From 6fea0a226245f4237163e607105f01b9dfb2ca2c Mon Sep 17 00:00:00 2001 From: Graham Hunter Date: Fri, 5 Jul 2019 12:48:16 +0000 Subject: [PATCH] Scalable Vector IR Type with further LTO fixes Reintroduces the scalable vector IR type from D32530, after it was reverted a couple of times due to increasing chromium LTO build times. This latest incarnation removes the walk over aggregate types from the verifier entirely, in favor of rejecting scalable vectors in the isValidElementType methods in ArrayType and StructType. This removes the 70% degradation observed with the second repro tarball from PR42210. Reviewers: thakis, hans, rengolin, sdesmalen Reviewed By: sdesmalen Differential Revision: https://reviews.llvm.org/D64079 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@365203 91177308-0d34-0410-b5e6-96231b3b80d8 --- docs/LangRef.rst | 54 ++++++--- include/llvm/ADT/DenseMapInfo.h | 16 +++ include/llvm/IR/DerivedTypes.h | 68 +++++++++-- include/llvm/IR/Type.h | 1 + include/llvm/Support/ScalableSize.h | 43 +++++++ lib/AsmParser/LLLexer.cpp | 1 + lib/AsmParser/LLParser.cpp | 13 +- lib/AsmParser/LLToken.h | 1 + lib/Bitcode/Reader/BitcodeReader.cpp | 6 +- lib/Bitcode/Writer/BitcodeWriter.cpp | 5 +- lib/IR/AsmWriter.cpp | 5 +- lib/IR/LLVMContextImpl.h | 2 +- lib/IR/Type.cpp | 17 +-- lib/IR/Verifier.cpp | 7 ++ test/Bitcode/compatibility.ll | 4 + test/Other/scalable-vector-array.ll | 8 ++ test/Other/scalable-vector-struct.ll | 8 ++ test/Verifier/scalable-global-vars.ll | 12 ++ unittests/IR/CMakeLists.txt | 1 + unittests/IR/VectorTypesTest.cpp | 164 ++++++++++++++++++++++++++ 20 files changed, 397 insertions(+), 39 deletions(-) create mode 100644 include/llvm/Support/ScalableSize.h create mode 100644 test/Other/scalable-vector-array.ll create mode 100644 test/Other/scalable-vector-struct.ll create mode 100644 test/Verifier/scalable-global-vars.ll create mode 100644 unittests/IR/VectorTypesTest.cpp diff --git a/docs/LangRef.rst b/docs/LangRef.rst index e7dd40af168..8325e08e180 100644 --- a/docs/LangRef.rst +++ b/docs/LangRef.rst @@ -675,6 +675,9 @@ an optional list of attached :ref:`metadata `. Variables and aliases can have a :ref:`Thread Local Storage Model `. +:ref:`Scalable vectors ` cannot be global variables or members of +structs or arrays because their size is unknown at compile time. + Syntax:: @ = [Linkage] [PreemptionSpecifier] [Visibility] @@ -2742,30 +2745,40 @@ Vector Type A vector type is a simple derived type that represents a vector of elements. Vector types are used when multiple primitive data are operated in parallel using a single instruction (SIMD). A vector type -requires a size (number of elements) and an underlying primitive data -type. Vector types are considered :ref:`first class `. +requires a size (number of elements), an underlying primitive data type, +and a scalable property to represent vectors where the exact hardware +vector length is unknown at compile time. Vector types are considered +:ref:`first class `. :Syntax: :: - < <# elements> x > + < <# elements> x > ; Fixed-length vector + < vscale x <# elements> x > ; Scalable vector The number of elements is a constant integer value larger than 0; elementtype may be any integer, floating-point or pointer type. Vectors -of size zero are not allowed. +of size zero are not allowed. For scalable vectors, the total number of +elements is a constant multiple (called vscale) of the specified number +of elements; vscale is a positive integer that is unknown at compile time +and the same hardware-dependent constant for all scalable vectors at run +time. The size of a specific scalable vector type is thus constant within +IR, even if the exact size in bytes cannot be determined until run time. :Examples: -+-------------------+--------------------------------------------------+ -| ``<4 x i32>`` | Vector of 4 32-bit integer values. | -+-------------------+--------------------------------------------------+ -| ``<8 x float>`` | Vector of 8 32-bit floating-point values. | -+-------------------+--------------------------------------------------+ -| ``<2 x i64>`` | Vector of 2 64-bit integer values. | -+-------------------+--------------------------------------------------+ -| ``<4 x i64*>`` | Vector of 4 pointers to 64-bit integer values. | -+-------------------+--------------------------------------------------+ ++------------------------+----------------------------------------------------+ +| ``<4 x i32>`` | Vector of 4 32-bit integer values. | ++------------------------+----------------------------------------------------+ +| ``<8 x float>`` | Vector of 8 32-bit floating-point values. | ++------------------------+----------------------------------------------------+ +| ``<2 x i64>`` | Vector of 2 64-bit integer values. | ++------------------------+----------------------------------------------------+ +| ``<4 x i64*>`` | Vector of 4 pointers to 64-bit integer values. | ++------------------------+----------------------------------------------------+ +| ```` | Vector with a multiple of 4 32-bit integer values. | ++------------------------+----------------------------------------------------+ .. _t_label: @@ -8188,6 +8201,7 @@ Syntax: :: = extractelement > , ; yields + = extractelement > , ; yields Overview: """"""""" @@ -8208,7 +8222,9 @@ Semantics: The result is a scalar of the same type as the element type of ``val``. Its value is the value at position ``idx`` of ``val``. If ``idx`` -exceeds the length of ``val``, the result is a +exceeds the length of ``val`` for a fixed-length vector, the result is a +:ref:`poison value `. For a scalable vector, if the value +of ``idx`` exceeds the runtime length of the vector, the result is a :ref:`poison value `. Example: @@ -8229,6 +8245,7 @@ Syntax: :: = insertelement > , , ; yields > + = insertelement > , , ; yields > Overview: """"""""" @@ -8250,7 +8267,9 @@ Semantics: The result is a vector of the same type as ``val``. Its element values are those of ``val`` except at position ``idx``, where it gets the value -``elt``. If ``idx`` exceeds the length of ``val``, the result +``elt``. If ``idx`` exceeds the length of ``val`` for a fixed-length vector, +the result is a :ref:`poison value `. For a scalable vector, +if the value of ``idx`` exceeds the runtime length of the vector, the result is a :ref:`poison value `. Example: @@ -8271,6 +8290,7 @@ Syntax: :: = shufflevector > , > , ; yields > + = shufflevector > , > v2, ; yields > Overview: """"""""" @@ -8302,6 +8322,10 @@ undef. If any element of the mask operand is undef, that element of the result is undef. If the shuffle mask selects an undef element from one of the input vectors, the resulting element is undef. +For scalable vectors, the only valid mask values at present are +``zeroinitializer`` and ``undef``, since we cannot write all indices as +literals for a vector with a length unknown at compile time. + Example: """""""" diff --git a/include/llvm/ADT/DenseMapInfo.h b/include/llvm/ADT/DenseMapInfo.h index 18d6dffa9a5..5ef6f3ad1b0 100644 --- a/include/llvm/ADT/DenseMapInfo.h +++ b/include/llvm/ADT/DenseMapInfo.h @@ -17,6 +17,7 @@ #include "llvm/ADT/Hashing.h" #include "llvm/ADT/StringRef.h" #include "llvm/Support/PointerLikeTypeTraits.h" +#include "llvm/Support/ScalableSize.h" #include #include #include @@ -268,6 +269,21 @@ template <> struct DenseMapInfo { static bool isEqual(hash_code LHS, hash_code RHS) { return LHS == RHS; } }; +template <> struct DenseMapInfo { + static inline ElementCount getEmptyKey() { return {~0U, true}; } + static inline ElementCount getTombstoneKey() { return {~0U - 1, false}; } + static unsigned getHashValue(const ElementCount& EltCnt) { + if (EltCnt.Scalable) + return (EltCnt.Min * 37U) - 1U; + + return EltCnt.Min * 37U; + } + + static bool isEqual(const ElementCount& LHS, const ElementCount& RHS) { + return LHS == RHS; + } +}; + } // end namespace llvm #endif // LLVM_ADT_DENSEMAPINFO_H diff --git a/include/llvm/IR/DerivedTypes.h b/include/llvm/IR/DerivedTypes.h index 5bf37294bb2..3c1d4278905 100644 --- a/include/llvm/IR/DerivedTypes.h +++ b/include/llvm/IR/DerivedTypes.h @@ -23,6 +23,7 @@ #include "llvm/IR/Type.h" #include "llvm/Support/Casting.h" #include "llvm/Support/Compiler.h" +#include "llvm/Support/ScalableSize.h" #include #include @@ -387,6 +388,8 @@ public: SequentialType(const SequentialType &) = delete; SequentialType &operator=(const SequentialType &) = delete; + /// For scalable vectors, this will return the minimum number of elements + /// in the vector. uint64_t getNumElements() const { return NumElements; } Type *getElementType() const { return ContainedType; } @@ -422,14 +425,37 @@ uint64_t Type::getArrayNumElements() const { /// Class to represent vector types. class VectorType : public SequentialType { - VectorType(Type *ElType, unsigned NumEl); + /// A fully specified VectorType is of the form . 'n' is the + /// minimum number of elements of type Ty contained within the vector, and + /// 'vscale x' indicates that the total element count is an integer multiple + /// of 'n', where the multiple is either guaranteed to be one, or is + /// statically unknown at compile time. + /// + /// If the multiple is known to be 1, then the extra term is discarded in + /// textual IR: + /// + /// <4 x i32> - a vector containing 4 i32s + /// - a vector containing an unknown integer multiple + /// of 4 i32s + + VectorType(Type *ElType, unsigned NumEl, bool Scalable = false); + VectorType(Type *ElType, ElementCount EC); + + // If true, the total number of elements is an unknown multiple of the + // minimum 'NumElements' from SequentialType. Otherwise the total number + // of elements is exactly equal to 'NumElements'. + bool Scalable; public: VectorType(const VectorType &) = delete; VectorType &operator=(const VectorType &) = delete; /// This static method is the primary way to construct an VectorType. - static VectorType *get(Type *ElementType, unsigned NumElements); + static VectorType *get(Type *ElementType, ElementCount EC); + static VectorType *get(Type *ElementType, unsigned NumElements, + bool Scalable = false) { + return VectorType::get(ElementType, {NumElements, Scalable}); + } /// This static method gets a VectorType with the same number of elements as /// the input type, and the element type is an integer type of the same width @@ -438,7 +464,7 @@ public: unsigned EltBits = VTy->getElementType()->getPrimitiveSizeInBits(); assert(EltBits && "Element size must be of a non-zero size"); Type *EltTy = IntegerType::get(VTy->getContext(), EltBits); - return VectorType::get(EltTy, VTy->getNumElements()); + return VectorType::get(EltTy, VTy->getElementCount()); } /// This static method is like getInteger except that the element types are @@ -446,7 +472,7 @@ public: static VectorType *getExtendedElementVectorType(VectorType *VTy) { unsigned EltBits = VTy->getElementType()->getPrimitiveSizeInBits(); Type *EltTy = IntegerType::get(VTy->getContext(), EltBits * 2); - return VectorType::get(EltTy, VTy->getNumElements()); + return VectorType::get(EltTy, VTy->getElementCount()); } /// This static method is like getInteger except that the element types are @@ -456,29 +482,45 @@ public: assert((EltBits & 1) == 0 && "Cannot truncate vector element with odd bit-width"); Type *EltTy = IntegerType::get(VTy->getContext(), EltBits / 2); - return VectorType::get(EltTy, VTy->getNumElements()); + return VectorType::get(EltTy, VTy->getElementCount()); } /// This static method returns a VectorType with half as many elements as the /// input type and the same element type. static VectorType *getHalfElementsVectorType(VectorType *VTy) { - unsigned NumElts = VTy->getNumElements(); - assert ((NumElts & 1) == 0 && + auto EltCnt = VTy->getElementCount(); + assert ((EltCnt.Min & 1) == 0 && "Cannot