Intel ADX
Intel ADX (Multi-Precision Add-Carry Instruction Extensions) is an extension by Intel to the x86 instruction set architecture for arbitrary-precision arithmetic. It was first supported in the Broadwell microarchitecture.[1][2]
New instructions
The instruction set extension contains just two new instructions, though MULX from BMI2 is also considered part the large integer arithmetic support.[3]
Both instructions are more efficient variants of the existing ADC instruction, with the difference being the two new instruction each only affect one flag, where ADC as a signed addition may set both overflow and carry flag, and as an old-style x86 instruction also reset the rest of the CPU flags. Having two versions with different flags means two chains of additions with carry can be calculated in parallel.[3]
| Instruction | Description |
|---|---|
ADCX
|
Adds two unsigned integers plus carry, with the carry read from the carry flag and if necessary set there. Does not affect other flags than carry. |
ADOX
|
Adds two unsigned integers plus carry, with the carry read from there overflow flag and if necessary set there. Does not affect other flags than overflow. |
References
- ^ "Intel Software Development Emulator". software.intel.com. July 23, 2013. Retrieved October 16, 2013.
- ^ Intel Architecture Instruction Set Extensions Programming Reference (Document number 319433-013B) // Intel, July 2012, Chapter 9: Additional new instructions
- ^ a b "New Instructions Supporting Large Integer Arithmetic on Intel®Architecture Processors" (PDF). Intel. Retrieved 2 January 2015.
External links
- Intel Architecture Instruction Set Extensions Programming Reference (PDF). Intel. 2013. Retrieved 2013-09-10.
{{cite book}}: Unknown parameter|month=ignored (help) - "New Instructions Supporting Large Integer Arithmetic on Intel® Architecture Processors" (PDF).
 | This microcomputer- or microprocessor-related article is a stub. You can help Wikipedia by expanding it. |