From 030a405a181176f1a7749819092f4ef8ea5f0758 Mon Sep 17 00:00:00 2001 From: Sameer Sahasrabuddhe Date: Fri, 11 Feb 2022 21:07:28 +0530 Subject: [PATCH] SWDEV-321398: replace hostcall module flag with function attribute This internal version is currently a squash of four upstream reviews: 1. D119087: [AMDGPU] [NFC] refactor the AMDGPU attributor 2. D119308: [AMDGPU] [NFC] Fix incorrect use of bitwise operator. 3. D119249: [Attributor][NFC] Expose new API in AAPointerInfo 4. D119216: [AMDGPU] replace hostcall module flag with function attribute Of these #1, #2 and #3 are submitted in upstream/main, while #4 is under review. The module flag to indicate use of hostcall is insufficient to catch all cases where hostcall might be in use by a kernel. This is now replaced by a function attribute that gets propagated to top-level kernel functions via their respective call-graph. If the attribute "amdgpu-no-hostcall-ptr" is absent on a kernel, the default behaviour is to emit kernel metadata indicating that the kernel uses the hostcall buffer pointer passed as an implicit argument. The attribute may be placed explicitly by the user, or inferred by the AMDGPU attributor by examining the call-graph. The attribute is inferred only if the function is not being sanitized, and the implictarg_ptr does not result in a load of any byte in the hostcall pointer argument. Change-Id: I6cc12050602c3f477575c3ca09a883797169e9e3 --- llvm/include/llvm/Transforms/IPO/Attributor.h | 42 +++ llvm/lib/Target/AMDGPU/AMDGPUAttributes.def | 29 ++ llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp | 202 +++++++----- .../AMDGPU/AMDGPUHSAMetadataStreamer.cpp | 4 +- .../Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp | 16 + llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h | 3 + .../Transforms/IPO/AttributorAttributes.cpp | 83 ++--- .../lib/Transforms/Utils/AMDGPUEmitPrintf.cpp | 3 - .../AMDGPU/addrspacecast-constantexpr.ll | 4 +- .../annotate-kernel-features-hsa-call.ll | 50 +-- .../AMDGPU/annotate-kernel-features-hsa.ll | 22 +- .../AMDGPU/annotate-kernel-features.ll | 18 +- .../CodeGen/AMDGPU/direct-indirect-call.ll | 2 +- .../AMDGPU/duplicate-attribute-indirect.ll | 2 +- .../AMDGPU/hsa-metadata-enqueue-kernel.ll | 3 + .../AMDGPU/hsa-metadata-hostcall-absent-v3.ll | 51 --- .../AMDGPU/hsa-metadata-hostcall-absent.ll | 48 --- ... hsa-metadata-hostcall-present-v3-asan.ll} | 9 +- .../AMDGPU/hsa-metadata-hostcall-present.ll | 53 --- .../AMDGPU/hsa-metadata-hostcall-v3.ll | 303 ++++++++++++++++++ .../CodeGen/AMDGPU/simple-indirect-call.ll | 2 +- .../uniform-work-group-attribute-missing.ll | 2 +- .../AMDGPU/uniform-work-group-multistep.ll | 4 +- ...niform-work-group-nested-function-calls.ll | 4 +- ...ork-group-prevent-attribute-propagation.ll | 4 +- .../uniform-work-group-recursion-test.ll | 6 +- .../CodeGen/AMDGPU/uniform-work-group-test.ll | 2 +- 27 files changed, 623 insertions(+), 348 deletions(-) create mode 100644 llvm/lib/Target/AMDGPU/AMDGPUAttributes.def delete mode 100644 llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent-v3.ll delete mode 100644 llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent.ll rename llvm/test/CodeGen/AMDGPU/{hsa-metadata-hostcall-present-v3.ll => hsa-metadata-hostcall-present-v3-asan.ll} (87%) delete mode 100644 llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present.ll create mode 100644 llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-v3.ll diff --git a/llvm/include/llvm/Transforms/IPO/Attributor.h b/llvm/include/llvm/Transforms/IPO/Attributor.h index 5ee5fc3aed9686..498b1246292eb4 100644 --- a/llvm/include/llvm/Transforms/IPO/Attributor.h +++ b/llvm/include/llvm/Transforms/IPO/Attributor.h @@ -4592,6 +4592,48 @@ struct AAPointerInfo : public AbstractAttribute { /// See AbstractAttribute::getIdAddr() const char *getIdAddr() const override { return &ID; } + /// Helper to represent an access offset and size, with logic to deal with + /// uncertainty and check for overlapping accesses. + struct OffsetAndSize : public std::pair { + using BaseTy = std::pair; + OffsetAndSize(int64_t Offset, int64_t Size) : BaseTy(Offset, Size) {} + OffsetAndSize(const BaseTy &P) : BaseTy(P) {} + int64_t getOffset() const { return first; } + int64_t getSize() const { return second; } + static OffsetAndSize getUnknown() { + return OffsetAndSize(Unknown, Unknown); + } + + /// Return true if offset or size are unknown. + bool offsetOrSizeAreUnknown() const { + return getOffset() == OffsetAndSize::Unknown || + getSize() == OffsetAndSize::Unknown; + } + + /// Return true if this offset and size pair might describe an address that + /// overlaps with \p OAS. + bool mayOverlap(const OffsetAndSize &OAS) const { + // Any unknown value and we are giving up -> overlap. + if (offsetOrSizeAreUnknown() || OAS.offsetOrSizeAreUnknown()) + return true; + + // Check if one offset point is in the other interval [offset, + // offset+size]. + return OAS.getOffset() + OAS.getSize() > getOffset() && + OAS.getOffset() < getOffset() + getSize(); + } + + /// Constant used to represent unknown offset or sizes. + static constexpr int64_t Unknown = 1 << 31; + }; + + /// Call \p CB on all accesses that might interfere with \p OAS and return + /// true if all such accesses were known and the callback returned true for + /// all of them, false otherwise. An access interferes with an offset-size + /// pair if it might read or write that memory region. + virtual bool forallInterferingAccesses( + OffsetAndSize OAS, function_ref CB) const = 0; + /// Call \p CB on all accesses that might interfere with \p LI and return true /// if all such accesses were known and the callback returned true for all of /// them, false otherwise. diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAttributes.def b/llvm/lib/Target/AMDGPU/AMDGPUAttributes.def new file mode 100644 index 00000000000000..fb9e17fb63e67c --- /dev/null +++ b/llvm/lib/Target/AMDGPU/AMDGPUAttributes.def @@ -0,0 +1,29 @@ +//===--- AMDGPUAttributes.def ---------------------------------*- C++ -*---===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception +// +//===----------------------------------------------------------------------===// +// +// This file contains descriptions of the various function attributes +// that indicate *absence* of the corresponding implicit kernel +// arguments. +// +//===----------------------------------------------------------------------===// + +// NOTE: NO INCLUDE GUARD