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/amdhsa-kernarg-size.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/amdhsa-kernarg-size.ll
@@ -0,0 +1,20 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 --amdhsa-code-object-version=3 < %s | FileCheck --check-prefixes=CHECK,COV3 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 --amdhsa-code-object-version=5 < %s | FileCheck --check-prefixes=CHECK,COV5 %s
+
+; CHECK-LABEL: kernel_with_implicitarg_ptr:
+; COV3:	.amdhsa_kernarg_size 64
+; COV5:	.amdhsa_kernarg_size 264
+define amdgpu_kernel void @kernel_with_implicitarg_ptr(i8 addrspace(4)* addrspace(1)* %ptr)  {
+  %implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
+  store volatile i8 addrspace(4)* %implicitarg.ptr, i8 addrspace(4)* addrspace(1)* %ptr
+  ret void
+}
+
+; CHECK-LABEL: kernel_without_implicitarg_ptr:
+; CHECK:	.amdhsa_kernarg_size 8
+define amdgpu_kernel void @kernel_without_implicitarg_ptr(i8 addrspace(4)* addrspace(1)* %ptr)  {
+  store volatile i8 addrspace(4)* undef, i8 addrspace(4)* addrspace(1)* %ptr
+  ret void
+}
+
+declare i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()