JonChesterfield created this revision.
JonChesterfield added reviewers: arsenm, rampitec, sdesmalen, rjmccall, rnk,
aaron.ballman.
Herald added subscribers: kosarev, kerbowa, t-tye, Anastasia, tpr, dstuttard,
yaxunl, jvesely, kzhuravl.
Herald added a project: All.
JonChesterfield requested review of this revision.
Herald added subscribers: cfe-commits, wdng.
Herald added a project: clang.
Allows emitting define amdgpu_kernel void @func() IR from C or C++.
This replaces the current workflow which is to write a stub in opencl that
calls an external C function implemented in C++ combined through llvm-link.
Calling the resulting function still requires a manual implementation of the
ABI from the host side. The primary application is for more rapid debugging
of the amdgpu backend by permuting a C or C++ test file instead of manually
updating an IR file.
Implementation closely follows D54425 <https://reviews.llvm.org/D54425>.
Non-amd reviewers from there.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D125970
Files:
clang/include/clang/Basic/Attr.td
clang/include/clang/Basic/Specifiers.h
clang/lib/AST/ItaniumMangle.cpp
clang/lib/AST/Type.cpp
clang/lib/AST/TypePrinter.cpp
clang/lib/Basic/Targets/AMDGPU.h
clang/lib/CodeGen/CGCall.cpp
clang/lib/CodeGen/CGDebugInfo.cpp
clang/lib/Sema/SemaDeclAttr.cpp
clang/lib/Sema/SemaType.cpp
clang/test/Sema/callingconv.c
clang/tools/libclang/CXType.cpp
Index: clang/tools/libclang/CXType.cpp
===================================================================
--- clang/tools/libclang/CXType.cpp
+++ clang/tools/libclang/CXType.cpp
@@ -676,6 +676,7 @@
TCALLINGCONV(PreserveMost);
TCALLINGCONV(PreserveAll);
case CC_SpirFunction: return CXCallingConv_Unexposed;
+ case CC_AMDGPUKernelCall: return CXCallingConv_Unexposed;
case CC_OpenCLKernel: return CXCallingConv_Unexposed;
break;
}
Index: clang/test/Sema/callingconv.c
===================================================================
--- clang/test/Sema/callingconv.c
+++ clang/test/Sema/callingconv.c
@@ -53,6 +53,8 @@
int __attribute__((aarch64_vector_pcs)) aavpcs(void); // expected-warning {{'aarch64_vector_pcs' calling convention is not supported for this target}}
+int __attribute__((amdgpu_kernel)) aavpcs(void); // expected-warning {{'amdgpu_kernel' calling convention is not supported for this target}}
+
// PR6361
void ctest3();
void __attribute__((cdecl)) ctest3() {}
Index: clang/lib/Sema/SemaType.cpp
===================================================================
--- clang/lib/Sema/SemaType.cpp
+++ clang/lib/Sema/SemaType.cpp
@@ -121,6 +121,7 @@
case ParsedAttr::AT_SwiftAsyncCall: \
case ParsedAttr::AT_VectorCall: \
case ParsedAttr::AT_AArch64VectorPcs: \
+ case ParsedAttr::AT_AMDGPUKernelCall: \
case ParsedAttr::AT_MSABI: \
case ParsedAttr::AT_SysVABI: \
case ParsedAttr::AT_Pcs: \
@@ -7481,6 +7482,8 @@
return createSimpleAttr<VectorCallAttr>(Ctx, Attr);
case ParsedAttr::AT_AArch64VectorPcs:
return createSimpleAttr<AArch64VectorPcsAttr>(Ctx, Attr);
+ case ParsedAttr::AT_AMDGPUKernelCall:
+ return createSimpleAttr<AMDGPUKernelCallAttr>(Ctx, Attr);
case ParsedAttr::AT_Pcs: {
// The attribute may have had a fixit applied where we treated an
// identifier as a string literal. The contents of the string are valid,
Index: clang/lib/Sema/SemaDeclAttr.cpp
===================================================================
--- clang/lib/Sema/SemaDeclAttr.cpp
+++ clang/lib/Sema/SemaDeclAttr.cpp
@@ -5024,6 +5024,9 @@
case ParsedAttr::AT_AArch64VectorPcs:
D->addAttr(::new (S.Context) AArch64VectorPcsAttr(S.Context, AL));
return;
+ case ParsedAttr::AT_AMDGPUKernelCall:
+ D->addAttr(::new (S.Context) AMDGPUKernelCallAttr(S.Context, AL));
+ return;
case ParsedAttr::AT_IntelOclBicc:
D->addAttr(::new (S.Context) IntelOclBiccAttr(S.Context, AL));
return;
@@ -5181,6 +5184,9 @@
case ParsedAttr::AT_AArch64VectorPcs:
CC = CC_AArch64VectorCall;
break;
+ case ParsedAttr::AT_AMDGPUKernelCall:
+ CC = CC_AMDGPUKernelCall;
+ break;
case ParsedAttr::AT_RegCall:
CC = CC_X86RegCall;
break;
@@ -5275,6 +5281,7 @@
break;
case TargetInfo::CCCR_Warning: {
+ fprintf(stderr, "some target specific check nonsense\n");
Diag(Attrs.getLoc(), diag::warn_cconv_unsupported)
<< Attrs << (int)CallingConventionIgnoredReason::ForThisTarget;
@@ -8793,6 +8800,7 @@
case ParsedAttr::AT_PreserveMost:
case ParsedAttr::AT_PreserveAll:
case ParsedAttr::AT_AArch64VectorPcs:
+ case ParsedAttr::AT_AMDGPUKernelCall:
handleCallConvAttr(S, D, AL);
break;
case ParsedAttr::AT_Suppress:
Index: clang/lib/CodeGen/CGDebugInfo.cpp
===================================================================
--- clang/lib/CodeGen/CGDebugInfo.cpp
+++ clang/lib/CodeGen/CGDebugInfo.cpp
@@ -1334,6 +1334,7 @@
case CC_SpirFunction:
return llvm::dwarf::DW_CC_LLVM_SpirFunction;
case CC_OpenCLKernel:
+ case CC_AMDGPUKernelCall:
return llvm::dwarf::DW_CC_LLVM_OpenCLKernel;
case CC_Swift:
return llvm::dwarf::DW_CC_LLVM_Swift;
Index: clang/lib/CodeGen/CGCall.cpp
===================================================================
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -62,6 +62,7 @@
// TODO: Add support for __vectorcall to LLVM.
