Index: cfe/trunk/lib/CodeGen/TargetInfo.cpp
===================================================================
--- cfe/trunk/lib/CodeGen/TargetInfo.cpp
+++ cfe/trunk/lib/CodeGen/TargetInfo.cpp
@@ -7664,7 +7664,7 @@
 
   if (M.getLangOpts().OpenCL && FD->hasAttr<OpenCLKernelAttr>() &&
       (M.getTriple().getOS() == llvm::Triple::AMDHSA))
-    F->addFnAttr("amdgpu-implicitarg-num-bytes", "32");
+    F->addFnAttr("amdgpu-implicitarg-num-bytes", "48");
 
   const auto *FlatWGS = FD->getAttr<AMDGPUFlatWorkGroupSizeAttr>();
   if (ReqdWGS || FlatWGS) {
Index: cfe/trunk/test/CodeGenOpenCL/amdgpu-attrs.cl
===================================================================
--- cfe/trunk/test/CodeGenOpenCL/amdgpu-attrs.cl
+++ cfe/trunk/test/CodeGenOpenCL/amdgpu-attrs.cl
@@ -158,30 +158,30 @@
 // CHECK-NOT: "amdgpu-num-sgpr"="0"
 // CHECK-NOT: "amdgpu-num-vgpr"="0"
 
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" 
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_64_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="64,64" "amdgpu-implicitarg-num-bytes"="32" 
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_16_128]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="16,128" "amdgpu-implicitarg-num-bytes"="32" 
-// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-waves-per-eu"="2"
-// CHECK-DAG: attributes [[WAVES_PER_EU_2_4]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-waves-per-eu"="2,4"
-// CHECK-DAG: attributes [[NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" 
-// CHECK-DAG: attributes [[NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" 
-
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-waves-per-eu"="2"
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-waves-per-eu"="2,4"
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" 
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" 
-// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
-// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
-// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
-// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
-// CHECK-DAG: attributes [[NUM_SGPR_32_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" 
-
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" 
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_64_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="64,64" "amdgpu-implicitarg-num-bytes"="48" 
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_16_128]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="16,128" "amdgpu-implicitarg-num-bytes"="48" 
+// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-waves-per-eu"="2"
+// CHECK-DAG: attributes [[WAVES_PER_EU_2_4]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-waves-per-eu"="2,4"
+// CHECK-DAG: attributes [[NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" 
+// CHECK-DAG: attributes [[NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-vgpr"="64" 
+
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-waves-per-eu"="2"
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-waves-per-eu"="2,4"
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" 
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-vgpr"="64" 
+// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
+// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
+// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
+// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
+// CHECK-DAG: attributes [[NUM_SGPR_32_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" 
+
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
 
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
-// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="32" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
+// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64]] = { convergent noinline nounwind optnone "amdgpu-flat-work-group-size"="32,64" "amdgpu-implicitarg-num-bytes"="48" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
 
 // CHECK-DAG: attributes [[A_FUNCTION]] = { convergent noinline nounwind optnone "correctly-rounded-divide-sqrt-fp-math"="false"