Index: llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -652,7 +652,8 @@
     return 16;
 
   // Assume all implicit inputs are used by default
-  return AMDGPU::getIntegerAttribute(F, "amdgpu-implicitarg-num-bytes", 56);
+  unsigned NBytes = (AMDGPU::getAmdhsaCodeObjectVersion() >= 5) ? 256 : 56;
+  return AMDGPU::getIntegerAttribute(F, "amdgpu-implicitarg-num-bytes", NBytes);
 }
 
 uint64_t AMDGPUSubtarget::getExplicitKernArgSize(const Function &F,
Index: llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll
+++ llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll
@@ -1,7 +1,8 @@
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,HSA %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=5 -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=COV5 %s
 ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,MESA %s
 
-; GCN-LABEL: {{^}}kernel_implicitarg_ptr_empty:
+; CHECK-LABEL: {{^}}kernel_implicitarg_ptr_empty:
 ; HSA: enable_sgpr_kernarg_segment_ptr = 1
 ; HSA: kernarg_segment_byte_size = 56
 ; HSA: kernarg_segment_alignment = 4
@@ -11,6 +12,8 @@
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_load_dword s0, s[4:5], 0x0
+
+; COV5: .amdhsa_kernarg_size 256
 define amdgpu_kernel void @kernel_implicitarg_ptr_empty() #0 {
   %implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
   %cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
@@ -18,7 +21,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}kernel_implicitarg_ptr_empty_0implicit:
+; CHECK-LABEL: {{^}}kernel_implicitarg_ptr_empty_0implicit:
 ; HSA: enable_sgpr_kernarg_segment_ptr = 0
 ; HSA: kernarg_segment_byte_size = 0
 ; HSA: kernarg_segment_alignment = 4
@@ -31,6 +34,8 @@
 ; HSA: s_load_dword s0, [[NULL]], 0x0
 
 ; MESA: s_load_dword s0, s[4:5], 0x0
+
+; COV5: .amdhsa_kernarg_size 0
 define amdgpu_kernel void @kernel_implicitarg_ptr_empty_0implicit() #3 {
   %implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
   %cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
@@ -38,7 +43,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}opencl_kernel_implicitarg_ptr_empty:
+; CHECK-LABEL: {{^}}opencl_kernel_implicitarg_ptr_empty:
 ; GCN: enable_sgpr_kernarg_segment_ptr = 1
 
 ; HSA: kernarg_segment_byte_size = 48
@@ -48,6 +53,8 @@
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_load_dword s0, s[4:5], 0x0
+
+; COV5: .amdhsa_kernarg_size 48
 define amdgpu_kernel void @opencl_kernel_implicitarg_ptr_empty() #1 {
   %implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
   %cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
@@ -55,7 +62,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}kernel_implicitarg_ptr:
+; CHECK-LABEL: {{^}}kernel_implicitarg_ptr:
 ; GCN: enable_sgpr_kernarg_segment_ptr = 1
 
 ; HSA: kernarg_segment_byte_size = 168
@@ -65,6 +72,8 @@
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_load_dword s0, s[4:5], 0x1c
+
+; COV5: .amdhsa_kernarg_size 368
 define amdgpu_kernel void @kernel_implicitarg_ptr([112 x i8]) #0 {
   %implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
   %cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
@@ -72,7 +81,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}opencl_kernel_implicitarg_ptr:
+; CHECK-LABEL: {{^}}opencl_kernel_implicitarg_ptr:
 ; GCN: enable_sgpr_kernarg_segment_ptr = 1
 
