[AMDGPU] Add gfx1251 subtarget #159430

rampitec · 2025-09-17T19:17:32Z

No description provided.

rampitec · 2025-09-17T19:17:49Z

[AMDGPU] Add gfx1251 runlines to cooperative atomcis tests. NFC #159437
[AMDGPU] Add gfx1251 subtarget #159430 👈 (View in Graphite)
main

This stack of pull requests is managed by Graphite. Learn more about stacking.

llvmbot · 2025-09-17T19:19:42Z

@llvm/pr-subscribers-objectyaml
@llvm/pr-subscribers-clang-driver
@llvm/pr-subscribers-backend-amdgpu

@llvm/pr-subscribers-clang-codegen

Author: Stanislav Mekhanoshin (rampitec)

Changes

Patch is 39.99 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/159430.diff

27 Files Affected:

(modified) clang/include/clang/Basic/OffloadArch.h (+1)
(modified) clang/lib/Basic/OffloadArch.cpp (+1)
(modified) clang/lib/Basic/Targets/NVPTX.cpp (+1)
(modified) clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp (+1)
(modified) clang/test/CodeGenOpenCL/amdgpu-features.cl (+2)
(modified) clang/test/Driver/amdgpu-macros.cl (+7)
(modified) clang/test/Driver/amdgpu-mcpu.cl (+2)
(modified) clang/test/Driver/cuda-bad-arch.cu (+2)
(modified) clang/test/Misc/target-invalid-cpu-note/amdgcn.c (+1)
(modified) clang/test/Misc/target-invalid-cpu-note/nvptx.c (+1)
(modified) clang/test/SemaOpenCL/builtins-amdgcn-error-gfx1250-cooperative-atomics.cl (+1)
(modified) llvm/docs/AMDGPUUsage.rst (+16)
(modified) llvm/include/llvm/BinaryFormat/ELF.h (+1)
(modified) llvm/include/llvm/TargetParser/TargetParser.h (+2-1)
(modified) llvm/lib/Object/ELFObjectFile.cpp (+2)
(modified) llvm/lib/ObjectYAML/ELFYAML.cpp (+1)
(modified) llvm/lib/Target/AMDGPU/AMDGPU.td (+4)
(modified) llvm/lib/Target/AMDGPU/GCNProcessors.td (+4)
(modified) llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp (+2)
(modified) llvm/lib/TargetParser/TargetParser.cpp (+3)
(modified) llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll (+2)
(modified) llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll (+2)
(added) llvm/test/MC/AMDGPU/hsa-gfx1251-v4.s (+346)
(modified) llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml (+7)
(modified) llvm/test/tools/llvm-objdump/ELF/AMDGPU/subtarget.ll (+5)
(modified) llvm/test/tools/llvm-readobj/ELF/AMDGPU/elf-headers.test (+9)
(modified) llvm/tools/llvm-readobj/ELFDumper.cpp (+1)

