[AMDGPU][NFC] dump Waitcnt using an ostream operator (#171251)

Author: ssahasra

llvm/include/llvm/ADT/StringExtras.h

@@ -541,6 +541,7 @@ class ListSeparator {
     }
     return Separator;
   }
+  bool unused() { return First; }
 };
 
 /// A forward iterator over partitions of string over a separator.

llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp

@@ -1451,9 +1451,9 @@ bool WaitcntGeneratorPreGFX12::applyPreexistingWaitcnt(
     } else if (Opcode == AMDGPU::S_WAITCNT_lds_direct) {
       assert(ST->hasVMemToLDSLoad());
       LLVM_DEBUG(dbgs() << "Processing S_WAITCNT_lds_direct: " << II
-                        << "Before: " << Wait.LoadCnt << '\n';);
+                        << "Before: " << Wait;);
       ScoreBrackets.determineWait(LOAD_CNT, FIRST_LDS_VGPR, Wait);
-      LLVM_DEBUG(dbgs() << "After: " << Wait.LoadCnt << '\n';);
+      LLVM_DEBUG(dbgs() << "After: " << Wait;);
 
       // It is possible (but unlikely) that this is the only wait instruction,
       // in which case, we exit this loop without a WaitcntInstr to consume

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

@@ -1712,6 +1712,30 @@ bool hasValueInRangeLikeMetadata(const MDNode &MD, int64_t Val) {
   return false;
 }
 
+raw_ostream &operator<<(raw_ostream &OS, const AMDGPU::Waitcnt &Wait) {
+  ListSeparator LS;
+  if (Wait.LoadCnt != ~0u)
+    OS << LS << "LoadCnt: " << Wait.LoadCnt;
+  if (Wait.ExpCnt != ~0u)
+    OS << LS << "ExpCnt: " << Wait.ExpCnt;
+  if (Wait.DsCnt != ~0u)
+    OS << LS << "DsCnt: " << Wait.DsCnt;
+  if (Wait.StoreCnt != ~0u)
+    OS << LS << "StoreCnt: " << Wait.StoreCnt;
+  if (Wait.SampleCnt != ~0u)
+    OS << LS << "SampleCnt: " << Wait.SampleCnt;
+  if (Wait.BvhCnt != ~0u)
+    OS << LS << "BvhCnt: " << Wait.BvhCnt;
+  if (Wait.KmCnt != ~0u)
+    OS << LS << "KmCnt: " << Wait.KmCnt;
+  if (Wait.XCnt != ~0u)
+    OS << LS << "XCnt: " << Wait.XCnt;
+  if (LS.unused())
+    OS << "none";
+  OS << '\n';
+  return OS;
+}
+
 unsigned getVmcntBitMask(const IsaVersion &Version) {
   return (1 << (getVmcntBitWidthLo(Version.Major) +
                 getVmcntBitWidthHi(Version.Major))) -

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h

@@ -1119,6 +1119,8 @@ struct Waitcnt {
         std::min(SampleCnt, Other.SampleCnt), std::min(BvhCnt, Other.BvhCnt),
         std::min(KmCnt, Other.KmCnt), std::min(XCnt, Other.XCnt));
   }
+
+  friend raw_ostream &operator<<(raw_ostream &OS, const AMDGPU::Waitcnt &Wait);
 };
 
 // The following methods are only meaningful on targets that support