diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -6507,11 +6507,27 @@
     * FLAT_SCRATCH
     * EXEC
     * GFX6-8: M0
-    * All SGPR and VGPR registers except the clobbered registers of SGPR4-31 and
-      VGPR0-31.
+    * All SGPR registers except the clobbered registers of SGPR4-31.
+    * VGPR40-47
+      VGPR56-63
+      VGPR72-79
+      VGPR88-95
+      VGPR104-111
+      VGPR120-127
+      VGPR136-143
+      VGPR152-159
+      VGPR168-175
+      VGPR184-191
+      VGPR200-207
+      VGPR216-223
+      VGPR232-239
+      VGPR248-255
+        *Except the argument registers, the VGPR cloberred and the preserved
+        registers are intermixed at regular intervals in order to
+        get a better occupancy.*
 
       For the AMDGPU backend, an inter-procedural register allocation (IPRA)
-      optimization may mark some of clobbered SGPR4-31 and VGPR0-31 registers as
+      optimization may mark some of clobbered SGPR and VGPR registers as
       preserved if it can be determined that the called function does not change
       their value.
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td b/llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td
--- a/llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td
@@ -89,6 +89,24 @@
   (sequence "VGPR%u", 32, 255)
 >;
 
+def CSR_AMDGPU_VGPRs : CalleeSavedRegs<
+  // The CSRs & scratch-registers are interleaved at a split boundary of 8.
+  (add (sequence "VGPR%u", 40, 47),
+    (sequence "VGPR%u", 56, 63),
+    (sequence "VGPR%u", 72, 79),
+    (sequence "VGPR%u", 88, 95),
+    (sequence "VGPR%u", 104, 111),
+    (sequence "VGPR%u", 120, 127),
+    (sequence "VGPR%u", 136, 143),
+    (sequence "VGPR%u", 152, 159),
+    (sequence "VGPR%u", 168, 175),
+    (sequence "VGPR%u", 184, 191),
+    (sequence "VGPR%u", 200, 207),
+    (sequence "VGPR%u", 216, 223),
+    (sequence "VGPR%u", 232, 239),
+    (sequence "VGPR%u", 248, 255))
+>;
+
 def CSR_AMDGPU_SGPRs_32_105 : CalleeSavedRegs<
   (sequence "SGPR%u", 32, 105)
 >;
@@ -104,7 +122,7 @@
 >;
 
 def CSR_AMDGPU_HighRegs : CalleeSavedRegs<
-  (add CSR_AMDGPU_VGPRs_32_255, CSR_AMDGPU_SGPRs_32_105)
+  (add CSR_AMDGPU_VGPRs, CSR_AMDGPU_SGPRs_32_105)
 >;
 
 // Calling convention for leaf functions
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.ll
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/insertelement.ll
@@ -727,9 +727,6 @@
 ; GPRIDX-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GPRIDX-NEXT:    s_mov_b32 s18, 0
 ; GPRIDX-NEXT:    s_mov_b32 s19, 0x40200000
-; GPRIDX-NEXT:    buffer_store_dword v32, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; GPRIDX-NEXT:    buffer_store_dword v33, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; GPRIDX-NEXT:    buffer_store_dword v34, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GPRIDX-NEXT:    s_mov_b32 s17, 0x401c0000
 ; GPRIDX-NEXT:    s_mov_b32 s16, s18
 ; GPRIDX-NEXT:    s_mov_b32 s15, 0x40180000
@@ -793,9 +790,6 @@
 ; GPRIDX-NEXT:    global_store_dwordx4 v[0:1], v[7:10], off
 ; GPRIDX-NEXT:    global_store_dwordx4 v[0:1], v[11:14], off
 ; GPRIDX-NEXT:    global_store_dwordx4 v[0:1], v[15:18], off
-; GPRIDX-NEXT:    buffer_load_dword v34, off, s[0:3], s32 ; 4-byte Folded Reload
-; GPRIDX-NEXT:    buffer_load_dword v33, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
-; GPRIDX-NEXT:    buffer_load_dword v32, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
 ; GPRIDX-NEXT:    s_waitcnt vmcnt(0)
 ; GPRIDX-NEXT:    s_setpc_b64 s[30:31]
 ;
@@ -816,9 +810,6 @@
 ; MOVREL-NEXT:    s_mov_b32 s8, s18
 ; MOVREL-NEXT:    s_mov_b64 s[6:7], 2.0
 ; MOVREL-NEXT:    s_mov_b64 s[4:5], 1.0
-; MOVREL-NEXT:    buffer_store_dword v32, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; MOVREL-NEXT:    buffer_store_dword v33, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
-; MOVREL-NEXT:    buffer_store_dword v34, off, s[0:3], s32 ; 4-byte Folded Spill
 ; MOVREL-NEXT:    v_mov_b32_e32 v34, s19
 ; MOVREL-NEXT:    v_mov_b32_e32 v33, s18
 ; MOVREL-NEXT:    v_mov_b32_e32 v32, s17
@@ -868,10 +859,6 @@
 ; MOVREL-NEXT:    global_store_dwordx4 v[0:1], v[7:10], off
 ; MOVREL-NEXT:    global_store_dwordx4 v[0:1], v[11:14], off
 ; MOVREL-NEXT:    global_store_dwordx4 v[0:1], v[15:18], off
-; MOVREL-NEXT:    buffer_load_dword v34, off, s[0:3], s32 ; 4-byte Folded Reload
-; MOVREL-NEXT:    buffer_load_dword v33, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
-; MOVREL-NEXT:    buffer_load_dword v32, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
-; MOVREL-NEXT:    s_waitcnt vmcnt(0)
 ; MOVREL-NEXT:    s_waitcnt_vscnt null, 0x0
 ; MOVREL-NEXT:    s_setpc_b64 s[30:31]
 entry:
diff --git a/llvm/test/CodeGen/AMDGPU/call-argument-types.ll b/llvm/test/CodeGen/AMDGPU/call-argument-types.ll
--- a/llvm/test/CodeGen/AMDGPU/call-argument-types.ll
+++ b/llvm/test/CodeGen/AMDGPU/call-argument-types.ll
@@ -744,17 +744,13 @@
 
 ; GCN-LABEL: {{^}}tail_call_byval_align16:
 ; GCN-NOT: s32
-; GCN: buffer_store_dword v32, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GCN: buffer_store_dword v33, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; GCN: buffer_load_dword v32, off, s[0:3], s32 offset:20
-; GCN: buffer_load_dword v33, off, s[0:3], s32 offset:16
+; GCN: buffer_load_dword v32, off, s[0:3], s32 offset:12
+; GCN: buffer_load_dword v33, off, s[0:3], s32 offset:8
 
 ; GCN: s_getpc_b64
 
 ; GCN: buffer_store_dword v32, off, s[0:3], s32 offset:4
 ; GCN: buffer_store_dword v33, off, s[0:3], s32{{$}}
-; GCN: buffer_load_dword v33, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
-; GCN: buffer_load_dword v32, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
 ; GCN-NOT: s32
 ; GCN: s_setpc_b64
 define void @tail_call_byval_align16(<32 x i32> %val, double %tmp) #0 {
@@ -766,15 +762,11 @@
 
 ; GCN-LABEL: {{^}}tail_call_stack_passed_arg_alignment_v32i32_f64:
 ; GCN-NOT: s32
-; GCN: buffer_store_dword v32, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GCN: buffer_store_dword v33, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
 ; GCN: buffer_load_dword v32, off, s[0:3], s32 offset:4
 ; GCN: buffer_load_dword v33, off, s[0:3], s32{{$}}
 ; GCN: s_getpc_b64
 ; GCN: buffer_store_dword v33, off, s[0:3], s32{{$}}
 ; GCN: buffer_store_dword v32, off, s[0:3], s32 offset:4
-; GCN: buffer_load_dword v33, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
-; GCN: buffer_load_dword v32, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
 ; GCN-NOT: s32
 ; GCN: s_setpc_b64
 define void @tail_call_stack_passed_arg_alignment_v32i32_f64(<32 x i32> %val, double %tmp) #0 {
diff --git a/llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll b/llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll
--- a/llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll
+++ b/llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll
@@ -13,15 +13,15 @@
 }
 
 ; GCN-LABEL: {{^}}indirect_use_vcc:
-; GCN: v_writelane_b32 v32, s33, 2
-; GCN: v_writelane_b32 v32, s30, 0
-; GCN: v_writelane_b32 v32, s31, 1
+; GCN: v_writelane_b32 v40, s33, 2
+; GCN: v_writelane_b32 v40, s30, 0
+; GCN: v_writelane_b32 v40, s31, 1
 ; GCN: s_swappc_b64
-; GCN: v_readlane_b32 s4, v32, 0
-; GCN: v_readlane_b32 s5, v32, 1
-; GCN: v_readlane_b32 s33, v32, 2
+; GCN: v_readlane_b32 s4, v40, 0
+; GCN: v_readlane_b32 s5, v40, 1
+; GCN: v_readlane_b32 s33, v40, 2
 ; GCN: ; NumSgprs: 36
-; GCN: ; NumVgprs: 33
+; GCN: ; NumVgprs: 41
 define void @indirect_use_vcc() #1 {
   call void @use_vcc()
   ret void
@@ -32,7 +32,7 @@
 ; CI: ; NumSgprs: 38
 ; VI-NOBUG: ; NumSgprs: 40
 ; VI-BUG: ; NumSgprs: 96
-; GCN: ; NumVgprs: 33
+; GCN: ; NumVgprs: 41
 define amdgpu_kernel void @indirect_2level_use_vcc_kernel(i32 addrspace(1)* %out) #0 {
   call void @indirect_use_vcc()
   ret void
@@ -50,7 +50,7 @@
 ; GCN-LABEL: {{^}}indirect_use_flat_scratch:
 ; CI: ; NumSgprs: 38
 ; VI: ; NumSgprs: 40
-; GCN: ; NumVgprs: 33
+; GCN: ; NumVgprs: 41
 define void @indirect_use_flat_scratch() #1 {
   call void @use_flat_scratch()
   ret void
@@ -61,7 +61,7 @@
 ; CI: ; NumSgprs: 38
 ; VI-NOBUG: ; NumSgprs: 40
 ; VI-BUG: ; NumSgprs: 96
-; GCN: ; NumVgprs: 33
+; GCN: ; NumVgprs: 41
 define amdgpu_kernel void @indirect_2level_use_flat_scratch_kernel(i32 addrspace(1)* %out) #0 {
   call void @indirect_use_flat_scratch()
   ret void
@@ -76,7 +76,7 @@
 }
 
