[AMDGPU] Define new targets gfx1200 and gfx1201 (#73133)

Define target names and ELF numbers for new GFX12 targets gfx1200 and
gfx1201. For now they behave identically to GFX11.

Author: jayfoad

clang/include/clang/Basic/Cuda.h

@@ -113,6 +113,8 @@ enum class CudaArch {
   GFX1103,
   GFX1150,
   GFX1151,
+  GFX1200,
+  GFX1201,
   Generic, // A processor model named 'generic' if the target backend defines a
            // public one.
   LAST,

clang/lib/Basic/Cuda.cpp

@@ -135,6 +135,8 @@ static const CudaArchToStringMap arch_names[] = {
     GFX(1103), // gfx1103
     GFX(1150), // gfx1150
     GFX(1151), // gfx1151
+    GFX(1200), // gfx1200
+    GFX(1201), // gfx1201
     {CudaArch::Generic, "generic", ""},
     // clang-format on
 };

clang/lib/Basic/Targets/NVPTX.cpp

@@ -214,6 +214,8 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case CudaArch::GFX1103:
       case CudaArch::GFX1150:
       case CudaArch::GFX1151:
+      case CudaArch::GFX1200:
+      case CudaArch::GFX1201:
       case CudaArch::Generic:
       case CudaArch::LAST:
         break;

clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp

@@ -3540,6 +3540,8 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
       case CudaArch::GFX1103:
       case CudaArch::GFX1150:
       case CudaArch::GFX1151:
+      case CudaArch::GFX1200:
+      case CudaArch::GFX1201:
       case CudaArch::Generic:
       case CudaArch::UNUSED:
       case CudaArch::UNKNOWN:

clang/test/CodeGenOpenCL/amdgpu-features.cl

@@ -49,6 +49,8 @@
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1103 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1103 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1150 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1150 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1151 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1151 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1200 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1200 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1201 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1201 %s
 
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1103 -target-feature +wavefrontsize64 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1103-W64 %s
 
@@ -98,6 +100,8 @@
 // GFX1103: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 // GFX1150: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 // GFX1151: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
+// GFX1200: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
+// GFX1201: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 
 // GFX1103-W64: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot10-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize64"
 

clang/test/Driver/amdgpu-macros.cl

@@ -128,6 +128,8 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1103 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1103 -DFAMILY=GFX11
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1150 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1150 -DFAMILY=GFX11
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1151 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1151 -DFAMILY=GFX11
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1200 -DFAMILY=GFX12
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1201 -DFAMILY=GFX12
 
 // ARCH-GCN-DAG: #define FP_FAST_FMA 1
 

clang/test/Driver/amdgpu-mcpu.cl

@@ -112,6 +112,8 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx1103 %s 2>&1 | FileCheck --check-prefix=GFX1103 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1150 %s 2>&1 | FileCheck --check-prefix=GFX1150 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1151 %s 2>&1 | FileCheck --check-prefix=GFX1151 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefix=GFX1200 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefix=GFX1201 %s
 
 // GCNDEFAULT-NOT: -target-cpu
 // GFX600:    "-target-cpu" "gfx600"
@@ -156,3 +158,5 @@
 // GFX1103:   "-target-cpu" "gfx1103"
 // GFX1150:   "-target-cpu" "gfx1150"
 // GFX1151:   "-target-cpu" "gfx1151"
+// GFX1200:   "-target-cpu" "gfx1200"
+// GFX1201:   "-target-cpu" "gfx1201"

clang/test/Misc/target-invalid-cpu-note.c

@@ -29,15 +29,15 @@
 
 // RUN: not %clang_cc1 -triple nvptx--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix NVPTX
 // NVPTX: error: unknown target CPU 'not-a-cpu'
-// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, sm_87, sm_89, sm_90, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151{{$}}
+// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, sm_87, sm_89, sm_90, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1200, gfx1201{{$}}
 
 // RUN: not %clang_cc1 -triple r600--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix R600
 // R600: error: unknown target CPU 'not-a-cpu'
 // R600-NEXT: note: valid target CPU values are: r600, rv630, rv635, r630, rs780, rs880, rv610, rv620, rv670, rv710, rv730, rv740, rv770, cedar, palm, cypress, hemlock, juniper, redwood, sumo, sumo2, barts, caicos, aruba, cayman, turks{{$}}
 
