double precision

(redirected from Double-precision)
Also found in: Acronyms.

double precision

[¦dəb·əl prə′sizh·ən]
(computer science)
The use of two computer words to represent a double-length number.

double precision

Using two computer words instead of one to hold a number used for calculations, thus allowing twice as large a number for more arithmetic precision. Contrast with single precision.
References in periodicals archive ?
When decoding the format-independent set of test vectors from Coonen [1984] into double-precision representation, the intersection with the battery of hexadecimal double-precision vectors from UCBTEST is rather large.
The Intel Xeon Phi 3100 family will offer more than 1000 Gigaflops (1 TFlops) double-precision performance, support for up to 6GB memory at 240GB/sec bandwidth, and a series of reliability features including memory error correction codes (ECC).
The system will offer a theoretical peak performance in half-precision floating point operations (a critical measure in the AI field) of 550 petaflops(1), and 37 petaflops of double-precision floating point operation performance, a conventional measure in simulation and other fields.
It offers 1,011 gigaflops of peak double-precision performance, 30MB of cache and memory capacity of 8GB.
In some cases, even double-precision fixed-point math may suffice.
Whereas no test set for decimal [equivalence] binary conversion is included in Coonen [1984], tables of decimal numbers are available [Tydeman 1996] which require a lot more than 53 bits to achieve correct rounding to double-precision binary representation.
The MPC7400 supplements AltiVec with a more powerful floating point unit, which is fully pipelined for double-precision operations, not just the single precision pipelined by the G3, and there is also an internal memory bus that is 128 bits wide, twice that of the G3.
The first presentation of the first silicon of "Knights Corner" co-processor showed that Intel architecture is capable of delivering more than 1 TFLOPs of double precision floating point performance (as measured by the Double-precision, General Matrix-Matrix multiplication benchmark -- DGEMM*).
3GHz processor with four 32-bit RISC processors plus an embedded double-precision floating-point processor, 16MB of user program memory and a large range of communications interfaces.
Due to the unique compute density of the new platform, only eight standard computer cabinets are required to expand Lomonosov, with each one providing peak performance of 100 teraFLOPS in double-precision operations.
Graphics processors lead in their ability to deliver several teraflops of single-precision and roughly half a teraflop of double-precision performance while consuming around 200 watts of power (between 185 and 225 watts).