AMDGPU: Add num spilled s/vgprs to metadata

[kzhuravl]

Summary

This was requested by tools.

[t-tye]

docs/AMDGPUUsage.rst

1298–1300

Suggest clarifying to:

Number of stores from a scalar register to a register allocator created spill location.

1301–1303

Suggest clarifying to:

Number of stores from a vector register to a register allocator created spill location.

[kzhuravl]

Address review feedback.

[t-tye]

LGTM provided it meets the needs of the tools? Have they reviewed?

[kzhuravl]

In D40321#937218, @t-tye wrote:

LGTM provided it meets the needs of the tools? Have they reviewed?

Yes.

docs/AMDGPUUsage.rst

"FixedWorkGroupSize"         sequence of              Corresponds to the
                                                            be launched with a
                                                            matching corresponding
                                                            work-group size.
      "IsXNACKEnabled"             boolean                  Indicates if the
                                                            generated machine
                                                            code is capable of
                                                            supporting XNACK. See
                                                            :ref:`amdgpu-target-features`.
+     "NumSpilledSGPRs"            integer                  Number of scalar
+                                                           registers spilled by
+                                                           a wavefront.
+     "NumSpilledVGPRs"            integer                  Number of vector
+                                                           registers spilled by
+                                                           a work-item.
      ============================ ============== ========= =====================
 
 ..
 
