AMDGPU: Remove amdgpu-max-work-group-size attribute

[arsenm]

Summary

This has been deprecated for a long time, and mesa recently switched
to amdgpu-flat-work-group-size.

[rampitec]

LGTM

[arsenm]

r362641

docs/AMDGPUUsage.rst

.. table:: AMDGPU LLVM IR Attributes
      ======================================= ==========================================================
      "amdgpu-flat-work-group-size"="min,max" Specify the minimum and maximum flat work group sizes that
                                              will be specified when the kernel is dispatched. Generated
                                              by the ``amdgpu_flat_work_group_size`` CLANG attribute [CLANG-ATTR]_.
      "amdgpu-implicitarg-num-bytes"="n"      Number of kernel argument bytes to add to the kernel
                                              argument block size for the implicit arguments. This
                                              varies by OS and language (for OpenCL see
                                              :ref:`opencl-kernel-implicit-arguments-appended-for-amdhsa-os-table`).
-     "amdgpu-max-work-group-size"="n"        Specify the maximum work-group size that will be specifed
-                                             when the kernel is dispatched.
      "amdgpu-num-sgpr"="n"                   Specifies the number of SGPRs to use. Generated by
                                              the ``amdgpu_num_sgpr`` CLANG attribute [CLANG-ATTR]_.
      "amdgpu-num-vgpr"="n"                   Specifies the number of VGPRs to use. Generated by the
                                              ``amdgpu_num_vgpr`` CLANG attribute [CLANG-ATTR]_.
      "amdgpu-waves-per-eu"="m,n"             Specify the minimum and maximum number of waves per
                                              execution unit. Generated by the ``amdgpu_waves_per_eu``
                                              CLANG attribute [CLANG-ATTR]_.
      "amdgpu-ieee" true/false.               Specify whether the function expects the IEEE field of the

lib/Target/AMDGPU/AMDGPUSubtarget.cpp

 
 std::pair<unsigned, unsigned> AMDGPUSubtarget::getFlatWorkGroupSizes(
   const Function &F) const {
   // FIXME: 1024 if function.
   // Default minimum/maximum flat work group sizes.
   std::pair<unsigned, unsigned> Default =
     getDefaultFlatWorkGroupSize(F.getCallingConv());
 
-  // TODO: Do not process "amdgpu-max-work-group-size" attribute once mesa
-  // starts using "amdgpu-flat-work-group-size" attribute.
-  Default.second = AMDGPU::getIntegerAttribute(
-    F, "amdgpu-max-work-group-size", Default.second);
-  Default.first = std::min(Default.first, Default.second);
-
   // Requested minimum/maximum flat work group sizes.
   std::pair<unsigned, unsigned> Requested = AMDGPU::getIntegerPairAttribute(
     F, "amdgpu-flat-work-group-size", Default);
 
   // Make sure requested minimum is less than requested maximum.
   if (Requested.first > Requested.second)
     return Default;
 
std::pair<unsigned, unsigned> AMDGPUSubtarget::getWavesPerEU(
   // If minimum/maximum flat work group sizes were explicitly requested using
   // "amdgpu-flat-work-group-size" attribute, then set default minimum/maximum
   // number of waves per execution unit to values implied by requested
   // minimum/maximum flat work group sizes.
   unsigned MinImpliedByFlatWorkGroupSize =
     getMaxWavesPerEU(FlatWorkGroupSizes.second);
   bool RequestedFlatWorkGroupSize = false;
 
-  // TODO: Do not process "amdgpu-max-work-group-size" attribute once mesa
-  // starts using "amdgpu-flat-work-group-size" attribute.
-  if (F.hasFnAttribute("amdgpu-max-work-group-size") ||
-      F.hasFnAttribute("amdgpu-flat-work-group-size")) {
+  if (F.hasFnAttribute("amdgpu-flat-work-group-size")) {
     Default.first = MinImpliedByFlatWorkGroupSize;
     RequestedFlatWorkGroupSize = true;
   }
 
   // Requested minimum/maximum number of waves per execution unit.
   std::pair<unsigned, unsigned> Requested = AMDGPU::getIntegerPairAttribute(
     F, "amdgpu-waves-per-eu", Default, true);
 

test/CodeGen/AMDGPU/large-work-group-promote-alloca.ll

entry:
   store i8 %tmp2, i8 addrspace(1)* %out, align 1
   %arrayidx12 = getelementptr inbounds [29 x i8], [29 x i8]* %stack, i64 0, i64 1
   %tmp3 = load i8, i8* %arrayidx12, align 1
   %arrayidx13 = getelementptr inbounds i8, i8 addrspace(1)* %out, i64 1
   store i8 %tmp3, i8 addrspace(1)* %arrayidx13, align 1
   ret void
 }
 
-attributes #0 = { nounwind "amdgpu-max-work-group-size"="63" }
+attributes #0 = { nounwind "amdgpu-flat-work-group-size"="63,63" }
 attributes #1 = { nounwind "amdgpu-waves-per-eu"="1,3" "amdgpu-flat-work-group-size"="256,256" }
 attributes #2 = { nounwind "amdgpu-waves-per-eu"="1,1" "amdgpu-flat-work-group-size"="1600,1600" }
 attributes #3 = { nounwind "amdgpu-waves-per-eu"="1,10" }
 attributes #4 = { nounwind "amdgpu-waves-per-eu"="1,10" }
 attributes #5 = { nounwind "amdgpu-waves-per-eu"="1,6" "amdgpu-flat-work-group-size"="64,64" }
 attributes #6 = { nounwind "amdgpu-waves-per-eu"="1,8" "amdgpu-flat-work-group-size"="64,64" }
 attributes #7 = { nounwind "amdgpu-waves-per-eu"="1,9" "amdgpu-flat-work-group-size"="64,64" }

test/CodeGen/AMDGPU/promote-alloca-calling-conv.ll

entry:
   %tmp3 = getelementptr [2 x i32], [2 x i32] addrspace(5)* %tmp, i32 0, i32 %in
   %val = call i32 @foo(i32 addrspace(5)* %tmp3)
   store i32 %val, i32 addrspace(1)* %out
   ret void
 }
 
 declare i32 @llvm.amdgcn.workitem.id.x() #1
 
-attributes #0 = { nounwind "amdgpu-max-work-group-size"="64" }
+attributes #0 = { nounwind "amdgpu-flat-work-group-size"="64,64" }
 attributes #1 = { nounwind readnone }