[AMDGPU] gfx1011/gfx1012 clang support

[kzhuravl]

LGTM

lib/Basic/Targets/AMDGPU.cpp

bool AMDGPUTargetInfo::initFeatureMap(
   using namespace llvm::AMDGPU;
 
   // XXX - What does the member GPU mean if device name string passed here?
   if (isAMDGCN(getTriple())) {
     if (CPU.empty())
       CPU = "gfx600";
 
     switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
+    case GK_GFX1012:
+    case GK_GFX1011:
+      Features["dot1-insts"] = true;
+      Features["dot2-insts"] = true;
+      Features["dot5-insts"] = true;
+      Features["dot6-insts"] = true;
+      LLVM_FALLTHROUGH;
     case GK_GFX1010:
       Features["dl-insts"] = true;
       Features["16-bit-insts"] = true;
       Features["dpp"] = true;
       Features["gfx9-insts"] = true;
       Features["gfx10-insts"] = true;
       Features["s-memrealtime"] = true;
       break;

test/CodeGenOpenCL/amdgpu-features.cl

 // REQUIRES: amdgpu-registered-target
 
 // Check that appropriate features are defined for every supported AMDGPU
 // "-target" and "-mcpu" options.
 
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx904 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX904 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx906 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX906 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1010 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1011 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1011 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1012 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1012 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx801 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX801 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx700 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX700 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx600 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX600 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx601 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX601 %s
 
 // GFX904: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
 // GFX1010: "target-features"="+16-bit-insts,+dl-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
+// GFX1011: "target-features"="+16-bit-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
+// GFX1012: "target-features"="+16-bit-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
 // GFX801: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+s-memrealtime"
 // GFX700: "target-features"="+ci-insts,+fp64-fp16-denormals,-fp32-denormals"
 // GFX600: "target-features"="+fp64-fp16-denormals,-fp32-denormals"
 // GFX601: "target-features"="+fp64-fp16-denormals,-fp32-denormals"
 
 kernel void test() {}

test/Driver/amdgpu-macros.cl

 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx810 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX810 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=stoney %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX810 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx900 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX900 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx902 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX902 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx904 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX904 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX906 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx909 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX909 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1010 %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1011 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1011 %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1012 %s
 
 // GFX600-DAG: #define FP_FAST_FMA 1
 // GFX601-DAG: #define FP_FAST_FMA 1
 // GFX700-DAG: #define FP_FAST_FMA 1
 // GFX701-DAG: #define FP_FAST_FMA 1
 // GFX702-DAG: #define FP_FAST_FMA 1
 // GFX703-DAG: #define FP_FAST_FMA 1
 // GFX704-DAG: #define FP_FAST_FMA 1
 // GFX801-DAG: #define FP_FAST_FMA 1
 // GFX802-DAG: #define FP_FAST_FMA 1
 // GFX803-DAG: #define FP_FAST_FMA 1
 // GFX810-DAG: #define FP_FAST_FMA 1
 // GFX900-DAG: #define FP_FAST_FMA 1
 // GFX902-DAG: #define FP_FAST_FMA 1
 // GFX904-DAG: #define FP_FAST_FMA 1
 // GFX906-DAG: #define FP_FAST_FMA 1
 // GFX909-DAG: #define FP_FAST_FMA 1
 // GFX1010-DAG: #define FP_FAST_FMA 1
+// GFX1011-DAG: #define FP_FAST_FMA 1
+// GFX1012-DAG: #define FP_FAST_FMA 1
 