DESIRED! + +AMDGPU_ATTRIBUTE(DISPATCH_PTR, "amdgpu-no-dispatch-ptr") +AMDGPU_ATTRIBUTE(QUEUE_PTR, "amdgpu-no-queue-ptr") +AMDGPU_ATTRIBUTE(DISPATCH_ID, "amdgpu-no-dispatch-id") +AMDGPU_ATTRIBUTE(IMPLICIT_ARG_PTR, "amdgpu-no-implicitarg-ptr") +AMDGPU_ATTRIBUTE(HOSTCALL_PTR, "amdgpu-no-hostcall-ptr") +AMDGPU_ATTRIBUTE(WORKGROUP_ID_X, "amdgpu-no-workgroup-id-x") +AMDGPU_ATTRIBUTE(WORKGROUP_ID_Y, "amdgpu-no-workgroup-id-y") +AMDGPU_ATTRIBUTE(WORKGROUP_ID_Z, "amdgpu-no-workgroup-id-z") +AMDGPU_ATTRIBUTE(WORKITEM_ID_X, "amdgpu-no-workitem-id-x") +AMDGPU_ATTRIBUTE(WORKITEM_ID_Y, "amdgpu-no-workitem-id-y") +AMDGPU_ATTRIBUTE(WORKITEM_ID_Z, "amdgpu-no-workitem-id-z") + +#undef AMDGPU_ATTRIBUTE diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp index 284e49b55ed626..f404e2eecedb5d 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp @@ -12,6 +12,7 @@ #include "AMDGPU.h" #include "GCNSubtarget.h" +#include "Utils/AMDGPUBaseInfo.h" #include "llvm/CodeGen/TargetPassConfig.h" #include "llvm/IR/IntrinsicsAMDGPU.h" #include "llvm/IR/IntrinsicsR600.h" @@ -22,37 +23,25 @@ using namespace llvm; +#define AMDGPU_ATTRIBUTE(Name, Str) Name##_POS, + +enum ImplicitArgumentPositions { + #include "AMDGPUAttributes.def" + LAST_ARG_POS +}; + +#define AMDGPU_ATTRIBUTE(Name, Str) Name = 1 << Name##_POS, + enum ImplicitArgumentMask { NOT_IMPLICIT_INPUT = 0, - - // SGPRs - DISPATCH_PTR = 1 << 0, - QUEUE_PTR = 1 << 1, - DISPATCH_ID = 1 << 2, - IMPLICIT_ARG_PTR = 1 << 3, - WORKGROUP_ID_X = 1 << 4, - WORKGROUP_ID_Y = 1 << 5, - WORKGROUP_ID_Z = 1 << 6, - - // VGPRS: - WORKITEM_ID_X = 1 << 7, - WORKITEM_ID_Y = 1 << 8, - WORKITEM_ID_Z = 1 << 9, - ALL_ARGUMENT_MASK = (1 << 10) - 1 + #include "AMDGPUAttributes.def" + ALL_ARGUMENT_MASK = (1 << LAST_ARG_POS) - 1 }; +#define AMDGPU_ATTRIBUTE(Name, Str) {Name, Str}, static constexpr std::pair ImplicitAttrs[] = { - {DISPATCH_PTR, "amdgpu-no-dispatch-ptr"}, - {QUEUE_PTR, "amdgpu-no-queue-ptr"}, - {DISPATCH_ID, "amdgpu-no-dispatch-id"}, - {IMPLICIT_ARG_PTR, "amdgpu-no-implicitarg-ptr"}, - {WORKGROUP_ID_X, "amdgpu-no-workgroup-id-x"}, - {WORKGROUP_ID_Y, "amdgpu-no-workgroup-id-y"}, - {WORKGROUP_ID_Z, "amdgpu-no-workgroup-id-z"}, - {WORKITEM_ID_X, "amdgpu-no-workitem-id-x"}, - {WORKITEM_ID_Y, "amdgpu-no-workitem-id-y"}, - {WORKITEM_ID_Z, "amdgpu-no-workitem-id-z"} + #include "AMDGPUAttributes.def" }; // We do not need to note the x workitem or workgroup id because they are always @@ -90,7 +79,7 @@ intrinsicToAttrMask(Intrinsic::ID ID, bool &NonKernelOnly, bool &IsQueuePtr) { case Intrinsic::amdgcn_queue_ptr: case Intrinsic::amdgcn_is_shared: case Intrinsic::amdgcn_is_private: - // TODO: Does not require queue ptr on gfx9+ + // TODO: Does not require the queue pointer on gfx9+ case Intrinsic::trap: case Intrinsic::debugtrap: IsQueuePtr = true; @@ -112,6 +101,17 @@ static bool isDSAddress(const Constant *C) { return AS == AMDGPUAS::LOCAL_ADDRESS || AS == AMDGPUAS::REGION_ADDRESS; } +/// Returns true if the function requires the implicit argument be passed +/// regardless of the function contents. +static bool funcRequiresHostcallPtr(const Function &F) { + // Sanitizers require the hostcall buffer passed in the implicit arguments. + return F.hasFnAttribute(Attribute::SanitizeAddress) || + F.hasFnAttribute(Attribute::SanitizeThread) || + F.hasFnAttribute(Attribute::SanitizeMemory) || + F.hasFnAttribute(Attribute::SanitizeHWAddress) || + F.hasFnAttribute(Attribute::SanitizeMemTag); +} + class AMDGPUInformationCache : public InformationCache { public: AMDGPUInformationCache(const Module &M, AnalysisGetter &AG, @@ -129,7 +129,7 @@ class AMDGPUInformationCache : public InformationCache { } private: - /// Check if the ConstantExpr \p CE requires queue ptr attribute. + /// Check if the ConstantExpr \p CE requires the queue pointer. static bool visitConstExpr(const ConstantExpr *CE) { if (CE->getOpcode() == Instruction::AddrSpaceCast) { unsigned SrcAS = CE->getOperand(0)->getType()->getPointerAddressSpace(); @@ -163,7 +163,7 @@ class AMDGPUInformationCache : public InformationCache { } public: - /// Returns true if \p Fn needs a queue ptr attribute because of \p C. + /// Returns true if \p Fn needs the queue pointer because of \p C. bool needsQueuePtr(const Constant *C, Function &Fn) { bool IsNonEntryFunc = !AMDGPU::isEntryFunctionCC(Fn.getCallingConv()); bool HasAperture = hasApertureRegs(Fn); @@ -182,7 +182,7 @@ class AMDGPUInformationCache : public InformationCache { } private: - /// Used to determine if the Constant needs a queue ptr attribute. + /// Used to determine if the Constant needs the queue pointer. DenseMap ConstantStatus; }; @@ -327,7 +327,20 @@ struct AAAMDAttributesFunction : public AAAMDAttributes { void initialize(Attributor &A) override { Function *F = getAssociatedFunction(); + + // If the function requires the implicit arg pointer due to sanitizers, + // assume it's needed even if explicitly marked as not requiring it. + const bool NeedsHostcall = funcRequiresHostcallPtr(*F); + if (NeedsHostcall) { + removeAssumedBits(IMPLICIT_ARG_PTR); + removeAssumedBits(HOSTCALL_PTR); + } + for (auto Attr : ImplicitAttrs) { + if (NeedsHostcall && + (Attr.first == IMPLICIT_ARG_PTR || Attr.first == HOSTCALL_PTR)) + continue; + if (F->hasFnAttribute(Attr.second)) addKnownBits(Attr.first); } @@ -355,7 +368,6 @@ struct AAAMDAttributesFunction : public AAAMDAttributes { return indicatePessimisticFixpoint(); bool IsNonEntryFunc = !AMDGPU::isEntryFunctionCC(F->getCallingConv()); - auto &InfoCache = static_cast(A.getInfoCache()); bool NeedsQueuePtr = false; @@ -377,13 +389,58 @@ struct AAAMDAttributesFunction : public AAAMDAttributes { } } - // If we found that we need amdgpu-queue-ptr, nothing else to do. + if (!NeedsQueuePtr) { + NeedsQueuePtr = checkForQueuePtr(A); + } + if (NeedsQueuePtr) { removeAssumedBits(QUEUE_PTR); - return getAssumed() != OrigAssumed ? ChangeStatus::CHANGED : - ChangeStatus::UNCHANGED; } + if (funcRetrievesHostcallPtr(A)) { + removeAssumedBits(IMPLICIT_ARG_PTR); + removeAssumedBits(HOSTCALL_PTR); + } + + return getAssumed() != OrigAssumed ? ChangeStatus::CHANGED + : ChangeStatus::UNCHANGED; + } + + ChangeStatus manifest(Attributor &A) override { + SmallVector AttrList; + LLVMContext &Ctx = getAssociatedFunction()->getContext(); + + for (auto Attr : ImplicitAttrs) { + if (isKnown(Attr.first)) + AttrList.push_back(Attribute::get(Ctx, Attr.second)); + } + + return IRAttributeManifest::manifestAttrs(A, getIRPosition(), AttrList, + /* ForceReplace */ true); + } + + const std::string getAsStr() const override { + std::string Str; + raw_string_ostream OS(Str); + OS << "AMDInfo["; + for (auto Attr : ImplicitAttrs) + OS << ' ' << Attr.second; + OS << " ]"; + return OS.str(); + } + + /// See AbstractAttribute::trackStatistics() + void trackStatistics() const override {} + +private: + bool checkForQueuePtr(Attributor &A) { + Function *F = getAssociatedFunction(); + bool IsNonEntryFunc = !AMDGPU::isEntryFunctionCC(F->getCallingConv()); + + auto &InfoCache = static_cast(A.getInfoCache()); + + bool NeedsQueuePtr = false; + auto CheckAddrSpaceCasts = [&](Instruction &I) { unsigned SrcAS = static_cast(I).getSrcAddressSpace(); if (castRequiresQueuePtr(SrcAS)) { @@ -398,7 +455,7 @@ struct AAAMDAttributesFunction : public AAAMDAttributes { // `checkForAllInstructions` is much more cheaper than going through all // instructions, try it first. - // amdgpu-queue-ptr is not needed if aperture regs is present. + // The queue pointer is not needed if aperture regs is present. if (!HasApertureRegs) { bool UsedAssumedInformation = false; A.checkForAllInstructions(CheckAddrSpaceCasts, *this, @@ -406,61 +463,55 @@ struct AAAMDAttributesFunction : public AAAMDAttributes { UsedAssumedInformation); } - // If we found that we need amdgpu-queue-ptr, nothing else to do. - if (NeedsQueuePtr) { - removeAssumedBits(QUEUE_PTR); - return getAssumed() != OrigAssumed ? ChangeStatus::CHANGED : - ChangeStatus::UNCHANGED; - } + // If we found that we need the queue pointer, nothing else to do. + if (NeedsQueuePtr) + return true; - if (!IsNonEntryFunc && HasApertureRegs) { - return getAssumed() != OrigAssumed ? ChangeStatus::CHANGED : - ChangeStatus::UNCHANGED; - } + if (!IsNonEntryFunc && HasApertureRegs) + return false; for (BasicBlock &BB : *F) { for (Instruction &I : BB) { for (const Use &U : I.operands()) { if (const auto *C = dyn_cast(U)) { - if (InfoCache.needsQueuePtr(C, *F)) { - removeAssumedBits(QUEUE_PTR); - return getAssumed() != OrigAssumed ? ChangeStatus::CHANGED : - ChangeStatus::UNCHANGED; - } + if (InfoCache.needsQueuePtr(C, *F)) + return true; } } } } - return getAssumed() != OrigAssumed ? ChangeStatus::CHANGED : - ChangeStatus::UNCHANGED; + return false; } - ChangeStatus manifest(Attributor &A) override { - SmallVector AttrList; - LLVMContext &Ctx = getAssociatedFunction()->getContext(); - - for (auto Attr : ImplicitAttrs) { - if (isKnown(Attr.first)) - AttrList.push_back(Attribute::get(Ctx, Attr.second)); - } + bool funcRetrievesHostcallPtr(Attributor &A) { + auto Pos = llvm::AMDGPU::getHostcallImplicitArgPosition(); + + // Check if this is a call to the implicitarg_ptr builtin and it + // is used to retrieve the hostcall pointer. The implicit arg for + // hostcall is not used only if every use of the implicitarg_ptr + // is a load that clearly does not retrieve any byte of the + // hostcall pointer. We check this by tracing all the uses of the + // initial call to the implicitarg_ptr intrinsic. + auto DoesNotLeadToHostcallPtr = [&](Instruction &I) { + auto &Call = cast(I); + if (Call.getIntrinsicID() != Intrinsic::amdgcn_implicitarg_ptr) + return true; + + const auto &PointerInfoAA = A.getAAFor( + *this, IRPosition::callsite_returned(Call), DepClassTy::REQUIRED); + + AAPointerInfo::OffsetAndSize OAS(Pos, 8); + return PointerInfoAA.forallInterferingAccesses( + OAS, [](const AAPointerInfo::Access &Acc, bool IsExact) { + return Acc.getRemoteInst()->isDroppable(); + }); + }; - return IRAttributeManifest::manifestAttrs(A, getIRPosition(), AttrList, - /* ForceReplace */ true); + bool UsedAssumedInformation = false; + return !A.checkForAllCallLikeInstructions(DoesNotLeadToHostcallPtr, *this, + UsedAssumedInformation); } - - const std::string getAsStr() const override { - std::string Str; - raw_string_ostream OS(Str); - OS << "AMDInfo["; - for (auto Attr : ImplicitAttrs) - OS << ' ' << Attr.second; - OS << " ]"; - return OS.str(); - } - - /// See AbstractAttribute::trackStatistics() - void trackStatistics() const override {} }; AAAMDAttributes &AAAMDAttributes::createForPosition(const IRPosition &IRP, @@ -497,7 +548,8 @@ class AMDGPUAttributor : public ModulePass { BumpPtrAllocator Allocator; AMDGPUInformationCache InfoCache(M, AG, Allocator, nullptr, *TM); DenseSet Allowed( - {&AAAMDAttributes::ID, &AAUniformWorkGroupSize::ID, &AACallEdges::ID}); + {&AAAMDAttributes::ID, &AAUniformWorkGroupSize::ID, + &AACallEdges::ID, &AAPointerInfo::ID}); Attributor A(Functions, InfoCache, CGUpdater, &Allowed); diff --git a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp index 3b4f92f613e77f..a3e1f08e3aa06c 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp @@ -405,7 +405,7 @@ void MetadataStreamerV2::emitHiddenKernelArgs(const Function &Func) { if (HiddenArgNumBytes >= 32) { if (Func.getParent()->getNamedMetadata("llvm.printf.fmts")) emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenPrintfBuffer); - else if (Func.getParent()->getFunction("__ockl_hostcall_internal")) { + else if (!Func.hasFnAttribute("amdgpu-no-hostcall-ptr")) { // The printf runtime binding pass should have ensured that hostcall and // printf are not used in the same module. assert(!Func.getParent()->getNamedMetadata("llvm.printf.fmts")); @@ -821,7 +821,7 @@ void MetadataStreamerV3::emitHiddenKernelArgs(const Function &Func, if (M->getNamedMetadata("llvm.printf.fmts")) emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_printf_buffer", Offset, Args); - else if (M->getModuleFlag("amdgpu_hostcall")) { + else if (!Func.hasFnAttribute("amdgpu-no-hostcall-ptr")) { // The printf runtime binding pass should have ensured that hostcall and // printf are not used in the same module. assert(!M->getNamedMetadata("llvm.printf.fmts")); diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp index 9da7b9f5145deb..b1473f21d6f083 100644 --- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp +++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp @@ -127,6 +127,22 @@ bool isHsaAbiVersion3Or4(const MCSubtargetInfo *STI) { return isHsaAbiVersion3(STI) || isHsaAbiVersion4(STI); } +// FIXME: All such magic numbers about the ABI should be in a +// central TD file. +unsigned getHostcallImplicitArgPosition() { + switch (AmdhsaCodeObjectVersion) { + case 2: + case 3: + case 4: + return 24; + case 5: + return 80; + default: + llvm_unreachable("Unexpected code object version"); + return 0; + } +} + #define GET_MIMGBaseOpcodesTable_IMPL #define GET_MIMGDimInfoTable_IMPL #define GET_MIMGInfoTable_IMPL diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h index aaf06125cdddb9..0a21f909f05e47 100644 --- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h +++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h @@ -51,6 +51,9 @@ bool isHsaAbiVersion4(const MCSubtargetInfo *STI); /// false otherwise. bool isHsaAbiVersion3Or4(const MCSubtargetInfo *STI); +/// \returns The offset of the hostcall pointer argument from implicitarg_ptr +unsigned getHostcallImplicitArgPosition(); + struct GcnBufferFormatInfo { unsigned Format; unsigned BitsPerComp; diff --git a/llvm/lib/Transforms/IPO/AttributorAttributes.cpp b/llvm/lib/Transforms/IPO/AttributorAttributes.cpp