 ; GCN-LABEL: {{^}}indirect_use_10_vgpr:
-; GCN: ; NumVgprs: 33
+; GCN: ; NumVgprs: 41
 define void @indirect_use_10_vgpr() #0 {
   call void @use_10_vgpr()
   ret void
@@ -84,23 +84,23 @@
 
 ; GCN-LABEL: {{^}}indirect_2_level_use_10_vgpr:
 ; GCN: is_dynamic_callstack = 0
-; GCN: ; NumVgprs: 33
+; GCN: ; NumVgprs: 41
 define amdgpu_kernel void @indirect_2_level_use_10_vgpr() #0 {
   call void @indirect_use_10_vgpr()
   ret void
 }
 
-; GCN-LABEL: {{^}}use_40_vgpr:
-; GCN: ; NumVgprs: 40
-define void @use_40_vgpr() #1 {
-  call void asm sideeffect "", "~{v39}"() #0
+; GCN-LABEL: {{^}}use_50_vgpr:
+; GCN: ; NumVgprs: 50
+define void @use_50_vgpr() #1 {
+  call void asm sideeffect "", "~{v49}"() #0
   ret void
 }
 
-; GCN-LABEL: {{^}}indirect_use_40_vgpr:
-; GCN: ; NumVgprs: 40
-define void @indirect_use_40_vgpr() #0 {
-  call void @use_40_vgpr()
+; GCN-LABEL: {{^}}indirect_use_50_vgpr:
+; GCN: ; NumVgprs: 50
+define void @indirect_use_50_vgpr() #0 {
+  call void @use_50_vgpr()
   ret void
 }
 
diff --git a/llvm/test/CodeGen/AMDGPU/call-preserved-registers.ll b/llvm/test/CodeGen/AMDGPU/call-preserved-registers.ll
--- a/llvm/test/CodeGen/AMDGPU/call-preserved-registers.ll
+++ b/llvm/test/CodeGen/AMDGPU/call-preserved-registers.ll
@@ -23,22 +23,22 @@
 
 ; GCN-LABEL: {{^}}test_func_call_external_void_func_void_clobber_s30_s31_call_external_void_func_void:
 ; GCN: buffer_store_dword
-; GCN: v_writelane_b32 v32, s33, 4
-; GCN: v_writelane_b32 v32, s34, 0
-; GCN: v_writelane_b32 v32, s35, 1
-; GCN: v_writelane_b32 v32, s30, 2
-; GCN: v_writelane_b32 v32, s31, 3
+; GCN: v_writelane_b32 v40, s33, 4
+; GCN: v_writelane_b32 v40, s34, 0
+; GCN: v_writelane_b32 v40, s35, 1
+; GCN: v_writelane_b32 v40, s30, 2
+; GCN: v_writelane_b32 v40, s31, 3
 
 ; GCN: s_swappc_b64
 ; GCN-NEXT: ;;#ASMSTART
 ; GCN-NEXT: ;;#ASMEND
 ; GCN-NEXT: s_swappc_b64
-; GCN-DAG: v_readlane_b32 s4, v32, 2
-; GCN-DAG: v_readlane_b32 s5, v32, 3
-; GCN: v_readlane_b32 s35, v32, 1
-; GCN: v_readlane_b32 s34, v32, 0
+; GCN-DAG: v_readlane_b32 s4, v40, 2
+; GCN-DAG: v_readlane_b32 s5, v40, 3
+; GCN: v_readlane_b32 s35, v40, 1
+; GCN: v_readlane_b32 s34, v40, 0
 
-; GCN: v_readlane_b32 s33, v32, 4
+; GCN: v_readlane_b32 s33, v40, 4
 ; GCN: buffer_load_dword
 ; GCN: s_setpc_b64
 define void @test_func_call_external_void_func_void_clobber_s30_s31_call_external_void_func_void() #0 {
@@ -49,16 +49,16 @@
 }
 
 ; GCN-LABEL: {{^}}test_func_call_external_void_funcx2:
-; GCN: buffer_store_dword v32
-; GCN: v_writelane_b32 v32, s33, 4
+; GCN: buffer_store_dword v40
+; GCN: v_writelane_b32 v40, s33, 4
 
 ; GCN: s_mov_b32 s33, s32
 ; GCN: s_add_u32 s32, s32, 0x400
 ; GCN: s_swappc_b64
 ; GCN-NEXT: s_swappc_b64
 
-; GCN: v_readlane_b32 s33, v32, 4
-; GCN: buffer_load_dword v32,
+; GCN: v_readlane_b32 s33, v40, 4
+; GCN: buffer_load_dword v40,
 define void @test_func_call_external_void_funcx2() #0 {
   call void @external_void_func_void()
   call void @external_void_func_void()
@@ -115,9 +115,9 @@
 }
 
 ; GCN-LABEL: {{^}}test_call_void_func_void_mayclobber_v31:
-; GCN: v_mov_b32_e32 v32, v31
+; GCN: v_mov_b32_e32 v40, v31
 ; GCN-NEXT: s_swappc_b64
-; GCN-NEXT: v_mov_b32_e32 v31, v32
+; GCN-NEXT: v_mov_b32_e32 v31, v40
 define amdgpu_kernel void @test_call_void_func_void_mayclobber_v31(i32 addrspace(1)* %out) #0 {
   %v31 = call i32 asm sideeffect "; def $0", "={v31}"()
   call void @external_void_func_void()
@@ -177,31 +177,31 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}test_call_void_func_void_preserves_v32: {{.*}}
+; GCN-LABEL: {{^}}test_call_void_func_void_preserves_v40: {{.*}}
 
 ; GCN-NOT: v32
 ; GCN: s_getpc_b64 s[4:5]
 ; GCN-NEXT: s_add_u32 s4, s4, external_void_func_void@rel32@lo+4
 ; GCN-NEXT: s_addc_u32 s5, s5, external_void_func_void@rel32@hi+4
 ; GCN: s_mov_b32 s32, 0
-; GCN-NOT: v32
+; GCN-NOT: v40
 
 ; GCN: ;;#ASMSTART
-; GCN-NEXT: ; def v32
+; GCN-NEXT: ; def v40
 ; GCN-NEXT: ;;#ASMEND
 
 ; GCN: s_swappc_b64 s[30:31], s[4:5]
 
-; GCN-NOT: v32
+; GCN-NOT: v40
 
 ; GCN: ;;#ASMSTART
-; GCN-NEXT: ; use v32
+; GCN-NEXT: ; use v40
 ; GCN-NEXT: ;;#ASMEND
 ; GCN-NEXT: s_endpgm
-define amdgpu_kernel void @test_call_void_func_void_preserves_v32(i32 addrspace(1)* %out) #0 {
-  %v32 = call i32 asm sideeffect "; def $0", "={v32}"()
+define amdgpu_kernel void @test_call_void_func_void_preserves_v40(i32 addrspace(1)* %out) #0 {
+  %v40 = call i32 asm sideeffect "; def $0", "={v40}"()
   call void @external_void_func_void()
-  call void asm sideeffect "; use $0", "{v32}"(i32 %v32)
+  call void asm sideeffect "; use $0", "{v40}"(i32 %v40)
   ret void
 }
 
@@ -255,12 +255,12 @@
 
 ; GCN-LABEL: {{^}}callee_saved_sgpr_func:
 ; GCN-NOT: s40
-; GCN: v_writelane_b32 v32, s40
+; GCN: v_writelane_b32 v40, s40
 ; GCN: s_swappc_b64
 ; GCN-NOT: s40
 ; GCN: ; use s40
 ; GCN-NOT: s40
-; GCN: v_readlane_b32 s40, v32
+; GCN: v_readlane_b32 s40, v40
 ; GCN-NOT: s40
 define void @callee_saved_sgpr_func() #2 {
   %s40 = call i32 asm sideeffect "; def s40", "={s40}"() #0
@@ -287,19 +287,19 @@
 ; First call preserved VGPR is used so it can't be used for SGPR spills.
 ; GCN-LABEL: {{^}}callee_saved_sgpr_vgpr_func:
 ; GCN-NOT: s40
-; GCN: v_writelane_b32 v33, s40
+; GCN: v_writelane_b32 v41, s40
 ; GCN: s_swappc_b64
 ; GCN-NOT: s40
 ; GCN: ; use s40
 ; GCN-NOT: s40
-; GCN: v_readlane_b32 s40, v33
+; GCN: v_readlane_b32 s40, v41
 ; GCN-NOT: s40
 define void @callee_saved_sgpr_vgpr_func() #2 {
   %s40 = call i32 asm sideeffect "; def s40", "={s40}"() #0
-  %v32 = call i32 asm sideeffect "; def v32", "={v32}"() #0
+  %v40 = call i32 asm sideeffect "; def v40", "={v40}"() #0
   call void @external_void_func_void()
   call void asm sideeffect "; use $0", "s"(i32 %s40) #0
-  call void asm sideeffect "; use $0", "v"(i32 %v32) #0
+  call void asm sideeffect "; use $0", "v"(i32 %v40) #0
   ret void
 }
 
diff --git a/llvm/test/CodeGen/AMDGPU/call-waitcnt.ll b/llvm/test/CodeGen/AMDGPU/call-waitcnt.ll
--- a/llvm/test/CodeGen/AMDGPU/call-waitcnt.ll
+++ b/llvm/test/CodeGen/AMDGPU/call-waitcnt.ll
@@ -64,11 +64,11 @@
 ; GCN-NEXT:    s_add_u32 s4, s4, func@rel32@lo+4
 ; GCN-NEXT:    s_addc_u32 s5, s5, func@rel32@hi+4
 ; GCN-NEXT:    s_mov_b32 s32, 0
-; GCN-NEXT:    v_mov_b32_e32 v32, 0
+; GCN-NEXT:    v_mov_b32_e32 v40, 0
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[4:5]
 ; GCN-NEXT:    v_mov_b32_e32 v0, s34
 ; GCN-NEXT:    v_mov_b32_e32 v1, s35
-; GCN-NEXT:    global_store_dword v[0:1], v32, off
+; GCN-NEXT:    global_store_dword v[0:1], v40, off
 ; GCN-NEXT:    s_endpgm
   call void @func(i32 0)
   store i32 0, i32 addrspace(1)* %ptr
diff --git a/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll b/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
--- a/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
+++ b/llvm/test/CodeGen/AMDGPU/callee-frame-setup.ll
@@ -127,8 +127,8 @@
 ; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s31, 1
 ; GCN: s_swappc_b64
 
