[AMDGPU] Adapt GCNRegBankReassign for 16 bit subregs

It allows it not to crash and analyze 16 bit subregs if those
appear in the instructions. At the same time it does not attempt
to reassign these. It still can correctly identify register
banks to let larger registers to be reassigned.

More work will be needed here when real instructions will use
these registers and more tests as well.

Differential Revision: https://reviews.llvm.org/D78772

diff --git a/llvm/lib/Target/AMDGPU/GCNRegBankReassign.cpp b/llvm/lib/Target/AMDGPU/GCNRegBankReassign.cpp
index b1c64ed..e4017be 100644 (file)
--- a/llvm/lib/Target/AMDGPU/GCNRegBankReassign.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNRegBankReassign.cpp
@@ -280,7 +280,9 @@ unsigned GCNRegBankReassign::getPhysRegBank(unsigned Reg) const {
 
   const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
   unsigned Size = TRI->getRegSizeInBits(*RC);
-  if (Size > 32)
+  if (Size == 16)
+    Reg = TRI->get32BitRegister(Reg);
+  else if (Size > 32)
     Reg = TRI->getSubReg(Reg, AMDGPU::sub0);
 
   if (TRI->hasVGPRs(RC)) {
@@ -306,9 +308,16 @@ uint32_t GCNRegBankReassign::getRegBankMask(unsigned Reg, unsigned SubReg,
   }
 
   const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg);
-  unsigned Size = TRI->getRegSizeInBits(*RC) / 32;
-  if (Size > 1)
-    Reg = TRI->getSubReg(Reg, AMDGPU::sub0);
+  unsigned Size = TRI->getRegSizeInBits(*RC);
+
+  if (Size == 16) {
+    Reg = TRI->get32BitRegister(Reg);
+    Size = 1;
+  } else {
+    Size /= 32;
+    if (Size > 1)
+      Reg = TRI->getSubReg(Reg, AMDGPU::sub0);
+  }
 
   if (TRI->hasVGPRs(RC)) {
     // VGPRs have 4 banks assigned in a round-robin fashion.
@@ -440,10 +449,19 @@ bool GCNRegBankReassign::isReassignable(unsigned Reg) const {
   }
 
   const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(PhysReg);
+  unsigned Size = TRI->getRegSizeInBits(*RC);
+
+  // TODO: Support 16 bit registers. Those needs to be moved with their
+  //       parent VGPR_32 and potentially a sibling 16 bit sub-register.
+  if (Size < 32)
+    return false;
+
   if (TRI->hasVGPRs(RC))
     return true;
 
-  unsigned Size = TRI->getRegSizeInBits(*RC);
+  if (Size == 16)
+    return AMDGPU::SGPR_LO16RegClass.contains(PhysReg);
+
   if (Size > 32)
     PhysReg = TRI->getSubReg(PhysReg, AMDGPU::sub0);
 

diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 4e8495a..c1ce858 100644 (file)
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -694,18 +694,8 @@ void SIInstrInfo::copyPhysReg(MachineBasicBlock &MBB,
     bool SrcLow = AMDGPU::VGPR_LO16RegClass.contains(SrcReg) ||
                   AMDGPU::SReg_LO16RegClass.contains(SrcReg) ||
                   AMDGPU::AGPR_LO16RegClass.contains(SrcReg);
-    const TargetRegisterClass *DstRC = IsSGPRDst ? &AMDGPU::SGPR_32RegClass
-                                     : IsAGPRDst ? &AMDGPU::AGPR_32RegClass
-                                                 : &AMDGPU::VGPR_32RegClass;
-    const TargetRegisterClass *SrcRC = IsSGPRSrc ? &AMDGPU::SGPR_32RegClass
-                                     : IsAGPRSrc ? &AMDGPU::AGPR_32RegClass
-                                                 : &AMDGPU::VGPR_32RegClass;
-    MCRegister NewDestReg =
-      RI.getMatchingSuperReg(DestReg, DstLow ? AMDGPU::lo16 : AMDGPU::hi16,
-                             DstRC);
-    MCRegister NewSrcReg =
-      RI.getMatchingSuperReg(SrcReg, SrcLow ? AMDGPU::lo16 : AMDGPU::hi16,
-                             SrcRC);
+    MCRegister NewDestReg = RI.get32BitRegister(DestReg);
+    MCRegister NewSrcReg = RI.get32BitRegister(SrcReg);
 
