[llvm] [AMDGPU] Support bottom-up postRA scheduing. (PR #135295)

[Matt Arsenault via llvm-commits]

================
@@ -423,7 +450,41 @@ void GCNHazardRecognizer::AdvanceCycle() {
 }
 
 void GCNHazardRecognizer::RecedeCycle() {
-  llvm_unreachable("hazard recognizer does not support bottom-up scheduling.");
+  // If no instruction was issued this cycle, pop the oldest placeholder.
+  if (!CurrCycleInstr) {
+    if (!EmittedInstrs.empty())
+      EmittedInstrs.pop_back();
+    return;
+  }
+
+  // If this is a bundle header, handle the entire bundle here.
+  if (CurrCycleInstr->isBundle()) {
+    processBundleBottomUp();
+    return;
+  }
+
+  unsigned NumWaitStates = TII.getNumWaitStates(*CurrCycleInstr);
+  if (!NumWaitStates) {
+    CurrCycleInstr = nullptr;
+    return;
+  }
+
+  // Add current instruction to the emitted list.
+  EmittedInstrs.push_back(CurrCycleInstr);
+
+  // Model remaining wait states by removing older placeholders.
+  for (unsigned I = 1, E = std::min(NumWaitStates, getMaxLookAhead()); I < E;
+       ++I) {
+    if (!EmittedInstrs.empty())
+      EmittedInstrs.pop_back();
+  }
----------------
arsenm wrote:

Probably needs more tests stressing the maximum lookahead 

https://github.com/llvm/llvm-project/pull/135295