Page 378 - ARM 64 Bit Assembly Language

368 Chapter 10

10.7.5 Estimate reciprocals

In general, multiplication is faster than division. In many cases of vector arithmetic, it is faster
to calculate reciprocals and use multiplication. These instructions perform the initial estimates
of the reciprocal values:

recpe Reciprocal Estimate, and
rsqrte Reciprocal Square Root Estimate.

These work on floating point and unsigned fixed point vectors. The estimates from this
instruction are accurate to within about eight bits. If higher accuracy is desired, then the
Newton-Raphson method can be used to improve the initial estimates. For more information,
see the Reciprocal Step instructions on page 369.

10.7.5.1 Syntax

u<op> Vd.Ta, Vn.Ta
f<op> Vd.Tb, Vn.Tb

• <op> is either recpe or rsqrte.
• Ta must be 2s or 4s.
• Tb must be 2s, 4s,or 2d.

10.7.5.2 Operations

Name Effect Description
(u|f)recpe n ← # of elements Find an approximate reciprocal of
for 0 ≤ i< n) do each element in a vector.
Vd[i]←≈ (1 ÷ Vm[i])
end for
(u|f)rsqrte n ← # of elements Find an approximate reciprocal
for 0 ≤ i< n) do square root of each element in a
√
Vd[i]←≈ (1 ÷ Vm[i]) vector.
end for

10.7.5.3 Examples

1 urecpe v1.4s,v6.4s // Get initial reciprocal estimates
2 frecpe v4.2d,v5.2d // Get initial reciprocal estimates