[llvm] r365217 - [AMDGPU] Added a new metadata for multi grid sync implicit argument
Yaxun Liu via llvm-commits
llvm-commits at lists.llvm.org
Fri Jul 5 09:05:17 PDT 2019
Author: yaxunl
Date: Fri Jul 5 09:05:17 2019
New Revision: 365217
URL: http://llvm.org/viewvc/llvm-project?rev=365217&view=rev
Log:
[AMDGPU] Added a new metadata for multi grid sync implicit argument
Patch by Christudasan Devadasan.
Differential Revision: https://reviews.llvm.org/D63886
Modified:
llvm/trunk/docs/AMDGPUUsage.rst
llvm/trunk/include/llvm/Support/AMDGPUMetadata.h
llvm/trunk/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
llvm/trunk/lib/Support/AMDGPUMetadata.cpp
llvm/trunk/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll
llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll
llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args-v3.ll
llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll
Modified: llvm/trunk/docs/AMDGPUUsage.rst
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/AMDGPUUsage.rst?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/docs/AMDGPUUsage.rst (original)
+++ llvm/trunk/docs/AMDGPUUsage.rst Fri Jul 5 09:05:17 2019
@@ -1391,6 +1391,11 @@ non-AMD key names should be prefixed by
the ancestor tree for determining
when the parent kernel has finished.
+ "HiddenMultiGridSyncArg"
+ A global address space pointer for
+ multi-grid synchronization is
+ passed in the kernarg.
+
"ValueType" string Required Kernel argument value type. Only
present if "ValueKind" is
"ByValue". For vector data
@@ -1880,6 +1885,11 @@ same *vendor-name*.
the ancestor tree for determining
when the parent kernel has finished.
+ "hidden_multigrid_sync_arg"
+ A global address space pointer for
+ multi-grid synchronization is
+ passed in the kernarg.
+
".value_type" string Required Kernel argument value type. Only
present if ".value_kind" is
"by_value". For vector data
@@ -5696,6 +5706,8 @@ When the language is OpenCL the followin
enqueue_kernel.
6 8 8 OpenCL address of AqlWrap struct used by
enqueue_kernel.
+ 7 8 8 Pointer argument used for Multi-gird
+ synchronization.
======== ==== ========= ===========================================
.. _amdgpu-hcc:
Modified: llvm/trunk/include/llvm/Support/AMDGPUMetadata.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Support/AMDGPUMetadata.h?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Support/AMDGPUMetadata.h (original)
+++ llvm/trunk/include/llvm/Support/AMDGPUMetadata.h Fri Jul 5 09:05:17 2019
@@ -74,6 +74,7 @@ enum class ValueKind : uint8_t {
HiddenPrintfBuffer = 11,
HiddenDefaultQueue = 12,
HiddenCompletionAction = 13,
+ HiddenMultiGridSyncArg = 14,
Unknown = 0xff
};
Modified: llvm/trunk/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp (original)
+++ llvm/trunk/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp Fri Jul 5 09:05:17 2019
@@ -121,6 +121,7 @@ bool MetadataVerifier::verifyKernelArgs(
.Case("hidden_printf_buffer", true)
.Case("hidden_default_queue", true)
.Case("hidden_completion_action", true)
+ .Case("hidden_multigrid_sync_arg", true)
.Default(false);
}))
return false;
Modified: llvm/trunk/lib/Support/AMDGPUMetadata.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/AMDGPUMetadata.cpp?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/lib/Support/AMDGPUMetadata.cpp (original)
+++ llvm/trunk/lib/Support/AMDGPUMetadata.cpp Fri Jul 5 09:05:17 2019
@@ -65,6 +65,8 @@ struct ScalarEnumerationTraits<ValueKind
YIO.enumCase(EN, "HiddenDefaultQueue", ValueKind::HiddenDefaultQueue);
YIO.enumCase(EN, "HiddenCompletionAction",
ValueKind::HiddenCompletionAction);
+ YIO.enumCase(EN, "HiddenMultiGridSyncArg",
+ ValueKind::HiddenMultiGridSyncArg);
}
};
Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp Fri Jul 5 09:05:17 2019
@@ -435,6 +435,10 @@ void MetadataStreamerV2::emitHiddenKerne
emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenNone);
}
}
+
+ // Emit the pointer argument for multi-grid object.