-; GCN-DAG: v_readlane_b32 s4, v32, 0
-; GCN-DAG: v_readlane_b32 s5, v32, 1
+; GCN-DAG: v_readlane_b32 s4, v40, 0
+; GCN-DAG: v_readlane_b32 s5, v40, 1
 
 ; GCN: s_sub_u32 s32, s32, 0x400
 ; GCN-NEXT: v_readlane_b32 s33, [[CSR_VGPR]], [[FP_SPILL_LANE]]
@@ -168,6 +168,7 @@
   call void asm sideeffect "", "~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15}"() #0
   call void asm sideeffect "", "~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23}"() #0
   call void asm sideeffect "", "~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"() #0
+  call void asm sideeffect "", "~{v32},~{v33},~{v34},~{v35},~{v36},~{v37},~{v38},~{v39}"() #0
 
   %wide.sgpr0 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
   %wide.sgpr1 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
@@ -207,14 +208,14 @@
 ; GCN-NEXT:s_mov_b32 [[FP_COPY:s[0-9]+]], s33
 ; GCN-NEXT: s_mov_b32 s33, s32
 ; GCN: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
-; GCN-DAG: buffer_store_dword v33, off, s[0:3], s33 ; 4-byte Folded Spill
+; GCN-DAG: buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GCN-DAG: buffer_store_dword [[ZERO]], off, s[0:3], s33 offset:8
 
 ; GCN:	;;#ASMSTART
-; GCN-NEXT: ; clobber v33
+; GCN-NEXT: ; clobber v41
 ; GCN-NEXT: ;;#ASMEND
 
-; GCN: buffer_load_dword v33, off, s[0:3], s33 ; 4-byte Folded Reload
+; GCN: buffer_load_dword v41, off, s[0:3], s33 ; 4-byte Folded Reload
 ; GCN: s_add_u32 s32, s32, 0x300
 ; GCN-NEXT: s_sub_u32 s32, s32, 0x300
 ; GCN-NEXT: s_mov_b32 s33, s4
@@ -223,7 +224,7 @@
 define void @callee_with_stack_no_fp_elim_csr_vgpr() #1 {
   %alloca = alloca i32, addrspace(5)
   store volatile i32 0, i32 addrspace(5)* %alloca
-  call void asm sideeffect "; clobber v33", "~{v33}"()
+  call void asm sideeffect "; clobber v41", "~{v41}"()
   ret void
 }
 
@@ -232,7 +233,7 @@
 ; GCN: s_waitcnt
 ; GCN-NEXT: v_writelane_b32 v1, s33, 63
 ; GCN-NEXT: s_mov_b32 s33, s32
-; GCN: buffer_store_dword v33, off, s[0:3], s33 ; 4-byte Folded Spill
+; GCN: buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GCN-COUNT-63: v_writelane_b32 v1
 ; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s33 offset:8
 ; GCN: ;;#ASMSTART
@@ -246,7 +247,7 @@
 define void @last_lane_vgpr_for_fp_csr() #1 {
   %alloca = alloca i32, addrspace(5)
   store volatile i32 0, i32 addrspace(5)* %alloca
-  call void asm sideeffect "; clobber v33", "~{v33}"()
+  call void asm sideeffect "; clobber v41", "~{v41}"()
   call void asm sideeffect "",
     "~{s40},~{s41},~{s42},~{s43},~{s44},~{s45},~{s46},~{s47},~{s48},~{s49}
     ,~{s50},~{s51},~{s52},~{s53},~{s54},~{s55},~{s56},~{s57},~{s58},~{s59}
@@ -264,14 +265,14 @@
 ; GCN: s_waitcnt
 ; GCN-NEXT: s_mov_b32 [[FP_COPY:s[0-9]+]], s33
 ; GCN-NEXT: s_mov_b32 s33, s32
-; GCN-NEXT: buffer_store_dword v33, off, s[0:3], s33 ; 4-byte Folded Spill
+; GCN-NEXT: buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
 ; GCN-COUNT-64: v_writelane_b32 v1,
 
 ; GCN: buffer_store_dword
 ; GCN: ;;#ASMSTART
 ; GCN-COUNT-64: v_readlane_b32 s{{[0-9]+}}, v1
 
-; GCN: buffer_load_dword v33, off, s[0:3], s33 ; 4-byte Folded Reload
+; GCN: buffer_load_dword v41, off, s[0:3], s33 ; 4-byte Folded Reload
 ; GCN: s_add_u32 s32, s32, 0x300
 ; GCN-NEXT: s_sub_u32 s32, s32, 0x300
 ; GCN-NEXT: s_mov_b32 s33, [[FP_COPY]]
@@ -280,7 +281,7 @@
 define void @no_new_vgpr_for_fp_csr() #1 {
   %alloca = alloca i32, addrspace(5)
   store volatile i32 0, i32 addrspace(5)* %alloca
-  call void asm sideeffect "; clobber v33", "~{v33}"()
+  call void asm sideeffect "; clobber v41", "~{v41}"()
   call void asm sideeffect "",
     "~{s39},~{s40},~{s41},~{s42},~{s43},~{s44},~{s45},~{s46},~{s47},~{s48},~{s49}
     ,~{s50},~{s51},~{s52},~{s53},~{s54},~{s55},~{s56},~{s57},~{s58},~{s59}
@@ -347,20 +348,20 @@
 ; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
 ; GCN-NEXT: buffer_store_dword [[CSR_VGPR:v[0-9]+]], off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
 ; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
-; GCN-NEXT: v_writelane_b32 v32, s33, 2
-; GCN-NEXT: v_writelane_b32 v32, s30, 0
+; GCN-NEXT: v_writelane_b32 [[CSR_VGPR]], s33, 2
+; GCN-NEXT: v_writelane_b32 [[CSR_VGPR]], s30, 0
 ; GCN-NEXT: s_mov_b32 s33, s32
 
-; GCN-DAG: v_writelane_b32 v32, s31, 1
+; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s31, 1
 ; GCN-DAG: buffer_store_dword
 ; GCN: s_add_u32 s32, s32, 0x300{{$}}
 
 ; GCN: ;;#ASMSTART
 
-; GCN: v_readlane_b32 s4, v32, 0
-; GCN-NEXT: v_readlane_b32 s5, v32, 1
+; GCN: v_readlane_b32 s4, [[CSR_VGPR]], 0
+; GCN-NEXT: v_readlane_b32 s5, [[CSR_VGPR]], 1
 ; GCN-NEXT: s_sub_u32 s32, s32, 0x300{{$}}
-; GCN-NEXT: v_readlane_b32 s33, v32, 2
+; GCN-NEXT: v_readlane_b32 s33, [[CSR_VGPR]], 2
 ; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
 ; GCN-NEXT: buffer_load_dword [[CSR_VGPR]], off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
 ; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
@@ -377,11 +378,11 @@
     ,~{s20},~{s21},~{s22},~{s23},~{s24},~{s25},~{s26},~{s27},~{s28},~{s29}
     ,~{s30},~{s31}"() #0
 
-  call void asm sideeffect "; clobber nonpreserved VGPRs",
+  call void asm sideeffect "; clobber nonpreserved initial VGPRs",
     "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9}
     ,~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19}
     ,~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29}
-    ,~{v30},~{v31}"() #1
+    ,~{v30},~{v31},~{v32},~{v33},~{v34},~{v35},~{v36},~{v37},~{v38},~{v39}"() #1
 
   ret void
 }
@@ -394,19 +395,19 @@
 ; GCN-NEXT: v_mov_b32_e32 [[SCRATCH_VGPR:v[0-9]+]], 0x1008
 ; GCN-NEXT: buffer_store_dword [[CSR_VGPR:v[0-9]+]], [[SCRATCH_VGPR]], s[0:3], s32 offen ; 4-byte Folded Spill
 ; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
-; GCN-NEXT: v_writelane_b32 v32, s33, 2
-; GCN-NEXT: v_writelane_b32 v32, s30, 0
+; GCN-NEXT: v_writelane_b32 [[CSR_VGPR]], s33, 2
+; GCN-NEXT: v_writelane_b32 [[CSR_VGPR]], s30, 0
 ; GCN-NEXT: s_mov_b32 s33, s32
-; GCN-DAG: v_writelane_b32 v32, s31, 1
+; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s31, 1
 ; GCN-DAG: s_add_u32 s32, s32, 0x40300{{$}}
 ; GCN-DAG: buffer_store_dword
 