 // GFX600-DAG: #define FP_FAST_FMAF 1
 // GFX601-NOT: #define FP_FAST_FMAF 1
 // GFX700-NOT: #define FP_FAST_FMAF 1
 // GFX701-DAG: #define FP_FAST_FMAF 1
 // GFX702-DAG: #define FP_FAST_FMAF 1
 // GFX703-NOT: #define FP_FAST_FMAF 1
 // GFX704-NOT: #define FP_FAST_FMAF 1
 // GFX801-DAG: #define FP_FAST_FMAF 1
 // GFX802-NOT: #define FP_FAST_FMAF 1
 // GFX803-NOT: #define FP_FAST_FMAF 1
 // GFX810-NOT: #define FP_FAST_FMAF 1
 // GFX900-DAG: #define FP_FAST_FMAF 1
 // GFX902-DAG: #define FP_FAST_FMAF 1
 // GFX904-DAG: #define FP_FAST_FMAF 1
 // GFX906-DAG: #define FP_FAST_FMAF 1
 // GFX909-DAG: #define FP_FAST_FMAF 1
 // GFX1010-DAG: #define FP_FAST_FMAF 1
+// GFX1011-DAG: #define FP_FAST_FMAF 1
+// GFX1012-DAG: #define FP_FAST_FMAF 1
 
 // ARCH-GCN-DAG: #define __AMDGCN__ 1
 // ARCH-GCN-DAG: #define __AMDGPU__ 1
 // ARCH-GCN-DAG: #define __AMD__ 1
 
 // GFX600-DAG: #define __HAS_FMAF__ 1
 // GFX601-DAG: #define __HAS_FMAF__ 1
 // GFX700-DAG: #define __HAS_FMAF__ 1
 // GFX701-DAG: #define __HAS_FMAF__ 1
 // GFX702-DAG: #define __HAS_FMAF__ 1
 // GFX703-DAG: #define __HAS_FMAF__ 1
 // GFX704-DAG: #define __HAS_FMAF__ 1
 // GFX801-DAG: #define __HAS_FMAF__ 1
 // GFX802-DAG: #define __HAS_FMAF__ 1
 // GFX803-DAG: #define __HAS_FMAF__ 1
 // GFX810-DAG: #define __HAS_FMAF__ 1
 // GFX900-DAG: #define __HAS_FMAF__ 1
 // GFX902-DAG: #define __HAS_FMAF__ 1
 // GFX904-DAG: #define __HAS_FMAF__ 1
 // GFX906-DAG: #define __HAS_FMAF__ 1
 // GFX909-DAG: #define __HAS_FMAF__ 1
 // GFX1010-DAG: #define __HAS_FMAF__ 1
+// GFX1011-DAG: #define __HAS_FMAF__ 1
+// GFX1012-DAG: #define __HAS_FMAF__ 1
 
 // GFX600-DAG: #define __HAS_FP64__ 1
 // GFX601-DAG: #define __HAS_FP64__ 1
 // GFX700-DAG: #define __HAS_FP64__ 1
 // GFX701-DAG: #define __HAS_FP64__ 1
 // GFX702-DAG: #define __HAS_FP64__ 1
 // GFX703-DAG: #define __HAS_FP64__ 1
 // GFX704-DAG: #define __HAS_FP64__ 1
 // GFX801-DAG: #define __HAS_FP64__ 1
 // GFX802-DAG: #define __HAS_FP64__ 1
 // GFX803-DAG: #define __HAS_FP64__ 1
 // GFX810-DAG: #define __HAS_FP64__ 1
 // GFX900-DAG: #define __HAS_FP64__ 1
 // GFX902-DAG: #define __HAS_FP64__ 1
 // GFX904-DAG: #define __HAS_FP64__ 1
 // GFX906-DAG: #define __HAS_FP64__ 1
 // GFX909-DAG: #define __HAS_FP64__ 1
 // GFX1010-DAG: #define __HAS_FP64__ 1
+// GFX1011-DAG: #define __HAS_FP64__ 1
+// GFX1012-DAG: #define __HAS_FP64__ 1
 
