[AMDGPU] added writelane intrinsic

Summary:
For use by LLPC SPV_AMD_shader_ballot extension.

The v_writelane instruction was already implemented for use by SGPR
spilling, but I had to add an extra dummy operand tied to the
destination, to represent that all lanes except the selected one keep
the old value of the destination register.

.ll test changes were due to schedule changes caused by that new
operand.

Differential Revision: https://reviews.llvm.org/D42838

llvm-svn: 326353

3 files changed, 47 insertions, 7 deletions

diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 654b96f792b..86c5f623dd0 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -2711,8 +2711,9 @@ bool SIInstrInfo::verifyInstruction(const MachineInstr &MI,
     }
   }
 
-  // Verify VOP*
-  if (isVOP1(MI) || isVOP2(MI) || isVOP3(MI) || isVOPC(MI) || isSDWA(MI)) {
+  // Verify VOP*. Ignore multiple sgpr operands on writelane.
+  if (Desc.getOpcode() != AMDGPU::V_WRITELANE_B32
+      && (isVOP1(MI) || isVOP2(MI) || isVOP3(MI) || isVOPC(MI) || isSDWA(MI))) {
     // Only look at the true operands. Only a real operand can use the constant
     // bus, and we don't want to check pseudo-operands like the source modifier
     // flags.
@@ -3147,6 +3148,29 @@ void SIInstrInfo::legalizeOperandsVOP2(MachineRegisterInfo &MRI,
       legalizeOpWithMove(MI, Src0Idx);
   }
 
+  // Special case: V_WRITELANE_B32 accepts only immediate or SGPR operands for
+  // both the value to write (src0) and lane select (src1).  Fix up non-SGPR
+  // src0/src1 with V_READFIRSTLANE.
+  if (Opc == AMDGPU::V_WRITELANE_B32) {
+    int Src0Idx = AMDGPU::getNamedOperandIdx(Opc, AMDGPU::OpName::src0);
+    MachineOperand &Src0 = MI.getOperand(Src0Idx);
+    const DebugLoc &DL = MI.getDebugLoc();
+    if (Src0.isReg() && RI.isVGPR(MRI, Src0.getReg())) {
+      unsigned Reg = MRI.createVirtualRegister(&AMDGPU::SReg_32_XM0RegClass);
+      BuildMI(*MI.getParent(), MI, DL, get(AMDGPU::V_READFIRSTLANE_B32), Reg)
+          .add(Src0);
+      Src0.ChangeToRegister(Reg, false);
+    }
+    if (Src1.isReg() && RI.isVGPR(MRI, Src1.getReg())) {
+      unsigned Reg = MRI.createVirtualRegister(&AMDGPU::SReg_32_XM0RegClass);
+      const DebugLoc &DL = MI.getDebugLoc();
+      BuildMI(*MI.getParent(), MI, DL, get(AMDGPU::V_READFIRSTLANE_B32), Reg)
+          .add(Src1);
+      Src1.ChangeToRegister(Reg, false);
+    }
+    return;
+  }
+
   // VOP2 src0 instructions support all operand types, so we don't need to check
   // their legality. If src1 is already legal, we don't need to do anything.
   if (isLegalRegOperand(MRI, InstrDesc.OpInfo[Src1Idx], Src1))
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index 21658ece2f2..0ade120487f 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -636,6 +636,7 @@ bool SIRegisterInfo::spillSGPR(MachineBasicBlock::iterator MI,
   MachineBasicBlock *MBB = MI->getParent();
   MachineFunction *MF = MBB->getParent();
   SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
+  DenseSet<unsigned> SGPRSpillVGPRDefinedSet;
 
   ArrayRef<SIMachineFunctionInfo::SpilledReg> VGPRSpills
     = MFI->getSGPRToVGPRSpills(Index);
@@ -732,11 +733,21 @@ bool SIRegisterInfo::spillSGPR(MachineBasicBlock::iterator MI,
     if (SpillToVGPR) {
       SIMachineFunctionInfo::SpilledReg Spill = VGPRSpills[i];
 
