llvm.add

This op has support for result type inference.

Operands

• lhs - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer

Results

• res - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer

llvm.addrspacecast

Operands

• arg - Single, anonymous/composite constraint, LLVM pointer type or LLVM dialect-compatible vector of LLVM pointer type

Results

• res - Single, anonymous/composite constraint, LLVM pointer type or LLVM dialect-compatible vector of LLVM pointer type

llvm.alloca

Attributes

• alignment - Optional, I64Attr, 64-bit signless integer attribute
• elem_type - Single, TypeAttr, any type attribute
• inalloca - Optional, UnitAttr, unit attribute

Operands

• arraySize - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_AnyPointer, LLVM pointer type

llvm.and

This op has support for result type inference.

Operands

• lhs - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer

Results

• res - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer

llvm.ashr

This op has support for result type inference.

Attributes

• isExact - Optional, UnitAttr, unit attribute

Operands

• lhs - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer

Results

• res - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer

llvm.atomicrmw

This op has support for result type inference.

Attributes

• bin_op - Single, AtomicBinOp, llvm.atomicrmw binary operations
• ordering - Single, AtomicOrdering, Atomic ordering for LLVM's memory model
• syncscope - Optional, StrAttr, string attribute
• alignment - Optional, I64Attr, 64-bit signless integer attribute
• volatile_ - Optional, UnitAttr, unit attribute
• access_groups - Optional, LLVM_AccessGroupArrayAttr, LLVM dialect access group metadata array
• alias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• noalias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• tbaa - Optional, LLVM_TBAATagArrayAttr, LLVM dialect TBAA tag metadata array

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type
• val - Single, LLVM_AtomicRMWType, floating point LLVM type or LLVM pointer type or signless integer or LLVM dialect-compatible fixed-length vector type

Results

• res - Single, LLVM_AtomicRMWType, floating point LLVM type or LLVM pointer type or signless integer or LLVM dialect-compatible fixed-length vector type

llvm.bitcast

Operands

• arg - Single, LLVM_AnyNonAggregate, LLVM-compatible non-aggregate type

Results

• res - Single, LLVM_AnyNonAggregate, LLVM-compatible non-aggregate type

llvm.blockaddress

llvm.blocktag

llvm.br

Attributes

• loop_annotation - Optional, LoopAnnotationAttr,

Operands

• destOperands - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type

llvm.call - Call to an LLVM function.

Attributes

• var_callee_type - Optional, anonymous/composite constraint, type attribute of LLVM function type
• callee - Optional, FlatSymbolRefAttr, flat symbol reference attribute
• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags
• CConv - Single, CConv, LLVM Calling Convention specification
• TailCallKind - Single, TailCallKind, LLVM Calling Convention specification
• memory_effects - Optional, LLVM_MemoryEffectsAttr,
• convergent - Optional, UnitAttr, unit attribute
• no_unwind - Optional, UnitAttr, unit attribute
• will_return - Optional, UnitAttr, unit attribute
• op_bundle_sizes - Single, DenseI32ArrayAttr, i32 dense array attribute
• op_bundle_tags - Optional, ArrayAttr, array attribute
• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• no_inline - Optional, UnitAttr, unit attribute
• always_inline - Optional, UnitAttr, unit attribute
• inline_hint - Optional, UnitAttr, unit attribute
• access_groups - Optional, LLVM_AccessGroupArrayAttr, LLVM dialect access group metadata array
• alias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• noalias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• tbaa - Optional, LLVM_TBAATagArrayAttr, LLVM dialect TBAA tag metadata array

Operands

• callee_operands - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type
• op_bundle_operands - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type

Results

• result - Optional, LLVM_Type, LLVM dialect-compatible type

Description

In LLVM IR, functions may return either 0 or 1 value. LLVM IR dialect implements this behavior by providing a variadic call operation for 0- and 1-result functions. Even though MLIR supports multi-result functions, LLVM IR dialect disallows them.

