diff --git a/llvm/test/CodeGen/AMDGPU/remat-smrd.mir b/llvm/test/CodeGen/AMDGPU/remat-smrd.mir
--- a/llvm/test/CodeGen/AMDGPU/remat-smrd.mir
+++ b/llvm/test/CodeGen/AMDGPU/remat-smrd.mir
@@ -165,6 +165,37 @@
     S_ENDPGM 0, implicit %0
 ...
 
+---
+name:            test_remat_s_load_dword_immx16_subreg
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $sgpr8_sgpr9, $vgpr0_vgpr1
+    ; GCN-LABEL: name: test_remat_s_load_dword_immx16_subreg
+    ; GCN: liveins: $sgpr8_sgpr9, $vgpr0_vgpr1
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: renamable $sgpr0_sgpr1 = COPY $sgpr8_sgpr9
+    ; GCN-NEXT: renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = S_LOAD_DWORDX16_IMM renamable $sgpr0_sgpr1, 0, 0 :: (dereferenceable invariant load (s512), align 4, addrspace 4)
+    ; GCN-NEXT: SI_SPILL_S512_SAVE killed renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19, %stack.0, implicit $exec, implicit $sp_reg :: (store (s512) into %stack.0, align 4, addrspace 5)
+    ; GCN-NEXT: renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = S_LOAD_DWORDX16_IMM renamable $sgpr0_sgpr1, 128, 0 :: (dereferenceable invariant load (s512), align 4, addrspace 4)
+    ; GCN-NEXT: renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = SI_SPILL_S512_RESTORE %stack.0, implicit $exec, implicit $sp_reg :: (load (s512) from %stack.0, align 4, addrspace 5)
+    ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19
+    ; GCN-NEXT: renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = S_LOAD_DWORDX16_IMM renamable $sgpr0_sgpr1, 128, 0 :: (dereferenceable invariant load (s512), align 4, addrspace 4)
+    ; GCN-NEXT: renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = SI_SPILL_S512_RESTORE %stack.0, implicit $exec, implicit $sp_reg :: (load (s512) from %stack.0, align 4, addrspace 5)
+    ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11
+    ; GCN-NEXT: S_ENDPGM 0, implicit killed renamable $sgpr0_sgpr1
+    %0:sreg_64_xexec = COPY $sgpr8_sgpr9
+    %1:sgpr_512 = S_LOAD_DWORDX16_IMM %0, 0, 0 :: (invariant dereferenceable load (s512), align 4, addrspace 4)
+    %2:sgpr_512 = S_LOAD_DWORDX16_IMM %0, 128, 0 :: (invariant dereferenceable load (s512), align 4, addrspace 4)
+    %2.sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15:sgpr_512 = COPY %1.sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15:sgpr_512
+    S_NOP 0, implicit %2.sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15
+    %3:sgpr_512 = S_LOAD_DWORDX16_IMM %0, 128, 0 :: (invariant dereferenceable load (s512), align 4, addrspace 4)
+    %3.sub0_sub1_sub2_sub3_sub4_sub5_sub6_sub7:sgpr_512 = COPY %1.sub0_sub1_sub2_sub3_sub4_sub5_sub6_sub7:sgpr_512
+    S_NOP 0, implicit %3.sub0_sub1_sub2_sub3_sub4_sub5_sub6_sub7:sgpr_512
+
+    S_ENDPGM 0, implicit %0
+...
+
 ---
 name:            test_remat_s_get_waveid_in_workgroup
 tracksRegLiveness: true
@@ -360,24 +391,20 @@
     S_ENDPGM 0, implicit %0
 ...
 
