[PATCH] D53558: Add gfx909 to GPU Arch

2018-10-23 Thread Tim Renouf via Phabricator via cfe-commits 
tpr created this revision.
Herald added subscribers: cfe-commits, jholewinski.
tpr added reviewers: yaxunl, kzhuravl.

Repository:
  rC Clang

https://reviews.llvm.org/D53558

Files:
  include/clang/Basic/Cuda.h
  lib/Basic/Cuda.cpp
  lib/Basic/Targets/NVPTX.cpp


Index: lib/Basic/Targets/NVPTX.cpp
===
--- lib/Basic/Targets/NVPTX.cpp
+++ lib/Basic/Targets/NVPTX.cpp
@@ -190,6 +190,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
   case CudaArch::LAST:
 break;
   case CudaArch::UNKNOWN:
Index: lib/Basic/Cuda.cpp
===
--- lib/Basic/Cuda.cpp
+++ lib/Basic/Cuda.cpp
@@ -94,6 +94,8 @@
 return "gfx904";
   case CudaArch::GFX906: // TBA
 return "gfx906";
+  case CudaArch::GFX909: // TBA
+return "gfx909";
   }
   llvm_unreachable("invalid enum");
 }
@@ -130,6 +132,7 @@
   .Case("gfx902", CudaArch::GFX902)
   .Case("gfx904", CudaArch::GFX904)
   .Case("gfx906", CudaArch::GFX906)
+  .Case("gfx909", CudaArch::GFX909)
   .Default(CudaArch::UNKNOWN);
 }
 
@@ -241,6 +244,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVirtualArch::COMPUTE_AMDGCN;
   }
   llvm_unreachable("invalid enum");
@@ -287,6 +291,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVersion::CUDA_70;
   }
   llvm_unreachable("invalid enum");
Index: include/clang/Basic/Cuda.h
===
--- include/clang/Basic/Cuda.h
+++ include/clang/Basic/Cuda.h
@@ -64,6 +64,7 @@
   GFX902,
   GFX904,
   GFX906,
+  GFX909,
   LAST,
 };
 const char *CudaArchToString(CudaArch A);


Index: lib/Basic/Targets/NVPTX.cpp
===
--- lib/Basic/Targets/NVPTX.cpp
+++ lib/Basic/Targets/NVPTX.cpp
@@ -190,6 +190,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
   case CudaArch::LAST:
 break;
   case CudaArch::UNKNOWN:
Index: lib/Basic/Cuda.cpp
===
--- lib/Basic/Cuda.cpp
+++ lib/Basic/Cuda.cpp
@@ -94,6 +94,8 @@
 return "gfx904";
   case CudaArch::GFX906: // TBA
 return "gfx906";
+  case CudaArch::GFX909: // TBA
+return "gfx909";
   }
   llvm_unreachable("invalid enum");
 }
@@ -130,6 +132,7 @@
   .Case("gfx902", CudaArch::GFX902)
   .Case("gfx904", CudaArch::GFX904)
   .Case("gfx906", CudaArch::GFX906)
+  .Case("gfx909", CudaArch::GFX909)
   .Default(CudaArch::UNKNOWN);
 }
 
@@ -241,6 +244,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVirtualArch::COMPUTE_AMDGCN;
   }
   llvm_unreachable("invalid enum");
@@ -287,6 +291,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVersion::CUDA_70;
   }
   llvm_unreachable("invalid enum");
Index: include/clang/Basic/Cuda.h
===
--- include/clang/Basic/Cuda.h
+++ include/clang/Basic/Cuda.h
@@ -64,6 +64,7 @@
   GFX902,
   GFX904,
   GFX906,
+  GFX909,
   LAST,
 };
 const char *CudaArchToString(CudaArch A);
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D53558: Add gfx909 to GPU Arch

2018-10-24 Thread Tim Renouf via Phabricator via cfe-commits 
This revision was automatically updated to reflect the committed changes.
Closed by commit rL345198: Add gfx909 to GPU Arch (authored by tpr, committed 
by ).
Herald added a subscriber: llvm-commits.

Repository:
  rL LLVM

https://reviews.llvm.org/D53558

Files:
  cfe/trunk/include/clang/Basic/Cuda.h
  cfe/trunk/lib/Basic/Cuda.cpp
  cfe/trunk/lib/Basic/Targets/NVPTX.cpp


Index: cfe/trunk/lib/Basic/Cuda.cpp
===
--- cfe/trunk/lib/Basic/Cuda.cpp
+++ cfe/trunk/lib/Basic/Cuda.cpp
@@ -94,6 +94,8 @@
 return "gfx904";
   case CudaArch::GFX906: // TBA
 return "gfx906";
+  case CudaArch::GFX909: // TBA
+return "gfx909";
   }
   llvm_unreachable("invalid enum");
 }
@@ -130,6 +132,7 @@
   .Case("gfx902", CudaArch::GFX902)
   .Case("gfx904", CudaArch::GFX904)
   .Case("gfx906", CudaArch::GFX906)
+  .Case("gfx909", CudaArch::GFX909)
   .Default(CudaArch::UNKNOWN);
 }
 