 ; GCN: ;;#ASMSTART
 
-; GCN: v_readlane_b32 s4, v32, 0
-; GCN-NEXT: v_readlane_b32 s5, v32, 1
+; GCN: v_readlane_b32 s4, [[CSR_VGPR]], 0
+; GCN-NEXT: v_readlane_b32 s5, [[CSR_VGPR]], 1
 ; GCN-NEXT: s_sub_u32 s32, s32, 0x40300{{$}}
-; GCN-NEXT: v_readlane_b32 s33, v32, 2
+; GCN-NEXT: v_readlane_b32 s33, [[CSR_VGPR]], 2
 ; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
 ; GCN-NEXT: v_mov_b32_e32 [[SCRATCH_VGPR:v[0-9]+]], 0x1008
 ; GCN-NEXT: buffer_load_dword [[CSR_VGPR]], [[SCRATCH_VGPR]], s[0:3], s32 offen ; 4-byte Folded Reload
@@ -429,7 +430,7 @@
     "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9}
     ,~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19}
     ,~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29}
-    ,~{v30},~{v31}"() #1
+    ,~{v30},~{v31},~{v32},~{v33},~{v34},~{v35},~{v36},~{v37},~{v38},~{v39}"() #1
 
   ret void
 }
diff --git a/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll b/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
--- a/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
+++ b/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
@@ -144,7 +144,7 @@
 ; GCN-NOT: s12
 ; GCN-NOT: s13
 ; GCN-NOT: s14
-; GCN: v_readlane_b32 s4, v32, 0
+; GCN: v_readlane_b32 s4, v40, 0
 define hidden void @func_indirect_use_workgroup_id_x() #1 {
   call void @use_workgroup_id_x()
   ret void
@@ -152,7 +152,7 @@
 
 ; GCN-LABEL: {{^}}func_indirect_use_workgroup_id_y:
 ; GCN-NOT: s4
-; GCN: v_readlane_b32 s4, v32, 0
+; GCN: v_readlane_b32 s4, v40, 0
 define hidden void @func_indirect_use_workgroup_id_y() #1 {
   call void @use_workgroup_id_y()
   ret void
@@ -160,7 +160,7 @@
 
 ; GCN-LABEL: {{^}}func_indirect_use_workgroup_id_z:
 ; GCN-NOT: s4
-; GCN: v_readlane_b32 s4, v32, 0
+; GCN: v_readlane_b32 s4, v40, 0
 define hidden void @func_indirect_use_workgroup_id_z() #1 {
   call void @use_workgroup_id_z()
   ret void
diff --git a/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll b/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
--- a/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
+++ b/llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
@@ -302,7 +302,7 @@
 ; Argument is in right place already
 ; GCN-LABEL: {{^}}func_indirect_use_workgroup_id_x:
 ; GCN-NOT: s4
-; GCN: v_readlane_b32 s4, v32, 0
+; GCN: v_readlane_b32 s4, v40, 0
 define hidden void @func_indirect_use_workgroup_id_x() #1 {
   call void @use_workgroup_id_x()
   ret void
@@ -310,7 +310,7 @@
 
 ; GCN-LABEL: {{^}}func_indirect_use_workgroup_id_y:
 ; GCN-NOT: s4
-; GCN: v_readlane_b32 s4, v32, 0
+; GCN: v_readlane_b32 s4, v40, 0
 define hidden void @func_indirect_use_workgroup_id_y() #1 {
   call void @use_workgroup_id_y()
   ret void
@@ -318,7 +318,7 @@
 
 ; GCN-LABEL: {{^}}func_indirect_use_workgroup_id_z:
 ; GCN-NOT: s4
-; GCN: v_readlane_b32 s4, v32, 0
+; GCN: v_readlane_b32 s4, v40, 0
 define hidden void @func_indirect_use_workgroup_id_z() #1 {
   call void @use_workgroup_id_z()
   ret void
diff --git a/llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll b/llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll
--- a/llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll
+++ b/llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll
@@ -396,13 +396,11 @@
 }
 
 ; GCN-LABEL: {{^}}too_many_args_use_workitem_id_x:
-; VARABI: buffer_store_dword v32, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; VARABI: buffer_load_dword v32, off, s[0:3], s32{{$}}
 ; VARABI: v_and_b32_e32 v32, 0x3ff, v32
 ; VARABI: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+]}}, v32
 
-; VARABI: buffer_load_dword v32, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
-; VARABI-NEXT: s_waitcnt
+; VARABI: s_waitcnt
 ; VARABI-NEXT: s_setpc_b64
 
 ; FIXEDABI: v_and_b32_e32 v31, 0x3ff, v31
@@ -514,15 +512,15 @@
 ; Requires loading and storing to stack slot.
 ; GCN-LABEL: {{^}}too_many_args_call_too_many_args_use_workitem_id_x:
 ; GCN-DAG: s_add_u32 s32, s32, 0x400{{$}}
-; GCN-DAG: buffer_store_dword v32, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; GCN-DAG: buffer_store_dword v40, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; GCN-DAG: buffer_load_dword v32, off, s[0:3], s33{{$}}
 
 ; GCN: buffer_store_dword v32, off, s[0:3], s32{{$}}
 
 ; GCN: s_swappc_b64
 
-; GCN: buffer_load_dword v32, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
 ; GCN: s_sub_u32 s32, s32, 0x400{{$}}
+; GCN: buffer_load_dword v40, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
 ; GCN: s_setpc_b64
 define void @too_many_args_call_too_many_args_use_workitem_id_x(
   i32 %arg0, i32 %arg1, i32 %arg2, i32 %arg3, i32 %arg4, i32 %arg5, i32 %arg6, i32 %arg7,
@@ -543,13 +541,11 @@
 ; frame[2] = VGPR spill slot
 
 ; GCN-LABEL: {{^}}too_many_args_use_workitem_id_x_byval:
-; VARABI: buffer_store_dword v32, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
 ; VARABI: buffer_load_dword v32, off, s[0:3], s32 offset:4
 ; VARABI-NEXT: s_waitcnt
 ; VARABI-NEXT: v_and_b32_e32 v32, 0x3ff, v32
 ; VARABI-NEXT: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, v32
 ; VARABI: buffer_load_dword v0, off, s[0:3], s32{{$}}
-; VARABI: buffer_load_dword v32, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
 ; VARABI: s_setpc_b64
 
 
@@ -700,10 +696,7 @@
   ret void
 }
 
-; Only one stack load should be emitted for all 3 values.
 ; GCN-LABEL: {{^}}too_many_args_use_workitem_id_xyz:
-; VARABI: buffer_store_dword v32, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-; VARABI: buffer_store_dword v33, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; VARABI-NOT: buffer_load_dword v{{[0-9]+}}, off, s[0:3], s32{{$}}
 ; VARABI: buffer_load_dword v32, off, s[0:3], s32{{$}}
 ; VARABI-NOT: buffer_load_dword
@@ -717,9 +710,7 @@
 ; VARABI-NEXT: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+]}}, [[BFE_Y]]
 ; VARABI-NEXT: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+]}}, [[BFE_Z]]
 
-; VARABI: buffer_load_dword v33, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
-; VARABI: buffer_load_dword v32, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
-; VARABI-NEXT: s_waitcnt
+; VARABI: s_waitcnt
 ; VARABI-NEXT: s_setpc_b64
 
