AMDGPU: Don't count mask branch pseudo towards skip threshold

[rampitec]

LGTM

[arsenm]

r362761

lib/Target/AMDGPU/SIInsertSkips.cpp

 
 char SIInsertSkips::ID = 0;
 
 INITIALIZE_PASS(SIInsertSkips, DEBUG_TYPE,
                 "SI insert s_cbranch_execz instructions", false, false)
 
 char &llvm::SIInsertSkipsPassID = SIInsertSkips::ID;
 
-static bool opcodeEmitsNoInsts(unsigned Opc) {
-  switch (Opc) {
-  case TargetOpcode::IMPLICIT_DEF:
-  case TargetOpcode::KILL:
-  case TargetOpcode::BUNDLE:
-  case TargetOpcode::CFI_INSTRUCTION:
-  case TargetOpcode::EH_LABEL:
-  case TargetOpcode::GC_LABEL:
-  case TargetOpcode::DBG_VALUE:
+static bool opcodeEmitsNoInsts(const MachineInstr &MI) {
+  if (MI.isMetaInstruction())
+    return true;
+
+  // Handle target specific opcodes.
+  switch (MI.getOpcode()) {
+  case AMDGPU::SI_MASK_BRANCH:
     return true;
   default:
     return false;
   }
 }
 
 bool SIInsertSkips::shouldSkip(const MachineBasicBlock &From,
                                const MachineBasicBlock &To) const {
   unsigned NumInstr = 0;
   const MachineFunction *MF = From.getParent();
 
   for (MachineFunction::const_iterator MBBI(&From), ToI(&To), End = MF->end();
        MBBI != End && MBBI != ToI; ++MBBI) {
     const MachineBasicBlock &MBB = *MBBI;
 
     for (MachineBasicBlock::const_iterator I = MBB.begin(), E = MBB.end();
          NumInstr < SkipThreshold && I != E; ++I) {
-      if (opcodeEmitsNoInsts(I->getOpcode()))
+      if (opcodeEmitsNoInsts(*I))
         continue;
 
       // FIXME: Since this is required for correctness, this should be inserted
       // during SILowerControlFlow.
 
       // When a uniform loop is inside non-uniform control flow, the branch
       // leaving the loop might be an S_CBRANCH_VCCNZ, which is never taken
       // when EXEC = 0. We should skip the loop lest it becomes infinite.

test/CodeGen/AMDGPU/insert-skips-ignored-insts.mir

+# RUN: llc -mtriple=amdgcn-amd-amdhsa -run-pass si-insert-skips -amdgpu-skip-threshold=2 %s -o - | FileCheck %s
+
+---
+
+# CHECK-LABEL: name: no_count_mask_branch_pseudo
+# CHECK: $vgpr1 = V_MOV_B32_e32 7, implicit $exec
+# CHECK-NEXT: SI_MASK_BRANCH
+# CHECK-NOT: S_CBRANCH_EXECZ
+name: no_count_mask_branch_pseudo
+body: |
+  bb.0:
+    successors: %bb.1
+
+    $vgpr1 = V_MOV_B32_e32 7, implicit $exec
+    SI_MASK_BRANCH %bb.2, implicit $exec
+
+  bb.1:
+    successors: %bb.2
+    $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+    SI_MASK_BRANCH %bb.3, implicit $exec
+
+  bb.2:
+    $vgpr0 = V_MOV_B32_e32 1, implicit $exec
+
+  bb.3:
+    S_ENDPGM 0
+...
+
+---
+
+# CHECK-LABEL: name: no_count_dbg_value
+# CHECK: $vgpr1 = V_MOV_B32_e32 7, implicit $exec
+# CHECK-NEXT: SI_MASK_BRANCH
+# CHECK-NOT: S_CBRANCH_EXECZ
+name: no_count_dbg_value
+body: |
+  bb.0:
+    successors: %bb.1
+
+    $vgpr1 = V_MOV_B32_e32 7, implicit $exec
+    SI_MASK_BRANCH %bb.2, implicit $exec
+
+  bb.1:
+    successors: %bb.2
+    $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+    DBG_VALUE
+
+  bb.2:
+    $vgpr0 = V_MOV_B32_e32 1, implicit $exec
+
+  bb.3:
+    S_ENDPGM 0
+...
+