@@ -241,6 +244,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVirtualArch::COMPUTE_AMDGCN;
   }
   llvm_unreachable("invalid enum");
@@ -287,6 +291,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVersion::CUDA_70;
   }
   llvm_unreachable("invalid enum");
Index: cfe/trunk/lib/Basic/Targets/NVPTX.cpp
===
--- cfe/trunk/lib/Basic/Targets/NVPTX.cpp
+++ cfe/trunk/lib/Basic/Targets/NVPTX.cpp
@@ -190,6 +190,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
   case CudaArch::LAST:
 break;
   case CudaArch::UNKNOWN:
Index: cfe/trunk/include/clang/Basic/Cuda.h
===
--- cfe/trunk/include/clang/Basic/Cuda.h
+++ cfe/trunk/include/clang/Basic/Cuda.h
@@ -64,6 +64,7 @@
   GFX902,
   GFX904,
   GFX906,
+  GFX909,
   LAST,
 };
 const char *CudaArchToString(CudaArch A);


Index: cfe/trunk/lib/Basic/Cuda.cpp
===
--- cfe/trunk/lib/Basic/Cuda.cpp
+++ cfe/trunk/lib/Basic/Cuda.cpp
@@ -94,6 +94,8 @@
 return "gfx904";
   case CudaArch::GFX906: // TBA
 return "gfx906";
+  case CudaArch::GFX909: // TBA
+return "gfx909";
   }
   llvm_unreachable("invalid enum");
 }
@@ -130,6 +132,7 @@
   .Case("gfx902", CudaArch::GFX902)
   .Case("gfx904", CudaArch::GFX904)
   .Case("gfx906", CudaArch::GFX906)
+  .Case("gfx909", CudaArch::GFX909)
   .Default(CudaArch::UNKNOWN);
 }
 
@@ -241,6 +244,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVirtualArch::COMPUTE_AMDGCN;
   }
   llvm_unreachable("invalid enum");
@@ -287,6 +291,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
 return CudaVersion::CUDA_70;
   }
   llvm_unreachable("invalid enum");
Index: cfe/trunk/lib/Basic/Targets/NVPTX.cpp
===
--- cfe/trunk/lib/Basic/Targets/NVPTX.cpp
+++ cfe/trunk/lib/Basic/Targets/NVPTX.cpp
@@ -190,6 +190,7 @@
   case CudaArch::GFX902:
   case CudaArch::GFX904:
   case CudaArch::GFX906:
+  case CudaArch::GFX909:
   case CudaArch::LAST:
 break;
   case CudaArch::UNKNOWN:
Index: cfe/trunk/include/clang/Basic/Cuda.h
===
--- cfe/trunk/include/clang/Basic/Cuda.h
+++ cfe/trunk/include/clang/Basic/Cuda.h
@@ -64,6 +64,7 @@
   GFX902,
   GFX904,
   GFX906,
+  GFX909,
   LAST,
 };
 const char *CudaArchToString(CudaArch A);
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D88916: [AMDGPU] Add gfx602, gfx705, gfx805 targets

2020-10-07 Thread Tim Renouf via Phabricator via cfe-commits 
tpr updated this revision to Diff 296623.
tpr added a comment.
Herald added subscribers: cfe-commits, jholewinski.
Herald added a project: clang.

V2: Add clang changes. Put TargetParser list in order.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D88916/new/

https://reviews.llvm.org/D88916

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  clang/test/Driver/cuda-arch-translation.cu
  clang/test/Misc/target-invalid-cpu-note.c
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1749,14 +1749,17 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_R600_TURKS),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX600),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX601),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX602),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX700),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX701),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX702),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX703),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX704),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX705),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX801),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX802),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX803),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX805),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX810),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX900),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX902),
Index: llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
===
--- llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -4,6 +4,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX601
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX601 -DFLAGS=0x21
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX602
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX602 -DFLAGS=0x3A
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX700
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX700 -DFLAGS=0x22
 
@@ -19,6 +22,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX704
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX704 -DFLAGS=0x26
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX705
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX705 -DFLAGS=0x3B
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX801
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX801 -DFLAGS=0x28
 
@@ -28,6 +34,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX803
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX803 -DFLAGS=0x2A
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX805
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX805 -DFLAGS=0x3C
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX810
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX810 -DFLAGS=0x2B
 
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -100,6 +100,15 @@
 # RUN: yaml2obj --docnum=34 %s -o %t.o.34
 # RUN: llvm-readobj -s -file-headers %t.o.34 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1010 %s
 # RUN: obj2yaml %t.o.34 | FileCheck --check-prefixes=YAML-GFX1010 %s
+# RUN: yaml2obj --docnum=35 %s -o %t.o.35
+# RUN: llvm-readobj -S --file-headers %t.o.35 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX602 %s
+# RUN: obj2yaml %t.o.35 | FileCheck --check-prefixes=YAML-GFX602 %s
+# RUN: yaml2obj --docnum=36 %s -o %t.o.36
+# RUN: llvm-readobj -S --file-headers %t.o.36 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX705 %s
+# RUN: obj2yaml %t.o.36 | F

[PATCH] D88916: [AMDGPU] Add gfx602, gfx705, gfx805 targets

2020-10-07 Thread Tim Renouf via Phabricator via cfe-commits 
tpr updated this revision to Diff 296648.
tpr added a comment.

