tests: koala and babybear field ops #580
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @agnxsh, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request significantly enhances the test coverage for the BabyBear and KoalaBear finite fields. It introduces new tests for core arithmetic operations (addition, subtraction, multiplication), validates field I/O, and ensures the consistency of modular squaring. These additions improve the robustness and reliability of these critical cryptographic components.
Highlights
- New Field Operation Tests: Comprehensive unit tests have been added for addition, subtraction, and multiplication operations for both BabyBear and KoalaBear finite fields.
- Field I/O Operation Tests: Tests for field input/output (marshalling) operations have been introduced for BabyBear and KoalaBear.
- Modular Squaring Consistency: Sanity checks have been extended to include BabyBear and KoalaBear, ensuring modular squaring consistency with multiplication.
- Curve Configuration Update: The testingCurve flag has been set to true for both BabyBear and KoalaBear curves to enable their use in testing environments.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
agnxsh
changed the title
There was a problem hiding this comment.
Code Review
This pull request adds a comprehensive set of tests for the KoalaBear and BabyBear fields, covering basic arithmetic operations, I/O, and sanity checks for modular squaring. The changes are well-structured and the test cases, including edge cases, are relevant. My feedback focuses on improving the maintainability of the test code by reducing duplication through helper functions and removing hardcoded magic numbers.
Comment on lines
+169
to
+402
| test "Addition mod 2^31 - 2^27 + 1": | ||
| block: | ||
| var x, y, z: Fp[BabyBear] | ||
|
|
||
| x.fromUint(80'u32) | ||
| y.fromUint(10'u32) | ||
| z.fromUint(90'u32) | ||
|
|
||
| x += y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 90'u32 | ||
|
|
||
| block: | ||
| var x, y, z: Fp[BabyBear] | ||
|
|
||
| x.fromUint(0x78000000'u32) # p-1 | ||
| y.fromUint(1'u32) | ||
| z.fromUint(0'u32) | ||
|
|
||
| x += y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 0'u32 | ||
|
|
||
| test "Substraction mod 2^31 - 2^27 + 1": | ||
| block: | ||
| var x, y, z: Fp[BabyBear] | ||
|
|
||
| x.fromUint(80'u32) | ||
| y.fromUint(10'u32) | ||
| z.fromUint(70'u32) | ||
|
|
||
| x -= y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 70'u32 | ||
|
|
||
| block: | ||
| var x, y, z: Fp[BabyBear] | ||
|
|
||
| x.fromUint(0'u32) | ||
| y.fromUint(1'u32) | ||
| z.fromUint(0x78000000'u32) # p-1 | ||
|
|
||
| x -= y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 0x78000000'u32 | ||
|
|
||
| test "Multiplication mod 2^31 - 2^27 + 1": | ||
| block: | ||
| var x, y, z, r: Fp[BabyBear] | ||
|
|
||
| x.fromUint(10'u32) | ||
| y.fromUint(10'u32) | ||
| z.fromUint(100'u32) | ||
|
|
||
| r.prod(x, y) | ||
|
|
||
| var r_bytes: array[4, byte] | ||
| r_bytes.marshal(r, cpuEndian) | ||
| let new_r = cast[uint32](r_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == r) | ||
| # Check equality when converting back to natural domain | ||
| new_r == 100'u32 | ||
|
|
||
| block: | ||
| var x, y, z, r: Fp[BabyBear] | ||
|
|
||
| x.fromUint(0x10000'u32) | ||
| y.fromUint(0x10000'u32) | ||
| z.fromUint(uint32((0x10000'u64 * 0x10000'u64) mod 0x78000001'u64)) | ||
|
|
||
| r.prod(x, y) | ||
|
|
||
| var r_bytes: array[4, byte] | ||
| r_bytes.marshal(r, cpuEndian) | ||
| let new_r = cast[uint32](r_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == r) | ||
| # Check equality when converting back to natural domain | ||
| new_r == uint32((0x10000'u64 * 0x10000'u64) mod 0x78000001'u64) | ||
|
|
||
| test "Addition mod 2^31 - 2^24 + 1": | ||
| block: | ||
| var x, y, z: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(50'u32) | ||
| y.fromUint(20'u32) | ||
| z.fromUint(70'u32) | ||
|
|
||
| x += y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 70'u32 | ||
|
|
||
| block: | ||
| var x, y, z: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(0x7f000000'u32) # p-1 | ||
| y.fromUint(1'u32) | ||
| z.fromUint(0'u32) | ||
|
|
||
| x += y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 0'u32 | ||
|
|
||
| test "Substraction mod 2^31 - 2^24 + 1": | ||
| block: | ||
| var x, y, z: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(70'u32) | ||
| y.fromUint(20'u32) | ||
| z.fromUint(50'u32) | ||
|
|
||
| x -= y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 50'u32 | ||
|
|
||
| block: | ||
| var x, y, z: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(0'u32) | ||
| y.fromUint(1'u32) | ||
| z.fromUint(0x7f000000'u32) # p-1 | ||
|
|
||
| x -= y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 0x7f000000'u32 | ||
|
|
||
| test "Multiplication mod 2^31 - 2^24 + 1": | ||
