diff --git a/llvm/lib/CodeGen/DeadMachineInstructionElim.cpp b/llvm/lib/CodeGen/DeadMachineInstructionElim.cpp
index 618ac3122a4e..d1529b08f708 100644
--- a/llvm/lib/CodeGen/DeadMachineInstructionElim.cpp
+++ b/llvm/lib/CodeGen/DeadMachineInstructionElim.cpp
@@ -82,6 +82,15 @@ bool DeadMachineInstructionElim::isDead(const MachineInstr *MI) const {
         if (LivePhysRegs.test(Reg) || MRI->isReserved(Reg))
           return false;
       } else {
+        if (MO.isDead()) {
+#ifndef NDEBUG
+          // Sanity check on uses of this dead register. All of them should be
+          // 'undef'.
+          for (auto &U : MRI->use_nodbg_operands(Reg))
+            assert(U.isUndef() && "'Undef' use on a 'dead' register is found!");
+#endif
+          continue;
+        }
         for (const MachineInstr &Use : MRI->use_nodbg_instructions(Reg)) {
           if (&Use != MI)
             // This def has a non-debug use. Don't delete the instruction!
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index 0d05f2445ba1..57853963b010 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -948,7 +948,7 @@ void GCNPassConfig::addOptimizedRegAlloc() {
   insertPass(&RegisterCoalescerID, &SIPreAllocateWWMRegsID, false);
 
   if (EnableDCEInRA)
-    insertPass(&RenameIndependentSubregsID, &DeadMachineInstructionElimID);
+    insertPass(&DetectDeadLanesID, &DeadMachineInstructionElimID);
 
   TargetPassConfig::addOptimizedRegAlloc();
 }
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
index cdd3e2693710..2fec729a3da9 100644
--- a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
@@ -1205,20 +1205,20 @@ define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out) {
 ;
 ; GFX1064-LABEL: add_i64_constant:
 ; GFX1064:       ; %bb.0: ; %entry
-; GFX1064-NEXT:    v_cmp_ne_u32_e64 s[2:3], 1, 0
+; GFX1064-NEXT:    v_cmp_ne_u32_e64 s[4:5], 1, 0
 ; GFX1064-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
 ; GFX1064-NEXT:    ; implicit-def: $vgpr1_vgpr2
-; GFX1064-NEXT:    v_mbcnt_lo_u32_b32_e64 v0, s2, 0
-; GFX1064-NEXT:    v_mbcnt_hi_u32_b32_e64 v0, s3, v0
+; GFX1064-NEXT:    v_mbcnt_lo_u32_b32_e64 v0, s4, 0
+; GFX1064-NEXT:    v_mbcnt_hi_u32_b32_e64 v0, s5, v0
 ; GFX1064-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v0
-; GFX1064-NEXT:    s_and_saveexec_b64 s[4:5], vcc
+; GFX1064-NEXT:    s_and_saveexec_b64 s[2:3], vcc
 ; GFX1064-NEXT:    ; mask branch BB5_2
 ; GFX1064-NEXT:    s_cbranch_execz BB5_2
 ; GFX1064-NEXT:  BB5_1:
-; GFX1064-NEXT:    s_bcnt1_i32_b64 s2, s[2:3]
+; GFX1064-NEXT:    s_bcnt1_i32_b64 s4, s[4:5]
 ; GFX1064-NEXT:    v_mov_b32_e32 v3, local_var64@abs32@lo
-; GFX1064-NEXT:    v_mul_hi_u32_u24_e64 v2, s2, 5
-; GFX1064-NEXT:    v_mul_u32_u24_e64 v1, s2, 5
+; GFX1064-NEXT:    v_mul_hi_u32_u24_e64 v2, s4, 5
+; GFX1064-NEXT:    v_mul_u32_u24_e64 v1, s4, 5
 ; GFX1064-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GFX1064-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX1064-NEXT:    ds_add_rtn_u64 v[1:2], v3, v[1:2]
@@ -1227,7 +1227,7 @@ define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out) {
 ; GFX1064-NEXT:    buffer_gl1_inv
 ; GFX1064-NEXT:  BB5_2:
 ; GFX1064-NEXT:    v_nop
-; GFX1064-NEXT:    s_or_b64 exec, exec, s[4:5]
+; GFX1064-NEXT:    s_or_b64 exec, exec, s[2:3]
 ; GFX1064-NEXT:    v_readfirstlane_b32 s2, v1
 ; GFX1064-NEXT:    v_readfirstlane_b32 s3, v2
 ; GFX1064-NEXT:    v_mad_u64_u32 v[0:1], s[2:3], v0, 5, s[2:3]
@@ -2310,20 +2310,20 @@ define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out) {
 ;
 ; GFX1064-LABEL: sub_i64_constant:
 ; GFX1064:       ; %bb.0: ; %entry
-; GFX1064-NEXT:    v_cmp_ne_u32_e64 s[2:3], 1, 0
+; GFX1064-NEXT:    v_cmp_ne_u32_e64 s[4:5], 1, 0
 ; GFX1064-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
 ; GFX1064-NEXT:    ; implicit-def: $vgpr1_vgpr2
-; GFX1064-NEXT:    v_mbcnt_lo_u32_b32_e64 v0, s2, 0
-; GFX1064-NEXT:    v_mbcnt_hi_u32_b32_e64 v0, s3, v0
+; GFX1064-NEXT:    v_mbcnt_lo_u32_b32_e64 v0, s4, 0
+; GFX1064-NEXT:    v_mbcnt_hi_u32_b32_e64 v0, s5, v0
 ; GFX1064-NEXT:    v_cmp_eq_u32_e32 vcc, 0, v0
-; GFX1064-NEXT:    s_and_saveexec_b64 s[4:5], vcc
+; GFX1064-NEXT:    s_and_saveexec_b64 s[2:3], vcc
 ; GFX1064-NEXT:    ; mask branch BB11_2
 ; GFX1064-NEXT:    s_cbranch_execz BB11_2
 ; GFX1064-NEXT:  BB11_1:
-; GFX1064-NEXT:    s_bcnt1_i32_b64 s2, s[2:3]
+; GFX1064-NEXT:    s_bcnt1_i32_b64 s4, s[4:5]
 ; GFX1064-NEXT:    v_mov_b32_e32 v3, local_var64@abs32@lo
-; GFX1064-NEXT:    v_mul_hi_u32_u24_e64 v2, s2, 5
-; GFX1064-NEXT:    v_mul_u32_u24_e64 v1, s2, 5
+; GFX1064-NEXT:    v_mul_hi_u32_u24_e64 v2, s4, 5
+; GFX1064-NEXT:    v_mul_u32_u24_e64 v1, s4, 5
 ; GFX1064-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
 ; GFX1064-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX1064-NEXT:    ds_sub_rtn_u64 v[1:2], v3, v[1:2]
@@ -2332,7 +2332,7 @@ define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out) {
 ; GFX1064-NEXT:    buffer_gl1_inv
 ; GFX1064-NEXT:  BB11_2:
 ; GFX1064-NEXT:    v_nop
-; GFX1064-NEXT:    s_or_b64 exec, exec, s[4:5]
+; GFX1064-NEXT:    s_or_b64 exec, exec, s[2:3]
 ; GFX1064-NEXT:    v_readfirstlane_b32 s2, v1
 ; GFX1064-NEXT:    v_mul_u32_u24_e32 v1, 5, v0
 ; GFX1064-NEXT:    v_readfirstlane_b32 s3, v2
diff --git a/llvm/test/CodeGen/AMDGPU/bswap.ll b/llvm/test/CodeGen/AMDGPU/bswap.ll
index b13e71539777..6f3cd39504a8 100644
--- a/llvm/test/CodeGen/AMDGPU/bswap.ll
+++ b/llvm/test/CodeGen/AMDGPU/bswap.ll
@@ -189,41 +189,41 @@ define amdgpu_kernel void @test_bswap_v8i32(<8 x i32> addrspace(1)* %out, <8 x i
 ;
 ; VI-LABEL: test_bswap_v8i32:
 ; VI:       ; %bb.0:
-; VI-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
+; VI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; VI-NEXT:    s_mov_b32 s12, 0xff00ff
-; VI-NEXT:    s_mov_b32 s11, 0xf000
-; VI-NEXT:    s_mov_b32 s10, -1
+; VI-NEXT:    s_mov_b32 s3, 0xf000
+; VI-NEXT:    s_mov_b32 s2, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    s_mov_b32 s8, s0
-; VI-NEXT:    s_mov_b32 s9, s1
-; VI-NEXT:    s_load_dwordx8 s[0:7], s[2:3], 0x0
+; VI-NEXT:    s_mov_b32 s0, s4
+; VI-NEXT:    s_mov_b32 s1, s5
+; VI-NEXT:    s_load_dwordx8 s[4:11], s[6:7], 0x0
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_alignbit_b32 v0, s3, s3, 8
-; VI-NEXT:    v_alignbit_b32 v1, s3, s3, 24
+; VI-NEXT:    v_alignbit_b32 v0, s7, s7, 8
+; VI-NEXT:    v_alignbit_b32 v1, s7, s7, 24
 ; VI-NEXT:    v_bfi_b32 v3, s12, v1, v0
-; VI-NEXT:    v_alignbit_b32 v2, s2, s2, 8
-; VI-NEXT:    v_alignbit_b32 v4, s2, s2, 24
-; VI-NEXT:    v_alignbit_b32 v0, s1, s1, 8
-; VI-NEXT:    v_alignbit_b32 v1, s1, s1, 24