diff --git a/clang/include/clang/Basic/OffloadArch.h b/clang/include/clang/Basic/OffloadArch.h
index 387a68452ea0c..befb69ff22d49 100644
--- a/clang/include/clang/Basic/OffloadArch.h
+++ b/clang/include/clang/Basic/OffloadArch.h
@@ -103,6 +103,7 @@ enum class OffloadArch {
   GFX1200,
   GFX1201,
   GFX1250,
+  GFX1251,
   AMDGCNSPIRV,
   Generic, // A processor model named 'generic' if the target backend defines a
            // public one.
diff --git a/clang/lib/Basic/OffloadArch.cpp b/clang/lib/Basic/OffloadArch.cpp
index 434817813c470..af08872a943a0 100644
--- a/clang/lib/Basic/OffloadArch.cpp
+++ b/clang/lib/Basic/OffloadArch.cpp
@@ -91,6 +91,7 @@ static const OffloadArchToStringMap ArchNames[] = {
     GFX(1200), // gfx1200
     GFX(1201), // gfx1201
     GFX(1250), // gfx1250
+    GFX(1251), // gfx1251
     {OffloadArch::AMDGCNSPIRV, "amdgcnspirv", "compute_amdgcn"},
     // Intel CPUs
     {OffloadArch::GRANITERAPIDS, "graniterapids", ""},
diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
index f7abc05903cdf..9651c3832f51d 100644
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -240,6 +240,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case OffloadArch::GFX1200:
       case OffloadArch::GFX1201:
       case OffloadArch::GFX1250:
+      case OffloadArch::GFX1251:
       case OffloadArch::AMDGCNSPIRV:
       case OffloadArch::Generic:
       case OffloadArch::GRANITERAPIDS:
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index 8a402fc3859cf..44a091e1b3c75 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -2336,6 +2336,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(const OMPRequiresDecl *D) {
       case OffloadArch::GFX1200:
       case OffloadArch::GFX1201:
       case OffloadArch::GFX1250:
+      case OffloadArch::GFX1251:
       case OffloadArch::AMDGCNSPIRV:
       case OffloadArch::Generic:
       case OffloadArch::GRANITERAPIDS:
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index 0fdb212553151..af1ef64764cf4 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -53,6 +53,7 @@
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1200 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1200 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1201 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1201 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1250 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1250 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1251 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1251 %s
 
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1103 -target-feature +wavefrontsize64 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1103-W64 %s
 
@@ -109,6 +110,7 @@
 // GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 // GFX1201: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 // GFX1250: "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+bf16-cvt-insts,+bf16-pk-insts,+bf16-trans-insts,+bitop3-insts,+ci-insts,+dl-insts,+dot7-insts,+dot8-insts,+dpp,+fp8-conversion-insts,+fp8e5m3-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx1250-insts,+gfx8-insts,+gfx9-insts,+permlane16-swap,+prng-inst,+setprio-inc-wg-inst,+tanh-insts,+tensor-cvt-lut-insts,+transpose-load-f4f6-insts,+vmem-pref-insts,+wavefrontsize32"
+// GFX1251: "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+bf16-cvt-insts,+bf16-pk-insts,+bf16-trans-insts,+bitop3-insts,+ci-insts,+dl-insts,+dot7-insts,+dot8-insts,+dpp,+fp8-conversion-insts,+fp8e5m3-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx1250-insts,+gfx8-insts,+gfx9-insts,+permlane16-swap,+prng-inst,+setprio-inc-wg-inst,+tanh-insts,+tensor-cvt-lut-insts,+transpose-load-f4f6-insts,+vmem-pref-insts,+wavefrontsize32"
 
 // GFX1103-W64: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize64"
 
diff --git a/clang/test/Driver/amdgpu-macros.cl b/clang/test/Driver/amdgpu-macros.cl
index a60593f2ab9ed..9fda2f3657430 100644
--- a/clang/test/Driver/amdgpu-macros.cl
+++ b/clang/test/Driver/amdgpu-macros.cl
@@ -131,6 +131,7 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1200 -DFAMILY=GFX12
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1201 -DFAMILY=GFX12
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1250 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1250 -DFAMILY=GFX12
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1251 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1251 -DFAMILY=GFX12
 
