[PATCH] D139931: [AMDGPU] Add `.workgroup_processor_mode` to v5 MD

[Pierre van Houtryve via Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG9fa46200ea2f: [AMDGPU] Add `.workgroup_processor_mode` to v5 MD (authored by Pierre-vh).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D139931/new/

https://reviews.llvm.org/D139931

Files:
  llvm/docs/AMDGPUUsage.rst
  llvm/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
  llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
  llvm/lib/Target/AMDGPU/GCNSubtarget.h
  llvm/test/CodeGen/AMDGPU/hsa-metadata-workgroup-processor-mode-v5.ll


Index: llvm/test/CodeGen/AMDGPU/hsa-metadata-workgroup-processor-mode-v5.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/hsa-metadata-workgroup-processor-mode-v5.ll
@@ -0,0 +1,14 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=5 -mcpu=gfx1010 -mattr=+cumode < %s | FileCheck -check-prefix=GFX10 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=5 -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10-CU %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=5 -mcpu=gfx1100 -mattr=+cumode < %s | FileCheck -check-prefix=GFX10 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=5 -mcpu=gfx1100 < %s | FileCheck -check-prefix=GFX10-CU %s
+
+; GFX10:    .amdhsa_workgroup_processor_mode 0
+; GFX10:    .workgroup_processor_mode: 0
+; GFX10-CU: .amdhsa_workgroup_processor_mode 1
+; GFX10-CU: .workgroup_processor_mode: 1
+
+define amdgpu_kernel void @wavefrontsize() {
+entry:
+  ret void
+}
Index: llvm/lib/Target/AMDGPU/GCNSubtarget.h
===================================================================
--- llvm/lib/Target/AMDGPU/GCNSubtarget.h
+++ llvm/lib/Target/AMDGPU/GCNSubtarget.h
@@ -298,6 +298,8 @@
   /// the original value.
   bool zeroesHigh16BitsOfDest(unsigned Opcode) const;
 
+  bool supportsWGP() const { return getGeneration() >= GFX10; }
+
   bool hasIntClamp() const {
     return HasIntClamp;
   }
Index: llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
@@ -877,6 +877,9 @@
   if (AMDGPU::getAmdhsaCodeObjectVersion() >= 5)
     Kern[".uses_dynamic_stack"] =
         Kern.getDocument()->getNode(ProgramInfo.DynamicCallStack);
+  if (AMDGPU::getAmdhsaCodeObjectVersion() >= 5 && STM.supportsWGP())
+    Kern[".workgroup_processor_mode"] =
+        Kern.getDocument()->getNode(ProgramInfo.WgpMode);
 
   // FIXME: The metadata treats the minimum as 16?
   Kern[".kernarg_segment_align"] =
Index: llvm/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
===================================================================
--- llvm/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
+++ llvm/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
@@ -262,6 +262,8 @@
   if (!verifyScalarEntry(KernelMap, ".uses_dynamic_stack", false,
                          msgpack::Type::Boolean))
     return false;
+  if (!verifyIntegerEntry(KernelMap, ".workgroup_processor_mode", false))
+    return false;
   if (!verifyIntegerEntry(KernelMap, ".kernarg_segment_align", true))
     return false;
   if (!verifyIntegerEntry(KernelMap, ".wavefront_size", true))
Index: llvm/docs/AMDGPUUsage.rst
===================================================================
--- llvm/docs/AMDGPUUsage.rst
+++ llvm/docs/AMDGPUUsage.rst
@@ -3571,12 +3571,14 @@
   .. table:: AMDHSA Code Object V5 Kernel Metadata Map Additions
      :name: amdgpu-amdhsa-code-object-kernel-metadata-map-table-v5
 
-     ===================== ============= ========== =======================================
-     String Key            Value Type     Required? Description
-     ===================== ============= ========== =======================================
-     ".uses_dynamic_stack" boolean                  Indicates if the generated machine code
-                                                    is using a dynamically sized stack.
-     ===================== ============= ========== =======================================
+     ============================= ============= ========== =======================================
+     String Key                    Value Type     Required? Description
+     ============================= ============= ========== =======================================
+     ".uses_dynamic_stack"         boolean                  Indicates if the generated machine code
+                                                            is using a dynamically sized stack.
+     ".workgroup_processor_mode"   boolean                  (GFX10+) Controls ENABLE_WGP_MODE in
+                                                            :ref:`amdgpu-amdhsa-kernel-descriptor-v3-table`.
+     ============================= ============= ========== =======================================
 
 ..
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D139931.482483.patch
Type: text/x-patch
Size: 4409 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221213/ba882be2/attachment.bin>