[AMDGPU] Do not allow register coalescer to create big superregs

Limit register coalescer by not allowing it to artificially increase
size of registers beyond dword. Such super-registers are in fact
register sequences and not distinct HW registers.

With more super-regs we would need to allocate adjacent registers
and constraint regalloc more than needed. Moreover, our super
registers are overlapping. For instance we have VGPR0_VGPR1_VGPR2,
VGPR1_VGPR2_VGPR3, VGPR2_VGPR3_VGPR4 etc, which complicates registers
allocation even more, resulting in excessive spilling.

Differential Revision: https://reviews.llvm.org/D28782

llvm-svn: 292413

4 files changed, 107 insertions, 9 deletions

diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index 612599b1283..84eb246800a 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -1474,3 +1474,23 @@ bool SIRegisterInfo::isVGPR(const MachineRegisterInfo &MRI,
                             unsigned Reg) const {
   return hasVGPRs(getRegClassForReg(MRI, Reg));
 }
+
+bool SIRegisterInfo::shouldCoalesce(MachineInstr *MI,
+                                    const TargetRegisterClass *SrcRC,
+                                    unsigned SubReg,
+                                    const TargetRegisterClass *DstRC,
+                                    unsigned DstSubReg,
+                                    const TargetRegisterClass *NewRC) const {
+  unsigned SrcSize = SrcRC->getSize();
+  unsigned DstSize = DstRC->getSize();
+  unsigned NewSize = NewRC->getSize();
+
+  // Do not increase size of registers beyond dword, we would need to allocate
+  // adjacent registers and constraint regalloc more than needed.
+
+  // Always allow dword coalescing.
+  if (SrcSize <= 4 || DstSize <= 4)
+    return true;
+
+  return NewSize <= DstSize || NewSize <= SrcSize;
+}
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.h b/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
index 0bcae7d9840..29c72b6a8f8 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
@@ -264,6 +264,13 @@ public:
   ArrayRef<int16_t> getRegSplitParts(const TargetRegisterClass *RC,
                                      unsigned EltSize) const;
 
+  bool shouldCoalesce(MachineInstr *MI,
+                      const TargetRegisterClass *SrcRC,
+                      unsigned SubReg,
+                      const TargetRegisterClass *DstRC,
+                      unsigned DstSubReg,
+                      const TargetRegisterClass *NewRC) const override;
+
 private:
   void buildSpillLoadStore(MachineBasicBlock::iterator MI,
                            unsigned LoadStoreOp,
diff --git a/llvm/test/CodeGen/AMDGPU/half.ll b/llvm/test/CodeGen/AMDGPU/half.ll
index f2bb3f9d110..e823f736f1e 100644
--- a/llvm/test/CodeGen/AMDGPU/half.ll
+++ b/llvm/test/CodeGen/AMDGPU/half.ll
@@ -399,15 +399,15 @@ define void @global_extload_v2f16_to_v2f64(<2 x double> addrspace(1)* %out, <2 x
 ; XVI-NOT: v_cvt_f32_f16
 
 ; GCN: buffer_load_dwordx2 v{{\[}}[[IN_LO:[0-9]+]]:[[IN_HI:[0-9]+]]
-; VI:  v_lshrrev_b32_e32 [[Y16:v[0-9]+]], 16, v[[IN_LO]]
-; GCN: v_cvt_f32_f16_e32 [[Z32:v[0-9]+]], v[[IN_HI]]
-; GCN: v_cvt_f32_f16_e32 [[X32:v[0-9]+]], v[[IN_LO]]
-; SI:  v_lshrrev_b32_e32 [[Y16:v[0-9]+]], 16, v[[IN_LO]]
-; GCN: v_cvt_f32_f16_e32 [[Y32:v[0-9]+]], [[Y16]]
-
-; GCN: v_cvt_f64_f32_e32 [[Z:v\[[0-9]+:[0-9]+\]]], [[Z32]]
-; GCN: v_cvt_f64_f32_e32 v{{\[}}[[XLO:[0-9]+]]:{{[0-9]+}}], [[X32]]
-; GCN: v_cvt_f64_f32_e32 v[{{[0-9]+}}:[[YHI:[0-9]+]]{{\]}}, [[Y32]]
+; VI-DAG:  v_lshrrev_b32_e32 [[Y16:v[0-9]+]], 16, v[[IN_LO]]
+; GCN-DAG: v_cvt_f32_f16_e32 [[Z32:v[0-9]+]], v[[IN_HI]]
+; GCN-DAG: v_cvt_f32_f16_e32 [[X32:v[0-9]+]], v[[IN_LO]]
+; SI:      v_lshrrev_b32_e32 [[Y16:v[0-9]+]], 16, v[[IN_LO]]
+; GCN-DAG: v_cvt_f32_f16_e32 [[Y32:v[0-9]+]], [[Y16]]
+
+; GCN-DAG: v_cvt_f64_f32_e32 [[Z:v\[[0-9]+:[0-9]+\]]], [[Z32]]
+; GCN-DAG: v_cvt_f64_f32_e32 v{{\[}}[[XLO:[0-9]+]]:{{[0-9]+}}], [[X32]]
+; GCN-DAG: v_cvt_f64_f32_e32 v[{{[0-9]+}}:[[YHI:[0-9]+]]{{\]}}, [[Y32]]
 ; GCN-NOT: v_cvt_f64_f32_e32
 