V3: AMDGCNGPUs table in TargetParser.cpp needs to be in GPUKind order,

  so fix the GPUKind order.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D88916/new/

https://reviews.llvm.org/D88916

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  clang/test/Driver/cuda-arch-translation.cu
  clang/test/Misc/target-invalid-cpu-note.c
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1749,14 +1749,17 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_R600_TURKS),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX600),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX601),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX602),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX700),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX701),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX702),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX703),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX704),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX705),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX801),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX802),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX803),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX805),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX810),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX900),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX902),
Index: llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
===
--- llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -4,6 +4,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX601
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX601 -DFLAGS=0x21
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX602
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX602 -DFLAGS=0x3A
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX700
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX700 -DFLAGS=0x22
 
@@ -19,6 +22,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX704
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX704 -DFLAGS=0x26
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX705
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX705 -DFLAGS=0x3B
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX801
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX801 -DFLAGS=0x28
 
@@ -28,6 +34,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX803
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX803 -DFLAGS=0x2A
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX805
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX805 -DFLAGS=0x3C
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX810
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX810 -DFLAGS=0x2B
 
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -100,6 +100,15 @@
 # RUN: yaml2obj --docnum=34 %s -o %t.o.34
 # RUN: llvm-readobj -s -file-headers %t.o.34 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1010 %s
 # RUN: obj2yaml %t.o.34 | FileCheck --check-prefixes=YAML-GFX1010 %s
+# RUN: yaml2obj --docnum=35 %s -o %t.o.35
+# RUN: llvm-readobj -S --file-headers %t.o.35 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX602 %s
+# RUN: obj2yaml %t.o.35 | FileCheck --check-prefixes=YAML-GFX602 %s
+# RUN: yaml2obj --docnum=36 %s -o %t.o.36
+# RUN: llvm-readobj -S --file-headers %t.o.36 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX705 %s
+# RUN: obj2yaml %t.o.36 | FileCheck --check-prefixes=YAML-GFX705

[PATCH] D88916: [AMDGPU] Add gfx602, gfx705, gfx805 targets

2020-10-10 Thread Tim Renouf via Phabricator via cfe-commits 
This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG666ef0db208b: [AMDGPU] Add gfx602, gfx705, gfx805 targets 
(authored by tpr).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D88916/new/

https://reviews.llvm.org/D88916

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  clang/test/Driver/cuda-arch-translation.cu
  clang/test/Misc/target-invalid-cpu-note.c
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1749,14 +1749,17 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_R600_TURKS),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX600),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX601),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX602),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX700),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX701),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX702),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX703),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX704),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX705),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX801),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX802),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX803),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX805),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX810),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX900),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX902),
Index: llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
===
--- llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -4,6 +4,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX601
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX601 -DFLAGS=0x21
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX602
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX602 -DFLAGS=0x3A
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX700
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX700 -DFLAGS=0x22
 
@@ -19,6 +22,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX704
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX704 -DFLAGS=0x26
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX705
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX705 -DFLAGS=0x3B
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX801
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX801 -DFLAGS=0x28
 
@@ -28,6 +34,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX803
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX803 -DFLAGS=0x2A
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX805
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX805 -DFLAGS=0x3C
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX810
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX810 -DFLAGS=0x2B
 
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -100,6 +100,15 @@
 # RUN: yaml2obj --docnum=34 %s -o %t.o.34
 # RUN: llvm-readobj -s -file-headers %t.o.34 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1010 %s
 # RUN: obj2yaml %t.o.34 | FileCheck --check-prefixes=YAML-GFX1010 %s
+# RUN: yaml2obj --docnum=35 %s -o %t.o.35
+# RUN: llvm-readobj -S --file-headers %t.o.35 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX602 %s
+# RUN: obj2yaml %t.o.35 | FileCheck --check-prefixes=YAML-GFX602 %s
+# RUN: yaml2obj --docnum=36 %s -o %t.o.36
+# RUN: llvm-readobj -S --file-headers %t.o.36 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX705 %s
+# R

[PATCH] D90419: [AMDGPU] Add gfx90c target

2020-10-29 Thread Tim Renouf via Phabricator via cfe-commits 
tpr created this revision.
Herald added subscribers: llvm-commits, cfe-commits, dexonsmith, kerbowa, 
rupprecht, hiraditya, t-tye, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl, 
arsenm, jholewinski.
Herald added a reviewer: jhenderson.
Herald added projects: clang, LLVM.
tpr requested review of this revision.
Herald added subscribers: MaskRay, wdng.