The call instruction supports both direct and indirect calls. Direct calls start with a function name (@-prefixed) and indirect calls start with an SSA value (%-prefixed). The direct callee, if present, is stored as a function attribute callee. For indirect calls, the callee is of !llvm.ptr type and is stored as the first value in callee_operands. If and only if the callee is a variadic function, the var_callee_type attribute must carry the variadic LLVM function type. The trailing type list contains the optional indirect callee type and the MLIR function type, which differs from the LLVM function type that uses an explicit void type to model functions that do not return a value.

If this operatin has the no_inline attribute, then this specific function call will never be inlined. The opposite behavior will occur if the call has always_inline attribute. The inline_hint attribute indicates that it is desirable to inline this function call.

Examples:

// Direct call without arguments and with one result.
%0 = llvm.call @foo() : () -> (f32)

// Direct call with arguments and without a result.
llvm.call @bar(%0) : (f32) -> ()

// Indirect call with an argument and without a result.
%1 = llvm.mlir.addressof @foo : !llvm.ptr
llvm.call %1(%0) : !llvm.ptr, (f32) -> ()

// Direct variadic call.
llvm.call @printf(%0, %1) vararg(!llvm.func<i32 (ptr, ...)>) : (!llvm.ptr, i32) -> i32

// Indirect variadic call
llvm.call %1(%0) vararg(!llvm.func<void (...)>) : !llvm.ptr, (i32) -> ()

llvm.call_intrinsic - Call to an LLVM intrinsic function.

Attributes

• intrin - Single, StrAttr, string attribute
• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags
• op_bundle_sizes - Single, DenseI32ArrayAttr, i32 dense array attribute
• op_bundle_tags - Optional, ArrayAttr, array attribute
• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes

Operands

• args - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type
• op_bundle_operands - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type

Results

• results - Optional, LLVM_Type, LLVM dialect-compatible type

Description

Call the specified llvm intrinsic. If the intrinsic is overloaded, use the MLIR function type of this op to determine which intrinsic to call.

llvm.cmpxchg

This op has support for result type inference.

Attributes

• success_ordering - Single, AtomicOrdering, Atomic ordering for LLVM's memory model
• failure_ordering - Single, AtomicOrdering, Atomic ordering for LLVM's memory model
• syncscope - Optional, StrAttr, string attribute
• alignment - Optional, I64Attr, 64-bit signless integer attribute
• weak - Optional, UnitAttr, unit attribute
• volatile_ - Optional, UnitAttr, unit attribute
• access_groups - Optional, LLVM_AccessGroupArrayAttr, LLVM dialect access group metadata array
• alias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• noalias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• tbaa - Optional, LLVM_TBAATagArrayAttr, LLVM dialect TBAA tag metadata array

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type
• cmp - Single, LLVM_AtomicCmpXchgType, signless integer or LLVM pointer type
• val - Single, LLVM_AtomicCmpXchgType, signless integer or LLVM pointer type

Results

• res - Single, LLVM_AnyStruct, LLVM structure type

llvm.comdat

llvm.comdat_selector

llvm.cond_br

Attributes

• branch_weights - Optional, DenseI32ArrayAttr, i32 dense array attribute
• loop_annotation - Optional, LoopAnnotationAttr,

Operands

• condition - Single, I1, 1-bit signless integer
• trueDestOperands - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type
• falseDestOperands - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type

llvm.dso_local_equivalent

llvm.extractelement - Extract an element from an LLVM vector.

This op has support for result type inference.

Operands

• vector - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• position - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.extractvalue - Extract a value from an LLVM struct.

Attributes

• position - Single, DenseI64ArrayAttr, i64 dense array attribute

Operands

• container - Single, LLVM_AnyAggregate, LLVM aggregate type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.fadd

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• lhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• rhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

llvm.fcmp

This op has support for result type inference.