 
@@ -826,7 +817,7 @@
 
 ; GCN: s_waitcnt
 ; GCN-NEXT: s_setpc_b64
-; GCN: ScratchSize: 8
+; GCN: ScratchSize: 0
 define void @too_many_args_use_workitem_id_x_stack_yz(
   i32 %arg0, i32 %arg1, i32 %arg2, i32 %arg3, i32 %arg4, i32 %arg5, i32 %arg6, i32 %arg7,
   i32 %arg8, i32 %arg9, i32 %arg10, i32 %arg11, i32 %arg12, i32 %arg13, i32 %arg14, i32 %arg15,
diff --git a/llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll b/llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
--- a/llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
+++ b/llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
@@ -28,23 +28,23 @@
 ; GCN:       ; %bb.0: ; %bb0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    s_or_saveexec_b64 s[4:5], -1
-; GCN-NEXT:    buffer_store_dword v32, off, s[0:3], s32 ; 4-byte Folded Spill
+; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT:    s_mov_b64 exec, s[4:5]
-; GCN-NEXT:    v_writelane_b32 v32, s33, 2
-; GCN-NEXT:    v_writelane_b32 v32, s30, 0
+; GCN-NEXT:    v_writelane_b32 v40, s33, 2
+; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_mov_b32 s33, s32
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, func_v2f32@rel32@lo+4
 ; GCN-NEXT:    s_addc_u32 s5, s5, func_v2f32@rel32@hi+4
-; GCN-NEXT:    v_writelane_b32 v32, s31, 1
+; GCN-NEXT:    v_writelane_b32 v40, s31, 1
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[4:5]
-; GCN-NEXT:    v_readlane_b32 s4, v32, 0
-; GCN-NEXT:    v_readlane_b32 s5, v32, 1
+; GCN-NEXT:    v_readlane_b32 s4, v40, 0
+; GCN-NEXT:    v_readlane_b32 s5, v40, 1
 ; GCN-NEXT:    s_sub_u32 s32, s32, 0x400
-; GCN-NEXT:    v_readlane_b32 s33, v32, 2
+; GCN-NEXT:    v_readlane_b32 s33, v40, 2
 ; GCN-NEXT:    s_or_saveexec_b64 s[6:7], -1
-; GCN-NEXT:    buffer_load_dword v32, off, s[0:3], s32 ; 4-byte Folded Reload
+; GCN-NEXT:    buffer_load_dword v40, off, s[0:3], s32 ; 4-byte Folded Reload
 ; GCN-NEXT:    s_mov_b64 exec, s[6:7]
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    s_setpc_b64 s[4:5]
@@ -62,23 +62,23 @@
 ; GCN:       ; %bb.0: ; %bb0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    s_or_saveexec_b64 s[4:5], -1
-; GCN-NEXT:    buffer_store_dword v32, off, s[0:3], s32 ; 4-byte Folded Spill
+; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT:    s_mov_b64 exec, s[4:5]
-; GCN-NEXT:    v_writelane_b32 v32, s33, 2
-; GCN-NEXT:    v_writelane_b32 v32, s30, 0
+; GCN-NEXT:    v_writelane_b32 v40, s33, 2
+; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_mov_b32 s33, s32
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, func_v3f32@rel32@lo+4
 ; GCN-NEXT:    s_addc_u32 s5, s5, func_v3f32@rel32@hi+4
-; GCN-NEXT:    v_writelane_b32 v32, s31, 1
+; GCN-NEXT:    v_writelane_b32 v40, s31, 1
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[4:5]
-; GCN-NEXT:    v_readlane_b32 s4, v32, 0
-; GCN-NEXT:    v_readlane_b32 s5, v32, 1
+; GCN-NEXT:    v_readlane_b32 s4, v40, 0
+; GCN-NEXT:    v_readlane_b32 s5, v40, 1
 ; GCN-NEXT:    s_sub_u32 s32, s32, 0x400
-; GCN-NEXT:    v_readlane_b32 s33, v32, 2
+; GCN-NEXT:    v_readlane_b32 s33, v40, 2
 ; GCN-NEXT:    s_or_saveexec_b64 s[6:7], -1
-; GCN-NEXT:    buffer_load_dword v32, off, s[0:3], s32 ; 4-byte Folded Reload
+; GCN-NEXT:    buffer_load_dword v40, off, s[0:3], s32 ; 4-byte Folded Reload
 ; GCN-NEXT:    s_mov_b64 exec, s[6:7]
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    s_setpc_b64 s[4:5]
@@ -96,23 +96,23 @@
 ; GCN:       ; %bb.0: ; %bb0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    s_or_saveexec_b64 s[4:5], -1
-; GCN-NEXT:    buffer_store_dword v32, off, s[0:3], s32 ; 4-byte Folded Spill
+; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT:    s_mov_b64 exec, s[4:5]
-; GCN-NEXT:    v_writelane_b32 v32, s33, 2
-; GCN-NEXT:    v_writelane_b32 v32, s30, 0
+; GCN-NEXT:    v_writelane_b32 v40, s33, 2
+; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_mov_b32 s33, s32
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, func_v4f16@rel32@lo+4
 ; GCN-NEXT:    s_addc_u32 s5, s5, func_v4f16@rel32@hi+4
-; GCN-NEXT:    v_writelane_b32 v32, s31, 1
+; GCN-NEXT:    v_writelane_b32 v40, s31, 1
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[4:5]
-; GCN-NEXT:    v_readlane_b32 s4, v32, 0
-; GCN-NEXT:    v_readlane_b32 s5, v32, 1
+; GCN-NEXT:    v_readlane_b32 s4, v40, 0
+; GCN-NEXT:    v_readlane_b32 s5, v40, 1
 ; GCN-NEXT:    s_sub_u32 s32, s32, 0x400
-; GCN-NEXT:    v_readlane_b32 s33, v32, 2
+; GCN-NEXT:    v_readlane_b32 s33, v40, 2
 ; GCN-NEXT:    s_or_saveexec_b64 s[6:7], -1
-; GCN-NEXT:    buffer_load_dword v32, off, s[0:3], s32 ; 4-byte Folded Reload
+; GCN-NEXT:    buffer_load_dword v40, off, s[0:3], s32 ; 4-byte Folded Reload
 ; GCN-NEXT:    s_mov_b64 exec, s[6:7]
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    s_setpc_b64 s[4:5]
@@ -130,24 +130,24 @@
 ; GCN:       ; %bb.0: ; %bb0
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GCN-NEXT:    s_or_saveexec_b64 s[4:5], -1
-; GCN-NEXT:    buffer_store_dword v32, off, s[0:3], s32 ; 4-byte Folded Spill
+; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT:    s_mov_b64 exec, s[4:5]
-; GCN-NEXT:    v_writelane_b32 v32, s33, 2
-; GCN-NEXT:    v_writelane_b32 v32, s30, 0
+; GCN-NEXT:    v_writelane_b32 v40, s33, 2
+; GCN-NEXT:    v_writelane_b32 v40, s30, 0
 ; GCN-NEXT:    s_mov_b32 s33, s32
 ; GCN-NEXT:    s_add_u32 s32, s32, 0x400
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, func_struct@rel32@lo+4
 ; GCN-NEXT:    s_addc_u32 s5, s5, func_struct@rel32@hi+4
-; GCN-NEXT:    v_writelane_b32 v32, s31, 1
+; GCN-NEXT:    v_writelane_b32 v40, s31, 1
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[4:5]
-; GCN-NEXT:    v_readlane_b32 s4, v32, 0
-; GCN-NEXT:    v_readlane_b32 s5, v32, 1
+; GCN-NEXT:    v_readlane_b32 s4, v40, 0
+; GCN-NEXT:    v_readlane_b32 s5, v40, 1
 ; GCN-NEXT:    v_mov_b32_e32 v1, v4
 ; GCN-NEXT:    s_sub_u32 s32, s32, 0x400
-; GCN-NEXT:    v_readlane_b32 s33, v32, 2
+; GCN-NEXT:    v_readlane_b32 s33, v40, 2
 ; GCN-NEXT:    s_or_saveexec_b64 s[6:7], -1
-; GCN-NEXT:    buffer_load_dword v32, off, s[0:3], s32 ; 4-byte Folded Reload
+; GCN-NEXT:    buffer_load_dword v40, off, s[0:3], s32 ; 4-byte Folded Reload
 ; GCN-NEXT:    s_mov_b64 exec, s[6:7]
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    s_setpc_b64 s[4:5]
diff --git a/llvm/test/CodeGen/AMDGPU/ipra-regmask.ll b/llvm/test/CodeGen/AMDGPU/ipra-regmask.ll
--- a/llvm/test/CodeGen/AMDGPU/ipra-regmask.ll
+++ b/llvm/test/CodeGen/AMDGPU/ipra-regmask.ll
@@ -3,7 +3,7 @@
 
 ; CHECK-DAG: csr Clobbered Registers: $vgpr0 $vgpr0_hi16 $vgpr0_lo16 $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31 $vgpr0_vgpr1_vgpr2_vgpr3 $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4 $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5 $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 $vgpr0_vgpr1 $vgpr0_vgpr1_vgpr2 {{$}}
 define void @csr() #0 {
-  call void asm sideeffect "", "~{v0},~{v36},~{v37}"() #0
+  call void asm sideeffect "", "~{v0},~{v44},~{v45}"() #0
   ret void
 }
 
diff --git a/llvm/test/CodeGen/AMDGPU/mul24-pass-ordering.ll b/llvm/test/CodeGen/AMDGPU/mul24-pass-ordering.ll
--- a/llvm/test/CodeGen/AMDGPU/mul24-pass-ordering.ll
+++ b/llvm/test/CodeGen/AMDGPU/mul24-pass-ordering.ll
@@ -187,44 +187,44 @@
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX9-NEXT:    s_or_saveexec_b64 s[4:5], -1
-; GFX9-NEXT:    buffer_store_dword v35, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
+; GFX9-NEXT:    buffer_store_dword v43, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
 ; GFX9-NEXT:    s_mov_b64 exec, s[4:5]
-; GFX9-NEXT:    v_writelane_b32 v35, s33, 4
+; GFX9-NEXT:    v_writelane_b32 v43, s33, 4
 ; GFX9-NEXT:    s_mov_b32 s33, s32
 ; GFX9-NEXT:    s_add_u32 s32, s32, 0x800
-; GFX9-NEXT:    buffer_store_dword v32, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
-; GFX9-NEXT:    buffer_store_dword v33, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
-; GFX9-NEXT:    buffer_store_dword v34, off, s[0:3], s33 ; 4-byte Folded Spill
-; GFX9-NEXT:    v_writelane_b32 v35, s34, 0
+; GFX9-NEXT:    buffer_store_dword v40, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
+; GFX9-NEXT:    buffer_store_dword v41, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; GFX9-NEXT:    buffer_store_dword v42, off, s[0:3], s33 ; 4-byte Folded Spill
+; GFX9-NEXT:    v_writelane_b32 v43, s34, 0
 ; GFX9-NEXT:    s_getpc_b64 s[4:5]
 ; GFX9-NEXT:    s_add_u32 s4, s4, foo@gotpcrel32@lo+4
 ; GFX9-NEXT:    s_addc_u32 s5, s5, foo@gotpcrel32@hi+4
-; GFX9-NEXT:    v_writelane_b32 v35, s35, 1
+; GFX9-NEXT:    v_writelane_b32 v43, s35, 1
 ; GFX9-NEXT:    s_load_dwordx2 s[34:35], s[4:5], 0x0
-; GFX9-NEXT:    v_mov_b32_e32 v32, v1
-; GFX9-NEXT:    v_mov_b32_e32 v33, v0
-; GFX9-NEXT:    v_writelane_b32 v35, s30, 2
-; GFX9-NEXT:    v_mul_u32_u24_e32 v0, v33, v32
-; GFX9-NEXT:    v_writelane_b32 v35, s31, 3
-; GFX9-NEXT:    v_and_b32_e32 v34, 0xffffff, v32
+; GFX9-NEXT:    v_mov_b32_e32 v40, v1
+; GFX9-NEXT:    v_mov_b32_e32 v41, v0
+; GFX9-NEXT:    v_writelane_b32 v43, s30, 2
+; GFX9-NEXT:    v_mul_u32_u24_e32 v0, v41, v40
+; GFX9-NEXT:    v_writelane_b32 v43, s31, 3
+; GFX9-NEXT:    v_and_b32_e32 v42, 0xffffff, v40
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[34:35]
-; GFX9-NEXT:    v_mad_u32_u24 v32, v33, v32, v34
-; GFX9-NEXT:    v_mov_b32_e32 v0, v32
+; GFX9-NEXT:    v_mad_u32_u24 v40, v41, v40, v42
+; GFX9-NEXT:    v_mov_b32_e32 v0, v40
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[34:35]
-; GFX9-NEXT:    v_add_u32_e32 v0, v32, v34
+; GFX9-NEXT:    v_add_u32_e32 v0, v40, v42
 ; GFX9-NEXT:    s_swappc_b64 s[30:31], s[34:35]
-; GFX9-NEXT:    v_readlane_b32 s4, v35, 2
-; GFX9-NEXT:    v_readlane_b32 s5, v35, 3
-; GFX9-NEXT:    v_readlane_b32 s35, v35, 1
-; GFX9-NEXT:    v_readlane_b32 s34, v35, 0
-; GFX9-NEXT:    buffer_load_dword v34, off, s[0:3], s33 ; 4-byte Folded Reload
-; GFX9-NEXT:    buffer_load_dword v33, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
-; GFX9-NEXT:    buffer_load_dword v32, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
+; GFX9-NEXT:    v_readlane_b32 s4, v43, 2
+; GFX9-NEXT:    v_readlane_b32 s5, v43, 3
+; GFX9-NEXT:    v_readlane_b32 s35, v43, 1
+; GFX9-NEXT:    v_readlane_b32 s34, v43, 0
+; GFX9-NEXT:    buffer_load_dword v42, off, s[0:3], s33 ; 4-byte Folded Reload
+; GFX9-NEXT:    buffer_load_dword v41, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
+; GFX9-NEXT:    buffer_load_dword v40, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
 ; GFX9-NEXT:    s_sub_u32 s32, s32, 0x800
-; GFX9-NEXT:    v_readlane_b32 s33, v35, 4
+; GFX9-NEXT:    v_readlane_b32 s33, v43, 4
 ; GFX9-NEXT:    s_or_saveexec_b64 s[6:7], -1
-; GFX9-NEXT:    buffer_load_dword v35, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
+; GFX9-NEXT:    buffer_load_dword v43, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
 ; GFX9-NEXT:    s_mov_b64 exec, s[6:7]
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-NEXT:    s_setpc_b64 s[4:5]
diff --git a/llvm/test/CodeGen/AMDGPU/nested-calls.ll b/llvm/test/CodeGen/AMDGPU/nested-calls.ll
--- a/llvm/test/CodeGen/AMDGPU/nested-calls.ll
+++ b/llvm/test/CodeGen/AMDGPU/nested-calls.ll
@@ -12,23 +12,23 @@
 