+; VI-NEXT:    v_alignbit_b32 v2, s6, s6, 8
+; VI-NEXT:    v_alignbit_b32 v4, s6, s6, 24
+; VI-NEXT:    v_alignbit_b32 v0, s5, s5, 8
+; VI-NEXT:    v_alignbit_b32 v1, s5, s5, 24
 ; VI-NEXT:    v_bfi_b32 v2, s12, v4, v2
 ; VI-NEXT:    v_bfi_b32 v1, s12, v1, v0
-; VI-NEXT:    v_alignbit_b32 v0, s0, s0, 8
-; VI-NEXT:    v_alignbit_b32 v4, s0, s0, 24
+; VI-NEXT:    v_alignbit_b32 v0, s4, s4, 8
+; VI-NEXT:    v_alignbit_b32 v4, s4, s4, 24
 ; VI-NEXT:    v_bfi_b32 v0, s12, v4, v0
-; VI-NEXT:    v_alignbit_b32 v4, s7, s7, 8
-; VI-NEXT:    v_alignbit_b32 v5, s7, s7, 24
+; VI-NEXT:    v_alignbit_b32 v4, s11, s11, 8
+; VI-NEXT:    v_alignbit_b32 v5, s11, s11, 24
 ; VI-NEXT:    v_bfi_b32 v7, s12, v5, v4
-; VI-NEXT:    v_alignbit_b32 v4, s6, s6, 8
-; VI-NEXT:    v_alignbit_b32 v5, s6, s6, 24
+; VI-NEXT:    v_alignbit_b32 v4, s10, s10, 8
+; VI-NEXT:    v_alignbit_b32 v5, s10, s10, 24
 ; VI-NEXT:    v_bfi_b32 v6, s12, v5, v4
-; VI-NEXT:    v_alignbit_b32 v4, s5, s5, 8
-; VI-NEXT:    v_alignbit_b32 v5, s5, s5, 24
+; VI-NEXT:    v_alignbit_b32 v4, s9, s9, 8
+; VI-NEXT:    v_alignbit_b32 v5, s9, s9, 24
 ; VI-NEXT:    v_bfi_b32 v5, s12, v5, v4
-; VI-NEXT:    v_alignbit_b32 v4, s4, s4, 8
-; VI-NEXT:    v_alignbit_b32 v8, s4, s4, 24
+; VI-NEXT:    v_alignbit_b32 v4, s8, s8, 8
+; VI-NEXT:    v_alignbit_b32 v8, s8, s8, 24
 ; VI-NEXT:    v_bfi_b32 v4, s12, v8, v4
-; VI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[8:11], 0 offset:16
-; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[8:11], 0
+; VI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[0:3], 0 offset:16
+; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; VI-NEXT:    s_endpgm
   %val = load <8 x i32>, <8 x i32> addrspace(1)* %in, align 32
   %bswap = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> %val) nounwind readnone
@@ -234,11 +234,11 @@ define amdgpu_kernel void @test_bswap_v8i32(<8 x i32> addrspace(1)* %out, <8 x i
 define amdgpu_kernel void @test_bswap_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %in) nounwind {
 ; SI-LABEL: test_bswap_i64:
 ; SI:       ; %bb.0:
-; SI-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x9
-; SI-NEXT:    s_mov_b32 s7, 0xf000
+; SI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
+; SI-NEXT:    s_mov_b32 s3, 0xf000
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    s_load_dwordx2 s[2:3], s[2:3], 0x0
-; SI-NEXT:    s_mov_b32 s6, -1
+; SI-NEXT:    s_load_dwordx2 s[6:7], s[6:7], 0x0
+; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    s_mov_b32 s19, 0xff0000
 ; SI-NEXT:    s_mov_b32 s9, 0
 ; SI-NEXT:    s_mov_b32 s15, 0xff00
@@ -247,34 +247,34 @@ define amdgpu_kernel void @test_bswap_i64(i64 addrspace(1)* %out, i64 addrspace(
 ; SI-NEXT:    s_mov_b32 s14, s9
 ; SI-NEXT:    s_mov_b32 s16, s9
 ; SI-NEXT:    s_mov_b32 s18, s9
-; SI-NEXT:    s_mov_b32 s4, s0
-; SI-NEXT:    s_mov_b32 s5, s1
+; SI-NEXT:    s_mov_b32 s0, s4
+; SI-NEXT:    s_mov_b32 s1, s5
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    v_mov_b32_e32 v0, s2
-; SI-NEXT:    v_alignbit_b32 v1, s3, v0, 24
-; SI-NEXT:    v_alignbit_b32 v0, s3, v0, 8
-; SI-NEXT:    s_lshr_b32 s8, s3, 24
-; SI-NEXT:    s_lshr_b32 s10, s3, 8
-; SI-NEXT:    s_lshl_b64 s[0:1], s[2:3], 8
-; SI-NEXT:    s_lshl_b64 s[20:21], s[2:3], 24
-; SI-NEXT:    s_lshl_b32 s17, s2, 24
-; SI-NEXT:    s_lshl_b32 s0, s2, 8
+; SI-NEXT:    v_mov_b32_e32 v0, s6
+; SI-NEXT:    v_alignbit_b32 v1, s7, v0, 24
+; SI-NEXT:    v_alignbit_b32 v0, s7, v0, 8
+; SI-NEXT:    s_lshr_b32 s8, s7, 24
+; SI-NEXT:    s_lshr_b32 s10, s7, 8
+; SI-NEXT:    s_lshl_b64 s[4:5], s[6:7], 8
+; SI-NEXT:    s_lshl_b64 s[20:21], s[6:7], 24
+; SI-NEXT:    s_lshl_b32 s17, s6, 24
+; SI-NEXT:    s_lshl_b32 s4, s6, 8
 ; SI-NEXT:    v_and_b32_e32 v1, s19, v1
 ; SI-NEXT:    v_and_b32_e32 v0, 0xff000000, v0
 ; SI-NEXT:    s_and_b32 s10, s10, s15
-; SI-NEXT:    s_and_b32 s13, s1, 0xff
+; SI-NEXT:    s_and_b32 s13, s5, 0xff
 ; SI-NEXT:    s_and_b32 s15, s21, s15
-; SI-NEXT:    s_and_b32 s19, s0, s19
+; SI-NEXT:    s_and_b32 s19, s4, s19
 ; SI-NEXT:    v_or_b32_e32 v0, v0, v1
-; SI-NEXT:    s_or_b64 s[0:1], s[10:11], s[8:9]
-; SI-NEXT:    s_or_b64 s[2:3], s[14:15], s[12:13]
+; SI-NEXT:    s_or_b64 s[4:5], s[10:11], s[8:9]
+; SI-NEXT:    s_or_b64 s[6:7], s[14:15], s[12:13]
 ; SI-NEXT:    s_or_b64 s[8:9], s[16:17], s[18:19]
-; SI-NEXT:    v_or_b32_e32 v0, s0, v0
-; SI-NEXT:    v_mov_b32_e32 v1, s1
-; SI-NEXT:    s_or_b64 s[0:1], s[8:9], s[2:3]
-; SI-NEXT:    v_or_b32_e32 v0, s0, v0
-; SI-NEXT:    v_or_b32_e32 v1, s1, v1
-; SI-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
+; SI-NEXT:    v_or_b32_e32 v0, s4, v0
+; SI-NEXT:    v_mov_b32_e32 v1, s5
+; SI-NEXT:    s_or_b64 s[4:5], s[8:9], s[6:7]
+; SI-NEXT:    v_or_b32_e32 v0, s4, v0
+; SI-NEXT:    v_or_b32_e32 v1, s5, v1
+; SI-NEXT:    buffer_store_dwordx2 v[0:1], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: test_bswap_i64:
@@ -328,47 +328,47 @@ define amdgpu_kernel void @test_bswap_i64(i64 addrspace(1)* %out, i64 addrspace(
 define amdgpu_kernel void @test_bswap_v2i64(<2 x i64> addrspace(1)* %out, <2 x i64> addrspace(1)* %in) nounwind {
 ; SI-LABEL: test_bswap_v2i64:
 ; SI:       ; %bb.0:
-; SI-NEXT:    s_load_dwordx4 s[8:11], s[0:1], 0x9
+; SI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
 ; SI-NEXT:    s_mov_b32 s3, 0xf000
 ; SI-NEXT:    s_mov_b32 s2, -1
 ; SI-NEXT:    s_mov_b32 s31, 0xff0000
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    s_load_dwordx4 s[4:7], s[10:11], 0x0
-; SI-NEXT:    s_mov_b32 s11, 0
+; SI-NEXT:    s_load_dwordx4 s[8:11], s[6:7], 0x0
+; SI-NEXT:    s_mov_b32 s7, 0
 ; SI-NEXT:    s_mov_b32 s22, 0xff000000
 ; SI-NEXT:    s_mov_b32 s27, 0xff00
 ; SI-NEXT:    s_movk_i32 s25, 0xff
-; SI-NEXT:    s_mov_b32 s13, s11
-; SI-NEXT:    s_mov_b32 s14, s11
-; SI-NEXT:    s_mov_b32 s16, s11
-; SI-NEXT:    s_mov_b32 s18, s11
-; SI-NEXT:    s_mov_b32 s20, s11
-; SI-NEXT:    s_mov_b32 s23, s11
-; SI-NEXT:    s_mov_b32 s24, s11
-; SI-NEXT:    s_mov_b32 s26, s11
-; SI-NEXT:    s_mov_b32 s28, s11
-; SI-NEXT:    s_mov_b32 s30, s11
-; SI-NEXT:    s_mov_b32 s0, s8
-; SI-NEXT:    s_mov_b32 s1, s9
+; SI-NEXT:    s_mov_b32 s13, s7
+; SI-NEXT:    s_mov_b32 s14, s7
+; SI-NEXT:    s_mov_b32 s16, s7
+; SI-NEXT:    s_mov_b32 s18, s7
+; SI-NEXT:    s_mov_b32 s20, s7
+; SI-NEXT:    s_mov_b32 s23, s7
+; SI-NEXT:    s_mov_b32 s24, s7
+; SI-NEXT:    s_mov_b32 s26, s7
+; SI-NEXT:    s_mov_b32 s28, s7
+; SI-NEXT:    s_mov_b32 s30, s7
+; SI-NEXT:    s_mov_b32 s0, s4
+; SI-NEXT:    s_mov_b32 s1, s5
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    v_mov_b32_e32 v0, s6
