycles_per_scop.ll

return:
   ret void
 }
 
 ; Declaration of globals - Check for cycles declaration.
 ; @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_cycles" = weak thread_local(initialexec) constant i64 0
 ; @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_cycles" = weak thread_local(initialexec) constant i64 0
 
 ; Bumping up number of cycles in f
-; CHECK:      %10 = load volatile i64, i64* @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_cycles"
-; CHECK-NEXT: %11 = add i64 %10, %7
-; CHECK-NEXT: store volatile i64 %11, i64* @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_cycles"
+; CHECK:      %12 = load volatile i64, i64* @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_cycles"
+; CHECK-NEXT: %13 = add i64 %12, %9
+; CHECK-NEXT: store volatile i64 %13, i64* @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_cycles"
 
 ; Bumping up number of cycles in g
-; CHECK:      %10 = load volatile i64, i64* @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_cycles"
-; CHECK-NEXT: %11 = add i64 %10, %7
-; CHECK-NEXT: store volatile i64 %11, i64* @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_cycles"
+; CHECK:      %12 = load volatile i64, i64* @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_cycles"
+; CHECK-NEXT: %13 = add i64 %12, %9
+; CHECK-NEXT: store volatile i64 %13, i64* @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_cycles"

test/Isl/CodeGen/perf_monitoring_trip_counts_per_scop.ll

return:
   ret void
 }
 
 ; Declaration of globals - Check for cycles declaration.
 ; CHECK: @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_trip_count" = weak thread_local(initialexec) constant i64 0
 ; CHECK: @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_trip_count" = weak thread_local(initialexec) constant i64 0
 
 ; Bumping up number of cycles in f
-; CHECK:        %12 = load volatile i64, i64* @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_trip_count"
-; CHECK-NEXT:   %13 = add i64 %12, 1
-; CHECK-NEXT:   store volatile i64 %13, i64* @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_trip_count"
+; CHECK:        %14 = load volatile i64, i64* @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_trip_count"
+; CHECK-NEXT:   %15 = add i64 %14, 1
+; CHECK-NEXT:   store volatile i64 %15, i64* @"__polly_perf_in_f_from__%next__to__%polly.merge_new_and_old_trip_count"
 
 ; Bumping up number of cycles in g
-; CHECK:       %12 = load volatile i64, i64* @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_trip_count"
-; CHECK-NEXT:  %13 = add i64 %12, 1
-; CHECK-NEXT:  store volatile i64 %13, i64* @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_trip_count"
+; CHECK:       %14 = load volatile i64, i64* @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_trip_count"
+; CHECK-NEXT:  %15 = add i64 %14, 1
+; CHECK-NEXT:  store volatile i64 %15, i64* @"__polly_perf_in_g_from__%next__to__%polly.merge_new_and_old_trip_count"