Attributes

• predicate - Single, FCmpPredicate, llvm.fcmp comparison predicate
• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• lhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• rhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, 1-bit signless integer or LLVM dialect-compatible vector of 1-bit signless integer

llvm.fdiv

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• lhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• rhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

llvm.fence

llvm.fmul

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• lhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• rhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

llvm.fneg

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• operand - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

llvm.fpext

Operands

• arg - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

llvm.fptosi

Operands

• arg - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer

llvm.fptoui

Operands

• arg - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer

llvm.fptrunc

Operands

• arg - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

llvm.freeze

This op has support for result type inference.

Operands

• val - Single, LLVM_Type, LLVM dialect-compatible type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.frem

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• lhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• rhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

llvm.fsub

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• lhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• rhs - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

llvm.func

llvm.getelementptr

Attributes

• rawConstantIndices - Single, DenseI32ArrayAttr, i32 dense array attribute
• elem_type - Single, TypeAttr, any type attribute

Operands

• base - Single, anonymous/composite constraint, LLVM pointer type or LLVM dialect-compatible vector of LLVM pointer type
• dynamicIndices - Variadic, anonymous/composite constraint, variadic of signless integer or LLVM dialect-compatible vector of signless integer

Results

• res - Single, anonymous/composite constraint, LLVM pointer type or LLVM dialect-compatible vector of LLVM pointer type

Description

This operation mirrors LLVM IRs 'getelementptr' operation that is used to perform pointer arithmetic.

Like in LLVM IR, it is possible to use both constants as well as SSA values as indices. In the case of indexing within a structure, it is required to either use constant indices directly, or supply a constant SSA value.

The no-wrap flags can be used to specify the low-level pointer arithmetic overflow behavior that LLVM uses after lowering the operation to LLVM IR. Valid options include 'inbounds' (pointer arithmetic must be within object bounds), 'nusw' (no unsigned signed wrap), and 'nuw' (no unsigned wrap). Note that 'inbounds' implies 'nusw' which is ensured by the enum definition. The flags can be set individually or in combination.

Examples:

// GEP with an SSA value offset
%0 = llvm.getelementptr %1[%2] : (!llvm.ptr, i64) -> !llvm.ptr, f32

// GEP with a constant offset and the inbounds attribute set
%0 = llvm.getelementptr inbounds %1[3] : (!llvm.ptr) -> !llvm.ptr, f32

// GEP with constant offsets into a structure
%0 = llvm.getelementptr %1[0, 1]
   : (!llvm.ptr) -> !llvm.ptr, !llvm.struct<(i32, f32)>

llvm.icmp

This op has support for result type inference.

Attributes

• predicate - Single, ICmpPredicate, llvm.icmp comparison predicate

Operands

• lhs - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer or LLVM pointer type or LLVM dialect-compatible vector of LLVM pointer type
• rhs - Single, anonymous/composite constraint, signless integer or LLVM dialect-compatible vector of signless integer or LLVM pointer type or LLVM dialect-compatible vector of LLVM pointer type

Results

• res - Single, anonymous/composite constraint, 1-bit signless integer or LLVM dialect-compatible vector of 1-bit signless integer

llvm.indirectbr

Attributes

• indbr_operand_segments - Single, DenseI32ArrayAttr, i32 dense array attribute

Operands

• addr - Single, LLVM_AnyPointer, LLVM pointer type
• succOperands - Variadic, AnyType, variadic of any type

Description

Transfer control flow to address in $addr. A list of possible target blocks in $successors can be provided and maybe used as a hint in LLVM:

...
llvm.func @g(...
  %dest = llvm.blockaddress <function = @g, tag = <id = 0>> : !llvm.ptr
  llvm.indirectbr %dest : !llvm.ptr, [
    ^head
  ]
^head:
  llvm.blocktag <id = 0>
  llvm.return %arg0 : i32
  ...