-; SI-NEXT:    v_alignbit_b32 v1, s7, v0, 24
-; SI-NEXT:    v_alignbit_b32 v0, s7, v0, 8
-; SI-NEXT:    s_lshr_b32 s10, s7, 24
-; SI-NEXT:    s_lshr_b32 s12, s7, 8
-; SI-NEXT:    s_lshl_b64 s[8:9], s[6:7], 8
-; SI-NEXT:    s_lshl_b64 s[32:33], s[6:7], 24
-; SI-NEXT:    s_lshl_b32 s19, s6, 24
-; SI-NEXT:    s_lshl_b32 s21, s6, 8
-; SI-NEXT:    v_mov_b32_e32 v2, s4
-; SI-NEXT:    v_alignbit_b32 v3, s5, v2, 24
-; SI-NEXT:    v_alignbit_b32 v2, s5, v2, 8
-; SI-NEXT:    s_lshr_b32 s32, s5, 8
-; SI-NEXT:    s_lshl_b64 s[6:7], s[4:5], 8
-; SI-NEXT:    s_and_b32 s15, s9, s25
-; SI-NEXT:    s_lshl_b64 s[8:9], s[4:5], 24
-; SI-NEXT:    s_lshl_b32 s29, s4, 24
-; SI-NEXT:    s_lshl_b32 s4, s4, 8
+; SI-NEXT:    v_mov_b32_e32 v0, s10
+; SI-NEXT:    v_alignbit_b32 v1, s11, v0, 24
+; SI-NEXT:    v_alignbit_b32 v0, s11, v0, 8
+; SI-NEXT:    s_lshr_b32 s6, s11, 24
+; SI-NEXT:    s_lshr_b32 s12, s11, 8
+; SI-NEXT:    s_lshl_b64 s[4:5], s[10:11], 8
+; SI-NEXT:    s_lshl_b64 s[32:33], s[10:11], 24
+; SI-NEXT:    s_lshl_b32 s19, s10, 24
+; SI-NEXT:    s_lshl_b32 s21, s10, 8
+; SI-NEXT:    v_mov_b32_e32 v2, s8
+; SI-NEXT:    v_alignbit_b32 v3, s9, v2, 24
+; SI-NEXT:    v_alignbit_b32 v2, s9, v2, 8
+; SI-NEXT:    s_lshr_b32 s32, s9, 8
+; SI-NEXT:    s_lshl_b64 s[10:11], s[8:9], 8
+; SI-NEXT:    s_and_b32 s15, s5, s25
+; SI-NEXT:    s_lshl_b64 s[4:5], s[8:9], 24
+; SI-NEXT:    s_lshl_b32 s29, s8, 24
+; SI-NEXT:    s_lshl_b32 s4, s8, 8
 ; SI-NEXT:    v_and_b32_e32 v1, s31, v1
 ; SI-NEXT:    v_and_b32_e32 v0, s22, v0
 ; SI-NEXT:    s_and_b32 s12, s12, s27
@@ -377,28 +377,28 @@ define amdgpu_kernel void @test_bswap_v2i64(<2 x i64> addrspace(1)* %out, <2 x i
 ; SI-NEXT:    v_and_b32_e32 v3, s31, v3
 ; SI-NEXT:    v_and_b32_e32 v2, s22, v2
 ; SI-NEXT:    s_and_b32 s22, s32, s27
-; SI-NEXT:    s_and_b32 s25, s7, s25
-; SI-NEXT:    s_and_b32 s27, s9, s27
+; SI-NEXT:    s_and_b32 s25, s11, s25
+; SI-NEXT:    s_and_b32 s27, s5, s27
 ; SI-NEXT:    s_and_b32 s31, s4, s31
 ; SI-NEXT:    v_or_b32_e32 v0, v0, v1
-; SI-NEXT:    s_or_b64 s[6:7], s[12:13], s[10:11]
-; SI-NEXT:    s_or_b64 s[8:9], s[16:17], s[14:15]
+; SI-NEXT:    s_or_b64 s[4:5], s[12:13], s[6:7]
+; SI-NEXT:    s_or_b64 s[10:11], s[16:17], s[14:15]
 ; SI-NEXT:    s_or_b64 s[12:13], s[18:19], s[20:21]
 ; SI-NEXT:    v_or_b32_e32 v1, v2, v3
-; SI-NEXT:    s_lshr_b32 s10, s5, 24
-; SI-NEXT:    s_or_b64 s[4:5], s[26:27], s[24:25]
+; SI-NEXT:    s_lshr_b32 s6, s9, 24
+; SI-NEXT:    s_or_b64 s[8:9], s[26:27], s[24:25]
 ; SI-NEXT:    s_or_b64 s[14:15], s[28:29], s[30:31]
-; SI-NEXT:    v_or_b32_e32 v0, s6, v0
-; SI-NEXT:    v_mov_b32_e32 v3, s7
-; SI-NEXT:    s_or_b64 s[6:7], s[12:13], s[8:9]
-; SI-NEXT:    s_or_b64 s[8:9], s[22:23], s[10:11]
-; SI-NEXT:    s_or_b64 s[4:5], s[14:15], s[4:5]
-; SI-NEXT:    v_or_b32_e32 v2, s6, v0
-; SI-NEXT:    v_or_b32_e32 v3, s7, v3
-; SI-NEXT:    v_or_b32_e32 v0, s8, v1
-; SI-NEXT:    v_mov_b32_e32 v1, s9
 ; SI-NEXT:    v_or_b32_e32 v0, s4, v0
-; SI-NEXT:    v_or_b32_e32 v1, s5, v1
+; SI-NEXT:    v_mov_b32_e32 v3, s5
+; SI-NEXT:    s_or_b64 s[4:5], s[12:13], s[10:11]
+; SI-NEXT:    s_or_b64 s[6:7], s[22:23], s[6:7]
+; SI-NEXT:    s_or_b64 s[8:9], s[14:15], s[8:9]
+; SI-NEXT:    v_or_b32_e32 v2, s4, v0
+; SI-NEXT:    v_or_b32_e32 v3, s5, v3
+; SI-NEXT:    v_or_b32_e32 v0, s6, v1
+; SI-NEXT:    v_mov_b32_e32 v1, s7
+; SI-NEXT:    v_or_b32_e32 v0, s8, v0
+; SI-NEXT:    v_or_b32_e32 v1, s9, v1
 ; SI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
diff --git a/llvm/test/CodeGen/AMDGPU/copy-illegal-type.ll b/llvm/test/CodeGen/AMDGPU/copy-illegal-type.ll
index ee16e7ebc8ed..3529db39dff2 100644
--- a/llvm/test/CodeGen/AMDGPU/copy-illegal-type.ll
+++ b/llvm/test/CodeGen/AMDGPU/copy-illegal-type.ll
@@ -314,26 +314,26 @@ define amdgpu_kernel void @test_copy_v4i8_extra_use(<4 x i8> addrspace(1)* %out0
 define amdgpu_kernel void @test_copy_v4i8_x2_extra_use(<4 x i8> addrspace(1)* %out0, <4 x i8> addrspace(1)* %out1, <4 x i8> addrspace(1)* %out2, <4 x i8> addrspace(1)* %in) nounwind {
 ; SI-LABEL: test_copy_v4i8_x2_extra_use:
 ; SI:       ; %bb.0:
-; SI-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x9
-; SI-NEXT:    s_mov_b32 s11, 0xf000
+; SI-NEXT:    s_load_dwordx8 s[4:11], s[0:1], 0x9
+; SI-NEXT:    s_mov_b32 s3, 0xf000
 ; SI-NEXT:    s_mov_b32 s14, 0
-; SI-NEXT:    s_mov_b32 s15, s11
+; SI-NEXT:    s_mov_b32 s15, s3
 ; SI-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    s_mov_b64 s[12:13], s[6:7]
+; SI-NEXT:    s_mov_b64 s[12:13], s[10:11]
 ; SI-NEXT:    v_mov_b32_e32 v1, 0
 ; SI-NEXT:    buffer_load_dword v0, v[0:1], s[12:15], 0 addr64
 ; SI-NEXT:    s_mov_b32 s16, 0xff00
 ; SI-NEXT:    s_movk_i32 s17, 0xff
-; SI-NEXT:    s_mov_b32 s10, -1
-; SI-NEXT:    s_mov_b32 s8, s4
-; SI-NEXT:    s_mov_b32 s9, s5
-; SI-NEXT:    s_mov_b32 s4, s2
-; SI-NEXT:    s_mov_b32 s5, s3
-; SI-NEXT:    s_mov_b32 s6, s10
-; SI-NEXT:    s_mov_b32 s7, s11
-; SI-NEXT:    s_mov_b32 s2, s10
-; SI-NEXT:    s_mov_b32 s3, s11
+; SI-NEXT:    s_mov_b32 s2, -1
+; SI-NEXT:    s_mov_b32 s0, s8
+; SI-NEXT:    s_mov_b32 s1, s9
+; SI-NEXT:    s_mov_b32 s8, s6
+; SI-NEXT:    s_mov_b32 s9, s7
+; SI-NEXT:    s_mov_b32 s10, s2
+; SI-NEXT:    s_mov_b32 s11, s3
+; SI-NEXT:    s_mov_b32 s6, s2
+; SI-NEXT:    s_mov_b32 s7, s3
 ; SI-NEXT:    s_waitcnt vmcnt(0)
 ; SI-NEXT:    v_add_i32_e32 v3, vcc, 9, v0
 ; SI-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
@@ -349,9 +349,9 @@ define amdgpu_kernel void @test_copy_v4i8_x2_extra_use(<4 x i8> addrspace(1)* %o
 ; SI-NEXT:    v_lshlrev_b32_e32 v1, 16, v1
 ; SI-NEXT:    v_or_b32_e32 v1, v1, v2
 ; SI-NEXT:    v_add_i32_e32 v1, vcc, 0x9000000, v1
+; SI-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; SI-NEXT:    buffer_store_dword v1, off, s[8:11], 0
 ; SI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
-; SI-NEXT:    buffer_store_dword v1, off, s[4:7], 0
-; SI-NEXT:    buffer_store_dword v0, off, s[8:11], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: test_copy_v4i8_x2_extra_use:
diff --git a/llvm/test/CodeGen/AMDGPU/dead-machine-elim-after-dead-lane.ll b/llvm/test/CodeGen/AMDGPU/dead-machine-elim-after-dead-lane.ll
new file mode 100644
index 000000000000..da4bce27b5c5
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/dead-machine-elim-after-dead-lane.ll
@@ -0,0 +1,28 @@
+; RUN: llc -march=amdgcn -verify-machineinstrs %s -o - | FileCheck %s
+
+; CHECK-LABEL: foo
+; CHECK-NOT: BUFFER_LOAD_DWORDX2_OFFSET
+; After dead code elimination, that buffer load should be eliminated finally
+; after dead lane detection.
