LD1ROB (scalar plus scalar)

Contiguous load and replicate thirty-two bytes (scalar index)

Load thirty-two contiguous bytes to elements of a 256-bit (octaword) vector from the memory address generated by a 64-bit scalar base address and scalar index which is added to the base address.

Inactive elements will not cause a read from Device memory or signal a fault, and are set to zero.

The resulting 256-bit vector is then replicated to fill the destination vector. The instruction requires that the Effective SVE vector length is at least 256 bits.

Only the first thirty-two predicate elements are used and higher numbered predicate elements are ignored.

ID_AA64ZFR0_EL1.F64MM indicates whether this instruction is implemented.

This instruction is illegal when executed in Streaming SVE mode, unless FEAT_SME_FA64 is implemented and enabled.

SVE
(FEAT_F64MM)

313029282726252423222120191817161514131211109876543210
10100100001Rm000PgRnZt
msz<1>msz<0>ssz

LD1ROB { <Zt>.B }, <Pg>/Z, [<Xn|SP>, <Xm>]

if !IsFeatureImplemented(FEAT_SVE) || !IsFeatureImplemented(FEAT_F64MM) then UNDEFINED; if Rm == '11111' then UNDEFINED; constant integer t = UInt(Zt); constant integer n = UInt(Rn); constant integer m = UInt(Rm); constant integer g = UInt(Pg); constant integer esize = 8;

Assembler Symbols

<Zt>

Is the name of the scalable vector register to be transferred, encoded in the "Zt" field.

<Pg>

Is the name of the governing scalable predicate register P0-P7, encoded in the "Pg" field.

<Xn|SP>

Is the 64-bit name of the general-purpose base register or stack pointer, encoded in the "Rn" field.

<Xm>

Is the 64-bit name of the general-purpose offset register, encoded in the "Rm" field.

Operation

CheckNonStreamingSVEEnabled(); constant integer VL = CurrentVL; constant integer PL = VL DIV 8; if VL < 256 then UNDEFINED; constant integer elements = 256 DIV esize; bits(64) base; constant bits(PL) mask = P[g, PL]; // low bits only bits(64) offset; bits(64) addr; bits(256) result; constant integer mbytes = esize DIV 8; constant boolean contiguous = TRUE; constant boolean nontemporal = FALSE; constant boolean tagchecked = TRUE; constant AccessDescriptor accdesc = CreateAccDescSVE(MemOp_LOAD, nontemporal, contiguous, tagchecked); if !AnyActiveElement(mask, esize) then if n == 31 && ConstrainUnpredictableBool(Unpredictable_CHECKSPNONEACTIVE) then CheckSPAlignment(); else if n == 31 then CheckSPAlignment(); base = if n == 31 then SP[] else X[n, 64]; offset = X[m, 64]; addr = AddressAdd(base, UInt(offset) * mbytes, accdesc); for e = 0 to elements-1 if ActivePredicateElement(mask, e, esize) then Elem[result, e, esize] = Mem[addr, mbytes, accdesc]; else Elem[result, e, esize] = Zeros(esize); addr = AddressIncrement(addr, mbytes, accdesc); Z[t, VL] = ZeroExtend(Replicate(result, VL DIV 256), VL);

Operational information

If FEAT_SVE2 is implemented or FEAT_SME is implemented, then if PSTATE.DIT is 1, the timing of this instruction is insensitive to the value of the data being loaded or stored when its governing predicate register contains the same value for each execution.


Internal version only: aarchmrs v2024-03_relA, pseudocode v2024-03_rel, sve v2024-03_rel ; Build timestamp: 2024-03-26T09:45

Copyright © 2010-2024 Arm Limited or its affiliates. All rights reserved. This document is Non-Confidential.