index cdfc7fe0d6572f..4c76633be4979d 100644 --- a/llvm/lib/Transforms/IPO/AttributorAttributes.cpp +++ b/llvm/lib/Transforms/IPO/AttributorAttributes.cpp @@ -759,9 +759,6 @@ namespace llvm { namespace AA { namespace PointerInfo { -/// An access kind description as used by AAPointerInfo. -struct OffsetAndSize; - struct State; } // namespace PointerInfo @@ -779,7 +776,7 @@ struct DenseMapInfo : DenseMapInfo { /// Helper that allows OffsetAndSize as a key in a DenseMap. template <> -struct DenseMapInfo +struct DenseMapInfo : DenseMapInfo> {}; /// Helper for AA::PointerInfo::Acccess DenseMap/Set usage ignoring everythign @@ -795,35 +792,6 @@ struct AccessAsInstructionInfo : DenseMapInfo { } // namespace llvm -/// Helper to represent an access offset and size, with logic to deal with -/// uncertainty and check for overlapping accesses. -struct AA::PointerInfo::OffsetAndSize : public std::pair { - using BaseTy = std::pair; - OffsetAndSize(int64_t Offset, int64_t Size) : BaseTy(Offset, Size) {} - OffsetAndSize(const BaseTy &P) : BaseTy(P) {} - int64_t getOffset() const { return first; } - int64_t getSize() const { return second; } - static OffsetAndSize getUnknown() { return OffsetAndSize(Unknown, Unknown); } - - /// Return true if this offset and size pair might describe an address that - /// overlaps with \p OAS. - bool mayOverlap(const OffsetAndSize &OAS) const { - // Any unknown value and we are giving up -> overlap. - if (OAS.getOffset() == OffsetAndSize::Unknown || - OAS.getSize() == OffsetAndSize::Unknown || - getOffset() == OffsetAndSize::Unknown || - getSize() == OffsetAndSize::Unknown) - return true; - - // Check if one offset point is in the other interval [offset, offset+size]. - return OAS.getOffset() + OAS.getSize() > getOffset() && - OAS.getOffset() < getOffset() + getSize(); - } - - /// Constant used to represent unknown offset or sizes. - static constexpr int64_t Unknown = 1 << 31; -}; - /// Implementation of the DenseMapInfo. /// ///{ @@ -957,14 +925,14 @@ struct AA::PointerInfo::State : public AbstractState { using Accesses = DenseSet; /// We store all accesses in bins denoted by their offset and size. - using AccessBinsTy = DenseMap; + using AccessBinsTy = DenseMap; AccessBinsTy::const_iterator begin() const { return AccessBins.begin(); } AccessBinsTy::const_iterator end() const { return AccessBins.end(); } protected: /// The bins with all the accesses for the associated pointer. - DenseMap AccessBins; + DenseMap AccessBins; /// Add a new access to the state at offset \p Offset and with size \p Size. /// The access is associated with \p I, writes \p Content (if anything), and @@ -975,7 +943,7 @@ struct AA::PointerInfo::State : public AbstractState { AAPointerInfo::AccessKind Kind, Type *Ty, Instruction *RemoteI = nullptr, Accesses *BinPtr = nullptr) { - OffsetAndSize Key{Offset, Size}; + AAPointerInfo::OffsetAndSize Key{Offset, Size}; Accesses &Bin = BinPtr ? *BinPtr : AccessBins[Key]; AAPointerInfo::Access Acc(&I, RemoteI ? RemoteI : &I, Content, Kind, Ty); // Check if we have an access for this instruction in this bin, if not, @@ -992,14 +960,34 @@ struct AA::PointerInfo::State : public AbstractState { return *It == Before ? ChangeStatus::UNCHANGED : ChangeStatus::CHANGED; } + /// See AAPointerInfo::forallInterferingAccesses. + bool forallInterferingAccesses( + AAPointerInfo::OffsetAndSize OAS, + function_ref CB) const { + if (!isValidState()) + return false; + + for (auto &It : AccessBins) { + AAPointerInfo::OffsetAndSize ItOAS = It.getFirst(); + if (!OAS.mayOverlap(ItOAS)) + continue; + bool IsExact = OAS == ItOAS && !OAS.offsetOrSizeAreUnknown(); + for (auto &Access : It.getSecond()) + if (!CB(Access, IsExact)) + return false; + } + return true; + } + /// See AAPointerInfo::forallInterferingAccesses. bool forallInterferingAccesses( Instruction &I, function_ref CB) const { if (!isValidState()) return false; + // First find the offset and size of I. - OffsetAndSize OAS(-1, -1); + AAPointerInfo::OffsetAndSize OAS(-1, -1); for (auto &It : AccessBins) { for (auto &Access : It.getSecond()) { if (Access.getRemoteInst() == &I) { @@ -1010,20 +998,13 @@ struct AA::PointerInfo::State : public AbstractState { if (OAS.getSize() != -1) break; } + // No access for I was found, we are done. if (OAS.getSize() == -1) return true; // Now that we have an offset and size, find all overlapping ones and use // the callback on the accesses. - for (auto &It : AccessBins) { - OffsetAndSize ItOAS = It.getFirst(); - if (!OAS.mayOverlap(ItOAS)) - continue; - for (auto &Access : It.getSecond()) - if (!CB(Access, OAS == ItOAS)) - return false; - } - return true; + return forallInterferingAccesses(OAS, CB); } private: @@ -1052,6 +1033,12 @@ struct AAPointerInfoImpl return AAPointerInfo::manifest(A); } + bool forallInterferingAccesses( + OffsetAndSize OAS, + function_ref CB) + const override { + return State::forallInterferingAccesses(OAS, CB); + } bool forallInterferingAccesses( LoadInst &LI, function_ref CB) const override { @@ -1115,7 +1102,7 @@ struct AAPointerInfoFloating : public AAPointerInfoImpl { bool handleAccess(Attributor &A, Instruction &I, Value &Ptr, Optional Content, AccessKind Kind, int64_t Offset, ChangeStatus &Changed, Type *Ty, - int64_t Size = AA::PointerInfo::OffsetAndSize::Unknown) { + int64_t Size = OffsetAndSize::Unknown) { using namespace AA::PointerInfo; // No need to find a size if one is given or the offset is unknown. if (Offset != OffsetAndSize::Unknown && Size == OffsetAndSize::Unknown && @@ -1131,7 +1118,7 @@ struct AAPointerInfoFloating : public AAPointerInfoImpl { /// Helper struct, will support ranges eventually. struct OffsetInfo { - int64_t Offset = AA::PointerInfo::OffsetAndSize::Unknown; + int64_t Offset = OffsetAndSize::Unknown; bool operator==(const OffsetInfo &OI) const { return Offset == OI.Offset; } }; diff --git a/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp b/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp index fdc914a72bfd7f..8cd16ca3906f1a 100644 --- a/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp +++ b/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp @@ -63,9 +63,6 @@ static Value *callPrintfBegin(IRBuilder<> &Builder, Value *Version) { auto Int64Ty = Builder.getInt64Ty(); auto M = Builder.GetInsertBlock()->getModule(); auto Fn = M->getOrInsertFunction("__ockl_printf_begin", Int64Ty, Int64Ty); - if (!M->getModuleFlag("amdgpu_hostcall")) { - M->addModuleFlag(llvm::Module::Override, "amdgpu_hostcall", 1); - } return Builder.CreateCall(Fn, Version); } diff --git a/llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll b/llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll index 