+define amdgpu_kernel void @foo() {
+entry:
+  switch i8 undef, label %foo.exit [
+    i8 4, label %sw.bb4
+    i8 10, label %sw.bb10
+  ]
+
+sw.bb4:
+  %x = load i64, i64 addrspace(1)* undef, align 8
+  %c = sitofp i64 %x to float
+  %v = insertelement <2 x float> <float undef, float 0.000000e+00>, float %c, i32 0
+  br label %foo.exit
+
+sw.bb10:
+  unreachable
+
+foo.exit:
+  %agg = phi <2 x float> [ %v, %sw.bb4 ], [ zeroinitializer, %entry ]
+  %s = extractelement <2 x float> %agg, i32 1
+  store float %s, float addrspace(1)* undef, align 4
+  ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/dead-mi-use-same-intr.mir b/llvm/test/CodeGen/AMDGPU/dead-mi-use-same-intr.mir
deleted file mode 100644
index 1e97f5399668..000000000000
--- a/llvm/test/CodeGen/AMDGPU/dead-mi-use-same-intr.mir
+++ /dev/null
@@ -1,55 +0,0 @@
-# RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -run-pass dead-mi-elimination -o - %s | FileCheck -check-prefix=GCN %s
-
-# GCN-LABEL: name: dead_undef
-# GCN:      bb.0:
-# GCN-NEXT: S_ENDPGM 0
----
-name:            dead_undef
-tracksRegLiveness: true
-registers:
-  - { id: 0, class: vgpr_32 }
-  - { id: 1, class: vgpr_32 }
-  - { id: 2, class: vgpr_32 }
-body: |
-  bb.0:
-  %0 = IMPLICIT_DEF
-  %1 = IMPLICIT_DEF
-  dead %2:vgpr_32 = V_MAC_F32_e32 %0:vgpr_32, %1:vgpr_32, undef %2:vgpr_32, implicit $exec
-  S_ENDPGM 0
-
-# GCN-LABEL: name: dead_defined
-# GCN:      bb.0:
-# GCN-NEXT: S_ENDPGM 0
----
-name:            dead_defined
-tracksRegLiveness: true
-registers:
-  - { id: 0, class: vgpr_32 }
-  - { id: 1, class: vgpr_32 }
-  - { id: 2, class: vgpr_32 }
-body: |
-  bb.0:
-  %0 = IMPLICIT_DEF
-  %1 = IMPLICIT_DEF
-  %2 = IMPLICIT_DEF
-  dead %2:vgpr_32 = V_MAC_F32_e32 %0:vgpr_32, %1:vgpr_32, %2:vgpr_32, implicit $exec
-  S_ENDPGM 0
-
-# Probably this dead mac can be removed anyway.
-# GCN-LABEL: name: dead_def_live_use
-# GCN:      dead %2:vgpr_32 = V_MAC_F32_e32 %0, %1, %2, implicit $exec
----
-name:            dead_def_live_use
-tracksRegLiveness: true
-registers:
-  - { id: 0, class: vgpr_32 }
-  - { id: 1, class: vgpr_32 }
-  - { id: 2, class: vgpr_32 }
-body: |
-  bb.0:
-  %0 = IMPLICIT_DEF
-  %1 = IMPLICIT_DEF
-  %2 = IMPLICIT_DEF
-  GLOBAL_STORE_DWORD undef $vgpr0_vgpr1, %2, 0, 0, 0, 0, implicit $exec
-  dead %2:vgpr_32 = V_MAC_F32_e32 %0:vgpr_32, %1:vgpr_32, %2:vgpr_32, implicit $exec
-  S_ENDPGM 0
diff --git a/llvm/test/CodeGen/AMDGPU/idot8u.ll b/llvm/test/CodeGen/AMDGPU/idot8u.ll
index 2041fbb82460..79f827cc230c 100644
--- a/llvm/test/CodeGen/AMDGPU/idot8u.ll
+++ b/llvm/test/CodeGen/AMDGPU/idot8u.ll
@@ -254,17 +254,17 @@ entry:
 define amdgpu_kernel void @udot8_acc16(<8 x i4> addrspace(1)* %src1,
 ; GFX7-LABEL: udot8_acc16:
 ; GFX7:       ; %bb.0: ; %entry
-; GFX7-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
-; GFX7-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0xd
-; GFX7-NEXT:    s_mov_b32 s11, 0xf000
-; GFX7-NEXT:    s_mov_b32 s10, -1
+; GFX7-NEXT:    s_load_dwordx4 s[8:11], s[0:1], 0x9
+; GFX7-NEXT:    s_load_dwordx2 s[4:5], s[0:1], 0xd
+; GFX7-NEXT:    s_mov_b32 s7, 0xf000
+; GFX7-NEXT:    s_mov_b32 s6, -1
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX7-NEXT:    s_load_dword s0, s[4:5], 0x0
-; GFX7-NEXT:    buffer_load_ushort v0, off, s[8:11], 0
-; GFX7-NEXT:    s_load_dword s1, s[6:7], 0x0
+; GFX7-NEXT:    s_load_dword s0, s[8:9], 0x0
+; GFX7-NEXT:    buffer_load_ushort v0, off, s[4:7], 0
+; GFX7-NEXT:    s_load_dword s1, s[10:11], 0x0
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX7-NEXT:    s_lshr_b32 s2, s0, 28
-; GFX7-NEXT:    s_bfe_u32 s4, s0, 0x40018
+; GFX7-NEXT:    s_bfe_u32 s8, s0, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s15, s1, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s16, s1, 0x40014
 ; GFX7-NEXT:    s_bfe_u32 s17, s1, 0x40010
@@ -273,9 +273,9 @@ define amdgpu_kernel void @udot8_acc16(<8 x i4> addrspace(1)* %src1,
 ; GFX7-NEXT:    s_bfe_u32 s20, s1, 0x40004
 ; GFX7-NEXT:    s_lshr_b32 s14, s1, 28
 ; GFX7-NEXT:    s_and_b32 s1, s1, 15
-; GFX7-NEXT:    s_bfe_u32 s5, s0, 0x40014
-; GFX7-NEXT:    s_bfe_u32 s6, s0, 0x40010
-; GFX7-NEXT:    s_bfe_u32 s7, s0, 0x4000c
+; GFX7-NEXT:    s_bfe_u32 s9, s0, 0x40014
+; GFX7-NEXT:    s_bfe_u32 s10, s0, 0x40010
+; GFX7-NEXT:    s_bfe_u32 s11, s0, 0x4000c
 ; GFX7-NEXT:    s_bfe_u32 s12, s0, 0x40008
 ; GFX7-NEXT:    s_bfe_u32 s13, s0, 0x40004
 ; GFX7-NEXT:    s_and_b32 s0, s0, 15
@@ -290,13 +290,13 @@ define amdgpu_kernel void @udot8_acc16(<8 x i4> addrspace(1)* %src1,
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s0, v1, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s13, v2, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s12, v3, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s7, v4, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s6, v5, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s5, v6, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s4, v7, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s11, v4, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s10, v5, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s9, v6, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s8, v7, v0
 ; GFX7-NEXT:    v_mov_b32_e32 v1, s14
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s2, v1, v0
-; GFX7-NEXT:    buffer_store_short v0, off, s[8:11], 0
+; GFX7-NEXT:    buffer_store_short v0, off, s[4:7], 0
 ; GFX7-NEXT:    s_endpgm
 ;
 ; GFX8-LABEL: udot8_acc16:
@@ -556,17 +556,17 @@ entry:
 define amdgpu_kernel void @udot8_acc8(<8 x i4> addrspace(1)* %src1,
 ; GFX7-LABEL: udot8_acc8:
 ; GFX7:       ; %bb.0: ; %entry
-; GFX7-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
-; GFX7-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0xd
-; GFX7-NEXT:    s_mov_b32 s11, 0xf000
-; GFX7-NEXT:    s_mov_b32 s10, -1
+; GFX7-NEXT:    s_load_dwordx4 s[8:11], s[0:1], 0x9
+; GFX7-NEXT:    s_load_dwordx2 s[4:5], s[0:1], 0xd
+; GFX7-NEXT:    s_mov_b32 s7, 0xf000
+; GFX7-NEXT:    s_mov_b32 s6, -1
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX7-NEXT:    s_load_dword s0, s[4:5], 0x0