This differentiates certain hardware that was previously included in
gfx909.

Change-Id: Ia901a7157eb2f73ccd9f25dbacec38427312377d


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D90419

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1779,6 +1779,7 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX906),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX908),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX909),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX90C),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1010),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1011),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1012),
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -166,6 +166,10 @@
 # RUN: llvm-readobj -s -file-headers %t.o.42 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1032 %s
 # RUN: obj2yaml %t.o.42 | FileCheck --check-prefixes=YAML-GFX1032 %s
 
+# RUN: yaml2obj --docnum=43 %s -o %t.o.43
+# RUN: llvm-readobj -s -file-headers %t.o.43 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX90C %s
+# RUN: obj2yaml %t.o.43 | FileCheck --check-prefixes=YAML-GFX90C %s
+
 # ELF-ALL: Flags [
 # ELF-R600:  EF_AMDGPU_MACH_R600_R600 (0x1)
 # ELF-R630:  EF_AMDGPU_MACH_R600_R630 (0x2)
@@ -203,6 +207,7 @@
 # ELF-GFX906:EF_AMDGPU_MACH_AMDGCN_GFX906 (0x2F)
 # ELF-GFX908:EF_AMDGPU_MACH_AMDGCN_GFX908 (0x30)
 # ELF-GFX909:EF_AMDGPU_MACH_AMDGCN_GFX909 (0x31)
+# ELF-GFX90C:EF_AMDGPU_MACH_AMDGCN_GFX90C (0x32)
 # ELF-GFX1010:   EF_AMDGPU_MACH_AMDGCN_GFX1010 (0x33)
 # ELF-GFX1011:   EF_AMDGPU_MACH_AMDGCN_GFX1011 (0x34)
 # ELF-GFX1012:   EF_AMDGPU_MACH_AMDGCN_GFX1012 (0x35)
@@ -247,6 +252,7 @@
 # YAML-GFX906:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX906 ]
 # YAML-GFX908:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX908 ]
 # YAML-GFX909:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX909 ]
+# YAML-GFX90C:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
 # YAML-GFX1010: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1010 ]
 # YAML-GFX1011: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1011 ]
 # YAML-GFX1012: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1012 ]
@@ -715,3 +721,14 @@
   Machine: EM_AMDGPU
   Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX1032 ]
 ...
+
+# Doc43
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:ELFDATA2LSB
+  OSABI:   ELFOSABI_NONE
+  Type:ET_REL
+  Machine: EM_AMDGPU
+  Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
+...
Index: llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
===
--- llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -52,6 +52,7 @@
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx906 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX906 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx908 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX908 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx909 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX909 %s
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx90c < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX90C %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1010 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1010 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1011 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1011 %s

[PATCH] D90419: [AMDGPU] Add gfx90c target

2020-10-29 Thread Tim Renouf via Phabricator via cfe-commits 
tpr updated this revision to Diff 301723.
tpr added a comment.

V2: Fixed copy-o in AMDGPUUsage.rst change.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90419/new/

https://reviews.llvm.org/D90419

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1779,6 +1779,7 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX906),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX908),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX909),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX90C),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1010),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1011),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1012),
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -166,6 +166,10 @@
 # RUN: llvm-readobj -s -file-headers %t.o.42 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1032 %s
 # RUN: obj2yaml %t.o.42 | FileCheck --check-prefixes=YAML-GFX1032 %s
 
+# RUN: yaml2obj --docnum=43 %s -o %t.o.43
+# RUN: llvm-readobj -s -file-headers %t.o.43 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX90C %s
+# RUN: obj2yaml %t.o.43 | FileCheck --check-prefixes=YAML-GFX90C %s
+
 # ELF-ALL: Flags [
 # ELF-R600:  EF_AMDGPU_MACH_R600_R600 (0x1)
 # ELF-R630:  EF_AMDGPU_MACH_R600_R630 (0x2)
@@ -203,6 +207,7 @@
 # ELF-GFX906:EF_AMDGPU_MACH_AMDGCN_GFX906 (0x2F)
 # ELF-GFX908:EF_AMDGPU_MACH_AMDGCN_GFX908 (0x30)
 # ELF-GFX909:EF_AMDGPU_MACH_AMDGCN_GFX909 (0x31)
+# ELF-GFX90C:EF_AMDGPU_MACH_AMDGCN_GFX90C (0x32)
 # ELF-GFX1010:   EF_AMDGPU_MACH_AMDGCN_GFX1010 (0x33)
 # ELF-GFX1011:   EF_AMDGPU_MACH_AMDGCN_GFX1011 (0x34)
 # ELF-GFX1012:   EF_AMDGPU_MACH_AMDGCN_GFX1012 (0x35)
@@ -247,6 +252,7 @@
 # YAML-GFX906:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX906 ]
 # YAML-GFX908:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX908 ]
 # YAML-GFX909:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX909 ]
+# YAML-GFX90C:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
 # YAML-GFX1010: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1010 ]
 # YAML-GFX1011: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1011 ]
 # YAML-GFX1012: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1012 ]
@@ -715,3 +721,14 @@
   Machine: EM_AMDGPU
   Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX1032 ]
 ...
+
+# Doc43
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:ELFDATA2LSB
+  OSABI:   ELFOSABI_NONE
+  Type:ET_REL
+  Machine: EM_AMDGPU
+  Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
+...
Index: llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
===
--- llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -52,6 +52,7 @@
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx906 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX906 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx908 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX908 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx909 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX909 %s
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx90c < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX90C %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1010 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1010 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1011 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1011 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1012 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1012 %s
@@ -103,6 +104,7 @@
 ; GFX908:EF_AMDGPU_MACH_AMDGCN_GFX908 (0x30)
 ; GFX908-NEXT:   EF_AMDGPU_SRAM_ECC   (0x200)
 ; GFX909:EF_AMDGPU_MACH_AMDGCN_G

