[RISCV] Move VMV0 elimination past machine SSA opts

This is the follow up to #125026 that keeps mask operands in virtual register form for as long as possible throughout the backend.

The diffs in this patch are from MachineCSE/MachineSink/RISCVVLOptimizer kicking in.

The invariant that the mask COPY never has a subreg no longer holds after MachineCSE (it coalesces some copies), so it needed to be relaxed.

Author: lukel97

llvm/lib/Target/RISCV/RISCVTargetMachine.cpp

@@ -588,8 +588,6 @@ void RISCVPassConfig::addPreEmitPass2() {
 
 void RISCVPassConfig::addMachineSSAOptimization() {
   addPass(createRISCVVectorPeepholePass());
-  // TODO: Move this to pre regalloc
-  addPass(createRISCVVMV0EliminationPass());
 
   TargetPassConfig::addMachineSSAOptimization();
 
@@ -602,10 +600,6 @@ void RISCVPassConfig::addMachineSSAOptimization() {
 }
 
 void RISCVPassConfig::addPreRegAlloc() {
-  // TODO: Move this as late as possible before regalloc
-  if (TM->getOptLevel() == CodeGenOptLevel::None)
-    addPass(createRISCVVMV0EliminationPass());
-
   addPass(createRISCVPreRAExpandPseudoPass());
   if (TM->getOptLevel() != CodeGenOptLevel::None) {
     addPass(createRISCVMergeBaseOffsetOptPass());
@@ -619,6 +613,8 @@ void RISCVPassConfig::addPreRegAlloc() {
 
   if (TM->getOptLevel() != CodeGenOptLevel::None && EnableMachinePipeliner)
     addPass(&MachinePipelinerID);
+
+  addPass(createRISCVVMV0EliminationPass());
 }
 
 void RISCVPassConfig::addFastRegAlloc() {

llvm/lib/Target/RISCV/RISCVVMV0Elimination.cpp

@@ -131,10 +131,9 @@ bool RISCVVMV0Elimination::runOnMachineFunction(MachineFunction &MF) {
 
           // Peek through a single copy to match what isel does.
           if (MachineInstr *SrcMI = MRI.getVRegDef(Src);
-              SrcMI->isCopy() && SrcMI->getOperand(1).getReg().isVirtual()) {
-            assert(SrcMI->getOperand(1).getSubReg() == RISCV::NoSubRegister);
+              SrcMI->isCopy() && SrcMI->getOperand(1).getReg().isVirtual() &&
+              SrcMI->getOperand(1).getSubReg() == RISCV::NoSubRegister)
             Src = SrcMI->getOperand(1).getReg();
-          }
 
           BuildMI(MBB, MI, MI.getDebugLoc(), TII->get(RISCV::COPY), RISCV::V0)
               .addReg(Src);

llvm/test/CodeGen/RISCV/O0-pipeline.ll

@@ -39,11 +39,11 @@
 ; CHECK-NEXT:       RISC-V DAG->DAG Pattern Instruction Selection
 ; CHECK-NEXT:       Finalize ISel and expand pseudo-instructions
 ; CHECK-NEXT:       Local Stack Slot Allocation
-; CHECK-NEXT:       RISC-V VMV0 Elimination
 ; CHECK-NEXT:       RISC-V Pre-RA pseudo instruction expansion pass
 ; CHECK-NEXT:       RISC-V Insert Read/Write CSR Pass
 ; CHECK-NEXT:       RISC-V Insert Write VXRM Pass
 ; CHECK-NEXT:       RISC-V Landing Pad Setup
+; CHECK-NEXT:       RISC-V VMV0 Elimination
 ; CHECK-NEXT:       Init Undef Pass
 ; CHECK-NEXT:       Eliminate PHI nodes for register allocation
 ; CHECK-NEXT:       Two-Address instruction pass

llvm/test/CodeGen/RISCV/O3-pipeline.ll

@@ -97,7 +97,6 @@
 ; CHECK-NEXT:       RISC-V DAG->DAG Pattern Instruction Selection
 ; CHECK-NEXT:       Finalize ISel and expand pseudo-instructions
 ; CHECK-NEXT:       RISC-V Vector Peephole Optimization
-; CHECK-NEXT:       RISC-V VMV0 Elimination
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Early Tail Duplication
 ; CHECK-NEXT:       Optimize machine instruction PHIs
@@ -128,6 +127,7 @@
 ; CHECK-NEXT:       RISC-V Insert Read/Write CSR Pass
 ; CHECK-NEXT:       RISC-V Insert Write VXRM Pass
 ; CHECK-NEXT:       RISC-V Landing Pad Setup
+; CHECK-NEXT:       RISC-V VMV0 Elimination
 ; CHECK-NEXT:       Detect Dead Lanes
 ; CHECK-NEXT:       Init Undef Pass
 ; CHECK-NEXT:       Process Implicit Definitions

llvm/test/CodeGen/RISCV/rvv/ceil-vp.ll

@@ -1515,40 +1515,36 @@ define <vscale x 16 x double> @vp_ceil_vv_nxv16f64(<vscale x 16 x double> %va, <
 ; CHECK-NEXT:    vmv1r.v v0, v6
 ; CHECK-NEXT:    vsetvli zero, a2, e64, m8, ta, ma
 ; CHECK-NEXT:    vfabs.v v24, v16, v0.t
+; CHECK-NEXT:    addi a2, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    vl8r.v v24, (a2) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vmflt.vf v6, v24, fa5, v0.t
 ; CHECK-NEXT:    fsrmi a2, 3
 ; CHECK-NEXT:    vmv1r.v v0, v6
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
 ; CHECK-NEXT:    vfcvt.x.f.v v24, v16, v0.t
-; CHECK-NEXT:    addi a3, sp, 16
-; CHECK-NEXT:    vs8r.v v24, (a3) # Unknown-size Folded Spill
 ; CHECK-NEXT:    fsrm a2
-; CHECK-NEXT:    addi a2, sp, 16
-; CHECK-NEXT:    vl8r.v v24, (a2) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
 ; CHECK-NEXT:    vfsgnj.vv v16, v24, v16, v0.t
-; CHECK-NEXT:    vs8r.v v16, (a2) # Unknown-size Folded Spill
 ; CHECK-NEXT:    bltu a0, a1, .LBB44_2
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    mv a0, a1
 ; CHECK-NEXT:  .LBB44_2:
 ; CHECK-NEXT:    vmv1r.v v0, v7
 ; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT:    vfabs.v v16, v8, v0.t
+; CHECK-NEXT:    vfabs.v v24, v8, v0.t
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vmflt.vf v7, v16, fa5, v0.t
+; CHECK-NEXT:    vmflt.vf v7, v24, fa5, v0.t
 ; CHECK-NEXT:    fsrmi a0, 3
 ; CHECK-NEXT:    vmv1r.v v0, v7
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vfcvt.x.f.v v16, v8, v0.t
+; CHECK-NEXT:    vfcvt.x.f.v v24, v8, v0.t
 ; CHECK-NEXT:    fsrm a0
-; CHECK-NEXT:    vfcvt.f.x.v v16, v16, v0.t
+; CHECK-NEXT:    vfcvt.f.x.v v24, v24, v0.t
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT:    vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vl8r.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vfsgnj.vv v8, v24, v8, v0.t
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    add sp, sp, a0