Search all intrinsics
SIMD ISAReturn TypeNameArgumentsInstruction Group
Neonpoly8x8x4_tvld4_dup_p8(poly8_t const * ptr)Load / Stride
Description
Load single 4-element structure and Replicate to all lanes of four registers. This instruction loads a 4-element structure from memory and replicates the structure to all the lanes of the four SIMD&FP registers.
Results
Vt4.8B result.val[3]Vt3.8B result.val[2]Vt2.8B result.val[1]Vt.8B result.val[0]
This intrinsic compiles to the following instructions:

LD4R {Vt.8B - Vt4.8B},[Xn]

Argument Preparation
ptr register: Xn
Architectures
v7, A32, A64

Operation

if HaveMTE2Ext() then
    SetTagCheckedInstruction(tag_checked);

CheckFPAdvSIMDEnabled64();

bits(64) address;
bits(64) offs;
bits(128) rval;
bits(esize) element;
constant integer ebytes = esize DIV 8;

if n == 31 then
    CheckSPAlignment();
    address = SP[];
else
    address = X[n];

offs = Zeros();
if replicate then
    // load and replicate to all elements
    for s = 0 to selem-1
        element = Mem[address + offs, ebytes, AccType_VEC];
        // replicate to fill 128- or 64-bit register
        V[t] = Replicate(element, datasize DIV esize);
        offs = offs + ebytes;
        t = (t + 1) MOD 32;
else
    // load/store one element per register
    for s = 0 to selem-1
        rval = V[t];
        if memop == MemOp_LOAD then
            // insert into one lane of 128-bit register
            Elem[rval, index, esize] = Mem[address + offs, ebytes, AccType_VEC];
            V[t] = rval;
        else // memop == MemOp_STORE
            // extract from one lane of 128-bit register
            Mem[address + offs, ebytes, AccType_VEC] = Elem[rval, index, esize];
        offs = offs + ebytes;
        t = (t + 1) MOD 32;

if wback then
    if m != 31 then
        offs = X[m];
    if n == 31 then
        SP[] = address + offs;
    else
        X[n] = address + offs;