Neon Intrinsics

Neon intrinsics are function calls that the compiler replaces with an appropriate Neon instruction or sequence of Neon instructions. Intrinsics provide almost as much control as writing assembly language, but leave the allocation of registers to the compiler, so that developers can focus on the algorithms. It can also perform instruction scheduling to remove pipeline stalls for the specified target processor. This leads to more maintainable source code than using assembly language. Neon Intrinsics is supported by Arm Compilers, gcc and LLVM. The Neon Programmer's Guide for Armv8-A provides more information about intrinsics and Neon programming in general.

Here are two introduction guides on using Neon Intrinsics with Android:

Click on the intrinsic name to display more information about the intrinsic. To search for an intrinsic, enter text in the search box, then click the button.

For more information about the concepts and usage related to the Neon intrinsics, see the Arm C Language Extensions documentation.


Unsigned Multiply-Add Long (vector). This instruction multiplies the vector elements in the lower or upper half of the first source SIMD&FP register by the corresponding vector elements of the second source SIMD&FP register, and accumulates the results with the vector elements of the destination SIMD&FP register. The destination vector elements are twice as long as the elements that are multiplied.

A64 Instruction

            UMLAL Vd.8H,Vn.8B,Vm.8B    

Argument Preparation

a → Vd.8H 
b → Vn.8B
c → Vm.8B


Vd.8H → result


bits(datasize) operand1 = Vpart[n, part];
bits(datasize) operand2 = Vpart[m, part];
bits(2*datasize) operand3 = V[d];
bits(2*datasize) result;
integer element1;
integer element2;
bits(2*esize) product;
bits(2*esize) accum;

for e = 0 to elements-1
    element1 = Int(Elem[operand1, e, esize], unsigned);
    element2 = Int(Elem[operand2, e, esize], unsigned);
    product = (element1*element2)<2*esize-1:0>;
    if sub_op then
        accum = Elem[operand3, e, 2*esize] - product;
        accum = Elem[operand3, e, 2*esize] + product;
    Elem[result, e, 2*esize] = accum;

V[d] = result;

Supported architectures