No description, website, or topics provided.
C++ Python Other
Switch branches/tags
Nothing to show
Clone or download
ondrasej Improved the accuracy of the x86-64 instruction parser and instruction
- REX.W and operand size override prefix encoding specifications are now
  three-state: required/not allowed/ignored. Modified the data
  structures + the instruction parsing/matching utilities to reflect
  this new structure.
- the NP prefix from the encoding specifications in SDM is now used to
  determine the state of the prefixed mentioned above.
- segment override and address size override prefixes now work also with
  VEX encoding.
- repeated legacy prefixes now do not cause errors in the parser.
- fixed matching of addressing modes for the case of 'load effective
  address' addressing.
Latest commit b0be1b9 Jul 6, 2018


Google's EXEgesis project aims to improve code generation in compilers, via:

  1. Providing machine-readable lists of instructions for hardware vendors and microarchitectures.
  2. Inferring latencies and µOps scheduling for each instruction/microarchitecture pair.
  3. Providing tools for debugging the performance of code based on this data.

For a high-level overview of our efforts, see the slides for a tech talk about EXEgesis (July 2017).


This repository provides a set of tools for extracting data about instructions and latencies from canonical sources and converting them into machine-readable form. Some require parsing PDF files; others are more straightforward.

When latencies and µOps scheduling are not available in the documentation, we auto generate benchmarks to measure them.

The output data is available in the form of a Protocol Buffer message.

It includes:

  • A textual description. e.g. Add with carry imm8 to AL.
  • The raw encoding. e.g. 14 ib and equivalent LLVM mnemonic. e.g. ADC8i8
  • Per-microarchitecture instruction latencies. e.g. min_latency: 2, max_latency: 2
  • Per-microarchitecture instruction schedulings. e.g. Port 0 or 1 or 5 or 6
    • This identifies the execution units on which the µOps can be scheduled.
    • For example, here is the description of Intel Haswell Microarchitecture, it contains 7 ports, the Add with carry imm8 to AL instruction above can execute on ports 0, 1, 5 or 6.

What's Next

  • Intel x86-64 - done
  • IBM POWER - underway
  • ARM Cortex - underway

Get Involved

We welcome patches -- see CONTRIBUTING for more information on how to submit a patch.