From 038b5537433ef9e91c0899bdc93c16c740fce0c8 Mon Sep 17 00:00:00 2001
From: Sameer Sahasrabuddhe <sameer.sahasrabuddhe@amd.com>
Date: Tue, 9 Dec 2025 07:54:52 +0530
Subject: [PATCH 1/2] [AMDGPU][NFC] dump Waitcnt using an ostream operator

---
 llvm/include/llvm/ADT/StringExtras.h          |  1 +
 .../Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp    | 24 +++++++++++++++++++
 llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h |  2 ++
 3 files changed, 27 insertions(+)

diff --git a/llvm/include/llvm/ADT/StringExtras.h b/llvm/include/llvm/ADT/StringExtras.h
index 2440e7678a831..abdf5337d68b2 100644
--- a/llvm/include/llvm/ADT/StringExtras.h
+++ b/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.
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
index c6e061f368aef..e2cec29ae3611 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
+++ b/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))) -
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
index 3a352006e006c..75db58a292c13 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
+++ b/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

From 854c902b87e5eb7ecec81c562b97dbd965ec0d07 Mon Sep 17 00:00:00 2001
From: Sameer Sahasrabuddhe <sameer.sahasrabuddhe@amd.com>
Date: Tue, 9 Dec 2025 19:59:34 +0530
Subject: [PATCH 2/2] clean up whitespace; introduce an actual use of the
 operator

---
 llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp    |  4 ++--
 .../lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp | 18 +++++++++---------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index 146f3604d9f8f..3d6fc309c7cf4 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/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
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
index e2cec29ae3611..78d2370f5bfa8 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
@@ -1715,23 +1715,23 @@ bool hasValueInRangeLikeMetadata(const MDNode &MD, int64_t Val) {
 raw_ostream &operator<<(raw_ostream &OS, const AMDGPU::Waitcnt &Wait) {
   ListSeparator LS;
   if (Wait.LoadCnt != ~0u)
-    OS << LS << " LoadCnt: " << Wait.LoadCnt;
+    OS << LS << "LoadCnt: " << Wait.LoadCnt;
   if (Wait.ExpCnt != ~0u)
-    OS << LS << " ExpCnt: " << Wait.ExpCnt;
+    OS << LS << "ExpCnt: " << Wait.ExpCnt;
   if (Wait.DsCnt != ~0u)
-    OS << LS << " DsCnt: " << Wait.DsCnt;
+    OS << LS << "DsCnt: " << Wait.DsCnt;
   if (Wait.StoreCnt != ~0u)
-    OS << LS << " StoreCnt: " << Wait.StoreCnt;
+    OS << LS << "StoreCnt: " << Wait.StoreCnt;
   if (Wait.SampleCnt != ~0u)
-    OS << LS << " SampleCnt: " << Wait.SampleCnt;
+    OS << LS << "SampleCnt: " << Wait.SampleCnt;
   if (Wait.BvhCnt != ~0u)
-    OS << LS << " BvhCnt: " << Wait.BvhCnt;
+    OS << LS << "BvhCnt: " << Wait.BvhCnt;
   if (Wait.KmCnt != ~0u)
-    OS << LS << " KmCnt: " << Wait.KmCnt;
+    OS << LS << "KmCnt: " << Wait.KmCnt;
   if (Wait.XCnt != ~0u)
-    OS << LS << " XCnt: " << Wait.XCnt;
+    OS << LS << "XCnt: " << Wait.XCnt;
   if (LS.unused())
-    OS << " none";
+    OS << "none";
   OS << '\n';
   return OS;
 }