Index: lib/Target/AMDGPU/SIRegisterInfo.h
===================================================================
--- lib/Target/AMDGPU/SIRegisterInfo.h
+++ lib/Target/AMDGPU/SIRegisterInfo.h
@@ -264,6 +264,13 @@
   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,
Index: lib/Target/AMDGPU/SIRegisterInfo.cpp
===================================================================
--- lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -1474,3 +1474,23 @@
                             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 and sub-dword coalescing.
+  if (SrcSize <= 4 || DstSize <= 4)
+    return true;
+
+  return NewSize <= DstSize || NewSize <= SrcSize;
+}
Index: test/CodeGen/AMDGPU/half.ll
===================================================================
--- test/CodeGen/AMDGPU/half.ll
+++ test/CodeGen/AMDGPU/half.ll
@@ -399,15 +399,15 @@
 ; 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{{$}}
Index: test/CodeGen/AMDGPU/limit-coalesce.mir
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/limit-coalesce.mir
@@ -0,0 +1,54 @@
+# RUN: llc -march=amdgcn -run-pass simple-register-coalescing -o - %s | FileCheck %s
+
+# Check that coalescer does not create 96 bit register tuple and uses 64 bit register
+# for addressing
+
+# CHECK:  - { id: 2, class: vreg_64 }
+# CHECK:  - { id: 3, class: vreg_64 }
+# CHECK:  - { id: 4, class: vreg_64 }
+# No more registers shall be defined
+# CHECK-NEXT: liveins:
+# CHECK:    FLAT_STORE_DWORDX2 %4,
+
+---
+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 }
+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 killed %3.sub0
+    undef %5.sub0 = COPY %4.sub1
+    %5.sub1 = COPY %4.sub0
+    FLAT_STORE_DWORDX2 killed %5, killed %vgpr0_vgpr1, 0, 0, 0, implicit %exec, implicit %flat_scr
+
+...