-; GFX7-NEXT:    buffer_load_ubyte v0, off, s[8:11], 0
-; GFX7-NEXT:    s_load_dword s1, s[6:7], 0x0
+; GFX7-NEXT:    s_load_dword s0, s[8:9], 0x0
+; GFX7-NEXT:    buffer_load_ubyte v0, off, s[4:7], 0
+; GFX7-NEXT:    s_load_dword s1, s[10:11], 0x0
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX7-NEXT:    s_lshr_b32 s2, s0, 28
-; GFX7-NEXT:    s_bfe_u32 s4, s0, 0x40018
+; GFX7-NEXT:    s_bfe_u32 s8, s0, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s15, s1, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s16, s1, 0x40014
 ; GFX7-NEXT:    s_bfe_u32 s17, s1, 0x40010
@@ -575,9 +575,9 @@ define amdgpu_kernel void @udot8_acc8(<8 x i4> addrspace(1)* %src1,
 ; GFX7-NEXT:    s_bfe_u32 s20, s1, 0x40004
 ; GFX7-NEXT:    s_lshr_b32 s14, s1, 28
 ; GFX7-NEXT:    s_and_b32 s1, s1, 15
-; GFX7-NEXT:    s_bfe_u32 s5, s0, 0x40014
-; GFX7-NEXT:    s_bfe_u32 s6, s0, 0x40010
-; GFX7-NEXT:    s_bfe_u32 s7, s0, 0x4000c
+; GFX7-NEXT:    s_bfe_u32 s9, s0, 0x40014
+; GFX7-NEXT:    s_bfe_u32 s10, s0, 0x40010
+; GFX7-NEXT:    s_bfe_u32 s11, s0, 0x4000c
 ; GFX7-NEXT:    s_bfe_u32 s12, s0, 0x40008
 ; GFX7-NEXT:    s_bfe_u32 s13, s0, 0x40004
 ; GFX7-NEXT:    s_and_b32 s0, s0, 15
@@ -592,13 +592,13 @@ define amdgpu_kernel void @udot8_acc8(<8 x i4> addrspace(1)* %src1,
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s0, v1, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s13, v2, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s12, v3, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s7, v4, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s6, v5, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s5, v6, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s4, v7, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s11, v4, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s10, v5, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s9, v6, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s8, v7, v0
 ; GFX7-NEXT:    v_mov_b32_e32 v1, s14
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s2, v1, v0
-; GFX7-NEXT:    buffer_store_byte v0, off, s[8:11], 0
+; GFX7-NEXT:    buffer_store_byte v0, off, s[4:7], 0
 ; GFX7-NEXT:    s_endpgm
 ;
 ; GFX8-LABEL: udot8_acc8:
@@ -858,17 +858,17 @@ entry:
 define amdgpu_kernel void @udot8_acc4(<8 x i4> addrspace(1)* %src1,
 ; GFX7-LABEL: udot8_acc4:
 ; GFX7:       ; %bb.0: ; %entry
-; GFX7-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
-; GFX7-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0xd
-; GFX7-NEXT:    s_mov_b32 s11, 0xf000
-; GFX7-NEXT:    s_mov_b32 s10, -1
+; GFX7-NEXT:    s_load_dwordx4 s[8:11], s[0:1], 0x9
+; GFX7-NEXT:    s_load_dwordx2 s[4:5], s[0:1], 0xd
+; GFX7-NEXT:    s_mov_b32 s7, 0xf000
+; GFX7-NEXT:    s_mov_b32 s6, -1
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX7-NEXT:    s_load_dword s0, s[4:5], 0x0
-; GFX7-NEXT:    buffer_load_ubyte v0, off, s[8:11], 0
-; GFX7-NEXT:    s_load_dword s1, s[6:7], 0x0
+; GFX7-NEXT:    s_load_dword s0, s[8:9], 0x0
+; GFX7-NEXT:    buffer_load_ubyte v0, off, s[4:7], 0
+; GFX7-NEXT:    s_load_dword s1, s[10:11], 0x0
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX7-NEXT:    s_lshr_b32 s2, s0, 28
-; GFX7-NEXT:    s_bfe_u32 s4, s0, 0x40018
+; GFX7-NEXT:    s_bfe_u32 s8, s0, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s15, s1, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s16, s1, 0x40014
 ; GFX7-NEXT:    s_bfe_u32 s17, s1, 0x40010
@@ -877,9 +877,9 @@ define amdgpu_kernel void @udot8_acc4(<8 x i4> addrspace(1)* %src1,
 ; GFX7-NEXT:    s_bfe_u32 s20, s1, 0x40004
 ; GFX7-NEXT:    s_lshr_b32 s14, s1, 28
 ; GFX7-NEXT:    s_and_b32 s1, s1, 15
-; GFX7-NEXT:    s_bfe_u32 s5, s0, 0x40014
-; GFX7-NEXT:    s_bfe_u32 s6, s0, 0x40010
-; GFX7-NEXT:    s_bfe_u32 s7, s0, 0x4000c
+; GFX7-NEXT:    s_bfe_u32 s9, s0, 0x40014
+; GFX7-NEXT:    s_bfe_u32 s10, s0, 0x40010
+; GFX7-NEXT:    s_bfe_u32 s11, s0, 0x4000c
 ; GFX7-NEXT:    s_bfe_u32 s12, s0, 0x40008
 ; GFX7-NEXT:    s_bfe_u32 s13, s0, 0x40004
 ; GFX7-NEXT:    s_and_b32 s0, s0, 15
@@ -894,14 +894,14 @@ define amdgpu_kernel void @udot8_acc4(<8 x i4> addrspace(1)* %src1,
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s0, v1, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s13, v2, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s12, v3, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s7, v4, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s6, v5, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s5, v6, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s4, v7, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s11, v4, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s10, v5, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s9, v6, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s8, v7, v0
 ; GFX7-NEXT:    v_mov_b32_e32 v1, s14
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s2, v1, v0
 ; GFX7-NEXT:    v_and_b32_e32 v0, 15, v0
-; GFX7-NEXT:    buffer_store_byte v0, off, s[8:11], 0
+; GFX7-NEXT:    buffer_store_byte v0, off, s[4:7], 0
 ; GFX7-NEXT:    s_endpgm
 ;
 ; GFX8-LABEL: udot8_acc4:
@@ -1157,17 +1157,17 @@ entry:
 define amdgpu_kernel void @udot8_CommutationInsideMAD(<8 x i4> addrspace(1)* %src1,
 ; GFX7-LABEL: udot8_CommutationInsideMAD:
 ; GFX7:       ; %bb.0: ; %entry
-; GFX7-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
-; GFX7-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0xd
-; GFX7-NEXT:    s_mov_b32 s11, 0xf000
-; GFX7-NEXT:    s_mov_b32 s10, -1
+; GFX7-NEXT:    s_load_dwordx4 s[8:11], s[0:1], 0x9
+; GFX7-NEXT:    s_load_dwordx2 s[4:5], s[0:1], 0xd
+; GFX7-NEXT:    s_mov_b32 s7, 0xf000
+; GFX7-NEXT:    s_mov_b32 s6, -1
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX7-NEXT:    s_load_dword s0, s[4:5], 0x0
-; GFX7-NEXT:    buffer_load_ubyte v0, off, s[8:11], 0
-; GFX7-NEXT:    s_load_dword s1, s[6:7], 0x0
+; GFX7-NEXT:    s_load_dword s0, s[8:9], 0x0
+; GFX7-NEXT:    buffer_load_ubyte v0, off, s[4:7], 0
+; GFX7-NEXT:    s_load_dword s1, s[10:11], 0x0
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX7-NEXT:    s_lshr_b32 s2, s0, 28