halve vector with odd number of elements."); - return VectorType::get(VTy->getElementType(), NumElts/2); + return VectorType::get(VTy->getElementType(), EltCnt/2); } /// This static method returns a VectorType with twice as many elements as the /// input type and the same element type. static VectorType *getDoubleElementsVectorType(VectorType *VTy) { - unsigned NumElts = VTy->getNumElements(); - return VectorType::get(VTy->getElementType(), NumElts*2); + auto EltCnt = VTy->getElementCount(); + assert((VTy->getNumElements() * 2ull) <= UINT_MAX && + "Too many elements in vector"); + return VectorType::get(VTy->getElementType(), EltCnt*2); } /// Return true if the specified type is valid as a element type. static bool isValidElementType(Type *ElemTy); - /// Return the number of bits in the Vector type. + /// Return an ElementCount instance to represent the (possibly scalable) + /// number of elements in the vector. + ElementCount getElementCount() const { + uint64_t MinimumEltCnt = getNumElements(); + assert(MinimumEltCnt <= UINT_MAX && "Too many elements in vector"); + return { (unsigned)MinimumEltCnt, Scalable }; + } + + /// Returns whether or not this is a scalable vector (meaning the total + /// element count is a multiple of the minimum). + bool isScalable() const { + return Scalable; + } + + /// Return the minimum number of bits in the Vector type. /// Returns zero when the vector is a vector of pointers. unsigned getBitWidth() const { return getNumElements() * getElementType()->getPrimitiveSizeInBits(); @@ -494,6 +536,10 @@ unsigned Type::getVectorNumElements() const { return cast(this)->getNumElements(); } +bool Type::getVectorIsScalable() const { + return cast(this)->isScalable(); +} + /// Class to represent pointers. class PointerType : public Type { explicit PointerType(Type *ElType, unsigned AddrSpace); diff --git a/include/llvm/IR/Type.h b/include/llvm/IR/Type.h index 5f9f44e8152..f2aa49030aa 100644 --- a/include/llvm/IR/Type.h +++ b/include/llvm/IR/Type.h @@ -366,6 +366,7 @@ public: return ContainedTys[0]; } + inline bool getVectorIsScalable() const; inline unsigned getVectorNumElements() const; Type *getVectorElementType() const { assert(getTypeID() == VectorTyID); diff --git a/include/llvm/Support/ScalableSize.h b/include/llvm/Support/ScalableSize.h new file mode 100644 index 00000000000..96bf043773a --- /dev/null +++ b/include/llvm/Support/ScalableSize.h @@ -0,0 +1,43 @@ +//===- ScalableSize.h - Scalable vector size info ---------------*- 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 provides a struct that can be used to query the size of IR types +// which may be scalable vectors. It provides convenience operators so that +// it can be used in much the same way as a single scalar value. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_SUPPORT_SCALABLESIZE_H +#define LLVM_SUPPORT_SCALABLESIZE_H + +namespace llvm { + +class ElementCount { +public: + unsigned Min; // Minimum number of vector elements. + bool Scalable; // If true, NumElements is a multiple of 'Min' determined + // at runtime rather than compile time. + + ElementCount(unsigned Min, bool Scalable) + : Min(Min), Scalable(Scalable) {} + + ElementCount operator*(unsigned RHS) { + return { Min * RHS, Scalable }; + } + ElementCount operator/(unsigned RHS) { + return { Min / RHS, Scalable }; + } + + bool operator==(const ElementCount& RHS) const { + return Min == RHS.Min && Scalable == RHS.Scalable; + } +}; + +} // end namespace llvm + +#endif // LLVM_SUPPORT_SCALABLESIZE_H diff --git a/lib/AsmParser/LLLexer.cpp b/lib/AsmParser/LLLexer.cpp index 0b553bf991d..a23afac27b7 100644 --- a/lib/AsmParser/LLLexer.cpp +++ b/lib/AsmParser/LLLexer.cpp @@ -708,6 +708,7 @@ lltok::Kind LLLexer::LexIdentifier() { KEYWORD(xchg); KEYWORD(nand); KEYWORD(max); KEYWORD(min); KEYWORD(umax); KEYWORD(umin); + KEYWORD(vscale); KEYWORD(x); KEYWORD(blockaddress); diff --git a/lib/AsmParser/LLParser.cpp