[SVE][IR] Scalable Vector size queries and IR instruction support

* Adds a TypeSize struct to represent the known minimum size of a type
  along with a flag to indicate that the runtime size is a integer multiple
  of that size
* Converts existing size query functions from Type.h and DataLayout.h to
  return a TypeSize result
* Adds convenience methods (including a transparent conversion operator
  to uint64_t) so that most existing code 'just works' as if the return
  values were still scalars.
* Uses the new size queries along with ElementCount to ensure that all
  supported instructions used with scalable vectors can be constructed
  in IR.

Reviewers: hfinkel, lattner, rkruppe, greened, rovka, rengolin, sdesmalen

Reviewed By: rovka, sdesmalen

Differential Revision: https://reviews.llvm.org/D53137

llvm-svn: 374042

Author: huntergr-arm

clang/lib/CodeGen/CGCall.cpp

@@ -4277,8 +4277,8 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
   // Update the largest vector width if any arguments have vector types.
   for (unsigned i = 0; i < IRCallArgs.size(); ++i) {
     if (auto *VT = dyn_cast<llvm::VectorType>(IRCallArgs[i]->getType()))
-      LargestVectorWidth = std::max(LargestVectorWidth,
-                                    VT->getPrimitiveSizeInBits());
+      LargestVectorWidth = std::max((uint64_t)LargestVectorWidth,
+                                   VT->getPrimitiveSizeInBits().getFixedSize());
   }
 
   // Compute the calling convention and attributes.
@@ -4361,8 +4361,8 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
 
   // Update largest vector width from the return type.
   if (auto *VT = dyn_cast<llvm::VectorType>(CI->getType()))
-    LargestVectorWidth = std::max(LargestVectorWidth,
-                                  VT->getPrimitiveSizeInBits());
+    LargestVectorWidth = std::max((uint64_t)LargestVectorWidth,
+                                  VT->getPrimitiveSizeInBits().getFixedSize());
 
   // Insert instrumentation or attach profile metadata at indirect call sites.
   // For more details, see the comment before the definition of

clang/lib/CodeGen/CGStmt.cpp

@@ -2073,8 +2073,8 @@ void CodeGenFunction::EmitAsmStmt(const AsmStmt &S) {
 
       // Update largest vector width for any vector types.
       if (auto *VT = dyn_cast<llvm::VectorType>(ResultRegTypes.back()))
-        LargestVectorWidth = std::max(LargestVectorWidth,
-                                      VT->getPrimitiveSizeInBits());
+        LargestVectorWidth = std::max((uint64_t)LargestVectorWidth,
+                                   VT->getPrimitiveSizeInBits().getFixedSize());
     } else {
       ArgTypes.push_back(Dest.getAddress().getType());
       Args.push_back(Dest.getPointer());
@@ -2098,8 +2098,8 @@ void CodeGenFunction::EmitAsmStmt(const AsmStmt &S) {
 
       // Update largest vector width for any vector types.
       if (auto *VT = dyn_cast<llvm::VectorType>(Arg->getType()))
-        LargestVectorWidth = std::max(LargestVectorWidth,
-                                      VT->getPrimitiveSizeInBits());
+        LargestVectorWidth = std::max((uint64_t)LargestVectorWidth,
+                                   VT->getPrimitiveSizeInBits().getFixedSize());
       if (Info.allowsRegister())
         InOutConstraints += llvm::utostr(i);
       else
@@ -2185,8 +2185,8 @@ void CodeGenFunction::EmitAsmStmt(const AsmStmt &S) {
 
     // Update largest vector width for any vector types.
     if (auto *VT = dyn_cast<llvm::VectorType>(Arg->getType()))
-      LargestVectorWidth = std::max(LargestVectorWidth,
-                                    VT->getPrimitiveSizeInBits());
+      LargestVectorWidth = std::max((uint64_t)LargestVectorWidth,
+                                   VT->getPrimitiveSizeInBits().getFixedSize());
 
     ArgTypes.push_back(Arg->getType());
     Args.push_back(Arg);

clang/lib/CodeGen/CodeGenFunction.cpp

@@ -431,13 +431,13 @@ void CodeGenFunction::FinishFunction(SourceLocation EndLoc) {
   // Scan function arguments for vector width.
   for (llvm::Argument &A : CurFn->args())
     if (auto *VT = dyn_cast<llvm::VectorType>(A.getType()))
-      LargestVectorWidth = std::max(LargestVectorWidth,
-                                    VT->getPrimitiveSizeInBits());
+      LargestVectorWidth = std::max((uint64_t)LargestVectorWidth,
+                                   VT->getPrimitiveSizeInBits().getFixedSize());
 