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx9-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx9_generic -DFAMILY=GFX9
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx9-4-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx9_4_generic -DFAMILY=GFX9
@@ -191,6 +192,12 @@
 // RUN:   %s 2>&1 | FileCheck --check-prefix=CUMODE-ON %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1250 -mno-cumode \
 // RUN:   %s 2>&1 | FileCheck -DMCPU=gfx1250 --check-prefixes=CUMODE-ON,WARN-CUMODE %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1251 \
+// RUN:   %s 2>&1 | FileCheck --check-prefix=CUMODE-ON %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1251 -mcumode \
+// RUN:   %s 2>&1 | FileCheck --check-prefix=CUMODE-ON %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1251 -mno-cumode \
+// RUN:   %s 2>&1 | FileCheck -DMCPU=gfx1251 --check-prefixes=CUMODE-ON,WARN-CUMODE %s
 // WARN-CUMODE-DAG: warning: ignoring '-mno-cumode' option as it is not currently supported for processor '[[MCPU]]' [-Woption-ignored]
 // CUMODE-ON-DAG: #define __AMDGCN_CUMODE__ 1
 // CUMODE-OFF-DAG: #define __AMDGCN_CUMODE__ 0
diff --git a/clang/test/Driver/amdgpu-mcpu.cl b/clang/test/Driver/amdgpu-mcpu.cl
index 6d302e4c59ad8..bca5be7f8d63a 100644
--- a/clang/test/Driver/amdgpu-mcpu.cl
+++ b/clang/test/Driver/amdgpu-mcpu.cl
@@ -116,6 +116,7 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefix=GFX1200 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefix=GFX1201 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1250 %s 2>&1 | FileCheck --check-prefix=GFX1250 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1251 %s 2>&1 | FileCheck --check-prefix=GFX1251 %s
 
 // RUN: %clang -### -target amdgcn -mcpu=gfx9-generic %s 2>&1 | FileCheck --check-prefix=GFX9_GENERIC %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx9-4-generic %s 2>&1 | FileCheck --check-prefix=GFX9_4_GENERIC %s
@@ -171,6 +172,7 @@
 // GFX1200:   "-target-cpu" "gfx1200"
 // GFX1201:   "-target-cpu" "gfx1201"
 // GFX1250:   "-target-cpu" "gfx1250"
+// GFX1251:   "-target-cpu" "gfx1251"
 
 // GFX9_GENERIC:      "-target-cpu" "gfx9-generic"
 // GFX9_4_GENERIC:    "-target-cpu" "gfx9-4-generic"
diff --git a/clang/test/Driver/cuda-bad-arch.cu b/clang/test/Driver/cuda-bad-arch.cu
index 6ac72296049bc..3f0bdd3aa7b4b 100644
--- a/clang/test/Driver/cuda-bad-arch.cu
+++ b/clang/test/Driver/cuda-bad-arch.cu
@@ -27,6 +27,8 @@
 // RUN: | FileCheck -check-prefix OK %s
 // RUN: %clang -### -x hip --target=x86_64-linux-gnu -nogpulib -nogpuinc --cuda-gpu-arch=gfx1250 -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix OK %s
+// RUN: %clang -### -x hip --target=x86_64-linux-gnu -nogpulib -nogpuinc --cuda-gpu-arch=gfx1251 -c %s 2>&1 \
+// RUN: | FileCheck -check-prefix OK %s
 