[PATCH] D90447: [AMDGPU] Add gfx1033 target

2020-10-30 Thread Tim Renouf via Phabricator via cfe-commits 
tpr created this revision.
Herald added subscribers: llvm-commits, cfe-commits, dexonsmith, kerbowa, 
rupprecht, hiraditya, t-tye, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl, 
arsenm.
Herald added a reviewer: jhenderson.
Herald added projects: clang, LLVM.
tpr requested review of this revision.
Herald added subscribers: MaskRay, wdng.

Change-Id: If2650fc7f31bbdd49c76e74a9ca8e3734d769761


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D90447

Files:
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
  llvm/test/MC/AMDGPU/gfx1011_dlops.s
  llvm/test/MC/AMDGPU/gfx1030_err.s
  llvm/test/MC/AMDGPU/gfx1030_new.s
  llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1786,6 +1786,7 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1030),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1031),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1032),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1033),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_XNACK),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_SRAM_ECC)
 };
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
===
--- llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -1,6 +1,7 @@
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 
 # GFX10: global_load_dword_addtid v1, s[2:3] offset:16
 0x10,0x80,0x58,0xdc,0x00,0x00,0x02,0x01
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
===
--- llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
+++ llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
@@ -1,5 +1,9 @@
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1011 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1012 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 
 # GFX10: v_dot2_f32_f16 v0, v1, v2, v3   ; encoding: [0x00,0x40,0x13,0xcc,0x01,0x05,0x0e,0x1c]
 0x00,0x40,0x13,0xcc,0x01,0x05,0x0e,0x1c
Index: llvm/test/MC/AMDGPU/gfx1030_new.s
===
--- llvm/test/MC/AMDGPU/gfx1030_new.s
+++ llvm/test/MC/AMDGPU/gfx1030_new.s
@@ -1,6 +1,7 @@
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
 
 global_load_dword_addtid v1, s[2:3] offset:16
 // GFX10: encoding: [0x10,0x80,0x58,0xdc,0x00,0x00,0x02,0x01]
Index: llvm/test/MC/AMDGPU/gfx1030_err.s
===
--- llvm/test/MC/AMDGPU/gfx1030_err.s
+++ llvm/test/MC/AMDGPU/gfx1030_err.s
@@ -1,6 +1,7 @@
 // RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1030 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1031 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
+// RUN:

[PATCH] D90419: [AMDGPU] Add gfx90c target

2020-10-30 Thread Tim Renouf via Phabricator via cfe-commits 
tpr updated this revision to Diff 301886.
tpr added a comment.

V3: Listed products. Marked as "xnack enabled".


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90419/new/

https://reviews.llvm.org/D90419

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1779,6 +1779,7 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX906),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX908),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX909),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX90C),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1010),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1011),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1012),
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -166,6 +166,10 @@
 # RUN: llvm-readobj -s -file-headers %t.o.42 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1032 %s
 # RUN: obj2yaml %t.o.42 | FileCheck --check-prefixes=YAML-GFX1032 %s
 