   // Update vector width based on return type.
   if (auto *VT = dyn_cast<llvm::VectorType>(CurFn->getReturnType()))
-    LargestVectorWidth = std::max(LargestVectorWidth,
-                                  VT->getPrimitiveSizeInBits());
+    LargestVectorWidth = std::max((uint64_t)LargestVectorWidth,
+                                  VT->getPrimitiveSizeInBits().getFixedSize());
 
   // Add the required-vector-width attribute. This contains the max width from:
   // 1. min-vector-width attribute used in the source program.

llvm/include/llvm/ADT/DenseMapInfo.h

@@ -17,7 +17,7 @@
 #include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Support/PointerLikeTypeTraits.h"
-#include "llvm/Support/ScalableSize.h"
+#include "llvm/Support/TypeSize.h"
 #include <cassert>
 #include <cstddef>
 #include <cstdint>

llvm/include/llvm/IR/DataLayout.h

@@ -30,6 +30,7 @@
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/Alignment.h"
+#include "llvm/Support/TypeSize.h"
 #include <cassert>
 #include <cstdint>
 #include <string>
@@ -437,23 +438,33 @@ class DataLayout {
 
   /// Returns the number of bits necessary to hold the specified type.
   ///
+  /// If Ty is a scalable vector type, the scalable property will be set and
+  /// the runtime size will be a positive integer multiple of the base size.
+  ///
   /// For example, returns 36 for i36 and 80 for x86_fp80. The type passed must
   /// have a size (Type::isSized() must return true).
-  uint64_t getTypeSizeInBits(Type *Ty) const;
+  TypeSize getTypeSizeInBits(Type *Ty) const;
 
   /// Returns the maximum number of bytes that may be overwritten by
   /// storing the specified type.
   ///
+  /// If Ty is a scalable vector type, the scalable property will be set and
+  /// the runtime size will be a positive integer multiple of the base size.
+  ///
   /// For example, returns 5 for i36 and 10 for x86_fp80.
-  uint64_t getTypeStoreSize(Type *Ty) const {
-    return (getTypeSizeInBits(Ty) + 7) / 8;
+  TypeSize getTypeStoreSize(Type *Ty) const {
+    auto BaseSize = getTypeSizeInBits(Ty);
+    return { (BaseSize.getKnownMinSize() + 7) / 8, BaseSize.isScalable() };
   }
 
   /// Returns the maximum number of bits that may be overwritten by
   /// storing the specified type; always a multiple of 8.
   ///
+  /// If Ty is a scalable vector type, the scalable property will be set and
+  /// the runtime size will be a positive integer multiple of the base size.
+  ///
   /// For example, returns 40 for i36 and 80 for x86_fp80.
-  uint64_t getTypeStoreSizeInBits(Type *Ty) const {
+  TypeSize getTypeStoreSizeInBits(Type *Ty) const {
     return 8 * getTypeStoreSize(Ty);
   }
 
@@ -468,19 +479,25 @@ class DataLayout {
   /// Returns the offset in bytes between successive objects of the
   /// specified type, including alignment padding.
   ///
+  /// If Ty is a scalable vector type, the scalable property will be set and
+  /// the runtime size will be a positive integer multiple of the base size.
+  ///
   /// This is the amount that alloca reserves for this type. For example,
   /// returns 12 or 16 for x86_fp80, depending on alignment.
-  uint64_t getTypeAllocSize(Type *Ty) const {
+  TypeSize getTypeAllocSize(Type *Ty) const {
     // Round up to the next alignment boundary.
     return alignTo(getTypeStoreSize(Ty), getABITypeAlignment(Ty));
   }
 
   /// Returns the offset in bits between successive objects of the
   /// specified type, including alignment padding; always a multiple of 8.
   ///
+  /// If Ty is a scalable vector type, the scalable property will be set and
+  /// the runtime size will be a positive integer multiple of the base size.
+  ///
   /// This is the amount that alloca reserves for this type. For example,
   /// returns 96 or 128 for x86_fp80, depending on alignment.
-  uint64_t getTypeAllocSizeInBits(Type *Ty) const {
+  TypeSize getTypeAllocSizeInBits(Type *Ty) const {
     return 8 * getTypeAllocSize(Ty);
   }
 
