Index: lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
+++ lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
@@ -730,7 +730,8 @@
     header.code_properties |= AMD_CODE_PROPERTY_IS_XNACK_SUPPORTED;
 
   // FIXME: Should use getKernArgSize
-  header.kernarg_segment_byte_size = MFI->getABIArgOffset();
+  header.kernarg_segment_byte_size =
+      STM.getKernArgSegmentSize(MFI->getABIArgOffset());
   header.wavefront_sgpr_count = KernelInfo.NumSGPR;
   header.workitem_vgpr_count = KernelInfo.NumVGPR;
   header.workitem_private_segment_byte_size = KernelInfo.ScratchSize;
Index: lib/Target/AMDGPU/AMDGPUSubtarget.h
===================================================================
--- lib/Target/AMDGPU/AMDGPUSubtarget.h
+++ lib/Target/AMDGPU/AMDGPUSubtarget.h
@@ -142,6 +142,10 @@
     return TargetTriple.getOS() == Triple::Mesa3D;
   }
 
+  bool isOpenCLEnv() const {
+    return TargetTriple.getEnvironment() == Triple::OpenCL;
+  }
+
   Generation getGeneration() const {
     return Gen;
   }
@@ -288,6 +292,14 @@
     return isAmdHsaOS() ? 8 : 4;
   }
 
+  unsigned getImplicitArgNumBytes() const {
+    if (isMesa3DOS())
+      return 16;
+    if (isAmdHsaOS() && isOpenCLEnv())
+      return 32;
+    return 0;
+  }
+
   unsigned getStackAlignment() const {
     // Scratch is allocated in 256 dword per wave blocks.
     return 4 * 256 / getWavefrontSize();
@@ -521,6 +533,8 @@
     return SGPRInitBug;
   }
 
+  unsigned getKernArgSegmentSize(unsigned ExplictArgBytes) const;
+
   /// Return the maximum number of waves per SIMD for kernels using \p SGPRs SGPRs
   unsigned getOccupancyWithNumSGPRs(unsigned SGPRs) const;
 
Index: lib/Target/AMDGPU/AMDGPUSubtarget.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -297,6 +297,15 @@
   return EnableVGPRSpilling || !AMDGPU::isShader(F.getCallingConv());
 }
 
+unsigned SISubtarget::getKernArgSegmentSize(unsigned ExplicitArgBytes) const {
+  unsigned ImplicitBytes = getImplicitArgNumBytes();
+  if (ImplicitBytes == 0)
+    return ExplicitArgBytes;
+
+  unsigned Alignment = getAlignmentForImplicitArgPtr();
+  return alignTo(ExplicitArgBytes, Alignment) + ImplicitBytes;
+}
+
 unsigned SISubtarget::getOccupancyWithNumSGPRs(unsigned SGPRs) const {
   if (getGeneration() >= SISubtarget::VOLCANIC_ISLANDS) {
     if (SGPRs <= 80)
Index: test/CodeGen/AMDGPU/llvm.amdgcn.kernarg.segment.ptr.ll
===================================================================
--- test/CodeGen/AMDGPU/llvm.amdgcn.kernarg.segment.ptr.ll
+++ test/CodeGen/AMDGPU/llvm.amdgcn.kernarg.segment.ptr.ll
@@ -1,4 +1,5 @@
-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V2,HSA,ALL %s
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V2,HSA,ALL,HSA-NOENV %s
+; RUN: llc -mtriple=amdgcn--amdhsa-opencl -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V2,HSA,ALL,HSA-OPENCL %s
 ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V2,OS-MESA3D,MESA,ALL %s
 ; RUN: llc -mtriple=amdgcn-mesa-unknown -verify-machineinstrs < %s | FileCheck -check-prefixes=OS-UNKNOWN,MESA,ALL %s
 
@@ -29,6 +30,9 @@
 }
 
 ; ALL-LABEL: {{^}}test_implicit_alignment
+; HSA-NOENV: kernarg_segment_byte_size = 10
+; HSA-OPENCL: kernarg_segment_byte_size = 48
+; OS-MESA3D: kernarg_segment_byte_size = 28
 ; OS-UNKNOWN: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xc
 ; HSA: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x4
 ; OS-MESA3D: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x3