[Openmp-commits] [openmp] 3453f3d - [AMDGPU] Add gfx1035 target

Aakanksha Patil via Openmp-commits openmp-commits at lists.llvm.org
Thu Jun 24 11:34:13 PDT 2021


Author: Aakanksha Patil
Date: 2021-06-24T14:32:41-04:00
New Revision: 3453f3dd46f5214e028cb33818b10c5d995cd858

URL: https://github.com/llvm/llvm-project/commit/3453f3dd46f5214e028cb33818b10c5d995cd858
DIFF: https://github.com/llvm/llvm-project/commit/3453f3dd46f5214e028cb33818b10c5d995cd858.diff

LOG: [AMDGPU] Add gfx1035 target

Differential Revision: https://reviews.llvm.org/D104804

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/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 13317f62c3c5a..aa12724cbf0c6 100644
--- a/clang/include/clang/Basic/Cuda.h
+++ b/clang/include/clang/Basic/Cuda.h
@@ -89,6 +89,7 @@ enum class CudaArch {
   GFX1032,
   GFX1033,
   GFX1034,
+  GFX1035,
   LAST,
 };
 

diff  --git a/clang/lib/Basic/Cuda.cpp b/clang/lib/Basic/Cuda.cpp
index fa7f78a25829f..766135bcb376f 100644
--- a/clang/lib/Basic/Cuda.cpp
+++ b/clang/lib/Basic/Cuda.cpp
@@ -111,6 +111,7 @@ static const CudaArchToStringMap arch_names[] = {
     GFX(1032), // gfx1032
     GFX(1033), // gfx1033
     GFX(1034), // gfx1034
+    GFX(1035), // gfx1035
     // clang-format on
 };
 #undef SM

diff  --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
index 8a8165e9c895c..595132e2e70ba 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -184,6 +184,7 @@ 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_GFX1035:
     case GK_GFX1034:
     case GK_GFX1033:
     case GK_GFX1032:

diff  --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index 885dac9ab79d7..56f8a179db3cc 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -213,6 +213,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case CudaArch::GFX1032:
       case CudaArch::GFX1033:
       case CudaArch::GFX1034:
+      case CudaArch::GFX1035:
       case CudaArch::LAST:
         break;
       case CudaArch::UNUSED:

diff  --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 772717c496757..2e79e2978d3da 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -4194,6 +4194,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
       case CudaArch::GFX1032:
       case CudaArch::GFX1033:
       case CudaArch::GFX1034:
+      case CudaArch::GFX1035:
       case CudaArch::UNUSED:
       case CudaArch::UNKNOWN:
         break;

diff  --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index b4b86d75c9ae7..a532da344df1a 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -34,6 +34,7 @@
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1032 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1032 %s
 // 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
 
 // GFX600: "target-features"="+s-memtime-inst"
 // GFX601: "target-features"="+s-memtime-inst"
@@ -66,5 +67,6 @@
 // GFX1032: "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"
 // 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"
 
 kernel void test() {}

diff  --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl
index bea4eab13fe5e..965fdda67945f 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -116,6 +116,7 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1032
 // 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
 
 // 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 8b472206db7c2..432533b10d9dc 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -101,6 +101,7 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefix=GFX1032 %s
 // 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
 
 // GCNDEFAULT-NOT: -target-cpu
 // GFX600:    "-target-cpu" "gfx600"
@@ -134,3 +135,4 @@
 // GFX1032:   "-target-cpu" "gfx1032"
 // GFX1033:   "-target-cpu" "gfx1033"
 // GFX1034:   "-target-cpu" "gfx1034"
+// GFX1035:   "-target-cpu" "gfx1035"

diff  --git a/clang/test/Misc/target-invalid-cpu-note.c b/clang/test/Misc/target-invalid-cpu-note.c
index b30a2709e0797..23f9f543becea 100644
--- a/clang/test/Misc/target-invalid-cpu-note.c
+++ b/clang/test/Misc/target-invalid-cpu-note.c
@@ -87,7 +87,7 @@
 // AMDGCN-SAME: gfx802, iceland, tonga, gfx803, fiji, polaris10, polaris11,
 // AMDGCN-SAME: gfx805, tongapro, gfx810, stoney, gfx900, gfx902, gfx904, gfx906,
 // AMDGCN-SAME: gfx908, gfx909, gfx90a, gfx90c, gfx1010, gfx1011, gfx1012, gfx1013, gfx1030, gfx1031,
-// AMDGCN-SAME: gfx1032, gfx1033, gfx1034
+// AMDGCN-SAME: gfx1032, gfx1033, gfx1034, gfx1035
 
 // 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 7d8aab577a4eb..8d6d86a35e97a 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -421,6 +421,12 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
                                                                                                         Add product
                                                                                                         names.
 