 ; Spill CSR VGPR used for SGPR spilling
 ; GCN: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
-; GCN-NEXT: buffer_store_dword v32, off, s[0:3], s32 ; 4-byte Folded Spill
+; GCN-NEXT: buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
-; GCN-DAG: v_writelane_b32 v32, s33, 2
+; GCN-DAG: v_writelane_b32 v40, s33, 2
 ; GCN-DAG: s_mov_b32 s33, s32
 ; GCN-DAG: s_add_u32 s32, s32, 0x400
-; GCN-DAG: v_writelane_b32 v32, s30, 0
-; GCN-DAG: v_writelane_b32 v32, s31, 1
+; GCN-DAG: v_writelane_b32 v40, s30, 0
+; GCN-DAG: v_writelane_b32 v40, s31, 1
 
 ; GCN: s_swappc_b64
 
-; GCN: v_readlane_b32 s4, v32, 0
-; GCN: v_readlane_b32 s5, v32, 1
+; GCN: v_readlane_b32 s4, v40, 0
+; GCN: v_readlane_b32 s5, v40, 1
 
 ; GCN-NEXT: s_sub_u32 s32, s32, 0x400
-; GCN-NEXT: v_readlane_b32 s33, v32, 2
+; GCN-NEXT: v_readlane_b32 s33, v40, 2
 ; GCN: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
-; GCN-NEXT: buffer_load_dword v32, off, s[0:3], s32 ; 4-byte Folded Reload
+; GCN-NEXT: buffer_load_dword v40, off, s[0:3], s32 ; 4-byte Folded Reload
 ; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
 ; GCN-NEXT: s_waitcnt vmcnt(0)
 ; GCN-NEXT: s_setpc_b64 s[4:5]
diff --git a/llvm/test/CodeGen/AMDGPU/regbank-reassign.mir b/llvm/test/CodeGen/AMDGPU/regbank-reassign.mir
--- a/llvm/test/CodeGen/AMDGPU/regbank-reassign.mir
+++ b/llvm/test/CodeGen/AMDGPU/regbank-reassign.mir
@@ -254,7 +254,7 @@
 ...
 
 # GCN-LABEL: csr{{$}}
-# GCN: V_AND_B32_e32 $vgpr4, $vgpr0,
+# GCN: V_AND_B32_e32 $vgpr37, $vgpr0,
 ---
 name:            csr
 tracksRegLiveness: true
diff --git a/llvm/test/CodeGen/AMDGPU/sibling-call.ll b/llvm/test/CodeGen/AMDGPU/sibling-call.ll
--- a/llvm/test/CodeGen/AMDGPU/sibling-call.ll
+++ b/llvm/test/CodeGen/AMDGPU/sibling-call.ll
@@ -152,9 +152,6 @@
 ; FIXME: Why load and store same location for stack args?
 ; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_a32i32:
 
-; GCN-DAG: buffer_store_dword v32, off, s[0:3], s32 offset:12 ; 4-byte Folded Spill
-; GCN-DAG: buffer_store_dword v33, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
-
 ; GCN-DAG: buffer_load_dword [[LOAD_0:v[0-9]+]], off, s[0:3], s32{{$}}
 ; GCN-DAG: buffer_load_dword [[LOAD_1:v[0-9]+]], off, s[0:3], s32 offset:4
 
@@ -163,9 +160,6 @@
 ; GCN-DAG: buffer_store_dword [[LOAD_0]], off, s[0:3], s32{{$}}
 ; GCN-DAG: buffer_store_dword [[LOAD_1]], off, s[0:3], s32 offset:4
 
-; GCN-DAG: buffer_load_dword v32, off, s[0:3], s32 offset:12 ; 4-byte Folded Reload
-; GCN-DAG: buffer_load_dword v33, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
-
 ; GCN-NOT: s32
 ; GCN: s_setpc_b64
 define fastcc i32 @sibling_call_i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] %c) #1 {
@@ -176,7 +170,7 @@
 
 ; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_a32i32_stack_object:
 ; GCN-DAG: v_mov_b32_e32 [[NINE:v[0-9]+]], 9
-; GCN: buffer_store_dword [[NINE]], off, s[0:3], s32 offset:40
+; GCN: buffer_store_dword [[NINE]], off, s[0:3], s32 offset:28
 ; GCN: s_setpc_b64
 define fastcc i32 @sibling_call_i32_fastcc_i32_i32_a32i32_stack_object(i32 %a, i32 %b, [32 x i32] %c) #1 {
 entry:
@@ -203,15 +197,15 @@
 ; Have another non-tail in the function
 ; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_other_call:
 ; GCN: s_or_saveexec_b64 s{{\[[0-9]+:[0-9]+\]}}, -1
-; GCN-NEXT: buffer_store_dword v34, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
+; GCN-NEXT: buffer_store_dword v42, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
 ; GCN-NEXT: s_mov_b64 exec
 ; GCN: s_mov_b32 s33, s32
 ; GCN-DAG: s_add_u32 s32, s32, 0x400
 
-; GCN-DAG: buffer_store_dword v32, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
-; GCN-DAG: buffer_store_dword v33, off, s[0:3], s33 ; 4-byte Folded Spill
-; GCN-DAG: v_writelane_b32 v34, s34, 0
-; GCN-DAG: v_writelane_b32 v34, s35, 1
+; GCN-DAG: buffer_store_dword v40, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; GCN-DAG: buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
+; GCN-DAG: v_writelane_b32 v42, s34, 0
+; GCN-DAG: v_writelane_b32 v42, s35, 1
 
 ; GCN-DAG: s_getpc_b64 s[4:5]
 ; GCN-DAG: s_add_u32 s4, s4, i32_fastcc_i32_i32@gotpcrel32@lo+4
@@ -220,11 +214,11 @@
 
 ; GCN: s_swappc_b64
 
-; GCN-DAG: v_readlane_b32 s34, v34, 0
-; GCN-DAG: v_readlane_b32 s35, v34, 1
+; GCN-DAG: v_readlane_b32 s34, v42, 0
+; GCN-DAG: v_readlane_b32 s35, v42, 1
 
-; GCN: buffer_load_dword v33, off, s[0:3], s33 ; 4-byte Folded Reload
-; GCN: buffer_load_dword v32, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
+; GCN: buffer_load_dword v41, off, s[0:3], s33 ; 4-byte Folded Reload
+; GCN: buffer_load_dword v40, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
 
 ; GCN: s_getpc_b64 s[4:5]
 ; GCN-NEXT: s_add_u32 s4, s4, sibling_call_i32_fastcc_i32_i32@rel32@lo+4
@@ -233,7 +227,7 @@
 ; GCN: s_sub_u32 s32, s32, 0x400
 ; GCN-NEXT: v_readlane_b32 s33,
 ; GCN-NEXT: s_or_saveexec_b64 s[6:7], -1
-; GCN-NEXT: buffer_load_dword v34, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
+; GCN-NEXT: buffer_load_dword v42, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
 ; GCN-NEXT: s_mov_b64 exec, s[6:7]
 ; GCN-NEXT: s_setpc_b64 s[4:5]
 define fastcc i32 @sibling_call_i32_fastcc_i32_i32_other_call(i32 %a, i32 %b, i32 %c) #1 {
@@ -248,11 +242,11 @@
 