668b2f9ed506b7..0850b8c7744317 100644 --- a/llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll +++ b/llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll @@ -230,6 +230,6 @@ attributes #1 = { nounwind } ; AKF_HSA: attributes #[[ATTR1]] = { nounwind } ;. ; ATTRIBUTOR_HSA: attributes #[[ATTR0:[0-9]+]] = { argmemonly nofree nounwind willreturn } -; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll index a9266323686338..c32713e9baf1db 100644 --- a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll +++ b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll @@ -837,7 +837,7 @@ define float @func_other_intrinsic_call(float %arg) #3 { ret float %fadd } -; Implicit arguments need to be enabled for sanitizers +; Hostcall needs to be enabled for sanitizers define amdgpu_kernel void @kern_sanitize_address() #4 { ; AKF_HSA-LABEL: define {{[^@]+}}@kern_sanitize_address ; AKF_HSA-SAME: () #[[ATTR5:[0-9]+]] { @@ -853,7 +853,7 @@ define amdgpu_kernel void @kern_sanitize_address() #4 { ret void } -; Implicit arguments need to be enabled for sanitizers +; Hostcall needs to be enabled for sanitizers define void @func_sanitize_address() #4 { ; AKF_HSA-LABEL: define {{[^@]+}}@func_sanitize_address ; AKF_HSA-SAME: () #[[ATTR5]] { @@ -869,7 +869,7 @@ define void @func_sanitize_address() #4 { ret void } -; Implicit arguments need to be enabled for sanitizers +; Hostcall needs to be enabled for sanitizers define void @func_indirect_sanitize_address() #3 { ; AKF_HSA-LABEL: define {{[^@]+}}@func_indirect_sanitize_address ; AKF_HSA-SAME: () #[[ATTR3]] { @@ -877,7 +877,7 @@ define void @func_indirect_sanitize_address() #3 { ; AKF_HSA-NEXT: ret void ; ; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@func_indirect_sanitize_address -; ATTRIBUTOR_HSA-SAME: () #[[ATTR16]] { +; ATTRIBUTOR_HSA-SAME: () #[[ATTR18:[0-9]+]] { ; ATTRIBUTOR_HSA-NEXT: call void @func_sanitize_address() ; ATTRIBUTOR_HSA-NEXT: ret void ; @@ -885,7 +885,7 @@ define void @func_indirect_sanitize_address() #3 { ret void } -; Implicit arguments need to be enabled for sanitizers +; Hostcall needs to be enabled for sanitizers define amdgpu_kernel void @kern_indirect_sanitize_address() #3 { ; AKF_HSA-LABEL: define {{[^@]+}}@kern_indirect_sanitize_address ; AKF_HSA-SAME: () #[[ATTR4]] { @@ -893,7 +893,7 @@ define amdgpu_kernel void @kern_indirect_sanitize_address() #3 { ; AKF_HSA-NEXT: ret void ; ; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@kern_indirect_sanitize_address -; ATTRIBUTOR_HSA-SAME: () #[[ATTR16]] { +; ATTRIBUTOR_HSA-SAME: () #[[ATTR18]] { ; ATTRIBUTOR_HSA-NEXT: call void @func_sanitize_address() ; ATTRIBUTOR_HSA-NEXT: ret void ; @@ -912,7 +912,7 @@ define amdgpu_kernel void @kern_decl_sanitize_address() #3 { ; AKF_HSA-NEXT: ret void ; ; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@kern_decl_sanitize_address -; ATTRIBUTOR_HSA-SAME: () #[[ATTR19:[0-9]+]] { +; ATTRIBUTOR_HSA-SAME: () #[[ATTR15]] { ; ATTRIBUTOR_HSA-NEXT: call void @extern_func_sanitize_address() ; ATTRIBUTOR_HSA-NEXT: ret void ; @@ -937,24 +937,24 @@ attributes #5 = { nounwind sanitize_address "amdgpu-no-implicitarg-ptr" } ; AKF_HSA: attributes #[[ATTR6:[0-9]+]] = { nounwind sanitize_address "amdgpu-no-implicitarg-ptr" } ;. ; ATTRIBUTOR_HSA: attributes #[[ATTR0:[0-9]+]] = { nounwind readnone speculatable willreturn } -; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR12]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx900" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR13]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx900" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR14]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR12]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx900" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR13]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx900" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR14]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" } ; ATTRIBUTOR_HSA: attributes #[[ATTR15]] = { nounwind "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR16]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR17]] = { nounwind sanitize_address "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR18:[0-9]+]] = { nounwind sanitize_address "amdgpu-no-implicitarg-ptr" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR19]] = { nounwind "amdgpu-no-implicitarg-ptr" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR16]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR17]] = { nounwind sanitize_address "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR18]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR19:[0-9]+]] = { nounwind sanitize_address "amdgpu-no-implicitarg-ptr" "uniform-work-group-size"="false" } ; ATTRIBUTOR_HSA: attributes #[[ATTR20]] = { nounwind } ;. diff --git a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll index 6b0ea17abd4100..52dff4e2627aa3 100644 --- a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll +++ b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll @@ -647,15 +647,15 @@ attributes #1 = { nounwind } ; AKF_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-stack-objects" } ;. ; ATTRIBUTOR_HSA: attributes #[[ATTR0:[0-9]+]] = { nounwind readnone speculatable willreturn } -; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features.ll b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features.ll index c93a6a4f797dea..31230b47baeb5b 100644 --- a/llvm/test/CodeGen/AMDGPU/annotate-kernel-features.ll +++ b/llvm/test/CodeGen/AMDGPU/annotate-kernel-features.ll @@ -418,13 +418,13 @@ attributes #1 = { nounwind } ; AKF_CHECK: attributes #[[ATTR1]] = { nounwind } ;. ; ATTRIBUTOR_CHECK: attributes #[[ATTR0:[0-9]+]] = { nounwind readnone speculatable willreturn } -; ATTRIBUTOR_CHECK: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_CHECK: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_CHECK: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_CHECK: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_CHECK: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_CHECK: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "uniform-work-group-size"="false" } -; ATTRIBUTOR_CHECK: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; ATTRIBUTOR_CHECK: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" } -; ATTRIBUTOR_CHECK: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" } +; ATTRIBUTOR_CHECK: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/direct-indirect-call.ll b/llvm/test/CodeGen/AMDGPU/direct-indirect-call.ll index da8fdb8acdce5b..6c6850030faf69 100644 --- a/llvm/test/CodeGen/AMDGPU/direct-indirect-call.ll +++ b/llvm/test/CodeGen/AMDGPU/direct-indirect-call.ll @@ -35,6 +35,6 @@ define amdgpu_kernel void @test_direct_indirect_call() { ret void } ;. -; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } ; CHECK: attributes #[[ATTR1]] = { "uniform-work-group-size"="false" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/duplicate-attribute-indirect.ll b/llvm/test/CodeGen/AMDGPU/duplicate-attribute-indirect.ll index c19dc86afb7bc5..c68d4362554d24 100644 --- a/llvm/test/CodeGen/AMDGPU/duplicate-attribute-indirect.ll +++ b/llvm/test/CodeGen/AMDGPU/duplicate-attribute-indirect.ll @@ -42,6 +42,6 @@ attributes #0 = { "amdgpu-no-dispatch-id" } ;. ; AKF_GCN: attributes #[[ATTR0]] = { "amdgpu-calls" "amdgpu-no-dispatch-id" "amdgpu-stack-objects" } ;. -; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } ; ATTRIBUTOR_GCN: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "uniform-work-group-size"="false" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-enqueue-kernel.