[llvm][CodeGen] Fixed a bug in stall cycle calculation for window scheduler (llvm#99451)

Fixed a bug in stall cycle calculation.
When a register defined by an instruction in the current iteration is
used by an instruction in the next iteration, we have modified the
number of stall cycle that need to be inserted.

Author: kaiyan96

llvm/lib/CodeGen/WindowScheduler.cpp

@@ -488,15 +488,16 @@ int WindowScheduler::calculateMaxCycle(ScheduleDAGInstrs &DAG,
 // ========================================
 int WindowScheduler::calculateStallCycle(unsigned Offset, int MaxCycle) {
   int MaxStallCycle = 0;
+  int CurrentII = MaxCycle + 1;
   auto Range = getScheduleRange(Offset, SchedInstrNum);
   for (auto &MI : Range) {
     auto *SU = TripleDAG->getSUnit(&MI);
     int DefCycle = getOriCycle(&MI);
     for (auto &Succ : SU->Succs) {
       if (Succ.isWeak() || Succ.getSUnit() == &TripleDAG->ExitSU)
         continue;
-      // If the expected cycle does not exceed MaxCycle, no check is needed.
-      if (DefCycle + (int)Succ.getLatency() <= MaxCycle)
+      // If the expected cycle does not exceed CurrentII, no check is needed.
+      if (DefCycle + (int)Succ.getLatency() <= CurrentII)
         continue;
       // If the cycle of the scheduled MI A is less than that of the scheduled
       // MI B, the scheduling will fail because the lifetime of the
@@ -506,7 +507,7 @@ int WindowScheduler::calculateStallCycle(unsigned Offset, int MaxCycle) {
       if (DefCycle < UseCycle)
         return WindowIILimit;
       // Get the stall cycle introduced by the register between two trips.
-      int StallCycle = DefCycle + (int)Succ.getLatency() - MaxCycle - UseCycle;
+      int StallCycle = DefCycle + (int)Succ.getLatency() - CurrentII - UseCycle;
       MaxStallCycle = std::max(MaxStallCycle, StallCycle);
     }
   }

llvm/test/CodeGen/Hexagon/swp-ws-stall-cycle.mir

@@ -0,0 +1,59 @@
+# REQUIRES: asserts
+# RUN: llc --march=hexagon %s -run-pass=pipeliner -debug-only=pipeliner \
+# RUN: -window-sched=force -filetype=null -verify-machineinstrs \
+# RUN: -window-region-limit=1 -window-search-ratio=100 -window-diff-limit=0 \
+# RUN: 2>&1 | FileCheck %s
+
+# CHECK-LABEL: Start analyzing II
+# CHECK: MaxStallCycle is 0
+# CHECK-LABEL: Start analyzing II
+# CHECK: MaxStallCycle is 0
+# CHECK-LABEL: Start analyzing II
+# CHECK: MaxStallCycle is 0
+
+---
+name:            test_window_stall_cycle
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    successors: %bb.3(0x40000000), %bb.1(0x40000000)
+    liveins: $r0, $r1
+  
+    %0:intregs = COPY $r1
+    %1:intregs = COPY $r0
+    %2:intregs = nsw A2_add %0, %1
+    %3:intregs = S2_lsr_i_r_acc %2, %2, 31
+    %4:intregs = S2_asr_i_r killed %3, 1
+    %5:predregs = C2_cmpgt %1, %4
+    %6:intregs = A2_tfrsi 0
+    J2_jumpt killed %5, %bb.3, implicit-def dead $pc
+    J2_jump %bb.1, implicit-def dead $pc
+  
+  bb.1:
+    successors: %bb.2(0x80000000)
+  
+    %7:intregs = A2_addi %4, 2
+    %8:intregs = A2_tfrsi 0
+    %9:intregs = A2_sub %4, %1
+    %10:intregs = A2_addi %9, 1
+    %11:intregs = COPY %10
+    J2_loop0r %bb.2, %11, implicit-def $lc0, implicit-def $sa0, implicit-def $usr
+  
+  bb.2 (machine-block-address-taken):
+    successors: %bb.3(0x04000000), %bb.2(0x7c000000)
+  
+    %12:intregs = PHI %7, %bb.1, %13, %bb.2
+    %14:intregs = PHI %8, %bb.1, %15, %bb.2
+    %16:intregs = PHI %8, %bb.1, %17, %bb.2
+    %18:intregs, %13:intregs = L2_loadri_pi %12, -4
+    %17:intregs = nsw A2_add killed %18, %16
+    %15:intregs = A2_max %17, %14
+    ENDLOOP0 %bb.2, implicit-def $pc, implicit-def $lc0, implicit $sa0, implicit $lc0
+    J2_jump %bb.3, implicit-def dead $pc
+  
+  bb.3:
+    %19:intregs = PHI %6, %bb.0, %15, %bb.2
+    $r0 = COPY %19
+    PS_jmpret $r31, implicit-def dead $pc, implicit $r0
+
+...