[llvm] c3e07a0 - [AMDGPU] SIInsertSkips: Refactor early exit block creation

[Carl Ritson via llvm-commits]

Author: Carl Ritson
Date: 2020-10-06T09:44:55+09:00
New Revision: c3e07a0018ec74216d662e0596584d2c846a1063

URL: https://github.com/llvm/llvm-project/commit/c3e07a0018ec74216d662e0596584d2c846a1063
DIFF: https://github.com/llvm/llvm-project/commit/c3e07a0018ec74216d662e0596584d2c846a1063.diff

LOG: [AMDGPU] SIInsertSkips: Refactor early exit block creation

Refactor exit block creation to a single call ensureEarlyExitBlock.
Add support for generating an early exit block which clears the
exec mask, but only add this instruction when required.
These changes are to facilitate adding more forms of early
termination for PS shaders in the near future.

Reviewed By: nhaehnle

Differential Revision: https://reviews.llvm.org/D88775

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/SIInsertSkips.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp b/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
index 510d7fd8b8d8..5bb5165bae52 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
@@ -58,12 +58,13 @@ class SIInsertSkips : public MachineFunctionPass {
   MachineDominatorTree *MDT = nullptr;
 
   MachineBasicBlock *EarlyExitBlock = nullptr;
+  bool EarlyExitClearsExec = false;
 
   bool shouldSkip(const MachineBasicBlock &From,
                   const MachineBasicBlock &To) const;
 
   bool dominatesAllReachable(MachineBasicBlock &MBB);
-  void createEarlyExitBlock(MachineBasicBlock &MBB);
+  void ensureEarlyExitBlock(MachineBasicBlock &MBB, bool ClearExec);
   void skipIfDead(MachineBasicBlock &MBB, MachineBasicBlock::iterator I,
                   DebugLoc DL);
 
@@ -180,15 +181,27 @@ static void generatePsEndPgm(MachineBasicBlock &MBB,
   BuildMI(MBB, I, DL, TII->get(AMDGPU::S_ENDPGM)).addImm(0);
 }
 
-void SIInsertSkips::createEarlyExitBlock(MachineBasicBlock &MBB) {
+void SIInsertSkips::ensureEarlyExitBlock(MachineBasicBlock &MBB,
+                                         bool ClearExec) {
   MachineFunction *MF = MBB.getParent();
   DebugLoc DL;
 
-  assert(!EarlyExitBlock);
-  EarlyExitBlock = MF->CreateMachineBasicBlock();
-  MF->insert(MF->end(), EarlyExitBlock);
+  if (!EarlyExitBlock) {
+    EarlyExitBlock = MF->CreateMachineBasicBlock();
+    MF->insert(MF->end(), EarlyExitBlock);
+    generatePsEndPgm(*EarlyExitBlock, EarlyExitBlock->end(), DL, TII);
+    EarlyExitClearsExec = false;
+  }
 
-  generatePsEndPgm(*EarlyExitBlock, EarlyExitBlock->end(), DL, TII);
+  if (ClearExec && !EarlyExitClearsExec) {
+    const GCNSubtarget &ST = MF->getSubtarget<GCNSubtarget>();
+    unsigned Mov = ST.isWave32() ? AMDGPU::S_MOV_B32 : AMDGPU::S_MOV_B64;
+    Register Exec = ST.isWave32() ? AMDGPU::EXEC_LO : AMDGPU::EXEC;
+    auto ExitI = EarlyExitBlock->getFirstNonPHI();
+    assert(ExitI->getOpcode() == AMDGPU::EXP_DONE);
+    BuildMI(*EarlyExitBlock, ExitI, DL, TII->get(Mov), Exec).addImm(0);
+    EarlyExitClearsExec = true;
+  }
 }
 
 static void splitBlock(MachineBasicBlock &MBB, MachineInstr &MI,
@@ -233,11 +246,7 @@ void SIInsertSkips::skipIfDead(MachineBasicBlock &MBB,
   if (NoSuccessor) {
     generatePsEndPgm(MBB, I, DL, TII);
   } else {
-    if (!EarlyExitBlock) {
-      createEarlyExitBlock(MBB);
-      // Update next block pointer to reflect any new blocks
-      NextBBI = std::next(MBB.getIterator());
-    }
+    ensureEarlyExitBlock(MBB, false);
 
     MachineInstr *BranchMI =
         BuildMI(MBB, I, DL, TII->get(AMDGPU::S_CBRANCH_EXECZ))