-; GFX7-NEXT:    s_bfe_u32 s4, s0, 0x40018
+; GFX7-NEXT:    s_bfe_u32 s8, s0, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s15, s1, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s16, s1, 0x40014
 ; GFX7-NEXT:    s_bfe_u32 s17, s1, 0x40010
@@ -1176,9 +1176,9 @@ define amdgpu_kernel void @udot8_CommutationInsideMAD(<8 x i4> addrspace(1)* %sr
 ; GFX7-NEXT:    s_bfe_u32 s20, s1, 0x40004
 ; GFX7-NEXT:    s_lshr_b32 s14, s1, 28
 ; GFX7-NEXT:    s_and_b32 s1, s1, 15
-; GFX7-NEXT:    s_bfe_u32 s5, s0, 0x40014
-; GFX7-NEXT:    s_bfe_u32 s6, s0, 0x40010
-; GFX7-NEXT:    s_bfe_u32 s7, s0, 0x4000c
+; GFX7-NEXT:    s_bfe_u32 s9, s0, 0x40014
+; GFX7-NEXT:    s_bfe_u32 s10, s0, 0x40010
+; GFX7-NEXT:    s_bfe_u32 s11, s0, 0x4000c
 ; GFX7-NEXT:    s_bfe_u32 s12, s0, 0x40008
 ; GFX7-NEXT:    s_bfe_u32 s13, s0, 0x40004
 ; GFX7-NEXT:    s_and_b32 s0, s0, 15
@@ -1193,14 +1193,14 @@ define amdgpu_kernel void @udot8_CommutationInsideMAD(<8 x i4> addrspace(1)* %sr
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s0, v1, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s13, v2, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s12, v3, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s7, v4, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s6, v5, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s5, v6, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s4, v7, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s11, v4, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s10, v5, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s9, v6, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s8, v7, v0
 ; GFX7-NEXT:    v_mov_b32_e32 v1, s14
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s2, v1, v0
 ; GFX7-NEXT:    v_and_b32_e32 v0, 15, v0
-; GFX7-NEXT:    buffer_store_byte v0, off, s[8:11], 0
+; GFX7-NEXT:    buffer_store_byte v0, off, s[4:7], 0
 ; GFX7-NEXT:    s_endpgm
 ;
 ; GFX8-LABEL: udot8_CommutationInsideMAD:
@@ -2645,17 +2645,17 @@ entry:
 define amdgpu_kernel void @udot8_acc4_vecMul(<8 x i4> addrspace(1)* %src1,
 ; GFX7-LABEL: udot8_acc4_vecMul:
 ; GFX7:       ; %bb.0: ; %entry
-; GFX7-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x9
-; GFX7-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0xd
-; GFX7-NEXT:    s_mov_b32 s11, 0xf000
-; GFX7-NEXT:    s_mov_b32 s10, -1
+; GFX7-NEXT:    s_load_dwordx4 s[8:11], s[0:1], 0x9
+; GFX7-NEXT:    s_load_dwordx2 s[4:5], s[0:1], 0xd
+; GFX7-NEXT:    s_mov_b32 s7, 0xf000
+; GFX7-NEXT:    s_mov_b32 s6, -1
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX7-NEXT:    s_load_dword s0, s[4:5], 0x0
-; GFX7-NEXT:    buffer_load_ubyte v0, off, s[8:11], 0
-; GFX7-NEXT:    s_load_dword s1, s[6:7], 0x0
+; GFX7-NEXT:    s_load_dword s0, s[8:9], 0x0
+; GFX7-NEXT:    buffer_load_ubyte v0, off, s[4:7], 0
+; GFX7-NEXT:    s_load_dword s1, s[10:11], 0x0
 ; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX7-NEXT:    s_lshr_b32 s2, s0, 28
-; GFX7-NEXT:    s_bfe_u32 s4, s0, 0x40018
+; GFX7-NEXT:    s_bfe_u32 s8, s0, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s15, s1, 0x40018
 ; GFX7-NEXT:    s_bfe_u32 s16, s1, 0x40014
 ; GFX7-NEXT:    s_bfe_u32 s17, s1, 0x40010
@@ -2664,9 +2664,9 @@ define amdgpu_kernel void @udot8_acc4_vecMul(<8 x i4> addrspace(1)* %src1,
 ; GFX7-NEXT:    s_bfe_u32 s20, s1, 0x40004
 ; GFX7-NEXT:    s_lshr_b32 s14, s1, 28
 ; GFX7-NEXT:    s_and_b32 s1, s1, 15
-; GFX7-NEXT:    s_bfe_u32 s5, s0, 0x40014
-; GFX7-NEXT:    s_bfe_u32 s6, s0, 0x40010
-; GFX7-NEXT:    s_bfe_u32 s7, s0, 0x4000c
+; GFX7-NEXT:    s_bfe_u32 s9, s0, 0x40014
+; GFX7-NEXT:    s_bfe_u32 s10, s0, 0x40010
+; GFX7-NEXT:    s_bfe_u32 s11, s0, 0x4000c
 ; GFX7-NEXT:    s_bfe_u32 s12, s0, 0x40008
 ; GFX7-NEXT:    s_bfe_u32 s13, s0, 0x40004
 ; GFX7-NEXT:    s_and_b32 s0, s0, 15
@@ -2681,14 +2681,14 @@ define amdgpu_kernel void @udot8_acc4_vecMul(<8 x i4> addrspace(1)* %src1,
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s0, v1, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s13, v2, v0
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s12, v3, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s7, v4, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s6, v5, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s5, v6, v0
-; GFX7-NEXT:    v_mad_u32_u24 v0, s4, v7, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s11, v4, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s10, v5, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s9, v6, v0
+; GFX7-NEXT:    v_mad_u32_u24 v0, s8, v7, v0
 ; GFX7-NEXT:    v_mov_b32_e32 v1, s14
 ; GFX7-NEXT:    v_mad_u32_u24 v0, s2, v1, v0
 ; GFX7-NEXT:    v_and_b32_e32 v0, 15, v0
-; GFX7-NEXT:    buffer_store_byte v0, off, s[8:11], 0
+; GFX7-NEXT:    buffer_store_byte v0, off, s[4:7], 0
 ; GFX7-NEXT:    s_endpgm
 ;
 ; GFX8-LABEL: udot8_acc4_vecMul:
diff --git a/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll b/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll
index 4c45856ce1dc..bceb144b06fa 100644
--- a/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll
+++ b/llvm/test/CodeGen/AMDGPU/insert_vector_elt.ll
@@ -1617,31 +1617,31 @@ define amdgpu_kernel void @dynamic_insertelement_v4f64(<4 x double> addrspace(1)
 define amdgpu_kernel void @dynamic_insertelement_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %a, i32 %b) #0 {
 ; SI-LABEL: dynamic_insertelement_v8f64:
 ; SI:       ; %bb.0:
-; SI-NEXT:    s_load_dwordx2 s[24:25], s[4:5], 0x0
-; SI-NEXT:    s_load_dwordx16 s[8:23], s[4:5], 0x10
+; SI-NEXT:    s_load_dwordx2 s[8:9], s[4:5], 0x0
+; SI-NEXT:    s_load_dwordx16 s[12:27], s[4:5], 0x10
 ; SI-NEXT:    s_load_dword s4, s[4:5], 0x20
 ; SI-NEXT:    v_mov_b32_e32 v16, 64
-; SI-NEXT:    s_mov_b32 s27, 0x100f000
-; SI-NEXT:    s_mov_b32 s26, -1
+; SI-NEXT:    s_mov_b32 s11, 0x100f000
+; SI-NEXT:    s_mov_b32 s10, -1
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
-; SI-NEXT:    v_mov_b32_e32 v0, s8
+; SI-NEXT:    v_mov_b32_e32 v0, s12
 ; SI-NEXT:    s_and_b32 s4, s4, 7
 ; SI-NEXT:    s_lshl_b32 s4, s4, 3
