[llvm] 8406958 - [AMDGPU] Add gfx1036 target

via llvm-commits llvm-commits at lists.llvm.org
Wed Mar 2 15:27:09 PST 2022


Author: Aakanksha
Date: 2022-03-02T23:26:38Z
New Revision: 840695814ae3e945dcc8c2e649929afeb8b629c1

URL: https://github.com/llvm/llvm-project/commit/840695814ae3e945dcc8c2e649929afeb8b629c1
DIFF: https://github.com/llvm/llvm-project/commit/840695814ae3e945dcc8c2e649929afeb8b629c1.diff

LOG: [AMDGPU] Add gfx1036 target

Differential Revision: https://reviews.llvm.org/D120846

Added: 
    

Modified: 
    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/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/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/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-objdump/ELF/AMDGPU/subtarget.ll
    llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
    llvm/tools/llvm-readobj/ELFDumper.cpp
    openmp/libomptarget/DeviceRTL/CMakeLists.txt
    openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp

Removed: 
    


################################################################################
diff  --git a/clang/include/clang/Basic/Cuda.h b/clang/include/clang/Basic/Cuda.h
index 2596ec7b4e83f..cfd960ff44435 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -96,6 +96,7 @@ enum class CudaArch {
   GFX1033,
   GFX1034,
   GFX1035,
+  GFX1036,
   Generic, // A processor model named 'generic' if the target backend defines a
            // public one.
   LAST,

diff  --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index 04ee577ec9aa2..adc61a567dbef 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -124,6 +124,7 @@ static const CudaArchToStringMap arch_names[] = {
     GFX(1033), // gfx1033
     GFX(1034), // gfx1034
     GFX(1035), // gfx1035
+    GFX(1036), // gfx1036
     {CudaArch::Generic, "generic", ""},
     // clang-format on
 };

diff  --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
index a20c79dfae200..4e68968eb2527 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -183,6 +183,7 @@ bool AMDGPUTargetInfo::initFeatureMap(
   // XXX - What does the member GPU mean if device name string passed here?
   if (isAMDGCN(getTriple())) {
     switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
+    case GK_GFX1036:
     case GK_GFX1035:
     case GK_GFX1034:
     case GK_GFX1033:

diff  --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index f56d2d015333e..f03d5c600e039 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -216,6 +216,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case CudaArch::GFX1033:
       case CudaArch::GFX1034:
       case CudaArch::GFX1035:
+      case CudaArch::GFX1036:
       case CudaArch::Generic:
       case CudaArch::LAST:
         break;

diff  --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index aa8afbb47b95c..a6cf18c43c19c 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -3927,6 +3927,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
       case CudaArch::GFX1033:
       case CudaArch::GFX1034:
       case CudaArch::GFX1035:
+      case CudaArch::GFX1036:
       case CudaArch::Generic:
       case CudaArch::UNUSED:
       case CudaArch::UNKNOWN:

diff  --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 55f569484560e..0967e932868eb 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -36,6 +36,7 @@
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1033 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1033 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1034 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1034 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1035 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1035 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1036 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1036 %s
 
 // GFX600: "target-features"="+s-memtime-inst"
 // GFX601: "target-features"="+s-memtime-inst"
@@ -70,5 +71,6 @@
 // GFX1033: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1034: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 // GFX1035: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
+// GFX1036: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+flat-address-space,+gfx10-3-insts,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime,+s-memtime-inst"
 
 kernel void test() {}

diff  --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl
index e92ee68063103..07c9179fe4175 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -118,6 +118,7 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1033
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1034
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1035 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1035
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1036 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1036
 
 // ARCH-GCN-DAG: #define FP_FAST_FMA 1
 

diff  --git a/clang/test/Driver/amdgpu-mcpu.cl b/clang/test/Driver/amdgpu-mcpu.cl
index edb5ec14d504f..350d0d5f5ed57 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -103,6 +103,7 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefix=GFX1033 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefix=GFX1034 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1035 %s 2>&1 | FileCheck --check-prefix=GFX1035 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1036 %s 2>&1 | FileCheck --check-prefix=GFX1036 %s
 