+ if (HiddenArgNumBytes >= 56)
+ emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenMultiGridSyncArg);
}
bool MetadataStreamerV2::emitTo(AMDGPUTargetStreamer &TargetStreamer) {
@@ -864,6 +868,10 @@ void MetadataStreamerV3::emitHiddenKerne
emitKernelArg(DL, Int8PtrTy, "hidden_none", Offset, Args);
}
}
+
+ // Emit the pointer argument for multi-grid object.
+ if (HiddenArgNumBytes >= 56)
+ emitKernelArg(DL, Int8PtrTy, "hidden_multigrid_sync_arg", Offset, Args);
}
msgpack::MapDocNode
Modified: llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full-v3.ll Fri Jul 5 09:05:17 2019
@@ -44,6 +44,8 @@
; CHECK-NOT: .value_kind: hidden_completion_action
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -85,6 +87,16 @@ define amdgpu_kernel void @test_char(i8
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_none
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -121,6 +133,21 @@ define amdgpu_kernel void @test_ushort2(
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -157,6 +184,21 @@ define amdgpu_kernel void @test_int3(<3
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 72
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 80
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -193,6 +235,21 @@ define amdgpu_kernel void @test_ulong4(<
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -229,6 +286,21 @@ define amdgpu_kernel void @test_half8(<8
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 96
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 104
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 112
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -265,6 +337,21 @@ define amdgpu_kernel void @test_float16(
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 160
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 168
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 176
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -302,6 +389,21 @@ define amdgpu_kernel void @test_double16
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -339,6 +441,21 @@ define amdgpu_kernel void @test_pointer(
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -375,6 +492,21 @@ define amdgpu_kernel void @test_image(%o
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -412,6 +544,21 @@ define amdgpu_kernel void @test_sampler(
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -449,6 +596,21 @@ define amdgpu_kernel void @test_queue(%o
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -485,6 +647,21 @@ define amdgpu_kernel void @test_struct(%
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -533,6 +710,21 @@ define amdgpu_kernel void @test_i128(i12
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -585,6 +777,21 @@ define amdgpu_kernel void @test_multi_ar
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 72
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -642,6 +849,21 @@ define amdgpu_kernel void @test_addr_spa
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 72
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -698,6 +920,21 @@ define amdgpu_kernel void @test_type_qua
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 72
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -736,6 +973,21 @@ define amdgpu_kernel void @test_access_q
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -773,6 +1025,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -810,6 +1077,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -847,6 +1129,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -884,6 +1181,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -921,6 +1233,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -958,6 +1285,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -995,6 +1337,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1037,6 +1394,21 @@ define amdgpu_kernel void @test_reqd_wgs
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1080,6 +1452,21 @@ define amdgpu_kernel void @test_wgs_hint
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1117,6 +1504,21 @@ define amdgpu_kernel void @test_arg_ptr_
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1153,6 +1555,21 @@ define amdgpu_kernel void @test_arg_stru
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1190,6 +1607,21 @@ define amdgpu_kernel void @test_arg_vect
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1283,6 +1715,21 @@ define amdgpu_kernel void @test_arg_unkn
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 72
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 80
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 88
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1382,6 +1829,21 @@ define amdgpu_kernel void @test_pointee_
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 72
