512-bit

From Infogalactic: the planetary knowledge core
Jump to: navigation, search


Bit
1 4 8 12 16 18 24 26 31 32 36 48 60 64 128 256 512
Application
16 32 64
Floating point precision
×½ ×1 ×2 ×4 ×8
Floating point decimal precision
32 64 128

In computer architecture, 512-bit integers, memory addresses, or other data units are those that are at most 512 bits wide. Also, 512-bit CPU and ALU architectures are those that are based on registers, address buses, or data buses of that size.

There are currently no mainstream general-purpose processors built to operate on 512-bit integers or addresses, though a number of processors do operate on 512-bit data. As of 2013, the Intel Xeon Phi has a vector processing unit with 512-bit vector registers, each one holding sixteen 32-bit elements or eight 64-bit elements, and a single instruction can operate on all these values in parallel. However, the Xeon Phi's vector processing unit does not operate on individual numbers that are 512 bits in length.[1]

Uses

References

  1. "Intel® Xeon PhiTM Coprocessor System Software Developers Guide" (PDF). Intel. November 8, 2012. Retrieved February 8, 2013.<templatestyles src="Module:Citation/CS1/styles.css"></templatestyles>
  2. "GTX 280 | Specifications". GeForce. Retrieved 2013-08-13.<templatestyles src="Module:Citation/CS1/styles.css"></templatestyles>
  3. "GTX 285 | Specifications". GeForce. Retrieved 2013-08-13.<templatestyles src="Module:Citation/CS1/styles.css"></templatestyles>
  4. "NVIDIA® Quadro® FX 5800 provides professionals with visual supercomputing from their desktops delivering results that push visualization beyond traditional 3D". Nvidia.com. Retrieved 2013-08-13.<templatestyles src="Module:Citation/CS1/styles.css"></templatestyles>