It also supports a list of operands that can be passed to a target block:

  llvm.indirectbr %dest : !llvm.ptr, [
    ^head(%arg0 : i32),
    ^tail(%arg1, %arg0 : i32, i32)
  ]
^head(%r0 : i32):
  llvm.return %r0 : i32
^tail(%r1 : i32, %r2 : i32):
  ...

llvm.inline_asm

Attributes

• asm_string - Single, StrAttr, string attribute
• constraints - Single, StrAttr, string attribute
• has_side_effects - Optional, UnitAttr, unit attribute
• is_align_stack - Optional, UnitAttr, unit attribute
• tail_call_kind - Single, TailCallKind, LLVM Calling Convention specification
• asm_dialect - Optional, AsmATTOrIntel, ATT (0) or Intel (1) asm dialect
• operand_attrs - Optional, ArrayAttr, array attribute

Operands

• operands - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type

Results

• res - Optional, LLVM_Type, LLVM dialect-compatible type

Description

The InlineAsmOp mirrors the underlying LLVM semantics with a notable exception: the embedded asm_string is not allowed to define or reference any symbol or any global variable: only the operands of the op may be read, written, or referenced. Attempting to define or reference any symbol or any global behavior is considered undefined behavior at this time. If tail_call_kind is used, the operation behaves like the specified tail call kind. The musttail kind it's not available for this operation, since it isn't supported by LLVM's inline asm.

llvm.insertelement - Insert an element into an LLVM vector.

This op has support for result type inference.

Operands

• vector - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• value - Single, LLVM_PrimitiveType, primitive LLVM type
• position - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

llvm.insertvalue - Insert a value into an LLVM struct.

This op has support for result type inference.

Attributes

• position - Single, DenseI64ArrayAttr, i64 dense array attribute

Operands

• container - Single, LLVM_AnyAggregate, LLVM aggregate type
• value - Single, LLVM_PrimitiveType, primitive LLVM type

Results

• res - Single, LLVM_AnyAggregate, LLVM aggregate type

llvm.intr.abs

Attributes

• is_int_min_poison - Single, I1Attr, 1-bit signless integer attribute

Operands

• in - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.acos

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.annotation

This op has support for result type inference.

Operands

• integer - Single, AnySignlessInteger, signless integer
• annotation - Single, LLVM_AnyPointer, LLVM pointer type
• fileName - Single, LLVM_AnyPointer, LLVM pointer type
• line - Single, I32, 32-bit signless integer

Results

• res - Single, AnySignlessInteger, signless integer

llvm.intr.asin

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.assume

Attributes

• op_bundle_sizes - Single, DenseI32ArrayAttr, i32 dense array attribute
• op_bundle_tags - Optional, ArrayAttr, array attribute

Operands

• cond - Single, I1, 1-bit signless integer
• op_bundle_operands - Variadic, LLVM_Type, variadic of LLVM dialect-compatible type

llvm.intr.atan2

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.atan

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.bitreverse

This op has support for result type inference.

Operands

• in - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.bswap

This op has support for result type inference.

Operands

• in - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.ceil

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.copysign

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.coro.align

llvm.intr.coro.begin

Operands

• token - Single, LLVM_TokenType, LLVM token type
• mem - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.coro.end

Operands

• handle - Single, LLVM_AnyPointer, LLVM pointer type
• unwind - Single, I1, 1-bit signless integer
• retvals - Single, LLVM_TokenType, LLVM token type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.coro.free

Operands

• id - Single, LLVM_TokenType, LLVM token type
• handle - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.coro.id

Operands

• align - Single, I32, 32-bit signless integer
• promise - Single, LLVM_AnyPointer, LLVM pointer type
• coroaddr - Single, LLVM_AnyPointer, LLVM pointer type
• fnaddrs - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.coro.promise

Operands

• handle - Single, LLVM_AnyPointer, LLVM pointer type
• align - Single, I32, 32-bit signless integer
• from - Single, I1, 1-bit signless integer

Results

• res - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.coro.resume

Operands

• handle - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.coro.save

Operands

• handle - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.coro.size

llvm.intr.coro.suspend

Operands

• save - Single, LLVM_TokenType, LLVM token type
• final - Single, I1, 1-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.cos

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.cosh

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.ctlz

This op has support for result type inference.

