[llvm-branch-commits] [flang] [libc] [libclc] [llvm] [AMDGPU] Replace gfx940 and gfx941 with gfx942 in offload and libclc (PR #125826)

[via llvm-branch-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Fabian Ritter (ritter-x2a)

<details>
<summary>Changes</summary>

gfx940 and gfx941 are no longer supported. This is one of a series of
PRs to remove them from the code base.

For SWDEV-512631 and SWDEV-512633

---
Full diff: https://github.com/llvm/llvm-project/pull/125826.diff


5 Files Affected:

- (modified) flang/cmake/modules/AddFlangOffloadRuntime.cmake (+1-1) 
- (modified) libc/docs/gpu/using.rst (+1-1) 
- (modified) libclc/CMakeLists.txt (+1-1) 
- (modified) offload/plugins-nextgen/amdgpu/src/rtl.cpp (-6) 
- (modified) offload/test/lit.cfg (+1-3) 


``````````diff
diff --git a/flang/cmake/modules/AddFlangOffloadRuntime.cmake b/flang/cmake/modules/AddFlangOffloadRuntime.cmake
index 8e4f47d18535dcb..f1f6eb57c5d6cf3 100644
--- a/flang/cmake/modules/AddFlangOffloadRuntime.cmake
+++ b/flang/cmake/modules/AddFlangOffloadRuntime.cmake
@@ -98,7 +98,7 @@ macro(enable_omp_offload_compilation files)
 
       set(all_amdgpu_architectures
         "gfx700;gfx701;gfx801;gfx803;gfx900;gfx902;gfx906"
-        "gfx908;gfx90a;gfx90c;gfx940;gfx1010;gfx1030"
+        "gfx908;gfx90a;gfx90c;gfx942;gfx1010;gfx1030"
         "gfx1031;gfx1032;gfx1033;gfx1034;gfx1035;gfx1036"
         "gfx1100;gfx1101;gfx1102;gfx1103;gfx1150;gfx1151"
         "gfx1152;gfx1153"
diff --git a/libc/docs/gpu/using.rst b/libc/docs/gpu/using.rst
index 1c1f9c9bfb0c696..f17f6287be31349 100644
--- a/libc/docs/gpu/using.rst
+++ b/libc/docs/gpu/using.rst
@@ -44,7 +44,7 @@ this shouldn't be necessary.
 
   $> clang openmp.c -fopenmp --offload-arch=gfx90a -Xoffload-linker -lc
   $> clang cuda.cu --offload-arch=sm_80 --offload-new-driver -fgpu-rdc -Xoffload-linker -lc
-  $> clang hip.hip --offload-arch=gfx940 --offload-new-driver -fgpu-rdc -Xoffload-linker -lc
+  $> clang hip.hip --offload-arch=gfx942 --offload-new-driver -fgpu-rdc -Xoffload-linker -lc
 
 This will automatically link in the needed function definitions if they were
 required by the user's application. Normally using the ``-fgpu-rdc`` option
diff --git a/libclc/CMakeLists.txt b/libclc/CMakeLists.txt
index ff52153354e0a9c..010f14da9f7e788 100644
--- a/libclc/CMakeLists.txt
+++ b/libclc/CMakeLists.txt
@@ -215,7 +215,7 @@ set( cayman_aliases aruba )
 set( tahiti_aliases pitcairn verde oland hainan bonaire kabini kaveri hawaii
   mullins tonga tongapro iceland carrizo fiji stoney polaris10 polaris11
   gfx602 gfx705 gfx805
-  gfx900 gfx902 gfx904 gfx906 gfx908 gfx909 gfx90a gfx90c gfx940 gfx941 gfx942
+  gfx900 gfx902 gfx904 gfx906 gfx908 gfx909 gfx90a gfx90c gfx942
   gfx1010 gfx1011 gfx1012 gfx1013
   gfx1030 gfx1031 gfx1032 gfx1033 gfx1034 gfx1035 gfx1036
   gfx1100 gfx1101 gfx1102 gfx1103
diff --git a/offload/plugins-nextgen/amdgpu/src/rtl.cpp b/offload/plugins-nextgen/amdgpu/src/rtl.cpp
index 92184ba796dbd83..e83d38a14f77f67 100644
--- a/offload/plugins-nextgen/amdgpu/src/rtl.cpp
+++ b/offload/plugins-nextgen/amdgpu/src/rtl.cpp
@@ -2854,12 +2854,6 @@ struct AMDGPUDeviceTy : public GenericDeviceTy, AMDGenericDeviceTy {
   Error checkIfAPU() {
     // TODO: replace with ROCr API once it becomes available.
     llvm::StringRef StrGfxName(ComputeUnitKind);
-    IsAPU = llvm::StringSwitch<bool>(StrGfxName)
-                .Case("gfx940", true)
-                .Default(false);
-    if (IsAPU)
-      return Plugin::success();
-
     bool MayBeAPU = llvm::StringSwitch<bool>(StrGfxName)
                         .Case("gfx942", true)
                         .Default(false);
diff --git a/offload/test/lit.cfg b/offload/test/lit.cfg
index 658ae5f9653ba90..fe28418d9c1b1a3 100644
--- a/offload/test/lit.cfg
+++ b/offload/test/lit.cfg
@@ -132,12 +132,10 @@ elif config.libomptarget_current_target.startswith('amdgcn'):
     # amdgpu_test_arch contains a list of AMD GPUs in the system
     # only check the first one assuming that we will run the test on it.
     if not (config.amdgpu_test_arch.startswith("gfx90a") or
-            config.amdgpu_test_arch.startswith("gfx940") or
             config.amdgpu_test_arch.startswith("gfx942")):
        supports_unified_shared_memory = False
     # check if AMD architecture is an APU:
-    if (config.amdgpu_test_arch.startswith("gfx940") or
-        (config.amdgpu_test_arch.startswith("gfx942") and
+    if ((config.amdgpu_test_arch.startswith("gfx942") and
          evaluate_bool_env(config.environment['IS_APU']))):
        supports_apu = True
 if supports_unified_shared_memory:

``````````

</details>


https://github.com/llvm/llvm-project/pull/125826