 ; HSA: kernarg_segment_byte_size = 160
@@ -82,6 +91,8 @@
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_load_dword s0, s[4:5], 0x1c
+
+; COV5: .amdhsa_kernarg_size 160
 define amdgpu_kernel void @opencl_kernel_implicitarg_ptr([112 x i8]) #1 {
   %implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
   %cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
@@ -89,7 +100,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}func_implicitarg_ptr:
+; CHECK-LABEL: {{^}}func_implicitarg_ptr:
 ; GCN: s_waitcnt
 ; GCN: s_load_dword s{{[0-9]+}}, s[8:9], 0x0
 ; GCN-NEXT: s_waitcnt
@@ -101,7 +112,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}opencl_func_implicitarg_ptr:
+; CHECK-LABEL: {{^}}opencl_func_implicitarg_ptr:
 ; GCN: s_waitcnt
 ; GCN: s_load_dword s{{[0-9]+}}, s[8:9], 0x0
 ; GCN-NEXT: s_waitcnt
@@ -113,7 +124,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty:
+; CHECK-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty:
 ; HSA: enable_sgpr_kernarg_segment_ptr = 1
 ; HSA: kernarg_segment_byte_size = 56
 ; HSA: kernarg_segment_alignment = 4
@@ -124,12 +135,14 @@
 
 ; GCN: s_mov_b64 s[8:9], s[4:5]
 ; GCN: s_swappc_b64
+
+; COV5: .amdhsa_kernarg_size 256
 define amdgpu_kernel void @kernel_call_implicitarg_ptr_func_empty() #0 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
-; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty_implicit0:
+; CHECK-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty_implicit0:
 ; HSA: enable_sgpr_kernarg_segment_ptr = 0
 ; HSA: kernarg_segment_byte_size = 0
 ; HSA: kernarg_segment_alignment = 4
@@ -141,12 +154,14 @@
 ; HSA: s_mov_b64 s[8:9], 0{{$}}
 ; MESA: s_mov_b64 s[8:9], s[4:5]{{$}}
 ; GCN: s_swappc_b64
+
+; COV5: .amdhsa_kernarg_size 0
 define amdgpu_kernel void @kernel_call_implicitarg_ptr_func_empty_implicit0() #3 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
-; GCN-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func_empty:
+; CHECK-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func_empty:
 ; GCN: enable_sgpr_kernarg_segment_ptr = 1
 ; HSA: kernarg_segment_byte_size = 48
 ; HSA: kernarg_segment_alignment = 4
@@ -155,16 +170,20 @@
 ; GCN-NOT: s4
 ; GCN-NOT: s5
 ; GCN: s_swappc_b64
+
+; COV5: .amdhsa_kernarg_size 48
 define amdgpu_kernel void @opencl_kernel_call_implicitarg_ptr_func_empty() #1 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
-; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func:
+; CHECK-LABEL: {{^}}kernel_call_implicitarg_ptr_func:
 ; GCN: enable_sgpr_kernarg_segment_ptr = 1
 ; HSA: kernarg_segment_byte_size = 168
 ; HSA: kernarg_segment_alignment = 4
 
+
+
 ; MESA: kernarg_segment_byte_size = 128
 ; MESA: kernarg_segment_alignment = 4
 
@@ -173,12 +192,14 @@
 
 ; GCN: s_addc_u32 s9, s5, 0{{$}}
 ; GCN: s_swappc_b64
+
+; COV5: .amdhsa_kernarg_size 368
 define amdgpu_kernel void @kernel_call_implicitarg_ptr_func([112 x i8]) #0 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
-; GCN-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func:
+; CHECK-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func:
 ; GCN: enable_sgpr_kernarg_segment_ptr = 1
 ; HSA: kernarg_segment_byte_size = 160
 ; HSA: kernarg_segment_alignment = 4
@@ -188,12 +209,14 @@
 ; GCN: s_add_u32 s8, s4, 0x70
 ; GCN: s_addc_u32 s9, s5, 0{{$}}
 ; GCN: s_swappc_b64
+
+; COV5: .amdhsa_kernarg_size 160
 define amdgpu_kernel void @opencl_kernel_call_implicitarg_ptr_func([112 x i8]) #1 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
-; GCN-LABEL: {{^}}func_call_implicitarg_ptr_func:
+; CHECK-LABEL: {{^}}func_call_implicitarg_ptr_func:
 ; GCN-NOT: s8
 ; GCN-NOT: s9
 ; GCN-NOT: s[8:9]
@@ -204,7 +227,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}opencl_func_call_implicitarg_ptr_func:
+; CHECK-LABEL: {{^}}opencl_func_call_implicitarg_ptr_func:
 ; GCN-NOT: s8
 ; GCN-NOT: s9
 ; GCN-NOT: s[8:9]
@@ -215,7 +238,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}func_kernarg_implicitarg_ptr:
+; CHECK-LABEL: {{^}}func_kernarg_implicitarg_ptr:
 ; GCN: s_waitcnt
 ; GCN-DAG: s_mov_b64 [[NULL:s\[[0-9]+:[0-9]+\]]], 0
 ; GCN-DAG: s_load_dword s{{[0-9]+}}, [[NULL]], 0x0
@@ -231,7 +254,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}opencl_func_kernarg_implicitarg_ptr:
+; CHECK-LABEL: {{^}}opencl_func_kernarg_implicitarg_ptr:
 ; GCN: s_waitcnt
 ; GCN-DAG: s_mov_b64 [[NULL:s\[[0-9]+:[0-9]+\]]], 0
 ; GCN-DAG: s_load_dword s{{[0-9]+}}, [[NULL]], 0x0
@@ -247,7 +270,7 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}kernel_call_kernarg_implicitarg_ptr_func:
+; CHECK-LABEL: {{^}}kernel_call_kernarg_implicitarg_ptr_func:
 ; GCN: s_add_u32 s8, s4, 0x70
 ; GCN: s_addc_u32 s9, s5, 0
 ; GCN: s_swappc_b64
@@ -256,10 +279,12 @@
   ret void
 }
 
