[llvm] [AMDGPU] Introduce Next-Use Analysis for SSA-based Register Allocation (PR #156079)

[via llvm-commits]

================
@@ -0,0 +1,482 @@
+//===-- AMDGPUNextUseAnalysis.cpp - Next Use Analysis ---------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+/// \file
+/// This file implements the Next Use Analysis for AMDGPU targets.
+//
+//===----------------------------------------------------------------------===//
+
+#include "AMDGPUNextUseAnalysis.h"
+#include "AMDGPU.h"
+
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/PostOrderIterator.h"
+#include "llvm/ADT/iterator_range.h"
+#include "llvm/CodeGen/MachineBasicBlock.h"
+#include "llvm/CodeGen/MachineDominators.h"
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineFunctionAnalysis.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/CodeGen/SlotIndexes.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/MC/LaneBitmask.h"
+#include "llvm/Passes/PassBuilder.h"
+#include "llvm/Passes/PassPlugin.h"
+#include "llvm/Support/Timer.h"
+
+#define DEBUG_TYPE "amdgpu-next-use"
+
+using namespace llvm;
+
+// Command-line option to enable timing instrumentation
+static cl::opt<bool>
+    EnableTimers("amdgpu-next-use-analysis-timers",
+                 cl::desc("Enable timing for Next Use Analysis"),
+                 cl::init(false), cl::Hidden);
+
+// Static timers for performance tracking across all analysis runs
+static llvm::TimerGroup TG("amdgpu-next-use", "AMDGPU Next Use Analysis");
+static llvm::Timer AnalyzeTimer("analyze", "Time spent in analyze()", TG);
+static llvm::Timer GetDistanceTimer("getNextUseDistance",
+                                    "Time spent in getNextUseDistance()", TG);
+
+// Three-tier ranking system for spiller decisions
+unsigned NextUseResult::materializeForRank(int64_t Stored,
+                                           unsigned SnapshotOffset) const {
+  int64_t Mat64 = materialize(Stored, SnapshotOffset);
+
+  // Tier 1: Finite distances (0 to LoopTag-1) → return as-is
+  // Tier 2: Loop-exit distances (LoopTag to DeadTag-1) → map to 60000-64999
+  // Tier 3: Dead registers (DeadTag+) → return DeadDistance (65535)
+  if (Mat64 >= DeadTag)
+    return DeadDistance;
+
+  if (Mat64 >= LoopTag) {
+    // Tier 2: Loop-exit distances get mapped to high range [60000, 64999]
+    int64_t LoopRemainder = Mat64 - LoopTag;
+    // Clamp the remainder to fit in available range (5000 values)
+    unsigned ClampedRemainder = static_cast<unsigned>(
+        std::min(LoopRemainder, static_cast<int64_t>(4999)));
----------------
ruiling wrote:

all these magic numbers need to be constexpr with meaningful names and with comments how they would work.

https://github.com/llvm/llvm-project/pull/156079