 // GCNDEFAULT-NOT: -target-cpu
 // GFX600:    "-target-cpu" "gfx600"
@@ -138,3 +139,4 @@
 // GFX1033:   "-target-cpu" "gfx1033"
 // GFX1034:   "-target-cpu" "gfx1034"
 // GFX1035:   "-target-cpu" "gfx1035"
+// GFX1036:   "-target-cpu" "gfx1036"

diff  --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
index d03b4f6918cdd..6567dda1df847 100644
--- a/clang/test/Misc/target-invalid-cpu-note.c
+++ b/clang/test/Misc/target-invalid-cpu-note.c
@@ -29,7 +29,7 @@
 
 // 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, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035{{$}}
+// NVPTX-NEXT: note: valid target CPU values are: sm_20, sm_21, sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75, sm_80, sm_86, gfx600, gfx601, gfx602, gfx700, gfx701, gfx702, gfx703, gfx704, gfx705, gfx801, gfx802, gfx803, gfx805, gfx810, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036{{$}}
 
 // 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'
@@ -37,7 +37,7 @@
 
 // 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, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035{{$}}
+// AMDGCN-NEXT: note: valid target CPU values are: gfx600, tahiti, gfx601, pitcairn, verde, gfx602, hainan, oland, gfx700, kaveri, gfx701, hawaii, gfx702, gfx703, kabini, mullins, gfx704, bonaire, gfx705, gfx801, carrizo, gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11, gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906, gfx908, gfx909, gfx90a, gfx90c, gfx940, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031, gfx1032, gfx1033, gfx1034, gfx1035, gfx1036{{$}}
 
 // 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'

diff  --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index 5fc90020b6f05..01056270046d5 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -435,6 +435,13 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
                                                                                                         Add product
                                                                                                         names.
 
+     ``gfx1036``                 ``amdgcn``   APU   - cumode          - Absolute      - *pal-amdpal*  *TBA*
+                                                    - wavefrontsize64   flat
+                                                                        scratch                       .. TODO::
+
+                                                                                                        Add product
+                                                                                                        names.
+
      =========== =============== ============ ===== ================= =============== =============== ======================
 
 .. _amdgpu-target-features:
@@ -1236,7 +1243,7 @@ The AMDGPU backend uses the following ELF header:
      ``EF_AMDGPU_MACH_AMDGCN_GFX1013``    0x042      ``gfx1013``
      *reserved*                           0x043      Reserved.
      *reserved*                           0x044      Reserved.
-     *reserved*                           0x045      Reserved.
+     ``EF_AMDGPU_MACH_AMDGCN_GFX1036``    0x045      ``gfx1036``
      ==================================== ========== =============================
 
 Sections

diff  --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index d6e76be8d18ac..b0fe46d2cc016 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -759,11 +759,11 @@ enum : unsigned {
   EF_AMDGPU_MACH_AMDGCN_GFX1013       = 0x042,
   EF_AMDGPU_MACH_AMDGCN_RESERVED_0X43 = 0x043,
   EF_AMDGPU_MACH_AMDGCN_RESERVED_0X44 = 0x044,
-  EF_AMDGPU_MACH_AMDGCN_RESERVED_0X45 = 0x045,
+  EF_AMDGPU_MACH_AMDGCN_GFX1036       = 0x045,
 
   // First/last AMDGCN-based processors.
   EF_AMDGPU_MACH_AMDGCN_FIRST = EF_AMDGPU_MACH_AMDGCN_GFX600,
-  EF_AMDGPU_MACH_AMDGCN_LAST = EF_AMDGPU_MACH_AMDGCN_RESERVED_0X45,
+  EF_AMDGPU_MACH_AMDGCN_LAST = EF_AMDGPU_MACH_AMDGCN_GFX1036,
 
   // Indicates if the "xnack" target feature is enabled for all code contained
   // in the object.

diff  --git a/llvm/include/llvm/Support/TargetParser.h b/llvm/include/llvm/Support/TargetParser.h
index 23d953e0d026a..0886083008529 100644
--- a/llvm/include/llvm/Support/TargetParser.h
+++ b/llvm/include/llvm/Support/TargetParser.h
@@ -98,9 +98,10 @@ enum GPUKind : uint32_t {
   GK_GFX1033 = 78,
   GK_GFX1034 = 79,
   GK_GFX1035 = 80,
+  GK_GFX1036 = 81,
 
   GK_AMDGCN_FIRST = GK_GFX600,
-  GK_AMDGCN_LAST = GK_GFX1035,
+  GK_AMDGCN_LAST = GK_GFX1036,
 };
 
 /// Instruction set architecture version.