+      // During SGPR spilling to VGPR, determine if the VGPR is defined. The
+      // only circumstance in which we say it is undefined is when it is the
+      // first spill to this VGPR in the first basic block.
+      bool VGPRDefined = true;
+      if (MBB == &MF->front())
+        VGPRDefined = !SGPRSpillVGPRDefinedSet.insert(Spill.VGPR).second;
+
+      // Mark the "old value of vgpr" input undef only if this is the first sgpr
+      // spill to this specific vgpr in the first basic block.
       BuildMI(*MBB, MI, DL,
               TII->getMCOpcodeFromPseudo(AMDGPU::V_WRITELANE_B32),
               Spill.VGPR)
         .addReg(SubReg, getKillRegState(IsKill))
-        .addImm(Spill.Lane);
+        .addImm(Spill.Lane)
+        .addReg(Spill.VGPR, VGPRDefined ? 0 : RegState::Undef);
 
       // FIXME: Since this spills to another register instead of an actual
       // frame index, we should delete the frame index when all references to
diff --git a/llvm/lib/Target/AMDGPU/VOP2Instructions.td b/llvm/lib/Target/AMDGPU/VOP2Instructions.td
index 8c49fd825e3..40bc0f06e60 100644
--- a/llvm/lib/Target/AMDGPU/VOP2Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP2Instructions.td
@@ -323,15 +323,17 @@ def VOP_READLANE : VOPProfile<[i32, i32, i32]> {
   let HasSDWA9 = 0;
 }
 
-def VOP_WRITELANE : VOPProfile<[i32, i32, i32]> {
+def VOP_WRITELANE : VOPProfile<[i32, i32, i32, i32]> {
   let Outs32 = (outs VGPR_32:$vdst);
   let Outs64 = Outs32;
-  let Ins32 = (ins SCSrc_b32:$src0, SCSrc_b32:$src1);
+  let Ins32 = (ins SCSrc_b32:$src0, SCSrc_b32:$src1, VGPR_32:$vdst_in);
   let Ins64 = Ins32;
   let Asm32 = " $vdst, $src0, $src1";
   let Asm64 = Asm32;
   let HasExt = 0;
   let HasSDWA9 = 0;
+  let HasSrc2 = 0;
+  let HasSrc2Mods = 0;
 }
 
 //===----------------------------------------------------------------------===//
@@ -399,7 +401,10 @@ let isConvergent = 1, Uses = []<Register> in {
 def V_READLANE_B32 : VOP2_Pseudo<"v_readlane_b32", VOP_READLANE,
   [(set i32:$vdst, (int_amdgcn_readlane i32:$src0, i32:$src1))], "">;
 
-def V_WRITELANE_B32 : VOP2_Pseudo<"v_writelane_b32", VOP_WRITELANE, [], "">;
+let Constraints = "$vdst = $vdst_in", DisableEncoding="$vdst_in" in {
+def V_WRITELANE_B32 : VOP2_Pseudo<"v_writelane_b32", VOP_WRITELANE,
+  [(set i32:$vdst, (int_amdgcn_writelane i32:$src0, i32:$src1, i32:$vdst_in))], "">;
+} // End $vdst = $vdst_in, DisableEncoding $vdst_in
 } // End isConvergent = 1
 
 defm V_BFM_B32 : VOP2Inst <"v_bfm_b32", VOP_NO_EXT<VOP_I32_I32_I32>>;
@@ -640,7 +645,7 @@ defm V_SUBBREV_U32        : VOP2be_Real_e32e64_si <0x2a>;
 
 defm V_READLANE_B32       : VOP2_Real_si <0x01>;
 
-let InOperandList = (ins SSrc_b32:$src0, SCSrc_b32:$src1) in {
+let InOperandList = (ins SSrc_b32:$src0, SCSrc_b32:$src1, VSrc_b32:$vdst_in) in {
 defm V_WRITELANE_B32      : VOP2_Real_si <0x02>;
 }