+# RUN: yaml2obj --docnum=43 %s -o %t.o.43
+# RUN: llvm-readobj -s -file-headers %t.o.43 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX90C %s
+# RUN: obj2yaml %t.o.43 | FileCheck --check-prefixes=YAML-GFX90C %s
+
 # ELF-ALL: Flags [
 # ELF-R600:  EF_AMDGPU_MACH_R600_R600 (0x1)
 # ELF-R630:  EF_AMDGPU_MACH_R600_R630 (0x2)
@@ -203,6 +207,7 @@
 # ELF-GFX906:EF_AMDGPU_MACH_AMDGCN_GFX906 (0x2F)
 # ELF-GFX908:EF_AMDGPU_MACH_AMDGCN_GFX908 (0x30)
 # ELF-GFX909:EF_AMDGPU_MACH_AMDGCN_GFX909 (0x31)
+# ELF-GFX90C:EF_AMDGPU_MACH_AMDGCN_GFX90C (0x32)
 # ELF-GFX1010:   EF_AMDGPU_MACH_AMDGCN_GFX1010 (0x33)
 # ELF-GFX1011:   EF_AMDGPU_MACH_AMDGCN_GFX1011 (0x34)
 # ELF-GFX1012:   EF_AMDGPU_MACH_AMDGCN_GFX1012 (0x35)
@@ -247,6 +252,7 @@
 # YAML-GFX906:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX906 ]
 # YAML-GFX908:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX908 ]
 # YAML-GFX909:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX909 ]
+# YAML-GFX90C:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
 # YAML-GFX1010: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1010 ]
 # YAML-GFX1011: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1011 ]
 # YAML-GFX1012: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1012 ]
@@ -715,3 +721,14 @@
   Machine: EM_AMDGPU
   Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX1032 ]
 ...
+
+# Doc43
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:ELFDATA2LSB
+  OSABI:   ELFOSABI_NONE
+  Type:ET_REL
+  Machine: EM_AMDGPU
+  Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
+...
Index: llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
===
--- llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -52,6 +52,7 @@
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx906 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX906 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx908 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX908 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx909 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX909 %s
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx90c < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX90C %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1010 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1010 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1011 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1011 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1012 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1012 %s
@@ -103,6 +104,7 @@
 ; GFX908:EF_AMDGPU_MACH_AMDGCN_GFX908 (0x30)
 ; GFX908-NEXT:   EF_AMDGPU_SRAM_ECC   (0x200)
 ; GFX909:EF_AMDGPU_MACH_AMDG

[PATCH] D90447: [AMDGPU] Add gfx1033 target

2020-10-30 Thread Tim Renouf via Phabricator via cfe-commits 
tpr updated this revision to Diff 301931.
tpr added a comment.

V2: Update ELFObjectFile.cpp and elf-header-flags-mach.yaml.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90447/new/

https://reviews.llvm.org/D90447

Files:
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
  llvm/test/MC/AMDGPU/gfx1011_dlops.s
  llvm/test/MC/AMDGPU/gfx1030_err.s
  llvm/test/MC/AMDGPU/gfx1030_new.s
  llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1786,6 +1786,7 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1030),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1031),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1032),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1033),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_XNACK),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_SRAM_ECC)
 };
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -170,6 +170,10 @@
 # RUN: llvm-readobj -s -file-headers %t.o.43 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX90C %s
 # RUN: obj2yaml %t.o.43 | FileCheck --check-prefixes=YAML-GFX90C %s
 
+# RUN: yaml2obj --docnum=44 %s > %t.o.44
+# RUN: llvm-readobj -s -file-headers %t.o.44 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1033 %s
+# RUN: obj2yaml %t.o.44 | FileCheck --check-prefixes=YAML-GFX1033 %s
+
 # ELF-ALL: Flags [
 # ELF-R600:  EF_AMDGPU_MACH_R600_R600 (0x1)
 # ELF-R630:  EF_AMDGPU_MACH_R600_R630 (0x2)
@@ -214,6 +218,7 @@
 # ELF-GFX1030:   EF_AMDGPU_MACH_AMDGCN_GFX1030 (0x36)
 # ELF-GFX1031:   EF_AMDGPU_MACH_AMDGCN_GFX1031 (0x37)
 # ELF-GFX1032:   EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
+# ELF-GFX1033:   EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
 # ELF-ALL: ]
 
 # YAML-R600:Flags: [ EF_AMDGPU_MACH_R600_R600 ]
@@ -259,6 +264,7 @@
 # YAML-GFX1030: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1030 ]
 # YAML-GFX1031: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1031 ]
 # YAML-GFX1032: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1032 ]
+# YAML-GFX1033: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1033 ]
 
 # Doc1
 --- !ELF
@@ -732,3 +738,14 @@
   Machine: EM_AMDGPU
   Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
 ...
+
+# Doc44
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:ELFDATA2LSB
+  OSABI:   ELFOSABI_NONE
+  Type:ET_REL
+  Machine: EM_AMDGPU
+  Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX1033 ]
+...
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
===
--- llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -1,6 +1,7 @@
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 
 # GFX10: global_load_dword_addtid v1, s[2:3] offset:16
 0x10,0x80,0x58,0xdc,0x00,0x00,0x02,0x01
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
===
--- llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
+++ llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
@@ -1,5 +1,9 @@
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1011 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1012 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX1

[PATCH] D90447: [AMDGPU] Add gfx1033 target

2020-10-30 Thread Tim Renouf via Phabricator via cfe-commits 
tpr updated this revision to Diff 301953.
tpr added a comment.
Herald added subscribers: emaste, jholewinski.
Herald added a reviewer: espindola.