 // We don't allow using NVPTX/AMDGCN for host compilation.
 // RUN: not %clang -### --no-offload-new-driver --cuda-host-only --target=nvptx-nvidia-cuda -nogpulib -nogpuinc -c %s 2>&1 \
diff --git a/clang/test/Misc/target-invalid-cpu-note/amdgcn.c b/clang/test/Misc/target-invalid-cpu-note/amdgcn.c
index 352658b6fb388..d31a7246e9d80 100644
--- a/clang/test/Misc/target-invalid-cpu-note/amdgcn.c
+++ b/clang/test/Misc/target-invalid-cpu-note/amdgcn.c
@@ -69,6 +69,7 @@
 // CHECK-SAME: {{^}}, gfx1200
 // CHECK-SAME: {{^}}, gfx1201
 // CHECK-SAME: {{^}}, gfx1250
+// CHECK-SAME: {{^}}, gfx1251
 // CHECK-SAME: {{^}}, gfx9-generic
 // CHECK-SAME: {{^}}, gfx10-1-generic
 // CHECK-SAME: {{^}}, gfx10-3-generic
diff --git a/clang/test/Misc/target-invalid-cpu-note/nvptx.c b/clang/test/Misc/target-invalid-cpu-note/nvptx.c
index b90f26e8b348d..5116f044ee1cf 100644
--- a/clang/test/Misc/target-invalid-cpu-note/nvptx.c
+++ b/clang/test/Misc/target-invalid-cpu-note/nvptx.c
@@ -88,5 +88,6 @@
 // CHECK-SAME: {{^}}, gfx1200
 // CHECK-SAME: {{^}}, gfx1201
 // CHECK-SAME: {{^}}, gfx1250
+// CHECK-SAME: {{^}}, gfx1251
 // CHECK-SAME: {{^}}, amdgcnspirv
 // CHECK-SAME: {{$}}
diff --git a/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx1250-cooperative-atomics.cl b/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx1250-cooperative-atomics.cl
index 0ab9a5a43e718..8f02e6775d37a 100644
--- a/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx1250-cooperative-atomics.cl
+++ b/clang/test/SemaOpenCL/builtins-amdgcn-error-gfx1250-cooperative-atomics.cl
@@ -1,6 +1,7 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
 // REQUIRES: amdgpu-registered-target
 // RUN: %clang_cc1 -verify -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1250 -emit-llvm -o - %s
+// RUN: %clang_cc1 -verify -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1251 -emit-llvm -o - %s
 
 typedef int    v2i   __attribute__((ext_vector_type(2)));
 typedef int    v4i   __attribute__((ext_vector_type(4)));
diff --git a/llvm/docs/AMDGPUUsage.rst b/llvm/docs/AMDGPUUsage.rst
index 1265ec40c06d6..26dd6cc243f34 100644
--- a/llvm/docs/AMDGPUUsage.rst
+++ b/llvm/docs/AMDGPUUsage.rst
@@ -537,6 +537,21 @@ Every processor supports every OS ABI (see :ref:`amdgpu-os`) with the following
                                                                       - Packed
                                                                         work-item                       Add product
                                                                         IDs                             names.
+                                                                      - Globally
+                                                                        Accessible
+                                                                        Scratch
+                                                                      - Workgroup
+                                                                        Clusters
+
+     ``gfx1251``                 ``amdgcn``   APU                     - Architected                   *TBA*
+                                                                        flat
+                                                                        scratch                       .. TODO::
+                                                                      - Packed
+                                                                        work-item                       Add product
+                                                                        IDs                             names.
+                                                                      - Globally
+                                                                        Accessible
+                                                                        Scratch
                                                                       - Workgroup
                                                                         Clusters
 
@@ -2367,6 +2382,7 @@ The AMDGPU backend uses the following ELF header:
      *reserved*                                 0x057      Reserved.
      ``EF_AMDGPU_MACH_AMDGCN_GFX1153``          0x058      ``gfx1153``.
      ``EF_AMDGPU_MACH_AMDGCN_GFX12_GENERIC``    0x059      ``gfx12-generic``
+     ``EF_AMDGPU_MACH_AMDGCN_GFX1251``          0x05a      ``gfx1251``
      ``EF_AMDGPU_MACH_AMDGCN_GFX9_4_GENERIC``   0x05f      ``gfx9-4-generic``
      ========================================== ========== =============================
 
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index 749971e354f66..8321767653503 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -859,6 +859,7 @@ enum : unsigned {
   EF_AMDGPU_MACH_AMDGCN_RESERVED_0X57   = 0x057,
   EF_AMDGPU_MACH_AMDGCN_GFX1153         = 0x058,
   EF_AMDGPU_MACH_AMDGCN_GFX12_GENERIC   = 0x059,
+  EF_AMDGPU_MACH_AMDGCN_GFX1251         = 0x05a,
   EF_AMDGPU_MACH_AMDGCN_GFX9_4_GENERIC  = 0x05f,
   // clang-format on
 
diff --git a/llvm/include/llvm/TargetParser/TargetParser.h b/llvm/include/llvm/TargetParser/TargetParser.h
index f8a4ee2f6fcfd..aad9859263480 100644
--- a/llvm/include/llvm/TargetParser/TargetParser.h
+++ b/llvm/include/llvm/TargetParser/TargetParser.h
@@ -113,9 +113,10 @@ enum GPUKind : uint32_t {
   GK_GFX1200,
   GK_GFX1201,
   GK_GFX1250,
+  GK_GFX1251,
 