     if (IsSGPRDst) {
       if (!IsSGPRSrc) {

diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index 9027eac..a043f30 100644 (file)
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -1798,3 +1798,21 @@ MachineInstr *SIRegisterInfo::findReachingDef(Register Reg, unsigned SubReg,
 
   return Def;
 }
+
+MCPhysReg SIRegisterInfo::get32BitRegister(MCPhysReg Reg) const {
+  const TargetRegisterClass *RC = getPhysRegClass(Reg);
+  assert(getRegSizeInBits(*RC) <= 32);
+
+  for (const TargetRegisterClass &RC : { AMDGPU::VGPR_32RegClass,
+                                         AMDGPU::SReg_32RegClass,
+                                         AMDGPU::AGPR_32RegClass } ) {
+    if (MCPhysReg Super = getMatchingSuperReg(Reg, AMDGPU::lo16, &RC))
+      return Super;
+  }
+  if (MCPhysReg Super = getMatchingSuperReg(Reg, AMDGPU::hi16,
+                                            &AMDGPU::VGPR_32RegClass)) {
+      return Super;
+  }
+
+  return AMDGPU::NoRegister;
+}

diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.h b/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
index 0597728..2f328e7 100644 (file)
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
@@ -283,7 +283,7 @@ public:
 
   // \returns a DWORD offset of a \p SubReg
   unsigned getChannelFromSubReg(unsigned SubReg) const {
-    return SubReg ? divideCeil(getSubRegIdxOffset(SubReg), 32) : 0;
+    return SubReg ? (getSubRegIdxOffset(SubReg) + 31) / 32 : 0;
   }
 
   // \returns a DWORD size of a \p SubReg
@@ -291,6 +291,10 @@ public:
     return getNumCoveredRegs(getSubRegIndexLaneMask(SubReg));
   }
 
+  // For a given 16 bit \p Reg \returns a 32 bit register holding it.
+  // \returns \p Reg otherwise.
+  MCPhysReg get32BitRegister(MCPhysReg Reg) const;
+
 private:
   void buildSpillLoadStore(MachineBasicBlock::iterator MI,
                            unsigned LoadStoreOp,