b/lib/AsmParser/LLParser.cpp index ab645348c53..085f3bd2999 100644 --- a/lib/AsmParser/LLParser.cpp +++ b/lib/AsmParser/LLParser.cpp @@ -2747,7 +2747,18 @@ bool LLParser::ParseStructBody(SmallVectorImpl &Body) { /// Type /// ::= '[' APSINTVAL 'x' Types ']' /// ::= '<' APSINTVAL 'x' Types '>' +/// ::= '<' 'vscale' 'x' APSINTVAL 'x' Types '>' bool LLParser::ParseArrayVectorType(Type *&Result, bool isVector) { + bool Scalable = false; + + if (isVector && Lex.getKind() == lltok::kw_vscale) { + Lex.Lex(); // consume the 'vscale' + if (ParseToken(lltok::kw_x, "expected 'x' after vscale")) + return true; + + Scalable = true; + } + if (Lex.getKind() != lltok::APSInt || Lex.getAPSIntVal().isSigned() || Lex.getAPSIntVal().getBitWidth() > 64) return TokError("expected number in address space"); @@ -2774,7 +2785,7 @@ bool LLParser::ParseArrayVectorType(Type *&Result, bool isVector) { return Error(SizeLoc, "size too large for vector"); if (!VectorType::isValidElementType(EltTy)) return Error(TypeLoc, "invalid vector element type"); - Result = VectorType::get(EltTy, unsigned(Size)); + Result = VectorType::get(EltTy, unsigned(Size), Scalable); } else { if (!ArrayType::isValidElementType(EltTy)) return Error(TypeLoc, "invalid array element type"); diff --git a/lib/AsmParser/LLToken.h b/lib/AsmParser/LLToken.h index acdfaa5ae90..8b0118e6942 100644 --- a/lib/AsmParser/LLToken.h +++ b/lib/AsmParser/LLToken.h @@ -37,6 +37,7 @@ enum Kind { bar, // | colon, // : + kw_vscale, kw_x, kw_true, kw_false, diff --git a/lib/Bitcode/Reader/BitcodeReader.cpp b/lib/Bitcode/Reader/BitcodeReader.cpp index 22d1b2165fd..a339f6eb710 100644 --- a/lib/Bitcode/Reader/BitcodeReader.cpp +++ b/lib/Bitcode/Reader/BitcodeReader.cpp @@ -1878,7 +1878,8 @@ Error BitcodeReader::parseTypeTableBody() { return error("Invalid type"); ResultTy = ArrayType::get(ResultTy, Record[0]); break; - case bitc::TYPE_CODE_VECTOR: // VECTOR: [numelts, eltty] + case bitc::TYPE_CODE_VECTOR: // VECTOR: [numelts, eltty] or + // [numelts, eltty, scalable] if (Record.size() < 2) return error("Invalid record"); if (Record[0] == 0) @@ -1886,7 +1887,8 @@ Error BitcodeReader::parseTypeTableBody() { ResultTy = getTypeByID(Record[1]); if (!ResultTy || !StructType::isValidElementType(ResultTy)) return error("Invalid type"); - ResultTy = VectorType::get(ResultTy, Record[0]); + bool Scalable = Record.size() > 2 ? Record[2] : false; + ResultTy = VectorType::get(ResultTy, Record[0], Scalable); break; } diff --git a/lib/Bitcode/Writer/BitcodeWriter.cpp b/lib/Bitcode/Writer/BitcodeWriter.cpp index 90de4688c8c..547889f82c7 100644 --- a/lib/Bitcode/Writer/BitcodeWriter.cpp +++ b/lib/Bitcode/Writer/BitcodeWriter.cpp @@ -941,10 +941,13 @@ void ModuleBitcodeWriter::writeTypeTable() { } case Type::VectorTyID: { VectorType *VT = cast(T); - // VECTOR [numelts, eltty] + // VECTOR [numelts, eltty] or + // [numelts, eltty, scalable] Code = bitc::TYPE_CODE_VECTOR; TypeVals.push_back(VT->getNumElements()); TypeVals.push_back(VE.getTypeID(VT->getElementType())); + if (VT->isScalable()) + TypeVals.push_back(VT->isScalable()); break; } } diff --git a/lib/IR/AsmWriter.cpp b/lib/IR/AsmWriter.cpp index a5adfd9c8a6..eb5760daecb 100644 --- a/lib/IR/AsmWriter.cpp +++ b/lib/IR/AsmWriter.cpp @@ -620,7 +620,10 @@ void TypePrinting::print(Type *Ty, raw_ostream &OS) { } case Type::VectorTyID: { VectorType *PTy = cast(Ty); - OS << "<" << PTy->getNumElements() << " x "; + OS << "<"; + if (PTy->isScalable()) + OS << "vscale x "; + OS << PTy->getNumElements() << " x "; print(PTy->getElementType(), OS); OS << '>'; return; diff --git a/lib/IR/LLVMContextImpl.h b/lib/IR/LLVMContextImpl.h index 4560617624e..78cf707e0e7 100644 --- a/lib/IR/LLVMContextImpl.h +++ b/lib/IR/LLVMContextImpl.h @@ -1334,7 +1334,7 @@ public: unsigned NamedStructTypesUniqueID = 0; DenseMap, ArrayType*> ArrayTypes; - DenseMap, VectorType*> VectorTypes; + DenseMap, VectorType*> VectorTypes; DenseMap