Attributes

• is_zero_poison - Single, I1Attr, 1-bit signless integer attribute

Operands

• in - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.ctpop

This op has support for result type inference.

Operands

• in - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.cttz

This op has support for result type inference.

Attributes

• is_zero_poison - Single, I1Attr, 1-bit signless integer attribute

Operands

• in - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.dbg.declare - Describes how the address relates to a source language variable.

Attributes

• varInfo - Single, LLVM_DILocalVariableAttr,
• locationExpr - Single, LLVM_DIExpressionAttr,

Operands

• addr - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.dbg.label

llvm.intr.dbg.value - Describes how the value relates to a source language variable.

Attributes

• varInfo - Single, LLVM_DILocalVariableAttr,
• locationExpr - Single, LLVM_DIExpressionAttr,

Operands

• value - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.debugtrap

llvm.intr.eh.typeid.for

Operands

• type_info - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.exp2

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.exp10

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.exp

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.expect

This op has support for result type inference.

Operands

• val - Single, AnySignlessInteger, signless integer
• expected - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.expect.with.probability

This op has support for result type inference.

Attributes

• prob - Single, F64Attr, 64-bit float attribute

Operands

• val - Single, AnySignlessInteger, signless integer
• expected - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.experimental.constrained.fpext

Attributes

• fpExceptionBehavior - Single, FPExceptionBehaviorAttr, LLVM Exception Behavior

Operands

• arg_0 - Single, LLVM_Type, LLVM dialect-compatible type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.experimental.constrained.fptrunc

Attributes

• roundingmode - Single, ValidRoundingModeAttr, LLVM Rounding Mode whose minimum value is 0
• fpExceptionBehavior - Single, FPExceptionBehaviorAttr, LLVM Exception Behavior

Operands

• arg_0 - Single, LLVM_Type, LLVM dialect-compatible type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.experimental.constrained.sitofp

Attributes

• roundingmode - Single, ValidRoundingModeAttr, LLVM Rounding Mode whose minimum value is 0
• fpExceptionBehavior - Single, FPExceptionBehaviorAttr, LLVM Exception Behavior

Operands

• arg_0 - Single, LLVM_Type, LLVM dialect-compatible type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.experimental.constrained.uitofp

Attributes

• roundingmode - Single, ValidRoundingModeAttr, LLVM Rounding Mode whose minimum value is 0
• fpExceptionBehavior - Single, FPExceptionBehaviorAttr, LLVM Exception Behavior

Operands

• arg_0 - Single, LLVM_Type, LLVM dialect-compatible type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.experimental.noalias.scope.decl

llvm.intr.experimental.vp.strided.load

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type
• stride - Single, AnySignlessInteger, signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.experimental.vp.strided.store

Operands

• val - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• ptr - Single, LLVM_AnyPointer, LLVM pointer type
• stride - Single, AnySignlessInteger, signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

llvm.intr.fabs

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.floor

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.fma

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• c - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.fmuladd

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• c - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.frexp

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• val - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.fshl

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• c - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.fshr

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• c - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.get.active.lane.mask

Operands

• base - Single, AnySignlessInteger, signless integer
• n - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.invariant.end

Attributes

• size - Single, I64Attr, 64-bit signless integer attribute

Operands

• start - Single, LLVM_DefaultPointer, LLVM pointer in address space 0
• ptr - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.invariant.start

This op has support for result type inference.

Attributes

• size - Single, I64Attr, 64-bit signless integer attribute

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_DefaultPointer, LLVM pointer in address space 0

llvm.intr.is.constant

This op has support for result type inference.

Operands

• val - Single, LLVM_Type, LLVM dialect-compatible type

Results

• res - Single, I1, 1-bit signless integer

llvm.intr.is.fpclass

Attributes

• bit - Single, I32Attr, 32-bit signless integer attribute

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.launder.invariant.group

This op has support for result type inference.

