widendv

From Mill Computing Wiki
Jump to: navigation, search
speculable  exu stream  exu block  compute phase   operation   in the decimal floating point value domain  

native on: Decimal8 Decimal16

Double the scalar width of the elements of a decimal float vector.

Decimal floats can be 4-16 byte wide. Although the 4 byte format is a pure interchange format and no floating arithmetic operations are available for them.

Vector widen operations always produce two result vectors to accomodate the widening of maximum size vectors. The first result vector then contains the widened values of the lower half of the operand, and the second result the upper.



widendv(d v) → d r0, d r1

operands: like Widenvd DD:2D2D


Core In Slots Latencies
Decimal8 E0 E1 2 2
Decimal16 E0 E1 2 2


Instruction Set, alphabetical, Instruction Set by Category, Instruction Set, sortable, filterable