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-enqueue-kernel.ll index eb49add8705c2b..0c394b6cd13bc1 100644 --- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-enqueue-kernel.ll +++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-enqueue-kernel.ll @@ -26,6 +26,9 @@ ; CHECK-NEXT: - Size: 8 ; CHECK-NEXT: Align: 8 ; CHECK-NEXT: ValueKind: HiddenGlobalOffsetZ +; CHECK-NEXT: - Size: 8 +; CHECK-NEXT: Align: 8 +; CHECK-NEXT: ValueKind: HiddenNone ; CHECK-NOT: ValueKind: HiddenDefaultQueue ; CHECK-NOT: ValueKind: HiddenCompletionAction define amdgpu_kernel void @test_non_enqueue_kernel_caller(i8 %a) #0 diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent-v3.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent-v3.ll deleted file mode 100644 index a1cee23387a89f..00000000000000 --- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent-v3.ll +++ /dev/null @@ -1,51 +0,0 @@ -; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s -; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s - -; CHECK: --- -; CHECK: amdhsa.kernels: -; CHECK: - .args: -; CHECK-NEXT: - .name: a -; CHECK-NEXT: .offset: 0 -; CHECK-NEXT: .size: 1 -; CHECK-NEXT: .type_name: char -; CHECK-NEXT: .value_kind: by_value -; CHECK-NEXT: - .offset: 8 -; CHECK-NEXT: .size: 8 -; CHECK-NEXT: .value_kind: hidden_global_offset_x -; CHECK-NEXT: - .offset: 16 -; CHECK-NEXT: .size: 8 -; CHECK-NEXT: .value_kind: hidden_global_offset_y -; CHECK-NEXT: - .offset: 24 -; CHECK-NEXT: .size: 8 -; CHECK-NEXT: .value_kind: hidden_global_offset_z - -; CHECK-NOT: .value_kind: hidden_hostcall_buffer - -; CHECK: .language: OpenCL C -; CHECK-NEXT: .language_version: -; CHECK-NEXT: - 2 -; CHECK-NEXT: - 0 -; CHECK: .name: test_kernel -; CHECK: .symbol: test_kernel.kd - -define amdgpu_kernel void @test_kernel(i8 %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 { - ret void -} - -; CHECK: amdhsa.version: -; CHECK-NEXT: - 1 -; CHECK-NEXT: - 0 - -attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" } - -!1 = !{i32 0} -!2 = !{!"none"} -!3 = !{!"char"} -!4 = !{!""} - -!opencl.ocl.version = !{!90} -!90 = !{i32 2, i32 0} - -; PARSER: AMDGPU HSA Metadata Parser Test: PASS diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent.ll deleted file mode 100644 index 702f32d4f98ca6..00000000000000 --- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-absent.ll +++ /dev/null @@ -1,48 +0,0 @@ -; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s -; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=gfx900 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s - -; CHECK: --- -; CHECK: Version: [ 1, 0 ] -; CHECK: Kernels: - -; CHECK: - Name: test_kernel -; CHECK-NEXT: SymbolName: 'test_kernel@kd' -; CHECK-NEXT: Language: OpenCL C -; CHECK-NEXT: LanguageVersion: [ 2, 0 ] -; CHECK-NEXT: Args: -; CHECK-NEXT: - Name: a -; CHECK-NEXT: TypeName: char -; CHECK-NEXT: Size: 1 -; CHECK-NEXT: Align: 1 -; CHECK-NEXT: ValueKind: ByValue -; CHECK-NEXT: AccQual: Default -; CHECK-NEXT: - Size: 8 -; CHECK-NEXT: Align: 8 -; CHECK-NEXT: ValueKind: HiddenGlobalOffsetX -; CHECK-NEXT: - Size: 8 -; CHECK-NEXT: Align: 8 -; CHECK-NEXT: ValueKind: HiddenGlobalOffsetY -; CHECK-NEXT: - Size: 8 -; CHECK-NEXT: Align: 8 -; CHECK-NEXT: ValueKind: HiddenGlobalOffsetZ -; CHECK-NOT: ValueKind: HiddenHostcallBuffer -; CHECK-NOT: ValueKind: HiddenDefaultQueue -; CHECK-NOT: ValueKind: HiddenCompletionAction - -define amdgpu_kernel void @test_kernel(i8 %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 { - ret void -} - -attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" } - -!1 = !{i32 0} -!2 = !{!"none"} -!3 = !{!"char"} -!4 = !{!""} - -!opencl.ocl.version = !{!90} -!90 = !{i32 2, i32 0} - -; PARSER: AMDGPU HSA Metadata Parser Test: PASS diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3-asan.ll similarity index 87% rename from llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll rename to llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3-asan.ll index 15186b389c8b63..8ae5948d995011 100644 --- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3.ll +++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present-v3-asan.ll @@ -1,5 +1,5 @@ ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s -; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck %s ; CHECK: --- ; CHECK: amdhsa.kernels: @@ -39,7 +39,7 @@ define amdgpu_kernel void @test_kernel(i8 %a) #0 ; CHECK-NEXT: - 1 ; CHECK-NEXT: - 0 -attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" } +attributes #0 = { sanitize_address "amdgpu-implicitarg-num-bytes"="48" } !1 = !{i32 0} !2 = !{!"none"} @@ -48,8 +48,3 @@ attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" } !opencl.ocl.version = !{!90} !90 = !{i32 2, i32 0} - -!llvm.module.flags = !{!0} -!0 = !{i32 1, !"amdgpu_hostcall", i32 1} - -; PARSER: AMDGPU HSA Metadata Parser Test: PASS diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present.ll deleted file mode 100644 index c79285338468cd..00000000000000 --- a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-present.ll +++ /dev/null @@ -1,53 +0,0 @@ -; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s -; RUN: llc -mtriple=amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=gfx900 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s - -; CHECK: --- -; CHECK: Version: [ 1, 0 ] -; CHECK: Kernels: - -; CHECK: - Name: test_kernel -; CHECK-NEXT: SymbolName: 'test_kernel@kd' -; CHECK-NEXT: Language: OpenCL C -; CHECK-NEXT: LanguageVersion: [ 2, 0 ] -; CHECK-NEXT: Args: -; CHECK-NEXT: - Name: a -; CHECK-NEXT: TypeName: char -; CHECK-NEXT: Size: 1 -; CHECK-NEXT: Align: 1 -; CHECK-NEXT: ValueKind: ByValue -; CHECK-NEXT: AccQual: Default -; CHECK-NEXT: - Size: 8 -; CHECK-NEXT: Align: 8 -; CHECK-NEXT: ValueKind: HiddenGlobalOffsetX -; CHECK-NEXT: - Size: 8 -; CHECK-NEXT: Align: 8 -; CHECK-NEXT: ValueKind: HiddenGlobalOffsetY -; CHECK-NEXT: - Size: 8 -; CHECK-NEXT: Align: 8 -; CHECK-NEXT: ValueKind: HiddenGlobalOffsetZ -; CHECK-NEXT: - Size: 8 -; CHECK-NEXT: Align: 8 -; CHECK-NEXT: ValueKind: HiddenHostcallBuffer -; CHECK-NEXT: AddrSpaceQual: Global -; CHECK-NOT: ValueKind: HiddenDefaultQueue -; CHECK-NOT: ValueKind: HiddenCompletionAction - -declare <2 x i64> @__ockl_hostcall_internal(i8*, i32, i64, i64, i64, i64, i64, i64, i64, i64) - -define amdgpu_kernel void @test_kernel(i8 %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 { - ret void -} - -attributes #0 = { "amdgpu-implicitarg-num-bytes"="48" } - -!1 = !