AMDGPU: Add runtime metadata for pointee alignment of argument

[yaxunl]

Summary

Add runtime metdata for pointee alignment of pointer type kernel argument. The key is KeyArgPointeeAlign and the value is a 32 bit unsigned integer.

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

void AMDGPUAsmPrinter::emitRuntimeMetadata(const Function &F) {
   OutStreamer->EmitIntValue(RuntimeMD::KeyKernelBegin, 1);
   emitRuntimeMDStringValue(*OutStreamer, RuntimeMD::KeyKernelName, F.getName());
 
   for (auto &Arg : F.args()) {
     // Emit KeyArgBegin.
     unsigned I = Arg.getArgNo();
     OutStreamer->EmitIntValue(RuntimeMD::KeyArgBegin, 1);
 
-    // Emit KeyArgSize and KeyArgAlign.
+    // Emit KeyArgSize, KeyArgAlign and KeyArgPointeeAlign.
     Type *T = Arg.getType();
     const DataLayout &DL = F.getParent()->getDataLayout();
     emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgSize,
                           DL.getTypeAllocSize(T), 4);
     emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgAlign,
                           DL.getABITypeAlignment(T), 4);
+    if (auto PT = dyn_cast<PointerType>(T)) {
+      auto ET = PT->getElementType();
+      if (ET->isSized())
+        emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgPointeeAlign,
+                          DL.getABITypeAlignment(ET), 4);
+    }
 
     // Emit KeyArgTypeName.
     auto TypeName = dyn_cast<MDString>(F.getMetadata(
       "kernel_arg_type")->getOperand(I))->getString();
     emitRuntimeMDStringValue(*OutStreamer, RuntimeMD::KeyArgTypeName, TypeName);
 
     // Emit KeyArgName.
     if (auto ArgNameMD = F.getMetadata("kernel_arg_name")) {

llvm/trunk/lib/Target/AMDGPU/AMDGPURuntimeMetadata.h

enum Key {
     KeyKernelIndex              = 24, // Kernel index for device enqueue
     KeySGPRs                    = 25, // Number of SGPRs
     KeyVGPRs                    = 26, // Number of VGPRs
     KeyMinWavesPerSIMD          = 27, // Minimum number of waves per SIMD
     KeyMaxWavesPerSIMD          = 28, // Maximum number of waves per SIMD
     KeyFlatWorkGroupSizeLimits  = 29, // Flat work group size limits
     KeyMaxWorkGroupSize         = 30, // Maximum work group size
     KeyNoPartialWorkGroups      = 31, // No partial work groups
+    KeyArgPointeeAlign          = 32, // Alignment of pointee type
   };
 
   enum Language : uint8_t {
     OpenCL_C      = 0,
     HCC           = 1,
     OpenMP        = 2,
     OpenCL_CPP    = 3,
 };

llvm/trunk/test/CodeGen/AMDGPU/runtime-metadata.ll

 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 12
 ; CHECK-NEXT: .ascii  "test_pointer"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16

 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 11
 ; CHECK-NEXT: .ascii  "test_struct"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .ascii  "struct A"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16

 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 15
 ; CHECK-NEXT: .ascii  "test_addr_space"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16

 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 14
 ; CHECK-NEXT: .ascii  "test_type_qual"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 19
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 17
 ; CHECK-NEXT: .byte 18
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14

 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 19
 ; CHECK-NEXT: .ascii  "test_arg_ptr_to_ptr"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 6
 ; CHECK-NEXT: .ascii  "int **"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16

 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 28
 ; CHECK-NEXT: .ascii  "test_arg_struct_contains_ptr"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .ascii  "struct B"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16

 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_arg_unknown_builtin_type(%opencl.clk_event_t addrspace(1)* %a) !kernel_arg_addr_space !81 !kernel_arg_access_qual !2 !kernel_arg_type !84 !kernel_arg_base_type !84 !kernel_arg_type_qual !4 {
   ret void
 }
 
+; CHECK-LABEL:{{^}}test_pointee_align:
+; CHECK: .section        .AMDGPU.runtime_metadata
+; CHECK-NEXT: .byte 4
+; CHECK-NEXT: .byte 6
+; CHECK-NEXT: .long 18
+; CHECK-NEXT: .ascii  "test_pointee_align"
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .long 6
+; CHECK-NEXT: .ascii  "long *"
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 16
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 1
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .long 6
+; CHECK-NEXT: .ascii  "char *"
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 16
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 3
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 2
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .long 7
+; CHECK-NEXT: .ascii  "char2 *"
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 16
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 3
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .long 7
+; CHECK-NEXT: .ascii  "char3 *"
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 16
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 3
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .long 7
+; CHECK-NEXT: .ascii  "char4 *"
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 16
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 3
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .long 7
+; CHECK-NEXT: .ascii  "char8 *"
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 16
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 3
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 4
+; CHECK-NEXT: .byte 32
+; CHECK-NEXT: .long 16
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .ascii  "char16 *"
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 16
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 3
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 5
+
+define amdgpu_kernel void @test_pointee_align(i64 addrspace(1)* %a, i8 addrspace(3)* %b, <2 x i8> addrspace(3)* %c, <3 x i8> addrspace(3)* %d, <4 x i8> addrspace(3)* %e, <8 x i8> addrspace(3)* %f, <16 x i8> addrspace(3)* %g) !kernel_arg_addr_space !91 !kernel_arg_access_qual !92 !kernel_arg_type !93 !kernel_arg_base_type !93 !kernel_arg_type_qual !94 {
+  ret void
+}
+
 !1 = !{i32 0}
 !2 = !{!"none"}
 !3 = !{!"int"}
 !4 = !{!""}
 !5 = !{i32 undef, i32 1}
 !6 = !{i32 1, i32 2, i32 4}
 !7 = !{<4 x i32> undef, i32 0}
 !8 = !{i32 8, i32 16, i32 32}

 !70 = !{!"volatile", !"const restrict", !"pipe"}
 !80 = !{!"int **"}
 !81 = !{i32 1}
 !82 = !{!"struct B"}
 !83 = !{!"global int* __attribute__((ext_vector_type(2)))"}
 !84 = !{!"clk_event_t"}
 !opencl.ocl.version = !{!90}
 !90 = !{i32 2, i32 0}
+!91 = !{i32 0, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3}
+!92 = !{!"none", !"none", !"none", !"none", !"none", !"none", !"none"}
+!93 = !{!"long *", !"char *", !"char2 *", !"char3 *", !"char4 *", !"char8 *", !"char16 *"}
+!94 = !{!"", !"", !"", !"", !"", !"", !""}