 Kernel Dispatch
 ~~~~~~~~~~~~~~~
 
 The HSA architected queuing language (AQL) defines a user space memory interface

include/llvm/Support/AMDGPUMetadata.h

 /// \brief Key for Kernel::CodeProps::Metadata::mNumVGPRs.
 constexpr char NumVGPRs[] = "NumVGPRs";
 /// \brief Key for Kernel::CodeProps::Metadata::mMaxFlatWorkGroupSize.
 constexpr char MaxFlatWorkGroupSize[] = "MaxFlatWorkGroupSize";
 /// \brief Key for Kernel::CodeProps::Metadata::mIsDynamicCallStack.
 constexpr char IsDynamicCallStack[] = "IsDynamicCallStack";
 /// \brief Key for Kernel::CodeProps::Metadata::mIsXNACKEnabled.
 constexpr char IsXNACKEnabled[] = "IsXNACKEnabled";
+/// \brief Key for Kernel::CodeProps::Metadata::mNumSpilledSGPRs.
+constexpr char NumSpilledSGPRs[] = "NumSpilledSGPRs";
+/// \brief Key for Kernel::CodeProps::Metadata::mNumSpilledVGPRs.
+constexpr char NumSpilledVGPRs[] = "NumSpilledVGPRs";
 } // end namespace Key
 
 /// \brief In-memory representation of kernel code properties metadata.
 struct Metadata final {
   /// \brief Size in bytes of the kernarg segment memory. Kernarg segment memory
   /// holds the values of the arguments to the kernel. Required.
   uint64_t mKernargSegmentSize = 0;
   /// \brief Size in bytes of the group segment memory required by a workgroup.
struct Metadata final {
   /// \brief Maximum flat work-group size supported by the kernel. Optional.
   uint32_t mMaxFlatWorkGroupSize = 0;
   /// \brief True if the generated machine code is using a dynamically sized
   /// call stack. Optional.
   bool mIsDynamicCallStack = false;
   /// \brief True if the generated machine code is capable of supporting XNACK.
   /// Optional.
   bool mIsXNACKEnabled = false;
+  /// \brief Number of SGPRs spilled by a wavefront. Optional.
+  uint16_t mNumSpilledSGPRs = 0;
+  /// \brief Number of VGPRs spilled by a workitem. Optional.
+  uint16_t mNumSpilledVGPRs = 0;
 
   /// \brief Default constructor.
   Metadata() = default;
 
   /// \returns True if kernel code properties metadata is empty, false
   /// otherwise.
   bool empty() const {
     return !notEmpty();

lib/Support/AMDGPUMetadata.cpp

static void mapping(IO &YIO, Kernel::CodeProps::Metadata &MD) {
     YIO.mapOptional(Kernel::CodeProps::Key::NumVGPRs,
                     MD.mNumVGPRs, uint16_t(0));
     YIO.mapOptional(Kernel::CodeProps::Key::MaxFlatWorkGroupSize,
                     MD.mMaxFlatWorkGroupSize, uint32_t(0));
     YIO.mapOptional(Kernel::CodeProps::Key::IsDynamicCallStack,
                     MD.mIsDynamicCallStack, false);
     YIO.mapOptional(Kernel::CodeProps::Key::IsXNACKEnabled,
                     MD.mIsXNACKEnabled, false);
+    YIO.mapOptional(Kernel::CodeProps::Key::NumSpilledSGPRs,
+                    MD.mNumSpilledSGPRs, uint16_t(0));
+    YIO.mapOptional(Kernel::CodeProps::Key::NumSpilledVGPRs,
+                    MD.mNumSpilledVGPRs, uint16_t(0));
   }
 };
 
 template <>
 struct MappingTraits<Kernel::DebugProps::Metadata> {
   static void mapping(IO &YIO, Kernel::DebugProps::Metadata &MD) {
     YIO.mapOptional(Kernel::DebugProps::Key::DebuggerABIVersion,
                     MD.mDebuggerABIVersion, std::vector<uint32_t>());

lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

AMDGPU::HSAMD::Kernel::CodeProps::Metadata AMDGPUAsmPrinter::getHSACodeProps(
   HSACodeProps.mKernargSegmentAlign =
       std::max(uint32_t(4), MFI.getMaxKernArgAlign());
   HSACodeProps.mWavefrontSize = STM.getWavefrontSize();
   HSACodeProps.mNumSGPRs = CurrentProgramInfo.NumSGPR;
   HSACodeProps.mNumVGPRs = CurrentProgramInfo.NumVGPR;
   HSACodeProps.mMaxFlatWorkGroupSize = MFI.getMaxFlatWorkGroupSize();
   HSACodeProps.mIsDynamicCallStack = ProgramInfo.DynamicCallStack;
   HSACodeProps.mIsXNACKEnabled = STM.isXNACKEnabled();
+  HSACodeProps.mNumSpilledSGPRs = MFI.getNumSpilledSGPRs();
+  HSACodeProps.mNumSpilledVGPRs = MFI.getNumSpilledVGPRs();
 
   return HSACodeProps;
 }
 
 AMDGPU::HSAMD::Kernel::DebugProps::Metadata AMDGPUAsmPrinter::getHSADebugProps(
     const MachineFunction &MF,
     const SIProgramInfo &ProgramInfo) const {
   const SISubtarget &STM = MF.getSubtarget<SISubtarget>();

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=gfx803 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX803 --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
 
+@var = addrspace(1) global float 0.0
+
 ; CHECK: ---
 ; CHECK:  Version: [ 1, 0 ]
-
 ; CHECK:  Kernels:
-; CHECK:    - Name:       test
-; CHECK:      SymbolName: 'test@kd'
-; CHECK:      CodeProps:
-; 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:        MaxFlatWorkGroupSize:    256
+
+; CHECK: - Name:       test
+; CHECK:   SymbolName: 'test@kd'
+; CHECK:   CodeProps:
+; CHECK:     KernargSegmentSize:      24
+; CHECK:     GroupSegmentFixedSize:   0
+; CHECK:     PrivateSegmentFixedSize: 0
+; CHECK:     KernargSegmentAlign:     8
+; CHECK:     WavefrontSize:           64
+; CHECK:     NumSGPRs:                6
+; GFX700:    NumVGPRs:                4
+; GFX803:    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
 }
+
+; CHECK: - Name:       num_spilled_sgprs
+; CHECK:   SymbolName: 'num_spilled_sgprs@kd'
+; CHECK:   CodeProps:
+; CHECK:     NumSpilledSGPRs: 41
+define amdgpu_kernel void @num_spilled_sgprs(
+    i32 addrspace(1)* %out0, i32 addrspace(1)* %out1, i32 addrspace(1)* %out2,