{i32 0} -!2 = !{!"none"} -!3 = !{!"char"} -!4 = !{!""} - -!opencl.ocl.version = !{!90} -!90 = !{i32 2, i32 0} - -; PARSER: AMDGPU HSA Metadata Parser Test: PASS diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-v3.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-v3.ll new file mode 100644 index 00000000000000..734ad53e9be0d4 --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hostcall-v3.ll @@ -0,0 +1,303 @@ +; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 < %s | FileCheck --check-prefix=CHECK %s + +declare void @function1() + +declare void @function2() #0 + +; Function Attrs: noinline +define void @function3(i8 addrspace(4)* %argptr, i8 addrspace(4)* addrspace(1)* %sink) #4 { + store i8 addrspace(4)* %argptr, i8 addrspace(4)* addrspace(1)* %sink, align 8 + ret void +} + +; Function Attrs: noinline +define void @function4(i64 %arg, i64* %a) #4 { + store i64 %arg, i64* %a + ret void +} + +; Function Attrs: noinline +define void @function5(i8 addrspace(4)* %ptr, i64* %sink) #4 { + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 8 + %cast = bitcast i8 addrspace(4)* %gep to i64 addrspace(4)* + %x = load i64, i64 addrspace(4)* %cast + store i64 %x, i64* %sink + ret void +} + +; Function Attrs: nounwind readnone speculatable willreturn +declare align 4 i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() #1 + +; CHECK: amdhsa.kernels: +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel10 +define amdgpu_kernel void @test_kernel10(i8* %a) #2 { + store i8 3, i8* %a, align 1 + ret void +} + +; Call to an extern function + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel20 +define amdgpu_kernel void @test_kernel20(i8* %a) #2 { + call void @function1() + store i8 3, i8* %a, align 1 + ret void +} + +; Explicit attribute on kernel + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel21 +define amdgpu_kernel void @test_kernel21(i8* %a) #3 { + call void @function1() + store i8 3, i8* %a, align 1 + ret void +} + +; Explicit attribute on extern callee + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel22 +define amdgpu_kernel void @test_kernel22(i8* %a) #2 { + call void @function2() + store i8 3, i8* %a, align 1 + ret void +} + +; Access more bytes than the pointer size + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel30 +define amdgpu_kernel void @test_kernel30(i128* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 16 + %cast = bitcast i8 addrspace(4)* %gep to i128 addrspace(4)* + %x = load i128, i128 addrspace(4)* %cast + store i128 %x, i128* %a + ret void +} + +; Typical load of hostcall buffer pointer + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel40 +define amdgpu_kernel void @test_kernel40(i64* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 24 + %cast = bitcast i8 addrspace(4)* %gep to i64 addrspace(4)* + %x = load i64, i64 addrspace(4)* %cast + store i64 %x, i64* %a + ret void +} + +; Typical usage, overriden by explicit attribute on kernel + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel41 +define amdgpu_kernel void @test_kernel41(i64* %a) #3 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 24 + %cast = bitcast i8 addrspace(4)* %gep to i64 addrspace(4)* + %x = load i64, i64 addrspace(4)* %cast + store i64 %x, i64* %a + ret void +} + +; Access to implicit arg before the hostcall pointer + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel42 +define amdgpu_kernel void @test_kernel42(i64* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 16 + %cast = bitcast i8 addrspace(4)* %gep to i64 addrspace(4)* + %x = load i64, i64 addrspace(4)* %cast + store i64 %x, i64* %a + ret void +} + +; Access to implicit arg after the hostcall pointer + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel43 +define amdgpu_kernel void @test_kernel43(i64* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 32 + %cast = bitcast i8 addrspace(4)* %gep to i64 addrspace(4)* + %x = load i64, i64 addrspace(4)* %cast + store i64 %x, i64* %a + ret void +} + +; Accessing a byte just before the hostcall pointer + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel44 +define amdgpu_kernel void @test_kernel44(i8* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 23 + %x = load i8, i8 addrspace(4)* %gep, align 1 + store i8 %x, i8* %a, align 1 + ret void +} + +; Accessing a byte inside the hostcall pointer + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel45 +define amdgpu_kernel void @test_kernel45(i8* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 24 + %x = load i8, i8 addrspace(4)* %gep, align 1 + store i8 %x, i8* %a, align 1 + ret void +} + +; Accessing a byte inside the hostcall pointer + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel46 +define amdgpu_kernel void @test_kernel46(i8* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 31 + %x = load i8, i8 addrspace(4)* %gep, align 1 + store i8 %x, i8* %a, align 1 + ret void +} + +; Accessing a byte just after the hostcall pointer + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel47 +define amdgpu_kernel void @test_kernel47(i8* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 32 + %x = load i8, i8 addrspace(4)* %gep, align 1 + store i8 %x, i8* %a, align 1 + ret void +} + +; Access with an unknown offset + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel50 +define amdgpu_kernel void @test_kernel50(i8* %a, i32 %b) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i32 %b + %x = load i8, i8 addrspace(4)* %gep, align 1 + store i8 %x, i8* %a, align 1 + ret void +} + +; Multiple geps reaching the hostcall pointer argument. + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel51 +define amdgpu_kernel void @test_kernel51(i8* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep1 = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 16 + %gep2 = getelementptr inbounds i8, i8 addrspace(4)* %gep1, i64 8 + %x = load i8, i8 addrspace(4)* %gep2, align 1 + store i8 %x, i8* %a, align 1 + ret void +} + +; Multiple geps not reaching the hostcall pointer