   GK_AMDGCN_FIRST = GK_GFX600,
-  GK_AMDGCN_LAST = GK_GFX1250,
+  GK_AMDGCN_LAST = GK_GFX1251,
 
   GK_GFX9_GENERIC,
   GK_GFX10_1_GENERIC,
diff --git a/llvm/lib/Object/ELFObjectFile.cpp b/llvm/lib/Object/ELFObjectFile.cpp
index aff047c297cc2..a2f9155699f82 100644
--- a/llvm/lib/Object/ELFObjectFile.cpp
+++ b/llvm/lib/Object/ELFObjectFile.cpp
@@ -599,6 +599,8 @@ StringRef ELFObjectFileBase::getAMDGPUCPUName() const {
     return "gfx1201";
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1250:
     return "gfx1250";
+  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1251:
+    return "gfx1251";
 
   // Generic AMDGCN targets
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC:
diff --git a/llvm/lib/ObjectYAML/ELFYAML.cpp b/llvm/lib/ObjectYAML/ELFYAML.cpp
index 62d80a24f4787..0228dedb3fbfa 100644
--- a/llvm/lib/ObjectYAML/ELFYAML.cpp
+++ b/llvm/lib/ObjectYAML/ELFYAML.cpp
@@ -634,6 +634,7 @@ void ScalarBitSetTraits<ELFYAML::ELF_EF>::bitset(IO &IO,
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1200, EF_AMDGPU_MACH);
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1201, EF_AMDGPU_MACH);
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1250, EF_AMDGPU_MACH);
+    BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX1251, EF_AMDGPU_MACH);
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC, EF_AMDGPU_MACH);
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX9_4_GENERIC, EF_AMDGPU_MACH);
     BCaseMask(EF_AMDGPU_MACH_AMDGCN_GFX10_1_GENERIC, EF_AMDGPU_MACH);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 35e64486184b1..23339b2ad228e 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -2108,6 +2108,10 @@ def FeatureISAVersion12_50 : FeatureSet<
    FeatureSetPrioIncWgInst,
 ]>;
 
+def FeatureISAVersion12_51 : FeatureSet<
+  !listconcat(FeatureISAVersion12_50.Features,
+  [FeatureDPALU_DPP])>;
+
 def FeatureISAVersion12_Generic: FeatureSet<
   !listconcat(FeatureISAVersion12.Features,
     [FeatureRequiresCOV6])>;
diff --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index 46b7c2f50780d..c6fb31f9cdbd2 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -329,3 +329,7 @@ def : ProcessorModel<"gfx12-generic", GFX12SpeedModel,
 def : ProcessorModel<"gfx1250", GFX1250SpeedModel,
   FeatureISAVersion12_50.Features
 >;
+
+def : ProcessorModel<"gfx1251", GFX1250SpeedModel,
+  FeatureISAVersion12_51.Features
+>;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index ff6a21239345d..5a0857322a39b 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_GFX1200: AK = GK_GFX1200; break;
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1201: AK = GK_GFX1201; break;
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1250: AK = GK_GFX1250; break;
+  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1251: AK = GK_GFX1251; break;
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC:     AK = GK_GFX9_GENERIC; break;
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX9_4_GENERIC:   AK = GK_GFX9_4_GENERIC; break;
   case ELF::EF_AMDGPU_MACH_AMDGCN_GFX10_1_GENERIC:  AK = GK_GFX10_1_GENERIC; break;
@@ -203,6 +204,7 @@ unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
   case GK_GFX1200: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1200;
   case GK_GFX1201: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1201;
   case GK_GFX1250: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1250;
+  case GK_GFX1251: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1251;
   case GK_GFX9_GENERIC:     return ELF::EF_AMDGPU_MACH_AMDGCN_GFX9_GENERIC;
   case GK_GFX9_4_GENERIC:   return ELF::EF_AMDGPU_MACH_AMDGCN_GFX9_4_GENERIC;
   case GK_GFX10_1_GENERIC:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX10_1_GENERIC;
diff --git a/llvm/lib/TargetParser/TargetParser.cpp b/llvm/lib/TargetParser/TargetParser.cpp
index acc8a2d83b8a0..34b09b14b0138 100644
--- a/llvm/lib/TargetParser/TargetParser.cpp
+++ b/llvm/lib/TargetParser/TargetParser.cpp
@@ -175,6 +175,7 @@ constexpr GPUInfo AMDGCNGPUs[] = {
     {{"gfx1200"},   {"gfx1200"}, GK_GFX1200, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
     {{"gfx1201"},   {"gfx1201"}, GK_GFX1201, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_WGP},
     {{"gfx1250"},   {"gfx1250"}, GK_GFX1250, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
+    {{"gfx1251"},   {"gfx1251"}, GK_GFX1251, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32},
 
