This is a collection of Intel®’ IA32® Software Developer's Manuals (URL of the day) and AMD' AMD64 Architecture Programmer's Manual together with the related specifications, application notes, white papers, and change logs. The collection aims to keep all available revisions. It was originally created by Michal Necasek, see OS/2 Museum.

If you have a public document, related to the IA32® specifications and missing from the collection, please mail it to me. The content of this URL and all sub-ULRs is available for convenient bulk download by rsync x86docs password "" (empty).

LDMIB, LDMED -- AArch32

LDMIB, LDMED

Load Multiple Increment Before (Empty Descending) loads multiple registers from consecutive memory locations using an address from a base register. The consecutive memory locations start just above this address, and the address of the last of those locations can optionally be written back to the base register.

The lowest-numbered register is loaded from the lowest memory address, through to the highest-numbered register from the highest memory address. See also Encoding of lists of general-purpose registers and the PC.

Armv8.2 permits the deprecation of some Load Multiple ordering behaviors in AArch32 state, for more information see FEAT_LSMAOC. The registers loaded can include the PC, causing a branch to a loaded address. This is an interworking branch, see Pseudocode description of operations on the AArch32 general-purpose registers and the PC. Related system instructions are LDM (User registers) and LDM (exception return).

A1

313029282726252423222120191817161514131211109876543210
!= 1111100110W1Rnregister_list
condPUopL

Encoding

LDMIB{<c>}{<q>} <Rn>{!}, <registers> // (Preferred syntax)

LDMED{<c>}{<q>} <Rn>{!}, <registers> // (Alternate syntax, Empty Descending stack)

Decode for this encoding

let n : integer = UInt(Rn); let registers : bits(16) = register_list; let wback : boolean = (W == '1'); if n == 15 || BitCount(registers) < 1 then UnpredictableProcedure(); end; if wback && registers[n] == '1' then UnpredictableProcedure(); end;

CONSTRAINED UNPREDICTABLE behavior

If BitCount(registers) < 1, then one of the following behaviors must occur:

If wback && registers<n> == '1', then one of the following behaviors must occur:

For more information about the CONSTRAINED UNPREDICTABLE behavior of this instruction, see Architectural Constraints on UNPREDICTABLE behaviors.

Assembler Symbols

<c>

See Standard assembler syntax fields.

<q>

See Standard assembler syntax fields.

<Rn>

Is the general-purpose base register, encoded in the "Rn" field.

!

The address adjusted by the size of the data loaded is written back to the base register. If specified, it is encoded in the "W" field as 1, otherwise this field defaults to 0.

<registers>

Is a list of one or more registers to be loaded, separated by commas and surrounded by { and }.

The PC can be in the list.

Arm deprecates using these instructions with both the LR and the PC in the list.

Operation

if ConditionPassed() then EncodingSpecificOperations(); var address : bits(32) = R(n) + 4; var data : bits(32); for i = 0 to 14 do if registers[i] == '1' then if i != n then R(i) = MemS{32}(address); else data = MemS{32}(address); end; address = address + 4; end; end; if registers[15] == '1' then LoadWritePC(MemS{32}(address)); end; if wback && registers[n] == '1' then R(n) = ARBITRARY : bits(32); end; if wback && registers[n] == '0' then R(n) = R(n) + 4*BitCount(registers); end; if !wback && registers[n] == '1' then R(n) = data; end; end;

Operational information

This instruction is a data-independent-time instruction as described in About the DIT bit.


2026-03_rel 2026-03-26 20:48:11

Copyright © 2010-2026 Arm Limited or its affiliates. All rights reserved. This document is Non-Confidential.