| block: | ||
| var x, y, z, r: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(12'u32) | ||
| y.fromUint(12'u32) | ||
| z.fromUint(144'u32) | ||
|
|
||
| r.prod(x, y) | ||
|
|
||
| var r_bytes: array[4, byte] | ||
| r_bytes.marshal(r, cpuEndian) | ||
| let new_r = cast[uint32](r_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == r) | ||
| # Check equality when converting back to natural domain | ||
| new_r == 144'u32 | ||
|
|
||
| block: | ||
| var x, y, z, r: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(0x10000'u32) | ||
| y.fromUint(0x20000'u32) | ||
| z.fromUint(uint32((0x10000'u64 * 0x20000'u64) mod 0x7f000001'u64)) | ||
|
|
||
| r.prod(x, y) | ||
|
|
||
| var r_bytes: array[4, byte] | ||
| r_bytes.marshal(r, cpuEndian) | ||
| let new_r = cast[uint32](r_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == r) | ||
| # Check equality when converting back to natural domain | ||
| new_r == uint32((0x10000'u64 * 0x20000'u64) mod 0x7f000001'u64) | ||
|
|
There was a problem hiding this comment.
The tests for BabyBear and KoalaBear contain a lot of duplicated code for addition, subtraction, and multiplication. This can be refactored using helper procedures to make the tests more concise and maintainable.
Here are some example helper procedures you could add:
proc testAdd[F: static Algebra](x_val, y_val, z_val: uint32) =
var x, y, z: Fp[F]
x.fromUint(x_val)
y.fromUint(y_val)
z.fromUint(z_val)
x += y
var x_bytes: array[4, byte]
x_bytes.marshal(x, cpuEndian)
let new_x = cast[uint32](x_bytes)
check:
bool(z == x)
new_x == z_val
proc testSub[F: static Algebra](x_val, y_val, z_val: uint32) =
var x, y, z: Fp[F]
x.fromUint(x_val)
y.fromUint(y_val)
z.fromUint(z_val)
x -= y
var x_bytes: array[4, byte]
x_bytes.marshal(x, cpuEndian)
let new_x = cast[uint32](x_bytes)
check:
bool(z == x)
new_x == z_val
proc testMul[F: static Algebra](x_val, y_val, z_val: uint32) =
var x, y, z, r: Fp[F]
x.fromUint(x_val)
y.fromUint(y_val)
z.fromUint(z_val)
r.prod(x, y)
var r_bytes: array[4, byte]
r_bytes.marshal(r, cpuEndian)
let new_r = cast[uint32](r_bytes)
check:
bool(z == r)
new_r == z_valWith these helpers, the tests become much simpler, for example:
test "Addition mod 2^31 - 2^27 + 1":
testAdd[BabyBear](80'u32, 10'u32, 90'u32)
testAdd[BabyBear](0x78000000'u32, 1'u32, 0'u32)
There was a problem hiding this comment.
This is a valid suggestion by Gemini
Comment on lines
+49
to
+138
| # BabyBear --------------------------------- | ||
| block: | ||
| # "Little-endian" - 0 | ||
| let x = 0'u64 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[BabyBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - 1 | ||
| let x = 1'u64 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[BabyBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - 2^15 | ||
| let x = 1'u64 shl 15 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[BabyBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - p-1 | ||
| let x = 2013265921'u64 - 1 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[BabyBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| # KoalaBear --------------------------------- | ||
| block: | ||
| # "Little-endian" - 0 | ||
| let x = 0'u64 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[KoalaBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - 1 | ||
| let x = 1'u64 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[KoalaBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - 2^15 | ||
| let x = 1'u64 shl 15 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[KoalaBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - p-1 | ||
| let x = 2130706433'u64 - 1 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[KoalaBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
There was a problem hiding this comment.
There's a lot of repeated code in the IO tests for BabyBear and KoalaBear. You could reduce this duplication by creating a helper procedure. This would make the tests more concise and easier to maintain.
Here's an example of a helper procedure:
proc checkFieldIO[F: static Algebra](value: uint64) =
let x_bytes = cast[array[8, byte]](value)
var f: Fp[F]
f.fromUint(value)
var r_bytes: array[8, byte]
marshal(r_bytes, f, littleEndian)
check: x_bytes == r_bytesThen you could refactor the test blocks like this:
# BabyBear ---------------------------------
block:
# "Little-endian" - 0
checkFieldIO[BabyBear](0'u64)
block:
# "Little-endian" - 1
checkFieldIO[BabyBear](1'u64)
# ... and so on for other test cases and KoalaBear.There was a problem hiding this comment.
This is a valid suggestion by gemini
mratsim
reviewed
Sep 6, 2025
| # ----------------------------------------------------------------------------- | ||
|
|
||
| curve BabyBear: # BabyBear field used in SNARKs and zkVMs | ||
| testingCurve: true |
There was a problem hiding this comment.