     {{"gfx9-generic"},      {"gfx9-generic"},    GK_GFX9_GENERIC,    FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_XNACK},
     {{"gfx10-1-generic"},   {"gfx10-1-generic"}, GK_GFX10_1_GENERIC, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32|FEATURE_XNACK|FEATURE_WGP},
@@ -330,6 +331,7 @@ AMDGPU::IsaVersion AMDGPU::getIsaVersion(StringRef GPU) {
   case GK_GFX1200: return {12, 0, 0};
   case GK_GFX1201: return {12, 0, 1};
   case GK_GFX1250: return {12, 5, 0};
+  case GK_GFX1251: return {12, 5, 1};
 
   // Generic targets return the lowest common denominator
   // within their family. That is, the ISA that is the most
@@ -404,6 +406,7 @@ static void fillAMDGCNFeatureMap(StringRef GPU, const Triple &T,
                                  StringMap<bool> &Features) {
   AMDGPU::GPUKind Kind = parseArchAMDGCN(GPU);
   switch (Kind) {
+  case GK_GFX1251:
   case GK_GFX1250:
     Features["ci-insts"] = true;
     Features["dot7-insts"] = true;
diff --git a/llvm/test/CodeGen/AMDGPU/directive-amdgc...
[truncated]

[AMDGPU] Add gfx1251 subtarget

0219b29

rampitec requested review from changpeng, kzhuravl and shiltian September 17, 2025 19:18

rampitec marked this pull request as ready for review September 17, 2025 19:19

shiltian approved these changes Sep 17, 2025

View reviewed changes

rampitec mentioned this pull request Sep 17, 2025

[AMDGPU] Add gfx1251 runlines to cooperative atomcis tests. NFC #159437

Merged

rampitec merged commit e556dc0 into main Sep 17, 2025
21 checks passed

rampitec deleted the users/rampitec/09-17-_amdgpu_add_gfx1251_subtarget branch September 17, 2025 20:02

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[AMDGPU] Add gfx1251 subtarget #159430

[AMDGPU] Add gfx1251 subtarget #159430

Uh oh!

rampitec commented Sep 17, 2025

Uh oh!

rampitec commented Sep 17, 2025 •

edited

Loading

Uh oh!

llvmbot commented Sep 17, 2025 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[AMDGPU] Add gfx1251 subtarget #159430

[AMDGPU] Add gfx1251 subtarget #159430

Uh oh!

Conversation

rampitec commented Sep 17, 2025

Uh oh!

rampitec commented Sep 17, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

llvmbot commented Sep 17, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

rampitec commented Sep 17, 2025 •

edited

Loading

llvmbot commented Sep 17, 2025 •

edited

Loading