 ; GCN-LABEL: {{^}}sibling_call_stack_objecti32_fastcc_i32_i32_a32i32:
 ; GCN-NOT: s33
-; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s32 offset:
+; GCN: buffer_load_dword v{{[0-9]+}}, off, s[0:3], s32 offset:
 
 ; GCN-NOT: s33
 
-; GCN: buffer_load_dword v{{[0-9]+}}, off, s[0:3], s32 offset:
+; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s32 offset:
 ; GCN: s_setpc_b64 s[4:5]
 define fastcc i32 @sibling_call_stack_objecti32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] %c) #1 {
 entry:
diff --git a/llvm/test/CodeGen/AMDGPU/spill-csr-frame-ptr-reg-copy.ll b/llvm/test/CodeGen/AMDGPU/spill-csr-frame-ptr-reg-copy.ll
--- a/llvm/test/CodeGen/AMDGPU/spill-csr-frame-ptr-reg-copy.ll
+++ b/llvm/test/CodeGen/AMDGPU/spill-csr-frame-ptr-reg-copy.ll
@@ -2,17 +2,17 @@
 
 ; GCN-LABEL: {{^}}spill_csr_s5_copy:
 ; GCN: s_or_saveexec_b64
-; GCN-NEXT: buffer_store_dword v32, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
+; GCN-NEXT: buffer_store_dword v40, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; GCN-NEXT: s_mov_b64 exec
-; GCN: v_writelane_b32 v32, s33, 2
+; GCN: v_writelane_b32 v40, s33, 2
 ; GCN: s_swappc_b64
 
 ; GCN: v_mov_b32_e32 [[K:v[0-9]+]], 9
 ; GCN: buffer_store_dword [[K]], off, s[0:3], s33{{$}}
 
-; GCN: v_readlane_b32 s33, v32, 2
+; GCN: v_readlane_b32 s33, v40, 2
 ; GCN: s_or_saveexec_b64
-; GCN-NEXT: buffer_load_dword v32, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
+; GCN-NEXT: buffer_load_dword v40, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
 ; GCN: s_mov_b64 exec
 ; GCN: s_setpc_b64
 define void @spill_csr_s5_copy() #0 {
diff --git a/llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll b/llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll
--- a/llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll
+++ b/llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll
@@ -29,7 +29,7 @@
 ; GCN-NEXT:    s_mov_b64 s[0:1], s[36:37]
 ; GCN-NEXT:    s_mov_b64 s[2:3], s[38:39]
 ; GCN-NEXT:    s_mov_b32 s32, 0xc0000
-; GCN-NEXT:    v_add_nc_u32_e64 v32, 4, 0x4000
+; GCN-NEXT:    v_add_nc_u32_e64 v40, 4, 0x4000
 ; GCN-NEXT:    ; implicit-def: $vcc_hi
 ; GCN-NEXT:    s_getpc_b64 s[4:5]
 ; GCN-NEXT:    s_add_u32 s4, s4, svm_eval_nodes@rel32@lo+4
@@ -41,8 +41,8 @@
 ; GCN-NEXT:    s_and_saveexec_b32 s0, vcc_lo
 ; GCN-NEXT:    s_cbranch_execz BB0_2
 ; GCN-NEXT:  ; %bb.1: ; %if.then4.i
-; GCN-NEXT:    buffer_load_dword v0, v32, s[36:39], s32 offen
-; GCN-NEXT:    buffer_load_dword v1, v32, s[36:39], s32 offen offset:4
+; GCN-NEXT:    buffer_load_dword v0, v40, s[36:39], s32 offen
+; GCN-NEXT:    buffer_load_dword v1, v40, s[36:39], s32 offen offset:4
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_add_nc_u32_e32 v0, v1, v0
 ; GCN-NEXT:    v_mul_lo_u32 v0, 0x41c64e6d, v0
diff --git a/llvm/test/CodeGen/AMDGPU/vgpr-tuple-allocation.ll b/llvm/test/CodeGen/AMDGPU/vgpr-tuple-allocation.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/vgpr-tuple-allocation.ll
@@ -0,0 +1,170 @@
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX10 %s
+
+declare void @extern_func()
+
+define <4 x float> @non_preserved_vgpr_tuple8(<8 x i32> %rsrc, <4 x i32> %samp, float %bias, float %zcompare, float %s, float %t, float %clamp) {
+; The vgpr tuple8 operand in image_gather4_c_b_cl instruction needs not be
+; preserved across the call and should get 8 scratch registers.
+
+; GFX9-LABEL: non_preserved_vgpr_tuple8:
+; GFX9: buffer_store_dword v44, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
+; GFX9: buffer_store_dword v40, off, s[0:3], s33 offset:12 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v41, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v42, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v43, off, s[0:3], s33 ; 4-byte Folded Spill
+
+; GFX9: v_mov_b32_e32 v37, v11
+; GFX9-NEXT: v_mov_b32_e32 v38, v10
+; GFX9-NEXT: v_mov_b32_e32 v49, v9
+; GFX9-NEXT: v_writelane_b32 v44, s30, 0
+; GFX9-NEXT: v_mov_b32_e32 v36, v16
+; GFX9-NEXT: v_mov_b32_e32 v35, v15
+; GFX9-NEXT: v_mov_b32_e32 v34, v14
+; GFX9-NEXT: v_mov_b32_e32 v33, v13
+; GFX9-NEXT: v_mov_b32_e32 v32, v12
+
+; GFX9: ;;#ASMSTART
+; GFX9-NEXT: ;;#ASMEND
+
+; GFX9: image_gather4_c_b_cl v[40:43], v[32:39], s[4:11], s[12:15] dmask:0x1
+; GFX9-NEXT: s_getpc_b64 s[4:5]
+; GFX9-NEXT: s_add_u32 s4, s4, extern_func@gotpcrel32@lo+4
+; GFX9-NEXT: s_addc_u32 s5, s5, extern_func@gotpcrel32@hi+4
+; GFX9-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX9-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-NEXT: s_swappc_b64 s[30:31], s[4:5]
+
+; GFX9: buffer_load_dword v43, off, s[0:3], s33 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v42, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v41, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v40, off, s[0:3], s33 offset:12 ; 4-byte Folded Reload
+; GFX9: buffer_load_dword v44, off, s[0:3], s32 offset:16 ; 4-byte Folded Reload
+; GFX9: s_setpc_b64 s[4:5]
+;
+; GFX10-LABEL: non_preserved_vgpr_tuple8:
+; GFX10: buffer_store_dword v44, off, s[0:3], s32 offset:16 ; 4-byte Folded Spill
+; GFX10: buffer_store_dword v40, off, s[0:3], s33 offset:12 ; 4-byte Folded Spill
+; GFX10-NEXT: buffer_store_dword v41, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
+; GFX10-NEXT: buffer_store_dword v42, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; GFX10-NEXT: buffer_store_dword v43, off, s[0:3], s33 ; 4-byte Folded Spill
+
+; GFX10: v_mov_b32_e32 v36, v16
+; GFX10-NEXT: v_mov_b32_e32 v35, v15
+; GFX10-NEXT: v_mov_b32_e32 v34, v14
+; GFX10-NEXT: v_mov_b32_e32 v33, v13
+; GFX10-NEXT: v_mov_b32_e32 v32, v12
+
+; GFX10: ;;#ASMSTART
+; GFX10-NEXT: ;;#ASMEND
+
+; GFX10: image_gather4_c_b_cl v[40:43], v[32:39], s[4:11], s[12:15] dmask:0x1
+; GFX10-NEXT: v_nop
+; GFX10-NEXT: s_getpc_b64 s[4:5]
+; GFX10-NEXT: s_add_u32 s4, s4, extern_func@gotpcrel32@lo+4
+; GFX10-NEXT: s_addc_u32 s5, s5, extern_func@gotpcrel32@hi+4
+; GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GFX10-NEXT: s_swappc_b64 s[30:31], s[4:5]
+
+; GFX10: buffer_load_dword v43, off, s[0:3], s33 ; 4-byte Folded Reload
+; GFX10-NEXT: buffer_load_dword v42, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
+; GFX10-NEXT: buffer_load_dword v41, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
+; GFX10-NEXT: buffer_load_dword v40, off, s[0:3], s33 offset:12 ; 4-byte Folded Reload
+
+; GFX10: buffer_load_dword v44, off, s[0:3], s32 offset:16 ; 4-byte Folded Reload
+; GFX10: s_setpc_b64 s[4:5]
+main_body:
+  call void asm sideeffect "", "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7}"() #0
+  call void asm sideeffect "", "~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15}"() #0
+  call void asm sideeffect "", "~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23}"() #0
+  call void asm sideeffect "", "~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"() #0
+  %v = call <4 x float> @llvm.amdgcn.image.gather4.c.b.cl.2d.v4f32.f32.f32(i32 1, float %bias, float %zcompare, float %s, float %t, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 false, i32 0, i32 0)
+  call void @extern_func()
+  ret <4 x float> %v
+}
+
+define <4 x float> @call_preserved_vgpr_tuple8(<8 x i32> %rsrc, <4 x i32> %samp, float %bias, float %zcompare, float %s, float %t, float %clamp) {
+; The vgpr tuple8 operand in image_gather4_c_b_cl instruction needs to be preserved
+; across the call and should get allcoated to 8 CSRs.
+; Only the lower 5 sub-registers of the tuple are preserved.
+; The upper 3 sub-registers are unused.
+
+; GFX9-LABEL: call_preserved_vgpr_tuple8:
+; GFX9: buffer_store_dword v56, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
+; GFX9: buffer_store_dword v40, off, s[0:3], s33 offset:16 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v41, off, s[0:3], s33 offset:12 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v42, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v43, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v44, off, s[0:3], s33 ; 4-byte Folded Spill
+
+; GFX9: v_mov_b32_e32 v44, v16
+; GFX9-NEXT: v_mov_b32_e32 v43, v15
+; GFX9-NEXT: v_mov_b32_e32 v42, v14
+; GFX9-NEXT: v_mov_b32_e32 v41, v13
+; GFX9-NEXT: v_mov_b32_e32 v40, v12
+
+; GFX9: s_getpc_b64 s[4:5]
+; GFX9-NEXT: s_add_u32 s4, s4, extern_func@gotpcrel32@lo+4
+; GFX9-NEXT: s_addc_u32 s5, s5, extern_func@gotpcrel32@hi+4
+; GFX9-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX9-NEXT: image_gather4_c_b_cl v[0:3], v[40:47], s[36:43], s[44:47] dmask:0x1
+; GFX9-NEXT: s_waitcnt vmcnt(0)
+; GFX9-NEXT: global_store_dwordx4 v[0:1], v[0:3], off
+; GFX9-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-NEXT: s_swappc_b64 s[30:31], s[4:5]
+; GFX9-NEXT: image_gather4_c_b_cl v[0:3], v[40:47], s[36:43], s[44:47] dmask:0x1
+
+; GFX9: buffer_load_dword v44, off, s[0:3], s33 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v43, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v42, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v41, off, s[0:3], s33 offset:12 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v40, off, s[0:3], s33 offset:16 ; 4-byte Folded Reload
+
+; GFX9: buffer_load_dword v56, off, s[0:3], s32 offset:20 ; 4-byte Folded Reload
+; GFX9: s_setpc_b64 s[4:5]
+;
+; GFX10-LABEL: call_preserved_vgpr_tuple8:
+; GFX10: buffer_store_dword v45, off, s[0:3], s32 offset:20 ; 4-byte Folded Spill
+; GFX10: buffer_store_dword v40, off, s[0:3], s33 offset:16 ; 4-byte Folded Spill
+; GFX10-NEXT: buffer_store_dword v41, off, s[0:3], s33 offset:12 ; 4-byte Folded Spill
+; GFX10-NEXT: buffer_store_dword v42, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
+; GFX10-NEXT: buffer_store_dword v43, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; GFX10-NEXT: buffer_store_dword v44, off, s[0:3], s33 ; 4-byte Folded Spill
+
+; GFX10: s_getpc_b64 s[4:5]
+; GFX10-NEXT: s_add_u32 s4, s4, extern_func@gotpcrel32@lo+4
+; GFX10-NEXT: s_addc_u32 s5, s5, extern_func@gotpcrel32@hi+4
+; GFX10-NEXT: v_mov_b32_e32 v40, v16
+; GFX10-NEXT: v_mov_b32_e32 v41, v15
+; GFX10-NEXT: image_gather4_c_b_cl v[0:3], v[12:19], s[36:43], s[44:47] dmask:0x1
+; GFX10-NEXT: v_mov_b32_e32 v42, v14
+; GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT: v_mov_b32_e32 v43, v13
+; GFX10-NEXT: v_mov_b32_e32 v44, v12
+; GFX10-NEXT: ; implicit-def: $vcc_hi
+; GFX10-NEXT: s_waitcnt vmcnt(0)
+; GFX10-NEXT: global_store_dwordx4 v[0:1], v[0:3], off
+; GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GFX10-NEXT: s_swappc_b64 s[30:31], s[4:5]
+; GFX10-NEXT: image_gather4_c_b_cl v[0:3], [v44, v43, v42, v41, v40], s[36:43], s[44:47] dmask:0x1
+
+; GFX10: buffer_load_dword v44, off, s[0:3], s33 ; 4-byte Folded Reload
+; GFX10-NEXT: buffer_load_dword v43, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
+; GFX10-NEXT: buffer_load_dword v42, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
+; GFX10-NEXT: buffer_load_dword v41, off, s[0:3], s33 offset:12 ; 4-byte Folded Reload
+; GFX10-NEXT: buffer_load_dword v40, off, s[0:3], s33 offset:16 ; 4-byte Folded Reload
+; GFX10: buffer_load_dword v45, off, s[0:3], s32 offset:20 ; 4-byte Folded Reload
+; GFX10: s_setpc_b64 s[4:5]
+main_body:
+  %v = call <4 x float> @llvm.amdgcn.image.gather4.c.b.cl.2d.v4f32.f32.f32(i32 1, float %bias, float %zcompare, float %s, float %t, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 false, i32 0, i32 0)
+  store <4 x float> %v, <4 x float> addrspace(1)* undef
+  call void @extern_func()
+  %v1 = call <4 x float> @llvm.amdgcn.image.gather4.c.b.cl.2d.v4f32.f32.f32(i32 1, float %bias, float %zcompare, float %s, float %t, float %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 false, i32 0, i32 0)
+  ret <4 x float> %v1
+}
+
+declare <4 x float> @llvm.amdgcn.image.gather4.c.b.cl.2d.v4f32.f32.f32(i32 immarg, float, float, float, float, float, <8 x i32>, <4 x i32>, i1 immarg, i32 immarg, i32 immarg) #1
+
+attributes #0 = { nounwind writeonly }
+attributes #1 = { nounwind readonly }
diff --git a/llvm/test/CodeGen/AMDGPU/virtregrewrite-undef-identity-copy.mir b/llvm/test/CodeGen/AMDGPU/virtregrewrite-undef-identity-copy.mir
--- a/llvm/test/CodeGen/AMDGPU/virtregrewrite-undef-identity-copy.mir
+++ b/llvm/test/CodeGen/AMDGPU/virtregrewrite-undef-identity-copy.mir
@@ -29,7 +29,7 @@
 body:             |
   bb.0:
     ; CHECK-LABEL: name: undef_identity_copy
-    ; CHECK: renamable $vgpr32_vgpr33_vgpr34_vgpr35 = FLAT_LOAD_DWORDX4 undef renamable $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, addrspace 1)
+    ; CHECK: renamable $vgpr40_vgpr41_vgpr42_vgpr43 = FLAT_LOAD_DWORDX4 undef renamable $vgpr0_vgpr1, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, addrspace 1)
     ; CHECK: renamable $sgpr6_sgpr7 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @foo + 4, target-flags(amdgpu-rel32-hi) @foo + 4, implicit-def dead $scc
     ; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95
     ; CHECK: $sgpr4 = COPY $sgpr95
@@ -38,9 +38,9 @@
     ; CHECK: renamable $sgpr6_sgpr7 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @bar + 4, target-flags(amdgpu-rel32-hi) @bar + 4, implicit-def dead $scc
     ; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95
     ; CHECK: $sgpr4 = COPY $sgpr95
-    ; CHECK: $vgpr0 = COPY renamable $vgpr32
-    ; CHECK: $vgpr1 = COPY renamable $vgpr33
-    ; CHECK: $vgpr2 = COPY renamable $vgpr34
+    ; CHECK: $vgpr0 = COPY renamable $vgpr40
+    ; CHECK: $vgpr1 = COPY renamable $vgpr41
+    ; CHECK: $vgpr2 = COPY renamable $vgpr42
     ; CHECK: $vgpr3 = KILL undef renamable $vgpr3
     ; CHECK: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr6_sgpr7, @bar, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4, implicit $vgpr0, implicit killed $vgpr1, implicit killed $vgpr2, implicit killed $vgpr3, implicit-def $vgpr0
     ; CHECK: ADJCALLSTACKDOWN 0, 4, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95
diff --git a/llvm/test/CodeGen/AMDGPU/wave32.ll b/llvm/test/CodeGen/AMDGPU/wave32.ll
--- a/llvm/test/CodeGen/AMDGPU/wave32.ll
+++ b/llvm/test/CodeGen/AMDGPU/wave32.ll
@@ -1058,30 +1058,30 @@
 