 ; GCN-DAG: buffer_store_dwordx4 v{{\[}}[[XLO]]:[[YHI]]{{\]}}, off, s{{\[[0-9]+:[0-9]+\]}}, 0{{$}}
diff --git a/llvm/test/CodeGen/AMDGPU/limit-coalesce.mir b/llvm/test/CodeGen/AMDGPU/limit-coalesce.mir
new file mode 100644
index 00000000000..106a96e32dc
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/limit-coalesce.mir
@@ -0,0 +1,71 @@
+# RUN: llc -march=amdgcn -run-pass simple-register-coalescing -o - %s | FileCheck %s
+
+# Check that coalescer does not create wider register tuple than in source
+
+# CHECK:  - { id: 2, class: vreg_64 }
+# CHECK:  - { id: 3, class: vreg_64 }
+# CHECK:  - { id: 4, class: vreg_64 }
+# CHECK:  - { id: 5, class: vreg_96 }
+# CHECK:  - { id: 6, class: vreg_96 }
+# CHECK:  - { id: 7, class: vreg_128 }
+# CHECK:  - { id: 8, class: vreg_128 }
+# No more registers shall be defined
+# CHECK-NEXT: liveins:
+# CHECK:    FLAT_STORE_DWORDX2 %vgpr0_vgpr1, %4,
+# CHECK:    FLAT_STORE_DWORDX3 %vgpr0_vgpr1, %6,
+
+---
+name:            main
+alignment:       0
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+tracksRegLiveness: true
+registers:
+  - { id: 1, class: sreg_32_xm0, preferred-register: '%1' }
+  - { id: 2, class: vreg_64, preferred-register: '%2' }
+  - { id: 3, class: vreg_64 }
+  - { id: 4, class: vreg_64 }
+  - { id: 5, class: vreg_64 }
+  - { id: 6, class: vreg_96 }
+  - { id: 7, class: vreg_96 }
+  - { id: 8, class: vreg_128 }
+  - { id: 9, class: vreg_128 }
+liveins:
+  - { reg: '%sgpr6', virtual-reg: '%1' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    0
+  adjustsStack:    false
+  hasCalls:        false
+  maxCallFrameSize: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+body:             |
+  bb.0.entry:
+    liveins: %sgpr0, %vgpr0_vgpr1
+
+    %3 = IMPLICIT_DEF
+    undef %4.sub0 = COPY %sgpr0
+    %4.sub1 = COPY %3.sub0
+    undef %5.sub0 = COPY %4.sub1
+    %5.sub1 = COPY %4.sub0
+    FLAT_STORE_DWORDX2 %vgpr0_vgpr1, killed %5, 0, 0, 0, implicit %exec, implicit %flat_scr
+
+    %6 = IMPLICIT_DEF
+    undef %7.sub0_sub1 = COPY %6
+    %7.sub2 = COPY %3.sub0
+    FLAT_STORE_DWORDX3 %vgpr0_vgpr1, killed %7, 0, 0, 0, implicit %exec, implicit %flat_scr
+
+    %8 = IMPLICIT_DEF
+    undef %9.sub0_sub1_sub2 = COPY %8
+    %9.sub3 = COPY %3.sub0
+    FLAT_STORE_DWORDX4 %vgpr0_vgpr1, killed %9, 0, 0, 0, implicit %exec, implicit %flat_scr
+...