-; SI-NEXT:    v_mov_b32_e32 v1, s9
-; SI-NEXT:    v_mov_b32_e32 v2, s10
-; SI-NEXT:    v_mov_b32_e32 v3, s11
-; SI-NEXT:    v_mov_b32_e32 v4, s12
-; SI-NEXT:    v_mov_b32_e32 v5, s13
-; SI-NEXT:    v_mov_b32_e32 v6, s14
-; SI-NEXT:    v_mov_b32_e32 v7, s15
-; SI-NEXT:    v_mov_b32_e32 v8, s16
-; SI-NEXT:    v_mov_b32_e32 v9, s17
-; SI-NEXT:    v_mov_b32_e32 v10, s18
-; SI-NEXT:    v_mov_b32_e32 v11, s19
-; SI-NEXT:    v_mov_b32_e32 v12, s20
-; SI-NEXT:    v_mov_b32_e32 v13, s21
-; SI-NEXT:    v_mov_b32_e32 v14, s22
-; SI-NEXT:    v_mov_b32_e32 v15, s23
+; SI-NEXT:    v_mov_b32_e32 v1, s13
+; SI-NEXT:    v_mov_b32_e32 v2, s14
+; SI-NEXT:    v_mov_b32_e32 v3, s15
+; SI-NEXT:    v_mov_b32_e32 v4, s16
+; SI-NEXT:    v_mov_b32_e32 v5, s17
+; SI-NEXT:    v_mov_b32_e32 v6, s18
+; SI-NEXT:    v_mov_b32_e32 v7, s19
+; SI-NEXT:    v_mov_b32_e32 v8, s20
+; SI-NEXT:    v_mov_b32_e32 v9, s21
+; SI-NEXT:    v_mov_b32_e32 v10, s22
+; SI-NEXT:    v_mov_b32_e32 v11, s23
+; SI-NEXT:    v_mov_b32_e32 v12, s24
+; SI-NEXT:    v_mov_b32_e32 v13, s25
+; SI-NEXT:    v_mov_b32_e32 v14, s26
+; SI-NEXT:    v_mov_b32_e32 v15, s27
 ; SI-NEXT:    buffer_store_dwordx4 v[12:15], off, s[0:3], s7 offset:112
 ; SI-NEXT:    buffer_store_dwordx4 v[8:11], off, s[0:3], s7 offset:96
 ; SI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[0:3], s7 offset:80
@@ -1655,39 +1655,40 @@ define amdgpu_kernel void @dynamic_insertelement_v8f64(<8 x double> addrspace(1)
 ; SI-NEXT:    buffer_load_dwordx4 v[8:11], off, s[0:3], s7 offset:96
 ; SI-NEXT:    buffer_load_dwordx4 v[12:15], off, s[0:3], s7 offset:112
 ; SI-NEXT:    s_waitcnt vmcnt(0)
-; SI-NEXT:    buffer_store_dwordx4 v[12:15], off, s[24:27], 0 offset:48
-; SI-NEXT:    buffer_store_dwordx4 v[8:11], off, s[24:27], 0 offset:32
-; SI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[24:27], 0 offset:16
-; SI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[24:27], 0
+; SI-NEXT:    buffer_store_dwordx4 v[12:15], off, s[8:11], 0 offset:48
+; SI-NEXT:    buffer_store_dwordx4 v[8:11], off, s[8:11], 0 offset:32
+; SI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[8:11], 0 offset:16
+; SI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[8:11], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: dynamic_insertelement_v8f64:
 ; VI:       ; %bb.0:
-; VI-NEXT:    s_load_dwordx2 s[24:25], s[4:5], 0x0
-; VI-NEXT:    s_load_dwordx16 s[8:23], s[4:5], 0x40
+; VI-NEXT:    s_load_dwordx2 s[8:9], s[4:5], 0x0
+; VI-NEXT:    s_load_dwordx16 s[12:27], s[4:5], 0x40
 ; VI-NEXT:    s_load_dword s4, s[4:5], 0x80
 ; VI-NEXT:    v_mov_b32_e32 v16, 64
-; VI-NEXT:    s_mov_b32 s27, 0x1100f000
-; VI-NEXT:    s_mov_b32 s26, -1
+; VI-NEXT:    s_mov_b32 s11, 0x1100f000
+; VI-NEXT:    s_mov_b32 s10, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v0, s8
+; VI-NEXT:    v_mov_b32_e32 v0, s12
 ; VI-NEXT:    s_and_b32 s4, s4, 7
 ; VI-NEXT:    s_lshl_b32 s4, s4, 3
-; VI-NEXT:    v_mov_b32_e32 v1, s9
-; VI-NEXT:    v_mov_b32_e32 v2, s10
-; VI-NEXT:    v_mov_b32_e32 v3, s11
-; VI-NEXT:    v_mov_b32_e32 v4, s12
-; VI-NEXT:    v_mov_b32_e32 v5, s13
-; VI-NEXT:    v_mov_b32_e32 v6, s14
-; VI-NEXT:    v_mov_b32_e32 v7, s15
-; VI-NEXT:    v_mov_b32_e32 v8, s16
-; VI-NEXT:    v_mov_b32_e32 v9, s17
-; VI-NEXT:    v_mov_b32_e32 v10, s18
-; VI-NEXT:    v_mov_b32_e32 v11, s19
-; VI-NEXT:    v_mov_b32_e32 v12, s20
-; VI-NEXT:    v_mov_b32_e32 v13, s21
-; VI-NEXT:    v_mov_b32_e32 v14, s22
-; VI-NEXT:    v_mov_b32_e32 v15, s23
+; VI-NEXT:    v_mov_b32_e32 v1, s13
+; VI-NEXT:    v_mov_b32_e32 v2, s14
+; VI-NEXT:    v_mov_b32_e32 v3, s15
+; VI-NEXT:    v_mov_b32_e32 v4, s16
+; VI-NEXT:    v_mov_b32_e32 v5, s17
+; VI-NEXT:    v_mov_b32_e32 v6, s18
+; VI-NEXT:    v_mov_b32_e32 v7, s19
+; VI-NEXT:    v_mov_b32_e32 v8, s20
+; VI-NEXT:    v_mov_b32_e32 v9, s21
+; VI-NEXT:    v_mov_b32_e32 v10, s22
+; VI-NEXT:    v_mov_b32_e32 v11, s23
+; VI-NEXT:    v_mov_b32_e32 v12, s24
+; VI-NEXT:    v_mov_b32_e32 v13, s25
+; VI-NEXT:    v_mov_b32_e32 v14, s26
+; VI-NEXT:    v_mov_b32_e32 v15, s27
+; VI-NEXT:    buffer_store_dwordx4 v[8:11], off, s[0:3], s7 offset:96
 ; VI-NEXT:    buffer_store_dwordx4 v[12:15], off, s[0:3], s7 offset:112
 ; VI-NEXT:    buffer_store_dwordx4 v[8:11], off, s[0:3], s7 offset:96
 ; VI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[0:3], s7 offset:80
@@ -1701,10 +1702,10 @@ define amdgpu_kernel void @dynamic_insertelement_v8f64(<8 x double> addrspace(1)
 ; VI-NEXT:    buffer_load_dwordx4 v[8:11], off, s[0:3], s7 offset:96
 ; VI-NEXT:    buffer_load_dwordx4 v[12:15], off, s[0:3], s7 offset:112
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    buffer_store_dwordx4 v[12:15], off, s[24:27], 0 offset:48
-; VI-NEXT:    buffer_store_dwordx4 v[8:11], off, s[24:27], 0 offset:32
-; VI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[24:27], 0 offset:16
-; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[24:27], 0
+; VI-NEXT:    buffer_store_dwordx4 v[12:15], off, s[8:11], 0 offset:48
+; VI-NEXT:    buffer_store_dwordx4 v[8:11], off, s[8:11], 0 offset:32
+; VI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[8:11], 0 offset:16
+; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[8:11], 0
 ; VI-NEXT:    s_endpgm
   %vecins = insertelement <8 x double> %a, double 8.0, i32 %b
   store <8 x double> %vecins, <8 x double> addrspace(1)* %out, align 16
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.ordered.swap.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.ordered.swap.ll
index acb1133c6a0b..924a4cd0414b 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.ordered.swap.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.ordered.swap.ll
@@ -15,13 +15,13 @@ define amdgpu_cs float @ds_ordered_swap(i32 addrspace(2)* inreg %gds, i32 %value
 }
 
 ; FUNC-LABEL: {{^}}ds_ordered_swap_conditional:
-; GCN: v_cmp_ne_u32_e32 vcc, 0, v0
+; GCN: v_cmp_ne_u32_e32 vcc, 0, v[[VALUE:[0-9]+]]
 ; GCN: s_and_saveexec_b64 s[[SAVED:\[[0-9]+:[0-9]+\]]], vcc
 ; // We have to use s_cbranch, because ds_ordered_count has side effects with EXEC=0
 ; GCN: s_cbranch_execz [[BB:BB._.]]
