TFHE-rs
WebsiteLibrariesProduct & ServicesDevelopersSupport
0.6
0.6
  • Welcome to TFHE-rs
  • Get Started
    • What is TFHE-rs?
    • Installation
    • Quick start
    • Types & Operations
    • Benchmarks
    • Security and cryptography
  • Fundamentals
    • Configuration and key generation
    • Server key
    • Encryption
    • Computation on encrypted data
    • Decryption
    • Encrypted pseudo random values
    • Serialization/deserialization
    • Compressing ciphertexts/keys
    • Debugging
  • Guides
    • Rust configuration
    • GPU acceleration
    • Overflow detection
    • Data versioning
    • Public key encryption
    • Zero-knowledge proofs
    • Generic trait bounds
    • Parallelized PBS
    • High-level API in C
    • JS on WASM API
    • Multi-threading with Rayon crate
    • Trivial ciphertexts
    • PBS statistics
  • Tutorials
    • All tutorials
    • Homomorphic parity bit
    • Homomorphic case changing on Ascii string
    • SHA256 with Boolean API
  • References
    • API references
    • Fine-grained APIs
      • Quick start
      • Boolean
        • Operations
        • Cryptographic parameters
        • Serialization/Deserialization
      • Shortint
        • Operations
        • Cryptographic parameters
        • Serialization/Deserialization
      • Integer
        • Operations
        • Cryptographic parameters
        • Serialization/Deserialization
    • Core crypto API
      • Quick start
      • Tutorial
  • Explanations
    • TFHE deep dive
  • Developers
    • Contributing
    • Release note
    • Feature request
    • Bug report
Powered by GitBook

Libraries

  • TFHE-rs
  • Concrete
  • Concrete ML
  • fhEVM

Developers

  • Blog
  • Documentation
  • Github
  • FHE resources

Company

  • About
  • Introduction to FHE
  • Media
  • Careers
On this page

Was this helpful?

Export as PDF
  1. Guides

PBS statistics

PreviousTrivial ciphertextsNextAll tutorials

Last updated 1 year ago

Was this helpful?

This document explains how to use the PBS statistics feature in TFHE-rs' shortint API to assess the overall computational intensity in FHE applications.

The shortint API now includes a global counter to track the number of Programmable Bootstrapping (PBS) executed with the pbs-stats feature. This feature enables precise tracking of PBS executions in a circuit. It helps to estimate the overall compute intensity of FHE code using either the shortint, integer, or High-Level APIs.

To know how many PBSes were executed, call get_pbs_count. To reset the PBS count, call reset_pbs_count. You can combine two functions to understand how many PBSes were executed in each part of your code.

When combined with the , this feature allows for quick estimations during iterations on the FHE code.

Here is an example of how to use the PBS counter:

use tfhe::prelude::*;
use tfhe::*;

pub fn main() {
    // Config and key generation
    let config = ConfigBuilder::default().build();

    let (cks, sks) = generate_keys(config);

    // Encryption
    let a = FheUint32::encrypt(42u32, &cks);
    let b = FheUint32::encrypt(16u32, &cks);

    // Set the server key
    set_server_key(sks);

    // Compute and get the PBS count for the 32 bits multiplication
    let c = &a * &b;
    let mul_32_count = get_pbs_count();

    // Reset the PBS count, and get the PBS count for a 32 bits bitwise AND
    reset_pbs_count();
    let d = &a & &b;
    let and_32_count = get_pbs_count();

    // Display the result
    println!("mul_32_count: {mul_32_count}");
    println!("and_32_count: {and_32_count}");
}
debug mode