 // GFX600-DAG: #define __HAS_LDEXPF__ 1
 // GFX601-DAG: #define __HAS_LDEXPF__ 1
 // GFX700-DAG: #define __HAS_LDEXPF__ 1
 // GFX701-DAG: #define __HAS_LDEXPF__ 1
 // GFX702-DAG: #define __HAS_LDEXPF__ 1
 // GFX703-DAG: #define __HAS_LDEXPF__ 1
 // GFX704-DAG: #define __HAS_LDEXPF__ 1
 // GFX801-DAG: #define __HAS_LDEXPF__ 1
 // GFX802-DAG: #define __HAS_LDEXPF__ 1
 // GFX803-DAG: #define __HAS_LDEXPF__ 1
 // GFX810-DAG: #define __HAS_LDEXPF__ 1
 // GFX900-DAG: #define __HAS_LDEXPF__ 1
 // GFX902-DAG: #define __HAS_LDEXPF__ 1
 // GFX904-DAG: #define __HAS_LDEXPF__ 1
 // GFX906-DAG: #define __HAS_LDEXPF__ 1
 // GFX909-DAG: #define __HAS_LDEXPF__ 1
 // GFX1010-DAG: #define __HAS_LDEXPF__ 1
+// GFX1011-DAG: #define __HAS_LDEXPF__ 1
+// GFX1012-DAG: #define __HAS_LDEXPF__ 1
 
 // GFX600-DAG: #define __gfx600__ 1
 // GFX601-DAG: #define __gfx601__ 1
 // GFX700-DAG: #define __gfx700__ 1
 // GFX701-DAG: #define __gfx701__ 1
 // GFX702-DAG: #define __gfx702__ 1
 // GFX703-DAG: #define __gfx703__ 1
 // GFX704-DAG: #define __gfx704__ 1
 // GFX801-DAG: #define __gfx801__ 1
 // GFX802-DAG: #define __gfx802__ 1
 // GFX803-DAG: #define __gfx803__ 1
 // GFX810-DAG: #define __gfx810__ 1
 // GFX900-DAG: #define __gfx900__ 1
 // GFX902-DAG: #define __gfx902__ 1
 // GFX904-DAG: #define __gfx904__ 1
 // GFX906-DAG: #define __gfx906__ 1
 // GFX909-DAG: #define __gfx909__ 1
 // GFX1010-DAG: #define __gfx1010__ 1
+// GFX1011-DAG: #define __gfx1011__ 1
+// GFX1012-DAG: #define __gfx1012__ 1

test/Driver/amdgpu-mcpu.cl

 // RUN: %clang -### -target amdgcn -mcpu=gfx810 %s 2>&1 | FileCheck --check-prefix=GFX810 %s
 // RUN: %clang -### -target amdgcn -mcpu=stoney %s 2>&1 | FileCheck --check-prefix=STONEY %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx900 %s 2>&1 | FileCheck --check-prefix=GFX900 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx902 %s 2>&1 | FileCheck --check-prefix=GFX902 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx904 %s 2>&1 | FileCheck --check-prefix=GFX904 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx906 %s 2>&1 | FileCheck --check-prefix=GFX906 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx909 %s 2>&1 | FileCheck --check-prefix=GFX909 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefix=GFX1010 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1011 %s 2>&1 | FileCheck --check-prefix=GFX1011 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1012 %s 2>&1 | FileCheck --check-prefix=GFX1012 %s
 
 // GFX600:    "-target-cpu" "gfx600"
 // TAHITI:    "-target-cpu" "tahiti"
 // GFX601:    "-target-cpu" "gfx601"
 // HAINAN:    "-target-cpu" "hainan"
 // OLAND:     "-target-cpu" "oland"
 // PITCAIRN:  "-target-cpu" "pitcairn"
 // VERDE:     "-target-cpu" "verde"

 // GFX810:    "-target-cpu" "gfx810"
 // STONEY:    "-target-cpu" "stoney"
 // GFX900:    "-target-cpu" "gfx900"
 // GFX902:    "-target-cpu" "gfx902"
 // GFX904:    "-target-cpu" "gfx904"
 // GFX906:    "-target-cpu" "gfx906"
 // GFX909:    "-target-cpu" "gfx909"
 // GFX1010:   "-target-cpu" "gfx1010"
+// GFX1011:   "-target-cpu" "gfx1011"
+// GFX1012:   "-target-cpu" "gfx1012"