diff  --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index 239ca4160f0cf..d5e46f90361a4 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -483,6 +483,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
     return "gfx1034";
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1035:
     return "gfx1035";
+  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1036:
+    return "gfx1036";
   default:
     llvm_unreachable("Unknown EF_AMDGPU_MACH value");
   }

diff  --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
index c3cc84b3952ee..23831cde61276 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -574,6 +574,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1033, EF_AMDGPU_MACH);
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1034, EF_AMDGPU_MACH);
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1035, EF_AMDGPU_MACH);
+    BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1036, EF_AMDGPU_MACH);
     switch (Object->Header.ABIVersion) {
     default:
       // ELFOSABI_AMDGPU_PAL, ELFOSABI_AMDGPU_MESA3D support *_V3 flags.

diff  --git a/llvm/lib/Support/TargetParser.cpp b/llvm/lib/Support/TargetParser.cpp
index 24d14580945c3..0b116993f8c41 100644
--- a/llvm/lib/Support/TargetParser.cpp
+++ b/llvm/lib/Support/TargetParser.cpp
@@ -115,6 +115,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
   {{"gfx1033"},   {"gfx1033"}, GK_GFX1033, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
   {{"gfx1034"},   {"gfx1034"}, GK_GFX1034, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
   {{"gfx1035"},   {"gfx1035"}, GK_GFX1035, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
+  {{"gfx1036"},   {"gfx1036"}, GK_GFX1036, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
 };
 
 const GPUInfo *getArchEntry(AMDGPU::GPUKind AK, ArrayRef<GPUInfo> Table) {
@@ -229,6 +230,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
   case GK_GFX1033: return {10, 3, 3};
   case GK_GFX1034: return {10, 3, 4};
   case GK_GFX1035: return {10, 3, 5};
+  case GK_GFX1036: return {10, 3, 6};
   default:         return {0, 0, 0};
   }
 }

diff  --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index aac1229c1ef4b..a097925e182a4 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -239,3 +239,7 @@ def : ProcessorModel<"gfx1034", GFX10SpeedModel,
 def : ProcessorModel<"gfx1035", GFX10SpeedModel,
   FeatureISAVersion10_3_0.Features
 >;
+
+def : ProcessorModel<"gfx1036", GFX10SpeedModel,
+  FeatureISAVersion10_3_0.Features
+>;

diff  --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 3412f23671a4c..d7cb27c32a8c8 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -117,6 +117,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1033: AK = GK_GFX1033; break;
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034: AK = GK_GFX1034; break;
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1035: AK = GK_GFX1035; break;
+  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1036: AK = GK_GFX1036; break;
   case ELF::EF_AMDGPU_MACH_NONE:           AK = GK_NONE;    break;
   }
 
@@ -181,6 +182,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
   case GK_GFX1033: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1033;
   case GK_GFX1034: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034;
   case GK_GFX1035: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1035;
+  case GK_GFX1036: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1036;
   case GK_NONE:    return ELF::EF_AMDGPU_MACH_NONE;
   }
 

diff  --git a/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll b/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
index fb5fd3896c9c9..b196a194ecf38 100644
--- a/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
+++ b/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
@@ -92,6 +92,7 @@
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1033 < %s | FileCheck --check-prefixes=V3-GFX1033 %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1034 < %s | FileCheck --check-prefixes=V3-GFX1034 %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1035 < %s | FileCheck --check-prefixes=V3-GFX1035 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1036 < %s | FileCheck --check-prefixes=V3-GFX1036 %s
 
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx600 < %s | FileCheck --check-prefixes=GFX600 %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tahiti < %s | FileCheck --check-prefixes=GFX600 %s
@@ -187,6 +188,7 @@
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1033 < %s | FileCheck --check-prefixes=GFX1033 %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1034 < %s | FileCheck --check-prefixes=GFX1034 %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1035 < %s | FileCheck --check-prefixes=GFX1035 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1036 < %s | FileCheck --check-prefixes=GFX1036 %s
 
 ; V3-GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
 ; V3-GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@@ -238,6 +240,7 @@
 ; V3-GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
 ; V3-GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
 ; V3-GFX1035: .amdgcn_target "amdgcn-amd-amdhsa--gfx1035"
+; V3-GFX1036: .amdgcn_target "amdgcn-amd-amdhsa--gfx1036"
 
 ; GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
 ; GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@@ -311,6 +314,7 @@
 ; GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
 ; GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
 ; GFX1035: .amdgcn_target "amdgcn-amd-amdhsa--gfx1035"
+; GFX1036: .amdgcn_target "amdgcn-amd-amdhsa--gfx1036"
 
 define amdgpu_kernel void @directive_amdgcn_target() {
   ret void

diff  --git a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
index 68b7bd630d5cf..c6bac2e15ad4a 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -65,6 +65,7 @@
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1033 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1033 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1034 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1034 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1035 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1035 %s
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1036 < %s | llvm-readobj --file-header - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1036 %s
 
 ; FIXME: With the default attributes the eflags are not accurate for
 ; xnack and sramecc. Subsequent Target-ID patches will address this.
@@ -127,6 +128,7 @@
 ; GFX1033:       EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
 ; GFX1034:       EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
 ; GFX1035:       EF_AMDGPU_MACH_AMDGCN_GFX1035 (0x3D)
+; GFX1036:       EF_AMDGPU_MACH_AMDGCN_GFX1036 (0x45)
 ; ALL:         ]
 
 define amdgpu_kernel void @elf_header() {

diff  --git a/llvm/test/MC/AMDGPU/gfx1011_dlops.s b/llvm/test/MC/AMDGPU/gfx1011_dlops.s
index 5c07d1b39f51a..18e831eb58beb 100644
--- a/llvm/test/MC/AMDGPU/gfx1011_dlops.s
+++ b/llvm/test/MC/AMDGPU/gfx1011_dlops.s
@@ -6,6 +6,7 @@
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1035 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1036 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
 
 v_dot2_f32_f16 v0, v1, v2, v3
 // GFX10: encoding: [0x00,0x40,0x13,0xcc,0x01,0x05,0x0e,0x1c]

diff  --git a/llvm/test/MC/AMDGPU/gfx1030_err.s b/llvm/test/MC/AMDGPU/gfx1030_err.s
index ef04e6857712d..11446e97ce7f8 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_err.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_err.s
@@ -4,6 +4,7 @@
 // RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1033 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1034 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1035 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
+// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1036 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
 
 v_dot8c_i32_i4 v5, v1, v2
 // GFX10: :[[@LINE-1]]:{{[0-9]+}}: error: instruction not supported on this GPU

diff  --git a/llvm/test/MC/AMDGPU/gfx1030_new.s b/llvm/test/MC/AMDGPU/gfx1030_new.s
index 9fbf04053bea9..f693ccdf3b3fb 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_new.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_new.s
@@ -4,6 +4,7 @@
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
 // RUN: llvm-mc -arch=amdgcn -mcpu=gfx1035 -show-encoding %s | FileCheck --check-prefix=GFX10 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx1036 -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]

diff  --git a/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
index 00d3e86ca7b16..41406aba22b75 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
@@ -6,6 +6,7 @@
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1035 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1036 -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

diff  --git a/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
index 03785e696422f..b668f9292a711 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -4,6 +4,7 @@
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1033 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1034 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
 # RUN: llvm-mc -arch=amdgcn -mcpu=gfx1035 -disassemble -show-encoding < %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1036 -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

diff  --git a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
index 11fbac825501f..78c7060ef7144 100644
--- a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -194,6 +194,10 @@
 # RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1035 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1035 %s
 # RUN: obj2yaml %t.o.AMDGCN_GFX1035 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1035 %s
 
+# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1036/' %s | yaml2obj -o %t.o.AMDGCN_GFX1036
+# RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1036 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1036 %s
+# RUN: obj2yaml %t.o.AMDGCN_GFX1036 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1036 %s
+
 # ELF-R600-ALL:       Format: elf32-amdgpu
 # ELF-R600-ALL:       Arch: r600
 # ELF-R600-ALL:       AddressSize: 32bit
@@ -357,7 +361,10 @@
 
 # ELF-AMDGCN-GFX1035:   EF_AMDGPU_MACH_AMDGCN_GFX1035 (0x3D)
 # YAML-AMDGCN-GFX1035:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1035 ]
-#
+
+# ELF-AMDGCN-GFX1036:   EF_AMDGPU_MACH_AMDGCN_GFX1036 (0x45)
+# YAML-AMDGCN-GFX1036:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1036 ]
+
 # ELF-AMDGCN-ALL:       ]
 