+    i32 addrspace(1)* %out3, i32 addrspace(1)* %out4, i32 addrspace(1)* %out5,
+    i32 addrspace(1)* %out6, i32 addrspace(1)* %out7, i32 addrspace(1)* %out8,
+    i32 addrspace(1)* %out9, i32 addrspace(1)* %outa, i32 addrspace(1)* %outb,
+    i32 addrspace(1)* %outc, i32 addrspace(1)* %outd, i32 addrspace(1)* %oute,
+    i32 addrspace(1)* %outf, i32 %in0, i32 %in1, i32 %in2, i32 %in3, i32 %in4,
+    i32 %in5, i32 %in6, i32 %in7, i32 %in8, i32 %in9, i32 %ina, i32 %inb,
+    i32 %inc, i32 %ind, i32 %ine, i32 %inf) #0 {
+entry:
+  store i32 %in0, i32 addrspace(1)* %out0
+  store i32 %in1, i32 addrspace(1)* %out1
+  store i32 %in2, i32 addrspace(1)* %out2
+  store i32 %in3, i32 addrspace(1)* %out3
+  store i32 %in4, i32 addrspace(1)* %out4
+  store i32 %in5, i32 addrspace(1)* %out5
+  store i32 %in6, i32 addrspace(1)* %out6
+  store i32 %in7, i32 addrspace(1)* %out7
+  store i32 %in8, i32 addrspace(1)* %out8
+  store i32 %in9, i32 addrspace(1)* %out9
+  store i32 %ina, i32 addrspace(1)* %outa
+  store i32 %inb, i32 addrspace(1)* %outb
+  store i32 %inc, i32 addrspace(1)* %outc
+  store i32 %ind, i32 addrspace(1)* %outd
+  store i32 %ine, i32 addrspace(1)* %oute
+  store i32 %inf, i32 addrspace(1)* %outf
+  ret void
+}
+
+; CHECK: - Name:       num_spilled_vgprs
+; CHECK:   SymbolName: 'num_spilled_vgprs@kd'
+; CHECK:   CodeProps:
+; CHECK:     NumSpilledVGPRs: 14
+define amdgpu_kernel void @num_spilled_vgprs() #1 {
+  %val0 = load volatile float, float addrspace(1)* @var
+  %val1 = load volatile float, float addrspace(1)* @var
+  %val2 = load volatile float, float addrspace(1)* @var
+  %val3 = load volatile float, float addrspace(1)* @var
+  %val4 = load volatile float, float addrspace(1)* @var
+  %val5 = load volatile float, float addrspace(1)* @var
+  %val6 = load volatile float, float addrspace(1)* @var
+  %val7 = load volatile float, float addrspace(1)* @var
+  %val8 = load volatile float, float addrspace(1)* @var
+  %val9 = load volatile float, float addrspace(1)* @var
+  %val10 = load volatile float, float addrspace(1)* @var
+  %val11 = load volatile float, float addrspace(1)* @var
+  %val12 = load volatile float, float addrspace(1)* @var
+  %val13 = load volatile float, float addrspace(1)* @var
+  %val14 = load volatile float, float addrspace(1)* @var
+  %val15 = load volatile float, float addrspace(1)* @var
+  %val16 = load volatile float, float addrspace(1)* @var
+  %val17 = load volatile float, float addrspace(1)* @var
+  %val18 = load volatile float, float addrspace(1)* @var
+  %val19 = load volatile float, float addrspace(1)* @var
+  %val20 = load volatile float, float addrspace(1)* @var
+  %val21 = load volatile float, float addrspace(1)* @var
+  %val22 = load volatile float, float addrspace(1)* @var
+  %val23 = load volatile float, float addrspace(1)* @var
+  %val24 = load volatile float, float addrspace(1)* @var
+  %val25 = load volatile float, float addrspace(1)* @var
+  %val26 = load volatile float, float addrspace(1)* @var
+  %val27 = load volatile float, float addrspace(1)* @var
+  %val28 = load volatile float, float addrspace(1)* @var
+  %val29 = load volatile float, float addrspace(1)* @var
+  %val30 = load volatile float, float addrspace(1)* @var
+
+  store volatile float %val0, float addrspace(1)* @var
+  store volatile float %val1, float addrspace(1)* @var
+  store volatile float %val2, float addrspace(1)* @var
+  store volatile float %val3, float addrspace(1)* @var
+  store volatile float %val4, float addrspace(1)* @var
+  store volatile float %val5, float addrspace(1)* @var
+  store volatile float %val6, float addrspace(1)* @var
+  store volatile float %val7, float addrspace(1)* @var
+  store volatile float %val8, float addrspace(1)* @var
+  store volatile float %val9, float addrspace(1)* @var
+  store volatile float %val10, float addrspace(1)* @var
+  store volatile float %val11, float addrspace(1)* @var
+  store volatile float %val12, float addrspace(1)* @var
+  store volatile float %val13, float addrspace(1)* @var
+  store volatile float %val14, float addrspace(1)* @var
+  store volatile float %val15, float addrspace(1)* @var
+  store volatile float %val16, float addrspace(1)* @var
+  store volatile float %val17, float addrspace(1)* @var
+  store volatile float %val18, float addrspace(1)* @var
+  store volatile float %val19, float addrspace(1)* @var
+  store volatile float %val20, float addrspace(1)* @var
+  store volatile float %val21, float addrspace(1)* @var
+  store volatile float %val22, float addrspace(1)* @var
+  store volatile float %val23, float addrspace(1)* @var
+  store volatile float %val24, float addrspace(1)* @var
+  store volatile float %val25, float addrspace(1)* @var
+  store volatile float %val26, float addrspace(1)* @var
+  store volatile float %val27, float addrspace(1)* @var
+  store volatile float %val28, float addrspace(1)* @var
+  store volatile float %val29, float addrspace(1)* @var
+  store volatile float %val30, float addrspace(1)* @var
+
+  ret void
+}
+
+attributes #0 = { "amdgpu-num-sgpr"="14" }
+attributes #1 = { "amdgpu-num-vgpr"="20" }

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
+// CHECK:          NumSpilledSGPRs: 1
+// CHECK:          NumSpilledVGPRs: 1
 .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
+        NumSpilledSGPRs:         1
+        NumSpilledVGPRs:         1
 .end_amd_amdgpu_hsa_metadata