[AMDGPU] Update OpenCL to use 48 bytes of implicit arguments for AMDGPU (CLANG)

[t-tye]

Summary

Add two additional implicit arguments for OpenCL for the AMDGPU target using the AMDHSA runtime to support device enqueue.

[t-tye]

@yaxunl Does this change need the OpenCL runtime metadata version to be incremented or does the OpenCL runtime already support this ability?

[yaxunl]

LGTM. Thanks!

cfe/trunk/lib/CodeGen/TargetInfo.cpp

void AMDGPUTargetCodeGenInfo::setTargetAttributes(
 
   llvm::Function *F = cast<llvm::Function>(GV);
 
   const auto *ReqdWGS = M.getLangOpts().OpenCL ?
     FD->getAttr<ReqdWorkGroupSizeAttr>() : nullptr;
 
   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) {
     unsigned Min = FlatWGS ? FlatWGS->getMin() : 0;
     unsigned Max = FlatWGS ? FlatWGS->getMax() : 0;
     if (ReqdWGS && Min == 0 && Max == 0)
       Min = Max = ReqdWGS->getXDim() * ReqdWGS->getYDim() * ReqdWGS->getZDim();
 

cfe/trunk/test/CodeGenOpenCL/amdgpu-attrs.cl

 // NONAMDHSA-NOT: "amdgpu-implicitarg-num-bytes"
 
 // CHECK-NOT: "amdgpu-flat-work-group-size"="0,0"
 // CHECK-NOT: "amdgpu-waves-per-eu"="0"
 // CHECK-NOT: "amdgpu-waves-per-eu"="0,0"
 // 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"