+     ``gfx1035``                 ``amdgcn``   APU   - cumode          - Absolute      - *pal-amdpal*  *TBA*
+                                                    - wavefrontsize64   flat
+                                                                        scratch                       .. TODO::
+                                                                                                        Add product
+                                                                                                        names.
+
      =========== =============== ============ ===== ================= =============== =============== ======================
 
 .. _amdgpu-target-features:
@@ -1151,7 +1157,7 @@ The AMDGPU backend uses the following ELF header:
      ``EF_AMDGPU_MACH_AMDGCN_GFX602``     0x03a      ``gfx602``
      ``EF_AMDGPU_MACH_AMDGCN_GFX705``     0x03b      ``gfx705``
      ``EF_AMDGPU_MACH_AMDGCN_GFX805``     0x03c      ``gfx805``
-     *reserved*                           0x03d      Reserved.
+     ``EF_AMDGPU_MACH_AMDGCN_GFX1035``    0x03d      ``gfx1035``
      ``EF_AMDGPU_MACH_AMDGCN_GFX1034``    0x03e      ``gfx1034``
      ``EF_AMDGPU_MACH_AMDGCN_GFX90A``     0x03f      ``gfx90a``
      *reserved*                           0x040      Reserved.

diff  --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index 99ad345bbcc40..bd784b973968e 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -737,7 +737,7 @@ enum : unsigned {
   EF_AMDGPU_MACH_AMDGCN_GFX602        = 0x03a,
   EF_AMDGPU_MACH_AMDGCN_GFX705        = 0x03b,
   EF_AMDGPU_MACH_AMDGCN_GFX805        = 0x03c,
-  EF_AMDGPU_MACH_AMDGCN_RESERVED_0X3D = 0x03d,
+  EF_AMDGPU_MACH_AMDGCN_GFX1035       = 0x03d,
   EF_AMDGPU_MACH_AMDGCN_GFX1034       = 0x03e,
   EF_AMDGPU_MACH_AMDGCN_GFX90A        = 0x03f,
   EF_AMDGPU_MACH_AMDGCN_RESERVED_0X40 = 0x040,

diff  --git a/llvm/include/llvm/Support/TargetParser.h b/llvm/include/llvm/Support/TargetParser.h
index e36ee01636bbe..366dd3cf55c61 100644
--- a/llvm/include/llvm/Support/TargetParser.h
+++ b/llvm/include/llvm/Support/TargetParser.h
@@ -95,9 +95,10 @@ enum GPUKind : uint32_t {
   GK_GFX1032 = 77,
   GK_GFX1033 = 78,
   GK_GFX1034 = 79,
+  GK_GFX1035 = 80,
 
   GK_AMDGCN_FIRST = GK_GFX600,
-  GK_AMDGCN_LAST = GK_GFX1034,
+  GK_AMDGCN_LAST = GK_GFX1035,
 };
 
 /// Instruction set architecture version.

diff  --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index 932f3aad27ca2..6613d79ab3d03 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -481,6 +481,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
     return "gfx1033";
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1034:
     return "gfx1034";
+  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1035:
+    return "gfx1035";
   default:
     llvm_unreachable("Unknown EF_AMDGPU_MACH value");
   }

diff  --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
index af6247e9339ac..50821544a687f 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -555,6 +555,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1032, EF_AMDGPU_MACH);
     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);
     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 d61b64b1f502f..1dadce4b90405 100644
--- a/llvm/lib/Support/TargetParser.cpp
+++ b/llvm/lib/Support/TargetParser.cpp
@@ -115,6 +115,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
   {{"gfx1032"},   {"gfx1032"}, GK_GFX1032, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
   {{"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},
 };
 
 const GPUInfo *getArchEntry(AMDGPU::GPUKind AK, ArrayRef<GPUInfo> Table) {
@@ -227,6 +228,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
   case GK_GFX1032: return {10, 3, 2};
   case GK_GFX1033: return {10, 3, 3};
   case GK_GFX1034: return {10, 3, 4};
+  case GK_GFX1035: return {10, 3, 5};
   default:         return {0, 0, 0};
   }
 }