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 80
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 88
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1424,6 +1886,21 @@ define amdgpu_kernel void @test_pointee_
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_printf_buffer
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 72
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 80
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .device_enqueue_symbol: __test_block_invoke_kernel_runtime_handle
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
@@ -1472,6 +1949,11 @@ define amdgpu_kernel void @__test_block_
; CHECK-NEXT: .size: 8
; CHECK-NEXT: .value_kind: hidden_completion_action
; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
; CHECK: .language: OpenCL C
; CHECK-NEXT: .language_version:
; CHECK-NEXT: - 2
@@ -1503,9 +1985,9 @@ define amdgpu_kernel void @unknown_addrs
; CHECK-NEXT: - 1
; CHECK-NEXT: - 0
-attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" }
-attributes #1 = { "amdgpu-implicitarg-num-bytes"="48" "runtime-handle"="__test_block_invoke_kernel_runtime_handle" }
-attributes #2 = { "amdgpu-implicitarg-num-bytes"="48" "calls-enqueue-kernel" }
+attributes #0 = { "amdgpu-implicitarg-num-bytes"="56" }
+attributes #1 = { "amdgpu-implicitarg-num-bytes"="56" "runtime-handle"="__test_block_invoke_kernel_runtime_handle" }
+attributes #2 = { "amdgpu-implicitarg-num-bytes"="56" "calls-enqueue-kernel" }
!llvm.printf.fmts = !{!100, !101}
Modified: llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll Fri Jul 5 09:05:17 2019
@@ -54,6 +54,9 @@
; CHECK-NEXT: AddrSpaceQual: Global
; CHECK-NOT: ValueKind: HiddenDefaultQueue
; CHECK-NOT: ValueKind: HiddenCompletionAction
+; CHECK: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_char(i8 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !9
!kernel_arg_base_type !9 !kernel_arg_type_qual !4 {
@@ -89,6 +92,21 @@ define amdgpu_kernel void @test_char(i8
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_ushort2(<2 x i16> %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !10
!kernel_arg_base_type !10 !kernel_arg_type_qual !4 {
@@ -124,6 +142,21 @@ define amdgpu_kernel void @test_ushort2(
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_int3(<3 x i32> %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !11
!kernel_arg_base_type !11 !kernel_arg_type_qual !4 {
@@ -159,6 +192,21 @@ define amdgpu_kernel void @test_int3(<3
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_ulong4(<4 x i64> %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !12
!kernel_arg_base_type !12 !kernel_arg_type_qual !4 {
@@ -194,6 +242,21 @@ define amdgpu_kernel void @test_ulong4(<
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_half8(<8 x half> %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !13
!kernel_arg_base_type !13 !kernel_arg_type_qual !4 {
@@ -229,6 +292,21 @@ define amdgpu_kernel void @test_half8(<8
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_float16(<16 x float> %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !14
!kernel_arg_base_type !14 !kernel_arg_type_qual !4 {
@@ -264,6 +342,21 @@ define amdgpu_kernel void @test_float16(
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_double16(<16 x double> %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !15
!kernel_arg_base_type !15 !kernel_arg_type_qual !4 {
@@ -300,6 +393,21 @@ define amdgpu_kernel void @test_double16
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_pointer(i32 addrspace(1)* %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !16
!kernel_arg_base_type !16 !kernel_arg_type_qual !4 {
@@ -336,6 +444,21 @@ define amdgpu_kernel void @test_pointer(
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_image(%opencl.image2d_t addrspace(1)* %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !17
!kernel_arg_base_type !17 !kernel_arg_type_qual !4 {
@@ -371,6 +494,21 @@ define amdgpu_kernel void @test_image(%o
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_sampler(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !18
!kernel_arg_base_type !18 !kernel_arg_type_qual !4 {
@@ -407,6 +545,21 @@ define amdgpu_kernel void @test_sampler(
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_queue(%opencl.queue_t addrspace(1)* %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !19
!kernel_arg_base_type !19 !kernel_arg_type_qual !4 {
@@ -443,6 +596,21 @@ define amdgpu_kernel void @test_queue(%o
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_struct(%struct.A addrspace(5)* byval %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !20
!kernel_arg_base_type !20 !kernel_arg_type_qual !4 {
@@ -478,6 +646,21 @@ define amdgpu_kernel void @test_struct(%