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.ldexp

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• val - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• power - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.lifetime.end

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.lifetime.start

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.llrint

Operands

• val - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.llround

Operands

• val - Single, LLVM_AnyFloat, floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.log2

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.log10

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.log

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.lrint

Operands

• val - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.lround

Operands

• val - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.masked.compressstore

Attributes

• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes

Operands

• value - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• ptr - Single, LLVM_AnyPointer, LLVM pointer type
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer

llvm.intr.masked.expandload

Attributes

• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• passthru - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.masked.gather

Attributes

• alignment - Single, I32Attr, 32-bit signless integer attribute

Operands

• ptrs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of LLVM pointer type
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• pass_thru - Variadic, LLVM_AnyVector, variadic of LLVM dialect-compatible vector type

Results

• res - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

llvm.intr.masked.load

Attributes

• alignment - Single, I32Attr, 32-bit signless integer attribute
• nontemporal - Optional, UnitAttr, unit attribute

Operands

• data - Single, LLVM_AnyPointer, LLVM pointer type
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• pass_thru - Optional, LLVM_AnyVector, LLVM dialect-compatible vector type

Results

• res - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

llvm.intr.masked.scatter

Attributes

• alignment - Single, I32Attr, 32-bit signless integer attribute

Operands

• value - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• ptrs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of LLVM pointer type
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer

llvm.intr.masked.store

Attributes

• alignment - Single, I32Attr, 32-bit signless integer attribute

Operands

• value - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• data - Single, LLVM_AnyPointer, LLVM pointer type
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer

llvm.intr.matrix.column.major.load

Attributes

• isVolatile - Single, I1Attr, 1-bit signless integer attribute
• rows - Single, I32Attr, 32-bit signless integer attribute
• columns - Single, I32Attr, 32-bit signless integer attribute

Operands

• data - Single, LLVM_AnyPointer, LLVM pointer type
• stride - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

llvm.intr.matrix.column.major.store

Attributes

• isVolatile - Single, I1Attr, 1-bit signless integer attribute
• rows - Single, I32Attr, 32-bit signless integer attribute
• columns - Single, I32Attr, 32-bit signless integer attribute

Operands

• matrix - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• data - Single, LLVM_AnyPointer, LLVM pointer type
• stride - Single, AnySignlessInteger, signless integer

llvm.intr.matrix.multiply

Attributes

• lhs_rows - Single, I32Attr, 32-bit signless integer attribute
• lhs_columns - Single, I32Attr, 32-bit signless integer attribute
• rhs_columns - Single, I32Attr, 32-bit signless integer attribute

Operands

• lhs - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• rhs - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

Results

• res - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

llvm.intr.matrix.transpose

Attributes

• rows - Single, I32Attr, 32-bit signless integer attribute
• columns - Single, I32Attr, 32-bit signless integer attribute

Operands

• matrix - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

Results

• res - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

llvm.intr.maximum

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.maxnum

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.memcpy

Attributes

• isVolatile - Single, I1Attr, 1-bit signless integer attribute
• access_groups - Optional, LLVM_AccessGroupArrayAttr, LLVM dialect access group metadata array
• alias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• noalias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• tbaa - Optional, LLVM_TBAATagArrayAttr, LLVM dialect TBAA tag metadata array
• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes

Operands

• dst - Single, LLVM_AnyPointer, LLVM pointer type
• src - Single, LLVM_AnyPointer, LLVM pointer type
• len - Single, AnySignlessInteger, signless integer

llvm.intr.memcpy.inline

Attributes

• len - Single, APIntAttr, arbitrary integer attribute
• isVolatile - Single, I1Attr, 1-bit signless integer attribute
• access_groups - Optional, LLVM_AccessGroupArrayAttr, LLVM dialect access group metadata array
• alias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• noalias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• tbaa - Optional, LLVM_TBAATagArrayAttr, LLVM dialect TBAA tag metadata array
• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes

Operands

• dst - Single, LLVM_AnyPointer, LLVM pointer type
• src - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.memmove