diff --git a/llvm/test/CodeGen/AMDGPU/regbank-reassign.mir b/llvm/test/CodeGen/AMDGPU/regbank-reassign.mir
index 6a74025..bec7969 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/regbank-reassign.mir
+++ b/llvm/test/CodeGen/AMDGPU/regbank-reassign.mir
@@ -364,3 +364,133 @@ body:             |
     DS_WRITE2_B32_gfx9 %2, %1.sub14, %1.sub15, 14, 15, 0, implicit $exec
     S_ENDPGM 0
 ...
+
+# GCN-LABEL: vgpr_lo16_sub{{$}}
+# GCN: renamable $vgpr0 = V_AND_B32_e32 killed $vgpr3, killed $vgpr1, implicit $exec
+# GCN: renamable $vgpr1_lo16 = COPY renamable $vgpr0_lo16
+---
+name:            vgpr_lo16_sub
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '$vgpr1' }
+  - { id: 1, class: vgpr_32, preferred-register: '$vgpr5' }
+  - { id: 2, class: vgpr_32 }
+  - { id: 3, class: vgpr_lo16 }
+body: |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1 = IMPLICIT_DEF
+    %2 = V_AND_B32_e32 %1, %0, implicit $exec
+    %3 = COPY %2.lo16
+    $vgpr1_lo16 = COPY %3
+    SI_RETURN_TO_EPILOG $vgpr1_lo16
+...
+
+# GCN-LABEL: vgpr_lo16{{$}}
+# GCN: $vgpr1_lo16 = COPY killed renamable $vgpr0_lo16
+---
+name:            vgpr_lo16
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vgpr_lo16, preferred-register: '$vgpr4_lo16' }
+body: |
+  bb.0:
+    liveins: $vgpr0_lo16
+
+    %0 = COPY $vgpr0_lo16
+    $vgpr1_lo16 = COPY %0
+    SI_RETURN_TO_EPILOG $vgpr1_lo16
+...
+
+# GCN-LABEL: vgpr_hi16_sub{{$}}
+# GCN: renamable $vgpr0 = V_AND_B32_e32 killed $vgpr3, killed $vgpr1, implicit $exec
+# GCN: renamable $vgpr1_hi16 = COPY renamable $vgpr0_hi16
+---
+name:            vgpr_hi16_sub
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '$vgpr1' }
+  - { id: 1, class: vgpr_32, preferred-register: '$vgpr5' }
+  - { id: 2, class: vgpr_32 }
+  - { id: 3, class: vgpr_hi16 }
+body: |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1 = IMPLICIT_DEF
+    %2 = V_AND_B32_e32 %1, %0, implicit $exec
+    %3 = COPY %2.hi16
+    $vgpr1_hi16 = COPY %3
+    SI_RETURN_TO_EPILOG $vgpr1_hi16
+...
+
+# GCN-LABEL: vgpr_hi16{{$}}
+# GCN: $vgpr1_hi16 = COPY killed renamable $vgpr0_hi16
+---
+name:            vgpr_hi16
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vgpr_hi16, preferred-register: '$vgpr4_hi16' }
+body: |
+  bb.0:
+    liveins: $vgpr0_hi16
+
+    %0 = COPY $vgpr0_hi16
+    $vgpr1_hi16 = COPY %0
+    SI_RETURN_TO_EPILOG $vgpr1_hi16
+...
+
+# GCN-LABEL: sgpr_lo16_sub{{$}}
+# GCN: renamable $sgpr0 = S_AND_B32 killed renamable $sgpr14, $sgpr0, implicit-def $scc
+# GCN: renamable $sgpr1_lo16 = COPY renamable $sgpr0_lo16
+---
+name:            sgpr_lo16_sub
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: sgpr_32, preferred-register: '$sgpr16' }
+  - { id: 1, class: sgpr_32 }
+  - { id: 2, class: sgpr_lo16 }
+body: |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    $sgpr0 = IMPLICIT_DEF
+    %1 = S_AND_B32 %0, $sgpr0, implicit-def $scc
+    %2 = COPY %1.lo16
+    $sgpr1_lo16 = COPY %2
+    SI_RETURN_TO_EPILOG $sgpr1_lo16
+...
+
+# GCN-LABEL: sgpr_lo16{{$}}
+# GCN: $sgpr1_lo16 = COPY killed renamable $sgpr0_lo16
+---
+name:            sgpr_lo16
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: sgpr_lo16, preferred-register: '$sgpr4_lo16' }
+body: |
+  bb.0:
+    liveins: $sgpr0_lo16
+
+    %0 = COPY $sgpr0_lo16
+    $sgpr1_lo16 = COPY %0
+    SI_RETURN_TO_EPILOG $sgpr1_lo16
+...
+
+# Check that we do not use VGPR3 which we would use otherwise.
+# We cannot use it because of interference with VGPR3_LO16.
+# GCN-LABEL: v1_vs_v5_src_interence{{$}}
+# GCN: V_AND_B32_e32 killed $vgpr7, killed $vgpr1,
+---
+name:            v1_vs_v5_src_interence
+tracksRegLiveness: true
+registers:
+  - { id: 0, class: vgpr_32, preferred-register: '$vgpr1' }
+  - { id: 1, class: vgpr_32, preferred-register: '$vgpr5' }
+  - { id: 2, class: vgpr_32 }
+body: |
+  bb.0:
+    %0 = IMPLICIT_DEF
+    %1 = IMPLICIT_DEF
+    $vgpr3_lo16 = IMPLICIT_DEF
+    %2 = V_AND_B32_e32 %1, %0, implicit $exec
+    S_ENDPGM 0
+...