case CC_X86VectorCall: return llvm::CallingConv::X86_VectorCall;
case CC_AArch64VectorCall: return llvm::CallingConv::AArch64_VectorCall;
+ case CC_AMDGPUKernelCall: return llvm::CallingConv::AMDGPU_KERNEL;
case CC_SpirFunction: return llvm::CallingConv::SPIR_FUNC;
case CC_OpenCLKernel: return CGM.getTargetCodeGenInfo().getOpenCLKernelCallingConv();
case CC_PreserveMost: return llvm::CallingConv::PreserveMost;
@@ -228,6 +229,9 @@
if (D->hasAttr<AArch64VectorPcsAttr>())
return CC_AArch64VectorCall;
+ if (D->hasAttr<AMDGPUKernelCallAttr>())
+ return CC_AMDGPUKernelCall;
+
if (D->hasAttr<IntelOclBiccAttr>())
return CC_IntelOclBicc;
Index: clang/lib/Basic/Targets/AMDGPU.h
===================================================================
--- clang/lib/Basic/Targets/AMDGPU.h
+++ clang/lib/Basic/Targets/AMDGPU.h
@@ -411,6 +411,7 @@
return CCCR_Warning;
case CC_C:
case CC_OpenCLKernel:
+ case CC_AMDGPUKernelCall:
return CCCR_OK;
}
}
Index: clang/lib/AST/TypePrinter.cpp
===================================================================
--- clang/lib/AST/TypePrinter.cpp
+++ clang/lib/AST/TypePrinter.cpp
@@ -960,6 +960,9 @@
case CC_AArch64VectorCall:
OS << "__attribute__((aarch64_vector_pcs))";
break;
+ case CC_AMDGPUKernelCall:
+ OS << "__attribute__((amdgpu_kernel))";
+ break;
case CC_IntelOclBicc:
OS << " __attribute__((intel_ocl_bicc))";
break;
@@ -1749,6 +1752,7 @@
break;
}
case attr::AArch64VectorPcs: OS << "aarch64_vector_pcs"; break;
+ case attr::AMDGPUKernelCall: OS << "amdgpu_kernel"; break;
case attr::IntelOclBicc: OS << "inteloclbicc"; break;
case attr::PreserveMost:
OS << "preserve_most";
Index: clang/lib/AST/Type.cpp
===================================================================
--- clang/lib/AST/Type.cpp
+++ clang/lib/AST/Type.cpp
@@ -3185,6 +3185,7 @@
case CC_AAPCS: return "aapcs";
case CC_AAPCS_VFP: return "aapcs-vfp";
case CC_AArch64VectorCall: return "aarch64_vector_pcs";
+ case CC_AMDGPUKernelCall: return "amdgpu_kernel";
case CC_IntelOclBicc: return "intel_ocl_bicc";
case CC_SpirFunction: return "spir_function";
case CC_OpenCLKernel: return "opencl_kernel";
@@ -3620,6 +3621,7 @@
case attr::SwiftAsyncCall:
case attr::VectorCall:
case attr::AArch64VectorPcs:
+ case attr::AMDGPUKernelCall:
case attr::Pascal:
case attr::MSABI:
case attr::SysVABI:
Index: clang/lib/AST/ItaniumMangle.cpp
===================================================================
--- clang/lib/AST/ItaniumMangle.cpp
+++ clang/lib/AST/ItaniumMangle.cpp
@@ -3149,6 +3149,7 @@
case CC_AAPCS:
case CC_AAPCS_VFP:
case CC_AArch64VectorCall:
+ case CC_AMDGPUKernelCall:
case CC_IntelOclBicc:
case CC_SpirFunction:
case CC_OpenCLKernel:
Index: clang/include/clang/Basic/Specifiers.h
===================================================================
--- clang/include/clang/Basic/Specifiers.h
+++ clang/include/clang/Basic/Specifiers.h
@@ -280,6 +280,7 @@
CC_PreserveMost, // __attribute__((preserve_most))
CC_PreserveAll, // __attribute__((preserve_all))
CC_AArch64VectorCall, // __attribute__((aarch64_vector_pcs))
+ CC_AMDGPUKernelCall, // __attribute__((amdgpu_kernel))
};
/// Checks whether the given calling convention supports variadic
Index: clang/include/clang/Basic/Attr.td
===================================================================
--- clang/include/clang/Basic/Attr.td
+++ clang/include/clang/Basic/Attr.td
@@ -1855,6 +1855,11 @@
let Subjects = SubjectList<[Function], ErrorDiag, "kernel functions">;
}
+def AMDGPUKernelCall : DeclOrTypeAttr {
+ let Spellings = [Clang<"amdgpu_kernel">];
+ let Documentation = [Undocumented];
+}
+
def BPFPreserveAccessIndex : InheritableAttr,
TargetSpecificAttr<TargetBPF> {
let Spellings = [Clang<"preserve_access_index">];
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
