AMDGPU: Start generating metadata for MaxFlatWorkGroupSize

[arsenm]

LGTM

llvm/trunk/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

HSACodeProps.mKernargSegmentSize =
       STM.getKernArgSegmentSize(MF, MFI.getABIArgOffset());
   HSACodeProps.mGroupSegmentFixedSize = ProgramInfo.LDSSize;
   HSACodeProps.mPrivateSegmentFixedSize = ProgramInfo.ScratchSize;
   HSACodeProps.mKernargSegmentAlign =
       std::max(uint32_t(4), MFI.getMaxKernArgAlign());
   HSACodeProps.mWavefrontSize = STM.getWavefrontSize();
   HSACodeProps.mNumSGPRs = CurrentProgramInfo.NumSGPR;
   HSACodeProps.mNumVGPRs = CurrentProgramInfo.NumVGPR;
-  // TODO: Emit HSACodeProps.mMaxFlatWorkgroupSize.
+  HSACodeProps.mMaxFlatWorkgroupSize = MFI.getMaxFlatWorkGroupSize();
   HSACodeProps.mIsDynamicCallStack = ProgramInfo.DynamicCallStack;
   HSACodeProps.mIsXNACKEnabled = STM.isXNACKEnabled();
 
   return HSACodeProps;
 }
 
 AMDGPU::HSAMD::Kernel::DebugProps::Metadata AMDGPUAsmPrinter::getHSADebugProps(
     const MachineFunction &MF,

llvm/trunk/test/CodeGen/AMDGPU/attr-amdgpu-flat-work-group-size.ll

-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 < %s | FileCheck --check-prefix=CHECK %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=HSAMD %s
 
 ; CHECK-LABEL: {{^}}min_64_max_64:
 ; CHECK: SGPRBlocks: 0
 ; CHECK: VGPRBlocks: 0
 ; CHECK: NumSGPRsForWavesPerEU: 1
 ; CHECK: NumVGPRsForWavesPerEU: 1
 define amdgpu_kernel void @min_64_max_64() #0 {
 entry:
define amdgpu_kernel void @min_1024_max_2048() #3 {
   store volatile float %val37, float addrspace(1)* @var
   store volatile float %val38, float addrspace(1)* @var
   store volatile float %val39, float addrspace(1)* @var
   store volatile float %val40, float addrspace(1)* @var
 
   ret void
 }
 attributes #3 = {"amdgpu-flat-work-group-size"="1024,2048"}
+
+; HSAMD: NT_AMD_AMDGPU_HSA_METADATA (HSA Metadata)
+; HSAMD: Version: [ 1, 0 ]
+; HSAMD: Kernels:
+; HSAMD: - Name:                 min_64_max_64
+; HSAMD:   MaxFlatWorkgroupSize: 64
+; HSAMD: - Name:                 min_64_max_128
+; HSAMD:   MaxFlatWorkgroupSize: 128
+; HSAMD: - Name:                 min_128_max_128
+; HSAMD:   MaxFlatWorkgroupSize: 128
+; HSAMD: - Name:                 min_1024_max_2048
+; HSAMD:   MaxFlatWorkgroupSize: 2048

llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-kernel-code-props.ll

 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX700 --check-prefix=NOTES %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx800 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX800 --check-prefix=NOTES %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX900 --check-prefix=NOTES %s
 
 ; CHECK: ---
 ; CHECK:  Version: [ 1, 0 ]
 
 ; CHECK:  Kernels:
 ; CHECK:    - Name:       test
 ; CHECK:      SymbolName: 'test@kd'
 ; CHECK:      CodeProps:
-; CHECK:        KernargSegmentSize:  24
-; CHECK:        GroupSegmentFixedSize: 0
+; CHECK:        KernargSegmentSize:      24
+; CHECK:        GroupSegmentFixedSize:   0
 ; CHECK:        PrivateSegmentFixedSize: 0
-; CHECK:        KernargSegmentAlign: 8
-; CHECK:        WavefrontSize: 64
-; GFX700:       NumSGPRs: 6
-; GFX800:       NumSGPRs: 96
-; GFX900:       NumSGPRs: 6
-; GFX700:       NumVGPRs: 4
-; GFX800:       NumVGPRs: 6
-; GFX900:       NumVGPRs: 6
+; CHECK:        KernargSegmentAlign:     8
+; CHECK:        WavefrontSize:           64
+; GFX700:       NumSGPRs:                6
+; GFX800:       NumSGPRs:                96
+; GFX900:       NumSGPRs:                6
+; GFX700:       NumVGPRs:                4
+; GFX800:       NumVGPRs:                6
+; GFX900:       NumVGPRs:                6
+; CHECK:        MaxFlatWorkgroupSize:    256
 define amdgpu_kernel void @test(
     half addrspace(1)* %r,
     half addrspace(1)* %a,
     half addrspace(1)* %b) {
 entry:
   %a.val = load half, half addrspace(1)* %a
   %b.val = load half, half addrspace(1)* %b
   %r.val = fadd half %a.val, %b.val
   store half %r.val, half addrspace(1)* %r
   ret void
 }

llvm/trunk/test/MC/AMDGPU/hsa-metadata-kernel-code-props.s

 // RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX700 %s
 // RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX800 %s
 // RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX900 %s
 
 // CHECK:  .amd_amdgpu_hsa_metadata
 // CHECK:    Version: [ 1, 0 ]
 // CHECK:    Kernels:
 // CHECK:      - Name:       test_kernel
 // CHECK:        SymbolName: 'test_kernel@kd'
 // CHECK:        CodeProps:
 // CHECK:          KernargSegmentSize:      24
 // CHECK:          GroupSegmentFixedSize:   24
 // CHECK:          PrivateSegmentFixedSize: 16
 // CHECK:          KernargSegmentAlign:     16
 // CHECK:          WavefrontSize:           64
+// CHECK:          MaxFlatWorkgroupSize:    256
 .amd_amdgpu_hsa_metadata
   Version: [ 1, 0 ]
   Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
   Kernels:
     - Name:            test_kernel
       SymbolName:      test_kernel@kd
       CodeProps:
         KernargSegmentSize:      24
         GroupSegmentFixedSize:   24
         PrivateSegmentFixedSize: 16
         KernargSegmentAlign:     16
         WavefrontSize:           64
+        MaxFlatWorkgroupSize:    256
 .end_amd_amdgpu_hsa_metadata