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_i128(i128 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !21
!kernel_arg_base_type !21 !kernel_arg_type_qual !4 {
@@ -527,6 +710,21 @@ define amdgpu_kernel void @test_i128(i12
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_multi_arg(i32 %a, <2 x i16> %b, <3 x i8> %c) #0
!kernel_arg_addr_space !22 !kernel_arg_access_qual !23 !kernel_arg_type !24
!kernel_arg_base_type !24 !kernel_arg_type_qual !25 {
@@ -580,6 +778,21 @@ define amdgpu_kernel void @test_multi_ar
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_addr_space(i32 addrspace(1)* %g,
i32 addrspace(4)* %c,
i32 addrspace(3)* %l) #0
@@ -638,6 +851,21 @@ define amdgpu_kernel void @test_addr_spa
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_type_qual(i32 addrspace(1)* %a,
i32 addrspace(1)* %b,
%opencl.pipe_t addrspace(1)* %c) #0
@@ -692,6 +920,21 @@ define amdgpu_kernel void @test_type_qua
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_access_qual(%opencl.image1d_t addrspace(1)* %ro,
%opencl.image2d_t addrspace(1)* %wo,
%opencl.image3d_t addrspace(1)* %rw) #0
@@ -731,6 +974,21 @@ define amdgpu_kernel void @test_access_q
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_vec_type_hint_half(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !26 {
@@ -768,6 +1026,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_vec_type_hint_float(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !27 {
@@ -805,6 +1078,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_vec_type_hint_double(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !28 {
@@ -842,6 +1130,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_vec_type_hint_char(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !29 {
@@ -879,6 +1182,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_vec_type_hint_short(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !30 {
@@ -916,6 +1234,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_vec_type_hint_long(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !31 {
@@ -953,6 +1286,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_vec_type_hint_unknown(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !32 {
@@ -991,6 +1339,21 @@ define amdgpu_kernel void @test_vec_type
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_reqd_wgs_vec_type_hint(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !5
@@ -1030,6 +1393,21 @@ define amdgpu_kernel void @test_reqd_wgs
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_wgs_hint_vec_type_hint(i32 %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
!kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !7
@@ -1067,6 +1445,21 @@ define amdgpu_kernel void @test_wgs_hint
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_arg_ptr_to_ptr(i32 addrspace(5)* addrspace(1)* %a) #0
!kernel_arg_addr_space !81 !kernel_arg_access_qual !2 !kernel_arg_type !80
!kernel_arg_base_type !80 !kernel_arg_type_qual !4 {
@@ -1138,6 +1531,21 @@ define amdgpu_kernel void @test_arg_stru
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_arg_vector_of_ptr(<2 x i32 addrspace(1)*> %a) #0
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !83
!kernel_arg_base_type !83 !kernel_arg_type_qual !4 {
@@ -1174,6 +1582,21 @@ define amdgpu_kernel void @test_arg_vect
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_arg_unknown_builtin_type(
%opencl.clk_event_t addrspace(1)* %a) #0
!kernel_arg_addr_space !81 !kernel_arg_access_qual !2 !kernel_arg_type !84
@@ -1272,6 +1695,21 @@ define amdgpu_kernel void @test_arg_unkn
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_pointee_align(i64 addrspace(1)* %a,
i8 addrspace(3)* %b,
<2 x i8> addrspace(3)* %c,
@@ -1376,6 +1814,21 @@ define amdgpu_kernel void @test_pointee_
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_pointee_align_attribute(i64 addrspace(1)* align 16 %a,
i8 addrspace(3)* align 8 %b,
<2 x i8> addrspace(3)* align 32 %c,
@@ -1421,6 +1874,21 @@ define amdgpu_kernel void @test_pointee_
; CHECK-NEXT: ValueKind: HiddenPrintfBuffer
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @__test_block_invoke_kernel(
<{ i32, i32, i8*, i8 addrspace(1)*, i8 }> %arg) #1
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !110
@@ -1467,6 +1935,11 @@ define amdgpu_kernel void @__test_block_
; CHECK-NEXT: ValueKind: HiddenCompletionAction
; CHECK-NEXT: ValueType: I8
; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
define amdgpu_kernel void @test_enqueue_kernel_caller(i8 %a) #2
!kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !9
!kernel_arg_base_type !9 !kernel_arg_type_qual !4 {
@@ -1484,9 +1957,9 @@ define amdgpu_kernel void @unknown_addrs
ret void
}
-attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" }