-#---------------------------------------------------------------------
-# Negative tests
-#---------------------------------------------------------------------
-
 ---
-name:            test_no_remat_s_load_dword_not_invariant
+name:            test_remat_s_load_dword_invariant_not_dereferenceable
 tracksRegLiveness: true
 body:             |
   bb.0:
     liveins: $sgpr8_sgpr9
-    ; GCN-LABEL: name: test_no_remat_s_load_dword_not_invariant
+    ; GCN-LABEL: name: test_remat_s_load_dword_invariant_not_dereferenceable
     ; GCN: liveins: $sgpr8_sgpr9
     ; GCN-NEXT: {{  $}}
     ; GCN-NEXT: renamable $sgpr2_sgpr3 = COPY $sgpr8_sgpr9
-    ; GCN-NEXT: renamable $sgpr0 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 0, 0 :: (dereferenceable load (s32), addrspace 4)
+    ; GCN-NEXT: renamable $sgpr0 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 0, 0 :: (invariant load (s32), addrspace 4)
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr0, %stack.0, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.0, addrspace 5)
-    ; GCN-NEXT: renamable $sgpr1 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 4, 0 :: (dereferenceable load (s32), addrspace 4)
-    ; GCN-NEXT: renamable $sgpr0 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 8, 0 :: (dereferenceable load (s32), addrspace 4)
+    ; GCN-NEXT: renamable $sgpr1 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 4, 0 :: (invariant load (s32), addrspace 4)
+    ; GCN-NEXT: renamable $sgpr0 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 8, 0 :: (invariant load (s32), addrspace 4)
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr0, %stack.1, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.1, addrspace 5)
     ; GCN-NEXT: renamable $sgpr0 = SI_SPILL_S32_RESTORE %stack.0, implicit $exec, implicit $sp_reg :: (load (s32) from %stack.0, addrspace 5)
     ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr0
@@ -386,29 +413,34 @@
     ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr0
     ; GCN-NEXT: S_ENDPGM 0, implicit killed renamable $sgpr2_sgpr3
     %0:sreg_64_xexec = COPY $sgpr8_sgpr9
-    %1:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 0, 0 :: (dereferenceable load (s32), addrspace 4)
-    %2:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 4, 0 :: (dereferenceable load (s32), addrspace 4)
-    %3:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 8, 0 :: (dereferenceable load (s32), addrspace 4)
+    %1:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 0, 0 :: (invariant load (s32), addrspace 4)
+    %2:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 4, 0 :: (invariant load (s32), addrspace 4)
+    %3:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 8, 0 :: (invariant load (s32), addrspace 4)
     S_NOP 0, implicit %1
     S_NOP 0, implicit %2
     S_NOP 0, implicit %3
     S_ENDPGM 0, implicit %0
 ...
 
+
+#---------------------------------------------------------------------
+# Negative tests
+#---------------------------------------------------------------------
+
 ---
-name:            test_no_remat_s_load_dword_not_dereferenceable
+name:            test_no_remat_s_load_dword_not_invariant
 tracksRegLiveness: true
 body:             |
   bb.0:
     liveins: $sgpr8_sgpr9
-    ; GCN-LABEL: name: test_no_remat_s_load_dword_not_dereferenceable
+    ; GCN-LABEL: name: test_no_remat_s_load_dword_not_invariant
     ; GCN: liveins: $sgpr8_sgpr9
     ; GCN-NEXT: {{  $}}
     ; GCN-NEXT: renamable $sgpr2_sgpr3 = COPY $sgpr8_sgpr9
-    ; GCN-NEXT: renamable $sgpr0 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 0, 0 :: (invariant load (s32), addrspace 4)
+    ; GCN-NEXT: renamable $sgpr0 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 0, 0 :: (dereferenceable load (s32), addrspace 4)
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr0, %stack.0, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.0, addrspace 5)
-    ; GCN-NEXT: renamable $sgpr1 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 4, 0 :: (invariant load (s32), addrspace 4)
-    ; GCN-NEXT: renamable $sgpr0 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 8, 0 :: (invariant load (s32), addrspace 4)
+    ; GCN-NEXT: renamable $sgpr1 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 4, 0 :: (dereferenceable load (s32), addrspace 4)
+    ; GCN-NEXT: renamable $sgpr0 = S_LOAD_DWORD_IMM renamable $sgpr2_sgpr3, 8, 0 :: (dereferenceable load (s32), addrspace 4)
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr0, %stack.1, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.1, addrspace 5)
     ; GCN-NEXT: renamable $sgpr0 = SI_SPILL_S32_RESTORE %stack.0, implicit $exec, implicit $sp_reg :: (load (s32) from %stack.0, addrspace 5)
     ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr0
@@ -417,9 +449,9 @@
     ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr0
     ; GCN-NEXT: S_ENDPGM 0, implicit killed renamable $sgpr2_sgpr3
     %0:sreg_64_xexec = COPY $sgpr8_sgpr9
-    %1:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 0, 0 :: (invariant load (s32), addrspace 4)
-    %2:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 4, 0 :: (invariant load (s32), addrspace 4)
-    %3:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 8, 0 :: (invariant load (s32), addrspace 4)
+    %1:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 0, 0 :: (dereferenceable load (s32), addrspace 4)
+    %2:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 4, 0 :: (dereferenceable load (s32), addrspace 4)
+    %3:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM %0, 8, 0 :: (dereferenceable load (s32), addrspace 4)
     S_NOP 0, implicit %1
     S_NOP 0, implicit %2
     S_NOP 0, implicit %3