PointerTypes; // Pointers in AddrSpace = 0 DenseMap, PointerType*> ASPointerTypes; diff --git a/lib/IR/Type.cpp b/lib/IR/Type.cpp index 4016bb10ba3..8ece7f223dd 100644 --- a/lib/IR/Type.cpp +++ b/lib/IR/Type.cpp @@ -504,6 +504,8 @@ StringRef StructType::getName() const { } bool StructType::isValidElementType(Type *ElemTy) { + if (auto *VTy = dyn_cast(ElemTy)) + return !VTy->isScalable(); return !ElemTy->isVoidTy() && !ElemTy->isLabelTy() && !ElemTy->isMetadataTy() && !ElemTy->isFunctionTy() && !ElemTy->isTokenTy(); @@ -590,6 +592,8 @@ ArrayType *ArrayType::get(Type *ElementType, uint64_t NumElements) { } bool ArrayType::isValidElementType(Type *ElemTy) { + if (auto *VTy = dyn_cast(ElemTy)) + return !VTy->isScalable(); return !ElemTy->isVoidTy() && !ElemTy->isLabelTy() && !ElemTy->isMetadataTy() && !ElemTy->isFunctionTy() && !ElemTy->isTokenTy(); @@ -599,21 +603,20 @@ bool ArrayType::isValidElementType(Type *ElemTy) { // VectorType Implementation //===----------------------------------------------------------------------===// -VectorType::VectorType(Type *ElType, unsigned NumEl) - : SequentialType(VectorTyID, ElType, NumEl) {} +VectorType::VectorType(Type *ElType, ElementCount EC) + : SequentialType(VectorTyID, ElType, EC.Min), Scalable(EC.Scalable) {} -VectorType *VectorType::get(Type *ElementType, unsigned NumElements) { - assert(NumElements > 0 && "#Elements of a VectorType must be greater than 0"); +VectorType *VectorType::get(Type *ElementType, ElementCount EC) { + assert(EC.Min > 0 && "#Elements of a VectorType must be greater than 0"); assert(isValidElementType(ElementType) && "Element type of a VectorType must " "be an integer, floating point, or " "pointer type."); LLVMContextImpl *pImpl = ElementType->getContext().pImpl; VectorType *&Entry = ElementType->getContext().pImpl - ->VectorTypes[std::make_pair(ElementType, NumElements)]; - + ->VectorTypes[std::make_pair(ElementType, EC)]; if (!Entry) - Entry = new (pImpl->Alloc) VectorType(ElementType, NumElements); + Entry = new (pImpl->Alloc) VectorType(ElementType, EC); return Entry; } diff --git a/lib/IR/Verifier.cpp b/lib/IR/Verifier.cpp index 0ab421e057d..b0464346557 100644 --- a/lib/IR/Verifier.cpp +++ b/lib/IR/Verifier.cpp @@ -691,6 +691,13 @@ void Verifier::visitGlobalVariable(const GlobalVariable &GV) { "DIGlobalVariableExpression"); } + // Scalable vectors cannot be global variables, since we don't know + // the runtime size. If the global is a struct or an array containing + // scalable vectors, that will be caught by the isValidElementType methods + // in StructType or ArrayType instead. + if (auto *VTy = dyn_cast(GV.getValueType())) + Assert(!VTy->isScalable(), "Globals cannot contain scalable vectors", &GV); + if (!GV.hasInitializer()) { visitGlobalValue(GV); return; diff --git a/test/Bitcode/compatibility.ll b/test/Bitcode/compatibility.ll index 19a6cb0acc1..991bde69b61 100644 --- a/test/Bitcode/compatibility.ll +++ b/test/Bitcode/compatibility.ll @@ -917,6 +917,10 @@ define void @typesystem() { ; CHECK: %t7 = alloca x86_mmx %t8 = alloca %opaquety* ; CHECK: %t8 = alloca %opaquety* + %t9 = alloca <4 x i32> + ; CHECK: %t9 = alloca <4 x i32> + %t10 = alloca + ; CHECK: %t10 = alloca ret void } diff --git a/test/Other/scalable-vector-array.ll b/test/Other/scalable-vector-array.ll new file mode 100644 index 00000000000..b5c7e90d792 --- /dev/null +++ b/test/Other/scalable-vector-array.ll @@ -0,0 +1,8 @@ +; RUN: not opt -S -verify < %s 2>&1 | FileCheck %s + +;; Arrays cannot contain scalable vectors; make sure we detect them even +;; when nested inside other aggregates. + +%ty = type { i64, [4 x ] } +; CHECK: error: invalid array element type +; CHECK: %ty = type { i64, [4 x ] } diff --git a/test/Other/scalable-vector-struct.ll b/test/Other/scalable-vector-struct.ll new file mode 100644 index 00000000000..44a8c5f5a81 --- /dev/null +++ b/test/Other/scalable-vector-struct.ll @@ -0,0 +1,8 @@ +; RUN: not opt -S -verify < %s 2>&1 | FileCheck %s + +;; Structs cannot contain scalable vectors; make sure we detect them even +;; when nested inside other aggregates. + +%ty = type [2 x { i32, }] +; CHECK: error: invalid element type for struct +; CHECK: %ty = type [2 x { i32, }] diff --git a/test/Verifier/scalable-global-vars.ll b/test/Verifier/scalable-global-vars.ll new file mode 100644 index 00000000000..572618c131d --- /dev/null +++ b/test/Verifier/scalable-global-vars.ll @@ -0,0 +1,12 @@ +; RUN: not opt -S -verify < %s 2>&1 | FileCheck %s + +;; Global variables cannot be scalable vectors, since we don't +;; know the size at compile time. + +; CHECK: Globals cannot contain scalable vectors +; CHECK-NEXT: * @ScalableVecGlobal +@ScalableVecGlobal = global zeroinitializer + +;; Global _pointers_ to scalable vectors are fine +; CHECK-NOT: Globals cannot contain scalable vectors +@ScalableVecPtr = global * zeroinitializer \ No newline at end of file diff --git a/unittests/IR/CMakeLists.txt b/unittests/IR/CMakeLists.txt index 5b35dc72683..d27c6d969f1 100644 --- a/unittests/IR/CMakeLists.txt +++ b/unittests/IR/CMakeLists.txt @@ -37,6 +37,7 @@ add_llvm_unittest(IRTests ValueHandleTest.cpp ValueMapTest.cpp ValueTest.cpp + VectorTypesTest.cpp VerifierTest.cpp WaymarkTest.cpp ) diff --git a/unittests/IR/VectorTypesTest.cpp b/unittests/IR/VectorTypesTest.cpp new file mode 100644 index 00000000000..f3caf6d6976 --- /dev/null +++ b/unittests/IR/VectorTypesTest.cpp @@ -0,0 +1,164 @@ +//===--- llvm/unittest/IR/VectorTypesTest.cpp - vector types unit tests ---===// +// +// 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 +// +//===----------------------------------------------------------------------===// + +#include "llvm/IR/DerivedTypes.h" +#include "llvm/IR/LLVMContext.h" +#include "llvm/Support/ScalableSize.h" +#include "gtest/gtest.h" +using namespace llvm; + +namespace { +TEST(VectorTypesTest, FixedLength) { + LLVMContext Ctx; + + Type *Int16Ty = Type::getInt16Ty(Ctx); + Type *Int32Ty = Type::getInt32Ty(Ctx); + Type *Int64Ty = Type::getInt64Ty(Ctx); + Type *Float64Ty = Type::getDoubleTy(Ctx); + + VectorType *V8Int32Ty = VectorType::get(Int32Ty, 8); + ASSERT_FALSE(V8Int32Ty->isScalable()); + EXPECT_EQ(V8Int32Ty->getNumElements(), 8U); + EXPECT_EQ(V8Int32Ty->getElementType()->getScalarSizeInBits(), 32U); + + VectorType *V8Int16Ty = VectorType::get(Int16Ty, {8, false}); + ASSERT_FALSE(V8Int16Ty->isScalable()); + EXPECT_EQ(V8Int16Ty->getNumElements(), 8U); + EXPECT_EQ(V8Int16Ty->getElementType()->getScalarSizeInBits(), 16U); + + ElementCount EltCnt(4, false); + VectorType *V4Int64Ty = VectorType::get(Int64Ty, EltCnt); + ASSERT_FALSE(V4Int64Ty->isScalable()); + EXPECT_EQ(V4Int64Ty->getNumElements(), 4U); + EXPECT_EQ(V4Int64Ty->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *V2Int64Ty = VectorType::get(Int64Ty, EltCnt/2); + ASSERT_FALSE(V2Int64Ty->isScalable()); + EXPECT_EQ(V2Int64Ty->getNumElements(), 2U); + EXPECT_EQ(V2Int64Ty->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *V8Int64Ty = VectorType::get(Int64Ty, EltCnt*2); + ASSERT_FALSE(V8Int64Ty->isScalable()); + EXPECT_EQ(V8Int64Ty->getNumElements(), 8U); + EXPECT_EQ(V8Int64Ty->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *V4Float64Ty = VectorType::get(Float64Ty, EltCnt); + ASSERT_FALSE(V4Float64Ty->isScalable()); + EXPECT_EQ(V4Float64Ty->getNumElements(), 4U); + EXPECT_EQ(V4Float64Ty->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *ExtTy = VectorType::getExtendedElementVectorType(V8Int16Ty); + EXPECT_EQ(ExtTy, V8Int32Ty); + ASSERT_FALSE(ExtTy->isScalable()); + EXPECT_EQ(ExtTy->getNumElements(), 8U); + EXPECT_EQ(ExtTy->getElementType()->getScalarSizeInBits(), 32U); + + VectorType *TruncTy = VectorType::getTruncatedElementVectorType(V8Int32Ty); + EXPECT_EQ(TruncTy, V8Int16Ty); + ASSERT_FALSE(TruncTy->isScalable()); + EXPECT_EQ(TruncTy->getNumElements(), 8U); + EXPECT_EQ(TruncTy->getElementType()->getScalarSizeInBits(), 