Index: llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -107,19 +107,19 @@
 
 bool SIInstrInfo::isReallyTriviallyReMaterializable(const MachineInstr &MI,
                                                     AAResults *AA) const {
-  if (isVOP1(MI) || isVOP3(MI) || isSDWA(MI)) {
-    // Normally VALU use of exec would block the rematerialization, but that
-    // is OK in this case to have an implicit exec read as all VALU do.
-    // We really want all of the generic logic for this except for this.
-
-    // Another potential implicit use is mode register. The core logic of
-    // the RA will not attempt rematerialization if mode is set anywhere
-    // in the function, otherwise it is safe since mode is not changed.
-    return !MI.hasImplicitDef() &&
-           MI.getNumImplicitOperands() == MI.getDesc().getNumImplicitUses();
-  }
-
-  return false;
+  // Normally VALU use of exec would block the rematerialization, but that
+  // is OK in this case to have an implicit exec read as all VALU do.
+
+  // Another potential implicit use is mode register. The core logic of
+  // the RA will not attempt rematerialization if mode is set anywhere
+  // in the function, otherwise it is safe since mode is not changed.
+
+  // A generic implementation bails on only virtual register use which
+  // effectively prevents rematerialization. On AMDGPU we only need to
+  // check we have no tied operands which normally model read-modify-write.
+  return !MI.hasImplicitDef() &&
+         MI.getNumImplicitOperands() == MI.getDesc().getNumImplicitUses() &&
+         !MI.getOperand(0).isTied();
 }
 
 bool SIInstrInfo::isIgnorableUse(const MachineOperand &MO) const {
Index: llvm/test/CodeGen/AMDGPU/remat-sop.mir
===================================================================
--- llvm/test/CodeGen/AMDGPU/remat-sop.mir
+++ llvm/test/CodeGen/AMDGPU/remat-sop.mir
@@ -51,6 +51,66 @@
     S_NOP 0, implicit %2
     S_ENDPGM 0
 ...
+# The liverange of %0 covers a point of rematerialization, source value is
+# availabe.
+---
+name:            test_remat_s_mov_b32_vreg_src_long_lr
+tracksRegLiveness: true
+machineFunctionInfo:
+  stackPtrOffsetReg:  $sgpr32
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: test_remat_s_mov_b32_vreg_src_long_lr
+    ; GCN: renamable $sgpr0 = IMPLICIT_DEF
+    ; GCN: renamable $sgpr1 = S_MOV_B32 renamable $sgpr0
+    ; GCN: S_NOP 0, implicit killed renamable $sgpr1
+    ; GCN: renamable $sgpr1 = S_MOV_B32 renamable $sgpr0
+    ; GCN: S_NOP 0, implicit killed renamable $sgpr1
+    ; GCN: renamable $sgpr1 = S_MOV_B32 renamable $sgpr0
+    ; GCN: S_NOP 0, implicit killed renamable $sgpr1
+    ; GCN: S_NOP 0, implicit killed renamable $sgpr0
+    ; GCN: S_ENDPGM 0
+    %0:sreg_32 = IMPLICIT_DEF
+    %1:sreg_32 = S_MOV_B32 %0:sreg_32
+    %2:sreg_32 = S_MOV_B32 %0:sreg_32
+    %3:sreg_32 = S_MOV_B32 %0:sreg_32
+    S_NOP 0, implicit %1
+    S_NOP 0, implicit %2
+    S_NOP 0, implicit %3
+    S_NOP 0, implicit %0
+    S_ENDPGM 0
+...
+# The liverange of %0 does not cover a point of rematerialization, source value is
+# unavailabe and we do not want to artificially extend the liverange.
+---
+name:            test_no_remat_s_mov_b32_vreg_src_short_lr
+tracksRegLiveness: true
+machineFunctionInfo:
+  stackPtrOffsetReg:  $sgpr32
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: test_no_remat_s_mov_b32_vreg_src_short_lr
+    ; GCN: renamable $sgpr0 = IMPLICIT_DEF
+    ; GCN: renamable $sgpr1 = S_MOV_B32 renamable $sgpr0
+    ; GCN: SI_SPILL_S32_SAVE killed renamable $sgpr1, %stack.1, implicit $exec, implicit $sgpr32 :: (store (s32) into %stack.1, addrspace 5)
+    ; GCN: renamable $sgpr1 = S_MOV_B32 renamable $sgpr0
+    ; GCN: SI_SPILL_S32_SAVE killed renamable $sgpr1, %stack.0, implicit $exec, implicit $sgpr32 :: (store (s32) into %stack.0, addrspace 5)
+    ; GCN: renamable $sgpr0 = S_MOV_B32 killed renamable $sgpr0
+    ; GCN: renamable $sgpr1 = SI_SPILL_S32_RESTORE %stack.1, implicit $exec, implicit $sgpr32 :: (load (s32) from %stack.1, addrspace 5)
+    ; GCN: S_NOP 0, implicit killed renamable $sgpr1
+    ; GCN: renamable $sgpr1 = SI_SPILL_S32_RESTORE %stack.0, implicit $exec, implicit $sgpr32 :: (load (s32) from %stack.0, addrspace 5)
+    ; GCN: S_NOP 0, implicit killed renamable $sgpr1
+    ; GCN: S_NOP 0, implicit killed renamable $sgpr0
+    ; GCN: S_ENDPGM 0
+    %0:sreg_32 = IMPLICIT_DEF
+    %1:sreg_32 = S_MOV_B32 %0:sreg_32
+    %2:sreg_32 = S_MOV_B32 %0:sreg_32
+    %3:sreg_32 = S_MOV_B32 %0:sreg_32
+    S_NOP 0, implicit %1
+    S_NOP 0, implicit %2
+    S_NOP 0, implicit %3
+    S_ENDPGM 0
+...
 ---
 name:            test_remat_s_mov_b64
 tracksRegLiveness: true