-; GCN-LABEL: {{^}}kernel_implicitarg_no_struct_align_padding:
+; CHECK-LABEL: {{^}}kernel_implicitarg_no_struct_align_padding:
 ; HSA: kernarg_segment_byte_size = 120
 ; MESA: kernarg_segment_byte_size = 84
 ; GCN: kernarg_segment_alignment = 6
+
+; COV5: .amdhsa_kernarg_size 120
 define amdgpu_kernel void @kernel_implicitarg_no_struct_align_padding(<16 x i32>, i32) #1 {
   %implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
   %cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
@@ -267,7 +292,6 @@
   ret void
 }
 
-
 ; HSA-LABEL: Kernels:
 ; HSA-LABEL: - Name:            kernel_implicitarg_ptr_empty
 ; HSA: CodeProps:
@@ -318,6 +342,55 @@
 ; HSA: KernargSegmentSize: 120
 ; HSA: KernargSegmentAlign: 64
 
+; COV5-LABEL:   amdhsa.kernels:
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 256
+; COV5-LABEL:   .name:           kernel_implicitarg_ptr_empty
+
+; COV5:         .kernarg_segment_align: 4
+; COV5-NEXT:    .kernarg_segment_size: 0
+; COV5-LABEL:   .name:           kernel_implicitarg_ptr_empty_0implicit
+
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 48
+; COV5-LABEL:   .name:           opencl_kernel_implicitarg_ptr_empty
+
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 368
+; COV5-LABEL:   .name:           kernel_implicitarg_ptr
+
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 160
+; COV5-LABEL:   .name:           opencl_kernel_implicitarg_ptr
+
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 256
+; COV5-LABEL:   .name:           kernel_call_implicitarg_ptr_func_empty
+
+; COV5:         .kernarg_segment_align: 4
+; COV5-NEXT:    .kernarg_segment_size: 0
+; COV5-LABEL:   .name:           kernel_call_implicitarg_ptr_func_empty_implicit0
+
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 48
+; COV5-LABEL:   .name:           opencl_kernel_call_implicitarg_ptr_func_empty
+
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 368
+; COV5-LABEL:   .name:           kernel_call_implicitarg_ptr_func
+
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 160
+; COV5-LABEL:   .name:           opencl_kernel_call_implicitarg_ptr_func
+
+; COV5:         .kernarg_segment_align: 8
+; COV5-NEXT:    .kernarg_segment_size: 368
+; COV5-LABEL:   .name:           kernel_call_kernarg_implicitarg_ptr_func
+
+; COV5:         .kernarg_segment_align: 64
+; COV5-NEXT:    .kernarg_segment_size: 120
+; COV5-LABEL:   .name:           kernel_implicitarg_no_struct_align_padding
+
 declare i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() #2
 declare i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr() #2