diff  --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index e4eb91613cb7e..3a68ed1934e15 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -231,3 +231,7 @@ def : ProcessorModel<"gfx1033", GFX10SpeedModel,
 def : ProcessorModel<"gfx1034", GFX10SpeedModel,
   FeatureISAVersion10_3_0.Features
 >;
+
+def : ProcessorModel<"gfx1035", GFX10SpeedModel,
+  FeatureISAVersion10_3_0.Features
+>;

diff  --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 0008c1574416c..9a9a2c973f448 100644
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -111,6 +111,7 @@ StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1032: AK = GK_GFX1032; break;
   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_NONE:           AK = GK_NONE;    break;
   }
 
@@ -173,6 +174,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
   case GK_GFX1032: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1032;
   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_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 f181f8548f4ff..a922c3fe8cb65 100644
--- a/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
+++ b/llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll
@@ -88,6 +88,7 @@
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=3 -mcpu=gfx1032 < %s | FileCheck --check-prefixes=V3-GFX1032 %s
 ; 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 -mcpu=gfx600 < %s | FileCheck --check-prefixes=GFX600 %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tahiti < %s | FileCheck --check-prefixes=GFX600 %s
@@ -179,6 +180,7 @@
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1032 < %s | FileCheck --check-prefixes=GFX1032 %s
 ; 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
 
 ; V3-GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
 ; V3-GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@@ -227,6 +229,7 @@
 ; V3-GFX1032: .amdgcn_target "amdgcn-amd-amdhsa--gfx1032"
 ; V3-GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
 ; V3-GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
+; V3-GFX1035: .amdgcn_target "amdgcn-amd-amdhsa--gfx1035"
 
 ; GFX600: .amdgcn_target "amdgcn-amd-amdhsa--gfx600"
 ; GFX601: .amdgcn_target "amdgcn-amd-amdhsa--gfx601"
@@ -296,6 +299,7 @@
 ; GFX1032: .amdgcn_target "amdgcn-amd-amdhsa--gfx1032"
 ; GFX1033: .amdgcn_target "amdgcn-amd-amdhsa--gfx1033"
 ; GFX1034: .amdgcn_target "amdgcn-amd-amdhsa--gfx1034"
+; GFX1035: .amdgcn_target "amdgcn-amd-amdhsa--gfx1035"
 
 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 2af743d3a1434..e8d89ed0879a6 100644
--- a/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
+++ b/llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll
@@ -63,6 +63,7 @@
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1032 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1032 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1033 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1033 %s
 ; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1034 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1034 %s
+; RUN: llc -filetype=obj -march=amdgcn -mcpu=gfx1035 < %s | llvm-readobj -file-headers - | FileCheck --check-prefixes=ALL,ARCH-GCN,GFX1035 %s
 
 ; FIXME: With the default attributes the eflags are not accurate for
 ; xnack and sramecc. Subsequent Target-ID patches will address this.
@@ -123,6 +124,7 @@
 ; GFX1032:       EF_AMDGPU_MACH_AMDGCN_GFX1032 (0x38)
 ; GFX1033:       EF_AMDGPU_MACH_AMDGCN_GFX1033 (0x39)
 ; GFX1034:       EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
+; GFX1035:       EF_AMDGPU_MACH_AMDGCN_GFX1035 (0x3D)
 ; 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 c2b798782d095..5c07d1b39f51a 100644
--- a/llvm/test/MC/AMDGPU/gfx1011_dlops.s
+++ b/llvm/test/MC/AMDGPU/gfx1011_dlops.s
@@ -5,6 +5,7 @@
 // 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
 // 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
 
 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 5f2b395412eb6..ef04e6857712d 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_err.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_err.s
@@ -3,6 +3,7 @@
 // RUN: not llvm-mc -arch=amdgcn -mcpu=gfx1032 %s 2>&1 | FileCheck --check-prefix=GFX10 --implicit-check-not=error: %s
 // 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
 
 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 47eb5a6e75db5..9fbf04053bea9 100644
--- a/llvm/test/MC/AMDGPU/gfx1030_new.s
+++ b/llvm/test/MC/AMDGPU/gfx1030_new.s
@@ -3,6 +3,7 @@
 // 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
 // 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
 