V3: Add missing bits.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90447/new/

https://reviews.llvm.org/D90447

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
  llvm/test/MC/AMDGPU/gfx1011_dlops.s
  llvm/test/MC/AMDGPU/gfx1030_err.s
  llvm/test/MC/AMDGPU/gfx1030_new.s
  llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1786,6 +1786,7 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1030),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1031),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1032),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1033),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_XNACK),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_SRAM_ECC)
 };
Index: llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
===
--- llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -58,6 +58,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX909
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX909 -DFLAGS=0x31
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX90C
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX90C -DFLAGS=0x32
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX1010
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1010 -DFLAGS=0x33
 
@@ -76,6 +79,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX1032
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1032 -DFLAGS=0x38
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX1033
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1033 -DFLAGS=0x39
+
 --- !ELF
 FileHeader:
   Class:   ELFCLASS64
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -170,6 +170,10 @@
 # RUN: llvm-readobj -s -file-headers %t.o.43 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX90C %s
 # RUN: obj2yaml %t.o.43 | FileCheck --check-prefixes=YAML-GFX90C %s
 
+# RUN: yaml2obj --docnum=44 %s > %t.o.44
+# RUN: llvm-readobj -s -file-headers %t.o.44 | FileCheck --check-prefixes=ELF-ALL,ELF-GFX1033 %s
+# RUN: obj2yaml %t.o.44 | FileCheck --check-prefixes=YAML-GFX1033 %s
+
 # ELF-ALL: Flags [
 # ELF-R600:  EF_AMDGPU_MACH_R600_R600 (0x1)
 # ELF-R630:  EF_AMDGPU_MACH_R600_R630 (0x2)
@@ -214,6 +218,7 @@
 # ELF-GFX1030:   EF_AMDGPU_MACH_AMDGCN_GFX1030 (0x36)
 # ELF-GFX1031:   EF_AMDGPU_MACH_AMDGCN_GFX1031 (0x37)
 # ELF-GFX1032:   EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
+# ELF-GFX1033:   EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
 # ELF-ALL: ]
 
 # YAML-R600:Flags: [ EF_AMDGPU_MACH_R600_R600 ]
@@ -259,6 +264,7 @@
 # YAML-GFX1030: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1030 ]
 # YAML-GFX1031: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1031 ]
 # YAML-GFX1032: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1032 ]
+# YAML-GFX1033: Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1033 ]
 
 # Doc1
 --- !ELF
@@ -732,3 +738,14 @@
   Machine: EM_AMDGPU
   Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
 ...
+
+# Doc44
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:ELFDATA2LSB
+  OSABI:   ELFOSABI_NONE
+  Type:ET_REL
+  Machine: EM_AMDGPU
+  Flags:   [ EF_AMDGPU_MACH_AMDGCN_GFX1033 ]
+...
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
===
--- llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -1,6 +1,7 @@
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -disassemble -show-encoding < %s

[PATCH] D90447: [AMDGPU] Add gfx1033 target

2020-11-01 Thread Tim Renouf via Phabricator via cfe-commits 
tpr added inline comments.



Comment at: llvm/docs/AMDGPUUsage.rst:317
+   
  names.
+ ``gfx1033`` ``amdgcn``   dGPU  - wavefrontsize64  
   *TBA*
+  [off]

t-tye wrote:
> t-tye wrote:
> > APU
> This still needs fixing.
It now says APU in the diff I'm looking at. Is there something else that needs 
changing?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90447/new/

https://reviews.llvm.org/D90447

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D90447: [AMDGPU] Add gfx1033 target

2020-11-03 Thread Tim Renouf via Phabricator via cfe-commits 
This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG89d41f3a2b82: [AMDGPU] Add gfx1033 target (authored by tpr).

Changed prior to commit:
  https://reviews.llvm.org/D90447?vs=301953&id=302591#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90447/new/

https://reviews.llvm.org/D90447

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
  llvm/test/MC/AMDGPU/gfx1011_dlops.s
  llvm/test/MC/AMDGPU/gfx1030_err.s
  llvm/test/MC/AMDGPU/gfx1030_new.s
  llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
  llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1786,6 +1786,7 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1030),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1031),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1032),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1033),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_XNACK),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_SRAM_ECC)
 };
Index: llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
===
--- llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -79,6 +79,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX1032
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1032 -DFLAGS=0x38
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX1033
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1033 -DFLAGS=0x39
+
 --- !ELF
 FileHeader:
   Class:   ELFCLASS64
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -170,6 +170,10 @@
 # RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1032 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1032 %s
 # RUN: obj2yaml %t.o.AMDGCN_GFX1032 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1032 %s
 
+# RUN: sed -e 's//64/' -e 's//AMDGCN_GFX1033/' %s | yaml2obj -o %t.o.AMDGCN_GFX1033
+# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1033 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1033 %s
+# RUN: obj2yaml %t.o.AMDGCN_GFX1033 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1033 %s
+
 