16U); + + VectorType *HalvedTy = VectorType::getHalfElementsVectorType(V4Int64Ty); + EXPECT_EQ(HalvedTy, V2Int64Ty); + ASSERT_FALSE(HalvedTy->isScalable()); + EXPECT_EQ(HalvedTy->getNumElements(), 2U); + EXPECT_EQ(HalvedTy->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *DoubledTy = VectorType::getDoubleElementsVectorType(V4Int64Ty); + EXPECT_EQ(DoubledTy, V8Int64Ty); + ASSERT_FALSE(DoubledTy->isScalable()); + EXPECT_EQ(DoubledTy->getNumElements(), 8U); + EXPECT_EQ(DoubledTy->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *ConvTy = VectorType::getInteger(V4Float64Ty); + EXPECT_EQ(ConvTy, V4Int64Ty); + ASSERT_FALSE(ConvTy->isScalable()); + EXPECT_EQ(ConvTy->getNumElements(), 4U); + EXPECT_EQ(ConvTy->getElementType()->getScalarSizeInBits(), 64U); + + EltCnt = V8Int64Ty->getElementCount(); + EXPECT_EQ(EltCnt.Min, 8U); + ASSERT_FALSE(EltCnt.Scalable); +} + +TEST(VectorTypesTest, Scalable) { + LLVMContext Ctx; + + Type *Int16Ty = Type::getInt16Ty(Ctx); + Type *Int32Ty = Type::getInt32Ty(Ctx); + Type *Int64Ty = Type::getInt64Ty(Ctx); + Type *Float64Ty = Type::getDoubleTy(Ctx); + + VectorType *ScV8Int32Ty = VectorType::get(Int32Ty, 8, true); + ASSERT_TRUE(ScV8Int32Ty->isScalable()); + EXPECT_EQ(ScV8Int32Ty->getNumElements(), 8U); + EXPECT_EQ(ScV8Int32Ty->getElementType()->getScalarSizeInBits(), 32U); + + VectorType *ScV8Int16Ty = VectorType::get(Int16Ty, {8, true}); + ASSERT_TRUE(ScV8Int16Ty->isScalable()); + EXPECT_EQ(ScV8Int16Ty->getNumElements(), 8U); + EXPECT_EQ(ScV8Int16Ty->getElementType()->getScalarSizeInBits(), 16U); + + ElementCount EltCnt(4, true); + VectorType *ScV4Int64Ty = VectorType::get(Int64Ty, EltCnt); + ASSERT_TRUE(ScV4Int64Ty->isScalable()); + EXPECT_EQ(ScV4Int64Ty->getNumElements(), 4U); + EXPECT_EQ(ScV4Int64Ty->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *ScV2Int64Ty = VectorType::get(Int64Ty, EltCnt/2); + ASSERT_TRUE(ScV2Int64Ty->isScalable()); + EXPECT_EQ(ScV2Int64Ty->getNumElements(), 2U); + EXPECT_EQ(ScV2Int64Ty->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *ScV8Int64Ty = VectorType::get(Int64Ty, EltCnt*2); + ASSERT_TRUE(ScV8Int64Ty->isScalable()); + EXPECT_EQ(ScV8Int64Ty->getNumElements(), 8U); + EXPECT_EQ(ScV8Int64Ty->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *ScV4Float64Ty = VectorType::get(Float64Ty, EltCnt); + ASSERT_TRUE(ScV4Float64Ty->isScalable()); + EXPECT_EQ(ScV4Float64Ty->getNumElements(), 4U); + EXPECT_EQ(ScV4Float64Ty->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *ExtTy = VectorType::getExtendedElementVectorType(ScV8Int16Ty); + EXPECT_EQ(ExtTy, ScV8Int32Ty); + ASSERT_TRUE(ExtTy->isScalable()); + EXPECT_EQ(ExtTy->getNumElements(), 8U); + EXPECT_EQ(ExtTy->getElementType()->getScalarSizeInBits(), 32U); + + VectorType *TruncTy = VectorType::getTruncatedElementVectorType(ScV8Int32Ty); + EXPECT_EQ(TruncTy, ScV8Int16Ty); + ASSERT_TRUE(TruncTy->isScalable()); + EXPECT_EQ(TruncTy->getNumElements(), 8U); + EXPECT_EQ(TruncTy->getElementType()->getScalarSizeInBits(), 16U); + + VectorType *HalvedTy = VectorType::getHalfElementsVectorType(ScV4Int64Ty); + EXPECT_EQ(HalvedTy, ScV2Int64Ty); + ASSERT_TRUE(HalvedTy->isScalable()); + EXPECT_EQ(HalvedTy->getNumElements(), 2U); + EXPECT_EQ(HalvedTy->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *DoubledTy = VectorType::getDoubleElementsVectorType(ScV4Int64Ty); + EXPECT_EQ(DoubledTy, ScV8Int64Ty); + ASSERT_TRUE(DoubledTy->isScalable()); + EXPECT_EQ(DoubledTy->getNumElements(), 8U); + EXPECT_EQ(DoubledTy->getElementType()->getScalarSizeInBits(), 64U); + + VectorType *ConvTy = VectorType::getInteger(ScV4Float64Ty); + EXPECT_EQ(ConvTy, ScV4Int64Ty); + ASSERT_TRUE(ConvTy->isScalable()); + EXPECT_EQ(ConvTy->getNumElements(), 4U); + EXPECT_EQ(ConvTy->getElementType()->getScalarSizeInBits(), 64U); + + EltCnt = ScV8Int64Ty->getElementCount(); + EXPECT_EQ(EltCnt.Min, 8U); + ASSERT_TRUE(EltCnt.Scalable); +} + +} // end anonymous namespace