 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 27f9caa09234a..00d3e86ca7b16 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1011_dasm_dlops.txt
@@ -5,6 +5,7 @@
 # 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
 # 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
 
 # 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 65ed5edcd2681..03785e696422f 100644
--- a/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt
@@ -3,6 +3,7 @@
 # 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
 # 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
 
 # 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 f5aca52e39bb4..62c2b83e8232e 100644
--- a/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
+++ b/llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml
@@ -186,6 +186,10 @@
 # RUN: llvm-readobj -S --file-headers %t.o.AMDGCN_GFX1034 | FileCheck --check-prefixes=ELF-AMDGCN-ALL,ELF-AMDGCN-GFX1034 %s
 # RUN: obj2yaml %t.o.AMDGCN_GFX1034 | FileCheck --check-prefixes=YAML-AMDGCN-ALL,YAML-AMDGCN-GFX1034 %s
 
+# RUN: sed -e 's/<BITS>/64/' -e 's/<MACH>/AMDGCN_GFX1035/' %s | yaml2obj -o %t.o.AMDGCN_GFX1035
+# 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
+
 # ELF-R600-ALL:       Format: elf32-amdgpu
 # ELF-R600-ALL:       Arch: r600
 # ELF-R600-ALL:       AddressSize: 32bit
@@ -344,6 +348,9 @@
 # ELF-AMDGCN-GFX1034:   EF_AMDGPU_MACH_AMDGCN_GFX1034 (0x3E)
 # YAML-AMDGCN-GFX1034:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1034 ]
 
+# ELF-AMDGCN-GFX1035:   EF_AMDGPU_MACH_AMDGCN_GFX1035 (0x3D)
+# YAML-AMDGCN-GFX1035:  Flags: [ EF_AMDGPU_MACH_AMDGCN_GFX1035 ]
+#
 # 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 a759a3e289dd3..425d631616da3 100644
--- a/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
+++ b/llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll
@@ -5,6 +5,10 @@ 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=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
+; RUN: 
diff  %t-specify.txt %t-detect.txt
 ;
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1034 -filetype=obj -O0 -o %t.o %s
 ; RUN: llvm-objdump -D --arch-name=amdgcn --mcpu=gfx1034 %t.o > %t-specify.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 8f026aa3bfc34..c8f44cadde9a4 100644
--- a/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
+++ b/llvm/test/tools/llvm-readobj/ELF/amdgpu-elf-headers.test
@@ -277,6 +277,14 @@
 # RUN: yaml2obj %s -o %t -DABI_VERSION=2 -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1034
 # 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_GFX1034 -DFLAG_VALUE=0x3E
 
+# RUN: yaml2obj %s -o %t -DABI_VERSION=0 -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=0 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1035 -DFLAG_VALUE=0x3D
+#
+# RUN: yaml2obj %s -o %t -DABI_VERSION=1 -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=1 -DFILE=%t -DFLAG_NAME=EF_AMDGPU_MACH_AMDGCN_GFX1035 -DFLAG_VALUE=0x3D
+#
+# 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_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 bf2b642c69557..11914fc808f68 100644
--- a/llvm/tools/llvm-readobj/ELFDumper.cpp
+++ b/llvm/tools/llvm-readobj/ELFDumper.cpp
@@ -1493,6 +1493,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion3[] = {
   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_MACH_AMDGCN_GFX1034),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1035),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_XNACK_V3),
   LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_FEATURE_SRAMECC_V3)
 };
@@ -1546,6 +1547,7 @@ static const EnumEntry<unsigned> ElfHeaderAMDGPUFlagsABIVersion4[] = {
   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_MACH_AMDGCN_GFX1034),
+  LLVM_READOBJ_ENUM_ENT(ELF, EF_AMDGPU_MACH_AMDGCN_GFX1035),
   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/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp b/openmp/libomptarget/plugins/amdgpu/impl/get_elf_mach_gfx_name.cpp
index 60fc30a0ffcd3..124ae6691e03f 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
@@ -51,6 +51,8 @@ const char *get_elf_mach_gfx_name(uint32_t EFlags) {
     return "gfx1033";
   case EF_AMDGPU_MACH_AMDGCN_GFX1034:
     return "gfx1034";
+  case EF_AMDGPU_MACH_AMDGCN_GFX1035:
+    return "gfx1035";
   default:
     return "--unknown gfx";
   }


        


More information about the Openmp-commits mailing list