 # ELF-R600-ALL:   Format: elf32-amdgpu
 # ELF-R600-ALL:   Arch: r600
@@ -317,6 +321,9 @@
 # ELF-AMDGCN-GFX1032:   EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
 # YAML-AMDGCN-GFX1032:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1032 ]
 
+# ELF-AMDGCN-GFX1033:   EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
+# YAML-AMDGCN-GFX1033:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1033 ]
+
 # ELF-AMDGCN-ALL:   ]
 
 
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
===
--- llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -1,6 +1,7 @@
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1030 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1031 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1032 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 
 # GFX10: global_load_dword_addtid v1, s[2:3] offset:16
 0x10,0x80,0x58,0xdc,0x00,0x00,0x02,0x01
Index: llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
===
--- llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
+++ llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
@@ -1,5 +1,9 @@
 # RUN: llvm-mc -arch=a

[PATCH] D90419: [AMDGPU] Add gfx90c target

2020-11-03 Thread Tim Renouf via Phabricator via cfe-commits 
This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGee3e64262757: [AMDGPU] Add gfx90c target (authored by tpr).
Herald added a subscriber: emaste.
Herald added a reviewer: espindola.

Changed prior to commit:
  https://reviews.llvm.org/D90419?vs=301886&id=302590#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D90419/new/

https://reviews.llvm.org/D90419

Files:
  clang/include/clang/Basic/Cuda.h
  clang/lib/Basic/Cuda.cpp
  clang/lib/Basic/Targets/AMDGPU.cpp
  clang/lib/Basic/Targets/NVPTX.cpp
  clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
  clang/test/CodeGenOpenCL/amdgpu-features.cl
  clang/test/Driver/amdgpu-macros.cl
  clang/test/Driver/amdgpu-mcpu.cl
  llvm/docs/AMDGPUUsage.rst
  llvm/include/llvm/BinaryFormat/ELF.h
  llvm/include/llvm/Support/TargetParser.h
  llvm/lib/Object/ELFObjectFile.cpp
  llvm/lib/ObjectYAML/ELFYAML.cpp
  llvm/lib/Support/TargetParser.cpp
  llvm/lib/Target/AMDGPU/AMDGPU.td
  llvm/lib/Target/AMDGPU/GCNProcessors.td
  llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
  llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
  llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
  llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
  llvm/tools/llvm-readobj/ELFDumper.cpp

Index: llvm/tools/llvm-readobj/ELFDumper.cpp
===
--- llvm/tools/llvm-readobj/ELFDumper.cpp
+++ llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1779,6 +1779,7 @@
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX906),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX908),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX909),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX90C),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1010),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1011),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1012),
Index: llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
===
--- llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -58,6 +58,9 @@
 # RUN: yaml2obj %s -o %t -DCPU=GFX909
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX909 -DFLAGS=0x31
 
+# RUN: yaml2obj %s -o %t -DCPU=GFX90C
+# RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX90C -DFLAGS=0x32
+
 # RUN: yaml2obj %s -o %t -DCPU=GFX1010
 # RUN: llvm-readobj -h %t | FileCheck %s --match-full-lines -DFILE=%t -DCPU=GFX1010 -DFLAGS=0x33
 
Index: llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
===
--- llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -142,6 +142,10 @@
 # RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX909 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX909 %s
 # RUN: obj2yaml %t.o.AMDGCN_GFX909 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX909 %s
 
+# RUN: sed -e 's//64/' -e 's//AMDGCN_GFX90C/' %s | yaml2obj -o %t.o.AMDGCN_GFX90C
+# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX90C | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX90C %s
+# RUN: obj2yaml %t.o.AMDGCN_GFX90C | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX90C %s
+
 # RUN: sed -e 's//64/' -e 's//AMDGCN_GFX1010/' %s | yaml2obj -o %t.o.AMDGCN_GFX1010
 # RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1010 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1010 %s
 # RUN: obj2yaml %t.o.AMDGCN_GFX1010 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1010 %s
@@ -292,6 +296,9 @@
 # ELF-AMDGCN-GFX909:EF_AMDGPU_MACH_AMDGCN_GFX909 (0x31)
 # YAML-AMDGCN-GFX909:   Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX909 ]
 
+# ELF-AMDGCN-GFX90C:EF_AMDGPU_MACH_AMDGCN_GFX90C (0x32)
+# YAML-AMDGCN-GFX90C:   Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX90C ]
+
 # ELF-AMDGCN-GFX1010:   EF_AMDGPU_MACH_AMDGCN_GFX1010 (0x33)
 # YAML-AMDGCN-GFX1010:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1010 ]
 
Index: llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
===
--- llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -52,6 +52,7 @@
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx906 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX906 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx908 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX908 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx909 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX909 %s
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx90c < %s | llvm-readobj -file-headers - | FileCheck --c