-attributes #1 = { "amdgpu-implicitarg-num-bytes"="48" "runtime-handle"="__test_block_invoke_kernel_runtime_handle" }
-attributes #2 = { "amdgpu-implicitarg-num-bytes"="48" "calls-enqueue-kernel" }
+attributes #0 = { "amdgpu-implicitarg-num-bytes"="56" }
+attributes #1 = { "amdgpu-implicitarg-num-bytes"="56" "runtime-handle"="__test_block_invoke_kernel_runtime_handle" }
+attributes #2 = { "amdgpu-implicitarg-num-bytes"="56" "calls-enqueue-kernel" }
!llvm.printf.fmts = !{!100, !101}
Modified: llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args-v3.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args-v3.ll?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args-v3.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args-v3.ll Fri Jul 5 09:05:17 2019
@@ -271,6 +271,71 @@ entry:
ret void
}
+; CHECK: - .args:
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .name: r
+; CHECK-NEXT: .offset: 0
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: global_buffer
+; CHECK-NEXT: .value_type: f16
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .name: a
+; CHECK-NEXT: .offset: 8
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: global_buffer
+; CHECK-NEXT: .value_type: f16
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .name: b
+; CHECK-NEXT: .offset: 16
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: global_buffer
+; CHECK-NEXT: .value_type: f16
+; CHECK-NEXT: - .offset: 24
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_global_offset_x
+; CHECK-NEXT: .value_type: i64
+; CHECK-NEXT: - .offset: 32
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_global_offset_y
+; CHECK-NEXT: .value_type: i64
+; CHECK-NEXT: - .offset: 40
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_global_offset_z
+; CHECK-NEXT: .value_type: i64
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 48
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 56
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 64
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_none
+; CHECK-NEXT: .value_type: i8
+; CHECK-NEXT: - .address_space: global
+; CHECK-NEXT: .offset: 72
+; CHECK-NEXT: .size: 8
+; CHECK-NEXT: .value_kind: hidden_multigrid_sync_arg
+; CHECK-NEXT: .value_type: i8
+; CHECK: .name: test56
+; CHECK: .symbol: test56.kd
+define amdgpu_kernel void @test56(
+ half addrspace(1)* %r,
+ half addrspace(1)* %a,
+ half addrspace(1)* %b) #5 {
+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: amdhsa.version:
; CHECK-NEXT: - 1
; CHECK-NEXT: - 0
@@ -280,3 +345,4 @@ attributes #1 = { "amdgpu-implicitarg-nu
attributes #2 = { "amdgpu-implicitarg-num-bytes"="24" }
attributes #3 = { "amdgpu-implicitarg-num-bytes"="32" }
attributes #4 = { "amdgpu-implicitarg-num-bytes"="48" }
+attributes #5 = { "amdgpu-implicitarg-num-bytes"="56" }
Modified: llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll?rev=365217&r1=365216&r2=365217&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll Fri Jul 5 09:05:17 2019
@@ -278,8 +278,75 @@ entry:
ret void
}
+; CHECK: - Name: test56
+; CHECK: SymbolName: 'test56 at kd'
+; CHECK: Args:
+; CHECK-NEXT: - Name: r
+; CHECK-NEXT: Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: GlobalBuffer
+; CHECK-NEXT: ValueType: F16
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Name: a
+; CHECK-NEXT: Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: GlobalBuffer
+; CHECK-NEXT: ValueType: F16
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Name: b
+; CHECK-NEXT: Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: GlobalBuffer
+; CHECK-NEXT: ValueType: F16
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenGlobalOffsetX
+; CHECK-NEXT: ValueType: I64
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenGlobalOffsetY
+; CHECK-NEXT: ValueType: I64
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenGlobalOffsetZ
+; CHECK-NEXT: ValueType: I64
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenNone
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: - Size: 8
+; CHECK-NEXT: Align: 8
+; CHECK-NEXT: ValueKind: HiddenMultiGridSyncArg
+; CHECK-NEXT: ValueType: I8
+; CHECK-NEXT: AddrSpaceQual: Global
+; CHECK-NEXT: CodeProps:
+define amdgpu_kernel void @test56(
+ half addrspace(1)* %r,
+ half addrspace(1)* %a,
+ half addrspace(1)* %b) #5 {
+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
+}
+
attributes #0 = { "amdgpu-implicitarg-num-bytes"="8" }
attributes #1 = { "amdgpu-implicitarg-num-bytes"="16" }
attributes #2 = { "amdgpu-implicitarg-num-bytes"="24" }
attributes #3 = { "amdgpu-implicitarg-num-bytes"="32" }
attributes #4 = { "amdgpu-implicitarg-num-bytes"="48" }
+attributes #5 = { "amdgpu-implicitarg-num-bytes"="56" }
More information about the llvm-commits
mailing list