 

diff  --git a/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll b/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
index 2f214408ff681..f70aa56d32630 100644
--- a/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
+++ b/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
@@ -5,6 +5,11 @@ define amdgpu_kernel void @test_kernel() {
 ; Test subtarget detection. Disassembly is only supported for GFX8 and beyond.
 ;
 ; ----------------------------------GFX10--------------------------------------
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1036 -filetype=obj -O0 -o %t.o %s
+; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1036 %t.o > %t-specify.txt
+; RUN: llvm-objdump -D %t.o > %t-detect.txt
+; RUN: 
diff  %t-specify.txt %t-detect.txt
+
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1035 -filetype=obj -O0 -o %t.o %s
 ; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1035 %t.o > %t-specify.txt
 ; RUN: llvm-objdump -D %t.o > %t-detect.txt

diff  --git a/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test b/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
index c6610a11b5be5..39ee0b11ffbb7 100644
--- a/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ b/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -295,6 +295,15 @@
 # RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1035
 # RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=2 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1035 -DFLAG_VALUE=0x3D
 
+# RUN: yaml2obj %s -o %t -DABI_VERSION=0 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1036
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=0 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1036 -DFLAG_VALUE=0x45
+
+# RUN: yaml2obj %s -o %t -DABI_VERSION=1 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1036
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=1 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1036 -DFLAG_VALUE=0x45
+
+# RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1036
+# RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,SINGLE-FLAG --match-full-lines -DABI_VERSION=2 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1036 -DFLAG_VALUE=0x45
+
 # RUN: yaml2obj %s -o %t -DABI_VERSION=0 -DFLAG_NAME="EF_AMDGPU_MACH_AMDGCN_GFX90A, EF_AMDGPU_FEATURE_XNACK_V3"
 # RUN: llvm-readobj -h %t | FileCheck %s --check-prefixes=ALL,KNOWN-ABI-VERSION,DOUBLE-FLAG --match-full-lines -DABI_VERSION=0 -DFILE=%t -DFLAG_0="EF_AMDGPU_FEATURE_XNACK_V3 (0x100)" -DFLAG_1="EF_AMDGPU_MACH_AMDGCN_GFX90A (0x3F)" -DFLAG_VALUE=0x13F
 

diff  --git a/llvm/tools/llvm-readobj/ELFDumper.cpp b/llvm/tools/llvm-readobj/ELFDumper.cpp
index f02ec2af832e9..b2945795c0ad7 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1538,6 +1538,7 @@ const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion3[] = {
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1033),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1034),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1035),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1036),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_V3),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_SRAMECC_V3)
 };
@@ -1593,6 +1594,7 @@ const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion4[] = {
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1033),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1034),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1035),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1036),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_ANY_V4),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_OFF_V4),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_ON_V4),

diff  --git a/openmp/libomptarget/DeviceRTL/CMakeLists.txt b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
index 408ba9fa07277..729adff3f88bc 100644
--- a/openmp/libomptarget/DeviceRTL/CMakeLists.txt
+++ b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
@@ -96,7 +96,7 @@ foreach(sm ${nvptx_sm_list})
   endif()
 endforeach()
 
-set(amdgpu_mcpus gfx700 gfx701 gfx801 gfx803 gfx900 gfx902 gfx906 gfx908 gfx90a gfx90c gfx940 gfx1010 gfx1030 gfx1031)
+set(amdgpu_mcpus gfx700 gfx701 gfx801 gfx803 gfx900 gfx902 gfx906 gfx908 gfx90a gfx90c gfx940 gfx1010 gfx1030 gfx1031 gfx1032 gfx1033 gfx1034 gfx1035 gfx1036)
 if (DEFINED LIBOMPTARGET_AMDGCN_GFXLIST)
   set(amdgpu_mcpus ${LIBOMPTARGET_AMDGCN_GFXLIST})
 endif()

diff  --git a/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp b/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
index 14782c9ac9d30..ee2ea3a1bafaf 100644
--- a/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
+++ b/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
@@ -60,6 +60,8 @@ const char *get_elf_mach_gfx_name(uint32_t EFlags) {
     return "gfx1034";
   case EF_AMDGPU_MACH_AMDGCN_GFX1035:
     return "gfx1035";
+  case EF_AMDGPU_MACH_AMDGCN_GFX1036:
+    return "gfx1036";
   default:
     return "--unknown gfx";
   }


        


More information about the llvm-commits mailing list