 ; GFX1064-NEXT: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
 ; GFX1032-NEXT: s_or_saveexec_b32 [[COPY_EXEC0:s[0-9]]], -1{{$}}
-; GCN-NEXT: buffer_store_dword v32, off, s[0:3], s32 ; 4-byte Folded Spill
+; GCN-NEXT: buffer_store_dword v40, off, s[0:3], s32 ; 4-byte Folded Spill
 ; GCN-NEXT: v_nop
 ; GFX1064-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
 ; GFX1032-NEXT: s_mov_b32 exec_lo, [[COPY_EXEC0]]
 
-; GCN-NEXT: v_writelane_b32 v32, s33, 2
+; GCN-NEXT: v_writelane_b32 v40, s33, 2
 ; GCN: s_mov_b32 s33, s32
 ; GFX1064: s_add_u32 s32, s32, 0x400
 ; GFX1032: s_add_u32 s32, s32, 0x200
 
 
-; GCN-DAG: v_writelane_b32 v32, s30, 0
-; GCN-DAG: v_writelane_b32 v32, s31, 1
+; GCN-DAG: v_writelane_b32 v40, s30, 0
+; GCN-DAG: v_writelane_b32 v40, s31, 1
 ; GCN: s_swappc_b64
-; GCN-DAG: v_readlane_b32 s4, v32, 0
-; GCN-DAG: v_readlane_b32 s5, v32, 1
+; GCN-DAG: v_readlane_b32 s4, v40, 0
+; GCN-DAG: v_readlane_b32 s5, v40, 1
 
 
 ; GFX1064: s_sub_u32 s32, s32, 0x400
 ; GFX1032: s_sub_u32 s32, s32, 0x200
-; GCN: v_readlane_b32 s33, v32, 2
+; GCN: v_readlane_b32 s33, v40, 2
 ; GFX1064: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
 ; GFX1032: s_or_saveexec_b32 [[COPY_EXEC1:s[0-9]]], -1{{$}}
-; GCN-NEXT: buffer_load_dword v32, off, s[0:3], s32 ; 4-byte Folded Reload
+; GCN-NEXT: buffer_load_dword v40, off, s[0:3], s32 ; 4-byte Folded Reload
 ; GCN-NEXT: v_nop
 ; GFX1064-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
 ; GFX1032-NEXT: s_mov_b32 exec_lo, [[COPY_EXEC1]]