You copied the Doc URL to your clipboard.

LDRD (literal)

Load Register Dual (literal) calculates an address from the PC value and an immediate offset, loads two words from memory, and writes them to two registers. For information about memory accesses see Memory accesses.

It has encodings from the following instruction sets: A32 ( A1 ) and T32 ( T1 ) .

A1

313029282726252423222120191817161514131211109876543210
!= 1111000(1)U1(0)01111Rtimm4H1101imm4L
cond

A1

LDRD{<c>}{<q>} <Rt>, <Rt2>, <label> // (Normal form)

LDRD{<c>}{<q>} <Rt>, <Rt2>, [PC, #{+/-}<imm>] // (Alternative form) 

if Rt<0> == '1' then UNPREDICTABLE;
t = UInt(Rt);  t2 = t+1;  imm32 = ZeroExtend(imm4H:imm4L, 32);  add = (U == '1');
if t2 == 15 then UNPREDICTABLE;

CONSTRAINED UNPREDICTABLE behavior

If Rt<0> == '1', then one of the following behaviors must occur:

  • The instruction is undefined.
  • The instruction executes as NOP.
  • The instruction executes with the additional decode: t<0> = '0';.
  • The instruction executes with the additional decode: t2 = t;.
  • The instruction executes as described, with no change to its behavior and no additional side-effects. This does not apply when Rt == '1111'.

If P == '0' || W == '1', then one of the following behaviors must occur:

  • The instruction is undefined.
  • The instruction executes as NOP.
  • The instruction executes as if P == 1 and W == 0.'

T1

15141312111098765432101514131211109876543210
1110100PU1W11111RtRt2imm8

T1 (!(P == 0 && W == 0))

LDRD{<c>}{<q>} <Rt>, <Rt2>, <label> // (Normal form)

LDRD{<c>}{<q>} <Rt>, <Rt2>, [PC, #{+/-}<imm>] // (Alternative form) 

if P == '0' && W == '0' then SEE "Related encodings";
t = UInt(Rt);  t2 = UInt(Rt2);
imm32 = ZeroExtend(imm8:'00', 32);  add = (U == '1');
if t == 15 || t2 == 15 || t == t2 then UNPREDICTABLE; // Armv8-A removes UNPREDICTABLE for R13
if W == '1' then UNPREDICTABLE;

CONSTRAINED UNPREDICTABLE behavior

If t == t2, then one of the following behaviors must occur:

  • The instruction is undefined.
  • The instruction executes as NOP.
  • The load instruction executes but the destination register takes an unknown value.

If W == '1', then one of the following behaviors must occur:

  • The instruction is undefined.
  • The instruction executes as NOP.
  • The instruction executes without writeback of the base address.
  • The instruction uses post-indexed addressing when P == '0' and uses pre-indexed addressing otherwise. The instruction is handled as described in Using R15.

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

Related encodings: Load/Store dual, Load/Store-Exclusive, Load-Acquire/Store-Release, table branch.

Assembler Symbols

<c>

See Standard assembler syntax fields.

<q>

See Standard assembler syntax fields.

<Rt>

For encoding A1: is the first general-purpose register to be transferred, encoded in the "Rt" field. This register must be even-numbered and not R14.

For encoding T1: is the first general-purpose register to be transferred, encoded in the "Rt" field.

<Rt2>

For encoding A1: is the second general-purpose register to be transferred. This register must be <R(t+1)>.

For encoding T1: is the second general-purpose register to be transferred, encoded in the "Rt2" field.

<label>

For encoding A1: the label of the literal data item that is to be loaded into <Rt>. The assembler calculates the required value of the offset from the Align(PC, 4) value of the instruction to this label. Any value in the range -255 to 255 is permitted.

If the offset is zero or positive, imm32 is equal to the offset and add == TRUE, encoded as U == 1. If the offset is negative, imm32 is equal to minus the offset and add == FALSE, encoded as U == 0.

For encoding T1: the label of the literal data item that is to be loaded into <Rt>. The assembler calculates the required value of the offset from the Align(PC, 4) value of the instruction to this label. Permitted values of the offset are multiples of 4 in the range -1020 to 1020.

If the offset is zero or positive, imm32 is equal to the offset and add == TRUE, encoded as U == 1.

If the offset is negative, imm32 is equal to minus the offset and add == FALSE, encoded as U == 0.

+/- Specifies the offset is added to or subtracted from the base register, defaulting to + if omitted and encoded in U:
U +/-
0 -
1 +
<imm>

For encoding A1: is the 8-bit unsigned immediate byte offset, in the range 0 to 255, defaulting to 0 if omitted, and encoded in the "imm4H:imm4L" field.

For encoding T1: is the optional 8-bit unsigned immediate byte offset, in the range 0 to 255, defaulting to 0 and encoded in the "imm8" field.

The alternative syntax permits the addition or subtraction of the offset and the immediate offset to be specified separately, including permitting a subtraction of 0 that cannot be specified using the normal syntax. For more information, see Use of labels in UAL instruction syntax.

Operation

if ConditionPassed() then
    EncodingSpecificOperations();
    address = if add then (Align(PC,4) + imm32) else (Align(PC,4) - imm32);
    if address == Align(address, 8) then
        data = MemA[address,8];
        if BigEndian() then
            R[t] = data<63:32>;
            R[t2] = data<31:0>;
        else
            R[t] = data<31:0>;
            R[t2] = data<63:32>;
    else
        R[t] = MemA[address,4];
        R[t2] = MemA[address+4,4];

Operational information

If CPSR.DIT is 1, the timing of this instruction is insensitive to the value of the data being loaded or stored.

Previous Next