@@ -598,40 +615,44 @@ class StructLayout {
 
 // The implementation of this method is provided inline as it is particularly
 // well suited to constant folding when called on a specific Type subclass.
-inline uint64_t DataLayout::getTypeSizeInBits(Type *Ty) const {
+inline TypeSize DataLayout::getTypeSizeInBits(Type *Ty) const {
   assert(Ty->isSized() && "Cannot getTypeInfo() on a type that is unsized!");
   switch (Ty->getTypeID()) {
   case Type::LabelTyID:
-    return getPointerSizeInBits(0);
+    return TypeSize::Fixed(getPointerSizeInBits(0));
   case Type::PointerTyID:
-    return getPointerSizeInBits(Ty->getPointerAddressSpace());
+    return TypeSize::Fixed(getPointerSizeInBits(Ty->getPointerAddressSpace()));
   case Type::ArrayTyID: {
     ArrayType *ATy = cast<ArrayType>(Ty);
     return ATy->getNumElements() *
            getTypeAllocSizeInBits(ATy->getElementType());
   }
   case Type::StructTyID:
     // Get the layout annotation... which is lazily created on demand.
-    return getStructLayout(cast<StructType>(Ty))->getSizeInBits();
+    return TypeSize::Fixed(
+                        getStructLayout(cast<StructType>(Ty))->getSizeInBits());
   case Type::IntegerTyID:
-    return Ty->getIntegerBitWidth();
+    return TypeSize::Fixed(Ty->getIntegerBitWidth());
   case Type::HalfTyID:
-    return 16;
+    return TypeSize::Fixed(16);
   case Type::FloatTyID:
-    return 32;
+    return TypeSize::Fixed(32);
   case Type::DoubleTyID:
   case Type::X86_MMXTyID:
-    return 64;
+    return TypeSize::Fixed(64);
   case Type::PPC_FP128TyID:
   case Type::FP128TyID:
-    return 128;
+    return TypeSize::Fixed(128);
   // In memory objects this is always aligned to a higher boundary, but
   // only 80 bits contain information.
   case Type::X86_FP80TyID:
-    return 80;
+    return TypeSize::Fixed(80);
   case Type::VectorTyID: {
     VectorType *VTy = cast<VectorType>(Ty);
-    return VTy->getNumElements() * getTypeSizeInBits(VTy->getElementType());
+    auto EltCnt = VTy->getElementCount();
+    uint64_t MinBits = EltCnt.Min *
+                        getTypeSizeInBits(VTy->getElementType()).getFixedSize();
+    return TypeSize(MinBits, EltCnt.Scalable);
   }
   default:
     llvm_unreachable("DataLayout::getTypeSizeInBits(): Unsupported type");

llvm/include/llvm/IR/DerivedTypes.h

@@ -23,7 +23,7 @@
 #include "llvm/IR/Type.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/Compiler.h"
-#include "llvm/Support/ScalableSize.h"
+#include "llvm/Support/TypeSize.h"
 #include <cassert>
 #include <cstdint>
 

llvm/include/llvm/IR/InstrTypes.h

@@ -975,7 +975,7 @@ class CmpInst : public Instruction {
   static Type* makeCmpResultType(Type* opnd_type) {
     if (VectorType* vt = dyn_cast<VectorType>(opnd_type)) {
       return VectorType::get(Type::getInt1Ty(opnd_type->getContext()),
-                             vt->getNumElements());
+                             vt->getElementCount());
     }
     return Type::getInt1Ty(opnd_type->getContext());
   }

llvm/include/llvm/IR/Type.h

@@ -21,6 +21,7 @@
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/TypeSize.h"
 #include <cassert>
 #include <cstdint>
 #include <iterator>
@@ -281,12 +282,15 @@ class Type {
   /// This will return zero if the type does not have a size or is not a
   /// primitive type.
   ///
+  /// If this is a scalable vector type, the scalable property will be set and
+  /// the runtime size will be a positive integer multiple of the base size.
+  ///
   /// Note that this may not reflect the size of memory allocated for an
   /// instance of the type or the number of bytes that are written when an
   /// instance of the type is stored to memory. The DataLayout class provides
   /// additional query functions to provide this information.
   ///
-  unsigned getPrimitiveSizeInBits() const LLVM_READONLY;
+  TypeSize getPrimitiveSizeInBits() const LLVM_READONLY;
 
   /// If this is a vector type, return the getPrimitiveSizeInBits value for the
   /// element type. Otherwise return the getPrimitiveSizeInBits value for this

llvm/include/llvm/Support/MachineValueType.h

@@ -17,7 +17,7 @@
 #include "llvm/ADT/iterator_range.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/MathExtras.h"
-#include "llvm/Support/ScalableSize.h"
+#include "llvm/Support/TypeSize.h"
 #include <cassert>
 
 namespace llvm {