 ; GCN: s_mov_b32 m0, s0
 ; VIGFX9-NEXT: s_nop 0
-; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v0 offset:4868 gds
+; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v[[VALUE]] offset:4868 gds
 ; GCN-NEXT: [[BB]]:
 ; // Wait for expcnt(0) before modifying EXEC
 ; GCN-NEXT: s_waitcnt expcnt(0)
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.round.f64.ll b/llvm/test/CodeGen/AMDGPU/llvm.round.f64.ll
index 09d745ae989f..8d04002d2770 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.round.f64.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.round.f64.ll
@@ -393,47 +393,47 @@ define amdgpu_kernel void @round_v4f64(<4 x double> addrspace(1)* %out, <4 x dou
 ;
 ; CI-LABEL: round_v4f64:
 ; CI:       ; %bb.0:
-; CI-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0x9
-; CI-NEXT:    s_load_dwordx8 s[0:7], s[0:1], 0x11
-; CI-NEXT:    s_brev_b32 s12, -2
+; CI-NEXT:    s_load_dwordx2 s[4:5], s[0:1], 0x9
+; CI-NEXT:    s_load_dwordx8 s[8:15], s[0:1], 0x11
+; CI-NEXT:    s_brev_b32 s2, -2
 ; CI-NEXT:    v_mov_b32_e32 v12, 0x3ff00000
-; CI-NEXT:    s_mov_b32 s11, 0xf000
-; CI-NEXT:    s_mov_b32 s10, -1
+; CI-NEXT:    s_mov_b32 s7, 0xf000
+; CI-NEXT:    s_mov_b32 s6, -1
 ; CI-NEXT:    s_waitcnt lgkmcnt(0)
-; CI-NEXT:    v_trunc_f64_e32 v[0:1], s[2:3]
-; CI-NEXT:    v_mov_b32_e32 v4, s3
-; CI-NEXT:    v_add_f64 v[2:3], s[2:3], -v[0:1]
-; CI-NEXT:    v_bfi_b32 v4, s12, v12, v4
+; CI-NEXT:    v_trunc_f64_e32 v[0:1], s[10:11]
+; CI-NEXT:    v_mov_b32_e32 v4, s11
+; CI-NEXT:    v_add_f64 v[2:3], s[10:11], -v[0:1]
+; CI-NEXT:    v_bfi_b32 v4, s2, v12, v4
 ; CI-NEXT:    v_cmp_ge_f64_e64 vcc, |v[2:3]|, 0.5
-; CI-NEXT:    v_trunc_f64_e32 v[8:9], s[0:1]
+; CI-NEXT:    v_trunc_f64_e32 v[8:9], s[8:9]
 ; CI-NEXT:    v_cndmask_b32_e32 v3, 0, v4, vcc
 ; CI-NEXT:    v_mov_b32_e32 v2, 0
 ; CI-NEXT:    v_add_f64 v[2:3], v[0:1], v[2:3]
-; CI-NEXT:    v_add_f64 v[0:1], s[0:1], -v[8:9]
-; CI-NEXT:    v_mov_b32_e32 v4, s1
+; CI-NEXT:    v_add_f64 v[0:1], s[8:9], -v[8:9]
+; CI-NEXT:    v_mov_b32_e32 v4, s9
 ; CI-NEXT:    v_cmp_ge_f64_e64 vcc, |v[0:1]|, 0.5
-; CI-NEXT:    v_bfi_b32 v4, s12, v12, v4
+; CI-NEXT:    v_bfi_b32 v4, s2, v12, v4
 ; CI-NEXT:    v_cndmask_b32_e32 v1, 0, v4, vcc
-; CI-NEXT:    v_trunc_f64_e32 v[4:5], s[6:7]
-; CI-NEXT:    v_mov_b32_e32 v10, s7
-; CI-NEXT:    v_add_f64 v[6:7], s[6:7], -v[4:5]
-; CI-NEXT:    v_bfi_b32 v10, s12, v12, v10
+; CI-NEXT:    v_trunc_f64_e32 v[4:5], s[14:15]
+; CI-NEXT:    v_mov_b32_e32 v10, s15
+; CI-NEXT:    v_add_f64 v[6:7], s[14:15], -v[4:5]
+; CI-NEXT:    v_bfi_b32 v10, s2, v12, v10
 ; CI-NEXT:    v_cmp_ge_f64_e64 vcc, |v[6:7]|, 0.5
 ; CI-NEXT:    v_mov_b32_e32 v6, 0
 ; CI-NEXT:    v_cndmask_b32_e32 v7, 0, v10, vcc
-; CI-NEXT:    v_trunc_f64_e32 v[10:11], s[4:5]
+; CI-NEXT:    v_trunc_f64_e32 v[10:11], s[12:13]
 ; CI-NEXT:    v_add_f64 v[6:7], v[4:5], v[6:7]
-; CI-NEXT:    v_add_f64 v[4:5], s[4:5], -v[10:11]
-; CI-NEXT:    v_mov_b32_e32 v13, s5
+; CI-NEXT:    v_add_f64 v[4:5], s[12:13], -v[10:11]
+; CI-NEXT:    v_mov_b32_e32 v13, s13
 ; CI-NEXT:    v_cmp_ge_f64_e64 vcc, |v[4:5]|, 0.5
-; CI-NEXT:    v_bfi_b32 v12, s12, v12, v13
+; CI-NEXT:    v_bfi_b32 v12, s2, v12, v13
 ; CI-NEXT:    v_mov_b32_e32 v0, 0
 ; CI-NEXT:    v_cndmask_b32_e32 v5, 0, v12, vcc
 ; CI-NEXT:    v_mov_b32_e32 v4, 0
 ; CI-NEXT:    v_add_f64 v[4:5], v[10:11], v[4:5]
 ; CI-NEXT:    v_add_f64 v[0:1], v[8:9], v[0:1]
-; CI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[8:11], 0 offset:16
-; CI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[8:11], 0
+; CI-NEXT:    buffer_store_dwordx4 v[4:7], off, s[4:7], 0 offset:16
+; CI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[4:7], 0
 ; CI-NEXT:    s_endpgm
   %result = call <4 x double> @llvm.round.v4f64(<4 x double> %in) #1
   store <4 x double> %result, <4 x double> addrspace(1)* %out
diff --git a/llvm/test/CodeGen/AMDGPU/loop_break.ll b/llvm/test/CodeGen/AMDGPU/loop_break.ll
index 684b183de690..ae4578511246 100644
--- a/llvm/test/CodeGen/AMDGPU/loop_break.ll
+++ b/llvm/test/CodeGen/AMDGPU/loop_break.ll
@@ -26,9 +26,9 @@
 ; GCN:      s_mov_b64         [[ACCUM_MASK:s\[[0-9]+:[0-9]+\]]], 0{{$}}
 
 ; GCN: [[LOOP_ENTRY:BB[0-9]+_[0-9]+]]: ; %bb1
-; GCN:     s_add_i32 s4, s4, 1
+; GCN:     s_add_i32 s6, s6, 1
 ; GCN:     s_or_b64 [[INNER_MASK:s\[[0-9]+:[0-9]+\]]], [[INNER_MASK]], exec
-; GCN:     s_cmp_gt_i32 s4, -1
+; GCN:     s_cmp_gt_i32 s6, -1
 ; GCN:     s_cbranch_scc1   [[FLOW:BB[0-9]+_[0-9]+]]
 
 ; GCN: ; %bb4
diff --git a/llvm/test/CodeGen/AMDGPU/select.f16.ll b/llvm/test/CodeGen/AMDGPU/select.f16.ll
index 16f48ae9df34..16125bbcd78b 100644
--- a/llvm/test/CodeGen/AMDGPU/select.f16.ll
+++ b/llvm/test/CodeGen/AMDGPU/select.f16.ll
@@ -395,28 +395,28 @@ define amdgpu_kernel void @select_v2f16(
 ; SI-LABEL: select_v2f16:
 ; SI:       ; %bb.0: ; %entry
 ; SI-NEXT:    s_load_dwordx8 s[4:11], s[0:1], 0x9
-; SI-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x11
-; SI-NEXT:    s_mov_b32 s15, 0xf000
-; SI-NEXT:    s_mov_b32 s14, -1
-; SI-NEXT:    s_mov_b32 s22, s14
+; SI-NEXT:    s_load_dwordx2 s[12:13], s[0:1], 0x11
+; SI-NEXT:    s_mov_b32 s3, 0xf000
+; SI-NEXT:    s_mov_b32 s2, -1
+; SI-NEXT:    s_mov_b32 s22, s2
 ; SI-NEXT:    s_waitcnt lgkmcnt(0)
 ; SI-NEXT:    s_mov_b32 s16, s10
 ; SI-NEXT:    s_mov_b32 s17, s11
-; SI-NEXT:    s_mov_b32 s10, s14
-; SI-NEXT:    s_mov_b32 s11, s15
+; SI-NEXT:    s_mov_b32 s10, s2
+; SI-NEXT:    s_mov_b32 s11, s3
 ; SI-NEXT:    s_mov_b32 s20, s6
 ; SI-NEXT:    s_mov_b32 s21, s7
-; SI-NEXT:    s_mov_b32 s23, s15
-; SI-NEXT:    s_mov_b32 s2, s14
-; SI-NEXT:    s_mov_b32 s3, s15
+; SI-NEXT:    s_mov_b32 s23, s3
+; SI-NEXT:    s_mov_b32 s14, s2
+; SI-NEXT:    s_mov_b32 s15, s3
 ; SI-NEXT:    buffer_load_dword v0, off, s[20:23], 0
-; SI-NEXT:    s_mov_b32 s18, s14
-; SI-NEXT:    s_mov_b32 s19, s15
+; SI-NEXT:    s_mov_b32 s18, s2
+; SI-NEXT:    s_mov_b32 s19, s3
 ; SI-NEXT:    buffer_load_dword v1, off, s[8:11], 0
-; SI-NEXT:    buffer_load_dword v2, off, s[0:3], 0
+; SI-NEXT:    buffer_load_dword v2, off, s[12:15], 0
 ; SI-NEXT:    buffer_load_dword v3, off, s[16:19], 0
-; SI-NEXT:    s_mov_b32 s12, s4
-; SI-NEXT:    s_mov_b32 s13, s5
+; SI-NEXT:    s_mov_b32 s0, s4
+; SI-NEXT:    s_mov_b32 s1, s5
 ; SI-NEXT:    s_waitcnt vmcnt(3)
 ; SI-NEXT:    v_lshrrev_b32_e32 v5, 16, v0
 ; SI-NEXT:    v_cvt_f32_f16_e32 v5, v5
@@ -441,7 +441,7 @@ define amdgpu_kernel void @select_v2f16(
 ; SI-NEXT:    v_cvt_f16_f32_e32 v0, v0
 ; SI-NEXT:    v_lshlrev_b32_e32 v1, 16, v2
 ; SI-NEXT:    v_or_b32_e32 v0, v0, v1
-; SI-NEXT:    buffer_store_dword v0, off, s[12:15], 0
+; SI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
 ; SI-NEXT:    s_endpgm
 ;
 ; VI-LABEL: select_v2f16:
diff --git a/llvm/test/CodeGen/AMDGPU/spill-vgpr-to-agpr.ll b/llvm/test/CodeGen/AMDGPU/spill-vgpr-to-agpr.ll
index f69f787cf4ad..78e2885c523a 100644
--- a/llvm/test/CodeGen/AMDGPU/spill-vgpr-to-agpr.ll
+++ b/llvm/test/CodeGen/AMDGPU/spill-vgpr-to-agpr.ll
@@ -246,7 +246,7 @@ define amdgpu_kernel void @max_256_vgprs_spill_9x32(<32 x float> addrspace(1)* %
 ; GFX908-DAG  v_accvgpr_read_b32
 
 ; GCN:    NumVgprs: 256
-; GFX900: ScratchSize: 580
+; GFX900: ScratchSize: 644
 ; GFX908-FIXME: ScratchSize: 0
 ; GCN:    VGPRBlocks: 63
 ; GCN:    NumVGPRsForWavesPerEU: 256