argument. + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel52 +define amdgpu_kernel void @test_kernel52(i8* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep1 = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 16 + %gep2 = getelementptr inbounds i8, i8 addrspace(4)* %gep1, i64 16 + %x = load i8, i8 addrspace(4)* %gep2, align 1 + store i8 %x, i8* %a, align 1 + ret void +} + +; Hostcall pointer used inside a function call + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel60 +define amdgpu_kernel void @test_kernel60(i64* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 24 + %cast = bitcast i8 addrspace(4)* %gep to i64 addrspace(4)* + %x = load i64, i64 addrspace(4)* %cast + call void @function4(i64 %x, i64* %a) + ret void +} + +; Hostcall pointer retrieved inside a function call; chain of geps + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel61 +define amdgpu_kernel void @test_kernel61(i64* %a) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i64 16 + call void @function5(i8 addrspace(4)* %gep, i64* %a) + ret void +} + +; Pointer captured + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel70 +define amdgpu_kernel void @test_kernel70(i8 addrspace(4)* addrspace(1)* %sink) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i32 42 + store i8 addrspace(4)* %gep, i8 addrspace(4)* addrspace(1)* %sink, align 8 + ret void +} + +; Pointer captured inside function call + +; CHECK: - .args: +; CHECK: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel71 +define amdgpu_kernel void @test_kernel71(i8 addrspace(4)* addrspace(1)* %sink) #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i32 42 + call void @function3(i8 addrspace(4)* %gep, i8 addrspace(4)* addrspace(1)* %sink) + ret void +} + +; Ineffective pointer capture + +; CHECK: - .args: +; CHECK-NOT: hidden_hostcall_buffer +; CHECK-LABEL: .name: test_kernel72 +define amdgpu_kernel void @test_kernel72() #2 { + %ptr = tail call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() + %gep = getelementptr inbounds i8, i8 addrspace(4)* %ptr, i32 42 + store i8 addrspace(4)* %gep, i8 addrspace(4)* addrspace(1)* undef, align 8 + ret void +} + +attributes #0 = { "amdgpu-no-hostcall-ptr" } +attributes #1 = { nounwind readnone speculatable willreturn } +attributes #2 = { "amdgpu-implicitarg-num-bytes"="48" } +attributes #3 = { "amdgpu-implicitarg-num-bytes"="48" "amdgpu-no-hostcall-ptr" } +attributes #4 = { noinline } diff --git a/llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll b/llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll index f4eaa608237627..3786e8ef2ad405 100644 --- a/llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll +++ b/llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll @@ -73,6 +73,6 @@ define amdgpu_kernel void @test_simple_indirect_call() { ;. ; AKF_GCN: attributes #[[ATTR0]] = { "amdgpu-calls" "amdgpu-stack-objects" } ;. -; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } ; ATTRIBUTOR_GCN: attributes #[[ATTR1]] = { "uniform-work-group-size"="false" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/uniform-work-group-attribute-missing.ll b/llvm/test/CodeGen/AMDGPU/uniform-work-group-attribute-missing.ll index 003d4c74c0fc9a..78caeeaa1f3de4 100644 --- a/llvm/test/CodeGen/AMDGPU/uniform-work-group-attribute-missing.ll +++ b/llvm/test/CodeGen/AMDGPU/uniform-work-group-attribute-missing.ll @@ -31,5 +31,5 @@ define amdgpu_kernel void @kernel1() #1 { attributes #0 = { "uniform-work-group-size"="true" } ;. -; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/uniform-work-group-multistep.ll b/llvm/test/CodeGen/AMDGPU/uniform-work-group-multistep.ll index e9179b0213b9c5..afb0d07f0c256b 100644 --- a/llvm/test/CodeGen/AMDGPU/uniform-work-group-multistep.ll +++ b/llvm/test/CodeGen/AMDGPU/uniform-work-group-multistep.ll @@ -97,6 +97,6 @@ define amdgpu_kernel void @kernel2() #0 { attributes #0 = { "uniform-work-group-size"="true" } ;. -; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } +; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/uniform-work-group-nested-function-calls.ll b/llvm/test/CodeGen/AMDGPU/uniform-work-group-nested-function-calls.ll index 292022039e5d69..2dc57b42cfbaa5 100644 --- a/llvm/test/CodeGen/AMDGPU/uniform-work-group-nested-function-calls.ll +++ b/llvm/test/CodeGen/AMDGPU/uniform-work-group-nested-function-calls.ll @@ -41,6 +41,6 @@ define amdgpu_kernel void @kernel3() #2 { attributes #2 = { "uniform-work-group-size"="true" } ;. -; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } +; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/uniform-work-group-prevent-attribute-propagation.ll b/llvm/test/CodeGen/AMDGPU/uniform-work-group-prevent-attribute-propagation.ll index cd888064cada2c..745928d7846772 100644 --- a/llvm/test/CodeGen/AMDGPU/uniform-work-group-prevent-attribute-propagation.ll +++ b/llvm/test/CodeGen/AMDGPU/uniform-work-group-prevent-attribute-propagation.ll @@ -41,6 +41,6 @@ define amdgpu_kernel void @kernel2() #2 { attributes #1 = { "uniform-work-group-size"="true" } ;. -; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } +; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/uniform-work-group-recursion-test.ll b/llvm/test/CodeGen/AMDGPU/uniform-work-group-recursion-test.ll index 3ac9f0675bfeff..7a5f1eae341f8f 100644 --- a/llvm/test/CodeGen/AMDGPU/uniform-work-group-recursion-test.ll +++ b/llvm/test/CodeGen/AMDGPU/uniform-work-group-recursion-test.ll @@ -101,7 +101,7 @@ define amdgpu_kernel void @kernel(i32 addrspace(1)* %m) #1 { attributes #0 = { nounwind readnone } attributes #1 = { "uniform-work-group-size"="true" } ;. -; CHECK: attributes #[[ATTR0]] = { nounwind readnone "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } -; CHECK: attributes #[[ATTR1]] = { nounwind readnone "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } -; CHECK: attributes #[[ATTR2]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } +; CHECK: attributes #[[ATTR0]] = { nounwind readnone "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; CHECK: attributes #[[ATTR1]] = { nounwind readnone "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } +; CHECK: attributes #[[ATTR2]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" } ;. diff --git a/llvm/test/CodeGen/AMDGPU/uniform-work-group-test.ll b/llvm/test/CodeGen/AMDGPU/uniform-work-group-test.ll index 1381f871369d26..bdc1c28f1654d4 100644 --- a/llvm/test/CodeGen/AMDGPU/uniform-work-group-test.ll +++ b/llvm/test/CodeGen/AMDGPU/uniform-work-group-test.ll @@ -61,5 +61,5 @@ define amdgpu_kernel void @kernel3() #0 { attributes #0 = { "uniform-work-group-size"="false" } ;. -; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } +; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" } ;.