Attributes

• isVolatile - Single, I1Attr, 1-bit signless integer attribute
• access_groups - Optional, LLVM_AccessGroupArrayAttr, LLVM dialect access group metadata array
• alias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• noalias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• tbaa - Optional, LLVM_TBAATagArrayAttr, LLVM dialect TBAA tag metadata array
• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes

Operands

• dst - Single, LLVM_AnyPointer, LLVM pointer type
• src - Single, LLVM_AnyPointer, LLVM pointer type
• len - Single, AnySignlessInteger, signless integer

llvm.intr.memset

Attributes

• isVolatile - Single, I1Attr, 1-bit signless integer attribute
• access_groups - Optional, LLVM_AccessGroupArrayAttr, LLVM dialect access group metadata array
• alias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• noalias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• tbaa - Optional, LLVM_TBAATagArrayAttr, LLVM dialect TBAA tag metadata array
• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes

Operands

• dst - Single, LLVM_AnyPointer, LLVM pointer type
• val - Single, I8, 8-bit signless integer
• len - Single, AnySignlessInteger, signless integer

llvm.intr.memset.inline

Attributes

• len - Single, APIntAttr, arbitrary integer attribute
• isVolatile - Single, I1Attr, 1-bit signless integer attribute
• access_groups - Optional, LLVM_AccessGroupArrayAttr, LLVM dialect access group metadata array
• alias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• noalias_scopes - Optional, LLVM_AliasScopeArrayAttr, LLVM dialect alias scope array
• tbaa - Optional, LLVM_TBAATagArrayAttr, LLVM dialect TBAA tag metadata array
• arg_attrs - Optional, DictArrayAttr, Array of dictionary attributes
• res_attrs - Optional, DictArrayAttr, Array of dictionary attributes

Operands

• dst - Single, LLVM_AnyPointer, LLVM pointer type
• val - Single, I8, 8-bit signless integer

llvm.intr.minimum

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.minnum

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.nearbyint

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.pow

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• a - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• b - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.powi

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• val - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type
• power - Single, AnySignlessInteger, signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.prefetch

Attributes

• rw - Single, I32Attr, 32-bit signless integer attribute
• hint - Single, I32Attr, 32-bit signless integer attribute
• cache - Single, I32Attr, 32-bit signless integer attribute

Operands

• addr - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.ptr.annotation

This op has support for result type inference.

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type
• annotation - Single, LLVM_AnyPointer, LLVM pointer type
• fileName - Single, LLVM_AnyPointer, LLVM pointer type
• line - Single, I32, 32-bit signless integer
• attr - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.ptrmask

This op has support for result type inference.

Operands

• ptr - Single, anonymous/composite constraint, LLVM pointer type or LLVM dialect-compatible vector of LLVM pointer type
• mask - Single, anonymous/composite constraint, integer or LLVM dialect-compatible vector of integer

Results

• res - Single, anonymous/composite constraint, LLVM pointer type or LLVM dialect-compatible vector of LLVM pointer type

llvm.intr.rint

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.round

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.roundeven

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.sadd.sat

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.sadd.with.overflow

Operands

• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.sin

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.sincos

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• val - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.sinh

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.smax

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.smin

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.smul.with.overflow

Operands

• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.sqrt

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.ssa.copy

This op has support for result type inference.

Operands

• operand - Single, AnyType, any type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.sshl.sat

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.ssub.sat

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.ssub.with.overflow

Operands

• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.stackrestore

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.stacksave

llvm.intr.stepvector

llvm.intr.strip.invariant.group

This op has support for result type inference.

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.tan

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.tanh

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.threadlocal.address

Operands

• global - Single, LLVM_AnyPointer, LLVM pointer type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.trap

llvm.intr.trunc

This op has support for result type inference.

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, floating point LLVM type or LLVM dialect-compatible vector of floating point LLVM type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.uadd.sat

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.uadd.with.overflow

Operands

• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.ubsantrap

llvm.intr.umax

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.umin

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.umul.with.overflow

Operands

• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.ushl.sat

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.usub.sat

This op has support for result type inference.