 // RUN: not %clang_cc1 -triple amdgcn--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix AMDGCN
 // AMDGCN: error: unknown target CPU 'not-a-cpu'
-// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151{{$}}
+// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx941, gfx942, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036, gfx1100, gfx1101, gfx1102, gfx1103, gfx1150, gfx1151, gfx1200, gfx1201{{$}}
 
 // RUN: not %clang_cc1 -triple wasm64--- -target-cpu not-a-cpu -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix WEBASM
 // WEBASM: error: unknown target CPU 'not-a-cpu'

llvm/docs/AMDGPUUsage.rst

@@ -504,6 +504,20 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
                                                                         work-item                       Add product
                                                                         IDs                             names.
 
+     ``gfx1200``                 ``amdgcn``   dGPU  - cumode          - Architected                   *TBA*
+                                                    - wavefrontsize64   flat
+                                                                        scratch                       .. TODO::
+                                                                      - Packed
+                                                                        work-item                       Add product
+                                                                        IDs                             names.
+
+     ``gfx1201``                 ``amdgcn``   dGPU  - cumode          - Architected                   *TBA*
+                                                    - wavefrontsize64   flat
+                                                                        scratch                       .. TODO::
+                                                                      - Packed
+                                                                        work-item                       Add product
+                                                                        IDs                             names.
+
      =========== =============== ============ ===== ================= =============== =============== ======================
 
 .. _amdgpu-target-features:
@@ -1667,11 +1681,13 @@ The AMDGPU backend uses the following ELF header:
      ``EF_AMDGPU_MACH_AMDGCN_GFX1036``    0x045      ``gfx1036``
      ``EF_AMDGPU_MACH_AMDGCN_GFX1101``    0x046      ``gfx1101``
      ``EF_AMDGPU_MACH_AMDGCN_GFX1102``    0x047      ``gfx1102``
-     *reserved*                           0x048      Reserved.
+     ``EF_AMDGPU_MACH_AMDGCN_GFX1200``    0x048      ``gfx1200``
      *reserved*                           0x049      Reserved.
      ``EF_AMDGPU_MACH_AMDGCN_GFX1151``    0x04a      ``gfx1151``
      ``EF_AMDGPU_MACH_AMDGCN_GFX941``     0x04b      ``gfx941``
      ``EF_AMDGPU_MACH_AMDGCN_GFX942``     0x04c      ``gfx942``
+     *reserved*                           0x04d      Reserved.
+     ``EF_AMDGPU_MACH_AMDGCN_GFX1201``    0x04e      ``gfx1201``
      ==================================== ========== =============================
 
 Sections

llvm/include/llvm/BinaryFormat/ELF.h

@@ -779,16 +779,18 @@ enum : unsigned {
   EF_AMDGPU_MACH_AMDGCN_GFX1036       = 0x045,
   EF_AMDGPU_MACH_AMDGCN_GFX1101       = 0x046,
   EF_AMDGPU_MACH_AMDGCN_GFX1102       = 0x047,
-  EF_AMDGPU_MACH_AMDGCN_RESERVED_0X48 = 0x048,
+  EF_AMDGPU_MACH_AMDGCN_GFX1200       = 0x048,
   EF_AMDGPU_MACH_AMDGCN_RESERVED_0X49 = 0x049,
   EF_AMDGPU_MACH_AMDGCN_GFX1151       = 0x04a,
   EF_AMDGPU_MACH_AMDGCN_GFX941        = 0x04b,
   EF_AMDGPU_MACH_AMDGCN_GFX942        = 0x04c,
+  EF_AMDGPU_MACH_AMDGCN_RESERVED_0X4D = 0x04d,
+  EF_AMDGPU_MACH_AMDGCN_GFX1201       = 0x04e,
   // clang-format on
 
   // First/last AMDGCN-based processors.
   EF_AMDGPU_MACH_AMDGCN_FIRST = EF_AMDGPU_MACH_AMDGCN_GFX600,
-  EF_AMDGPU_MACH_AMDGCN_LAST = EF_AMDGPU_MACH_AMDGCN_GFX942,
+  EF_AMDGPU_MACH_AMDGCN_LAST = EF_AMDGPU_MACH_AMDGCN_GFX1201,
 
   // Indicates if the "xnack" target feature is enabled for all code contained
   // in the object.