Operands

• a - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• b - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.usub.with.overflow

Operands

• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8
• anonymous - Single, anonymous/composite constraint, of ranks 1scalable vector of 16-bit float or bfloat16 type values of length 8

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vacopy - Copies the current argument position from src_list to dest_list.

Operands

• dest_list - Single, LLVM_AnyPointer, LLVM pointer type
• src_list - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.vaend - Destroys arg_list, which has been initialized by intr.vastart or intr.vacopy.

Operands

• arg_list - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.var.annotation

Operands

• val - Single, LLVM_AnyPointer, LLVM pointer type
• annotation - Single, LLVM_AnyPointer, LLVM pointer type
• fileName - Single, LLVM_AnyPointer, LLVM pointer type
• line - Single, I32, 32-bit signless integer
• attr - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.vastart - Initializes arg_list for subsequent variadic argument extractions.

Operands

• arg_list - Single, LLVM_AnyPointer, LLVM pointer type

llvm.intr.vector.deinterleave2

Operands

• vec - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.extract

Attributes

• pos - Single, I64Attr, 64-bit signless integer attribute

Operands

• srcvec - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

Results

• res - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

llvm.intr.vector.insert

This op has support for result type inference.

Attributes

• pos - Single, I64Attr, 64-bit signless integer attribute

Operands

• dstvec - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• srcvec - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

Results

• res - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

llvm.intr.vector.interleave2

Operands

• vec1 - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• vec2 - Single, LLVM_AnyVector, LLVM dialect-compatible vector type

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.add

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.and

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.fadd

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• start_value - Single, AnyFloat, floating-point
• input - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.fmax

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.fmaximum

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.fmin

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.fminimum

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.fmul

Attributes

• fastmathFlags - Single, LLVM_FastmathFlagsAttr, LLVM fastmath flags

Operands

• start_value - Single, AnyFloat, floating-point
• input - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.mul

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.or

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.smax

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.smin

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.umax

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.umin

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vector.reduce.xor

Operands

• in - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.add

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.and

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.ashr

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fadd

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fdiv

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fma

Operands

• op1 - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• op2 - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• op3 - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fmul

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fmuladd

Operands

• op1 - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• op2 - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• op3 - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fneg

Operands

• op - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fpext

Operands

• src - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fptosi

Operands

• src - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fptoui

Operands

• src - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fptrunc

Operands

• src - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.frem

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.fsub

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.inttoptr

Operands

• src - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.load

Operands

• ptr - Single, LLVM_AnyPointer, LLVM pointer type
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.lshr

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.merge

Operands

• cond - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• true_val - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• false_val - Single, LLVM_AnyVector, LLVM dialect-compatible vector type
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.mul

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.or

Operands

• lhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• rhs - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.ptrtoint

Operands

• src - Single, anonymous/composite constraint, LLVM dialect-compatible vector of LLVM pointer type
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.reduce.add

Operands

• satrt_value - Single, AnySignlessInteger, signless integer
• val - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.reduce.and

Operands

• satrt_value - Single, AnySignlessInteger, signless integer
• val - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.reduce.fadd

Operands

• satrt_value - Single, AnyFloat, floating-point
• val - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.reduce.fmax

Operands

• satrt_value - Single, AnyFloat, floating-point
• val - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.reduce.fmin

Operands

• satrt_value - Single, AnyFloat, floating-point
• val - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.reduce.fmul

Operands

• satrt_value - Single, AnyFloat, floating-point
• val - Single, anonymous/composite constraint, LLVM dialect-compatible vector of floating-point
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer

Results

• res - Single, LLVM_Type, LLVM dialect-compatible type

llvm.intr.vp.reduce.mul

Operands

• satrt_value - Single, AnySignlessInteger, signless integer
• val - Single, anonymous/composite constraint, LLVM dialect-compatible vector of signless integer
• mask - Single, anonymous/composite constraint, LLVM dialect-compatible vector of 1-bit signless integer
• evl - Single, I32, 32-bit signless integer