Testing curves is for fields/curves that aren't used in end-user applications like mod 101, it's unnecessary here
mratsim
requested changes
Sep 6, 2025
Comment on lines
+169
to
+402
| test "Addition mod 2^31 - 2^27 + 1": | ||
| block: | ||
| var x, y, z: Fp[BabyBear] | ||
|
|
||
| x.fromUint(80'u32) | ||
| y.fromUint(10'u32) | ||
| z.fromUint(90'u32) | ||
|
|
||
| x += y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 90'u32 | ||
|
|
||
| block: | ||
| var x, y, z: Fp[BabyBear] | ||
|
|
||
| x.fromUint(0x78000000'u32) # p-1 | ||
| y.fromUint(1'u32) | ||
| z.fromUint(0'u32) | ||
|
|
||
| x += y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 0'u32 | ||
|
|
||
| test "Substraction mod 2^31 - 2^27 + 1": | ||
| block: | ||
| var x, y, z: Fp[BabyBear] | ||
|
|
||
| x.fromUint(80'u32) | ||
| y.fromUint(10'u32) | ||
| z.fromUint(70'u32) | ||
|
|
||
| x -= y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 70'u32 | ||
|
|
||
| block: | ||
| var x, y, z: Fp[BabyBear] | ||
|
|
||
| x.fromUint(0'u32) | ||
| y.fromUint(1'u32) | ||
| z.fromUint(0x78000000'u32) # p-1 | ||
|
|
||
| x -= y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 0x78000000'u32 | ||
|
|
||
| test "Multiplication mod 2^31 - 2^27 + 1": | ||
| block: | ||
| var x, y, z, r: Fp[BabyBear] | ||
|
|
||
| x.fromUint(10'u32) | ||
| y.fromUint(10'u32) | ||
| z.fromUint(100'u32) | ||
|
|
||
| r.prod(x, y) | ||
|
|
||
| var r_bytes: array[4, byte] | ||
| r_bytes.marshal(r, cpuEndian) | ||
| let new_r = cast[uint32](r_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == r) | ||
| # Check equality when converting back to natural domain | ||
| new_r == 100'u32 | ||
|
|
||
| block: | ||
| var x, y, z, r: Fp[BabyBear] | ||
|
|
||
| x.fromUint(0x10000'u32) | ||
| y.fromUint(0x10000'u32) | ||
| z.fromUint(uint32((0x10000'u64 * 0x10000'u64) mod 0x78000001'u64)) | ||
|
|
||
| r.prod(x, y) | ||
|
|
||
| var r_bytes: array[4, byte] | ||
| r_bytes.marshal(r, cpuEndian) | ||
| let new_r = cast[uint32](r_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == r) | ||
| # Check equality when converting back to natural domain | ||
| new_r == uint32((0x10000'u64 * 0x10000'u64) mod 0x78000001'u64) | ||
|
|
||
| test "Addition mod 2^31 - 2^24 + 1": | ||
| block: | ||
| var x, y, z: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(50'u32) | ||
| y.fromUint(20'u32) | ||
| z.fromUint(70'u32) | ||
|
|
||
| x += y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 70'u32 | ||
|
|
||
| block: | ||
| var x, y, z: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(0x7f000000'u32) # p-1 | ||
| y.fromUint(1'u32) | ||
| z.fromUint(0'u32) | ||
|
|
||
| x += y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 0'u32 | ||
|
|
||
| test "Substraction mod 2^31 - 2^24 + 1": | ||
| block: | ||
| var x, y, z: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(70'u32) | ||
| y.fromUint(20'u32) | ||
| z.fromUint(50'u32) | ||
|
|
||
| x -= y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 50'u32 | ||
|
|
||
| block: | ||
| var x, y, z: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(0'u32) | ||
| y.fromUint(1'u32) | ||
| z.fromUint(0x7f000000'u32) # p-1 | ||
|
|
||
| x -= y | ||
|
|
||
| var x_bytes: array[4, byte] | ||
| x_bytes.marshal(x, cpuEndian) | ||
| let new_x = cast[uint32](x_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == x) | ||
| # Check equality when converting back to natural domain | ||
| new_x == 0x7f000000'u32 | ||
|
|
||
| test "Multiplication mod 2^31 - 2^24 + 1": | ||
| block: | ||
| var x, y, z, r: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(12'u32) | ||
| y.fromUint(12'u32) | ||
| z.fromUint(144'u32) | ||
|
|
||
| r.prod(x, y) | ||
|
|
||
| var r_bytes: array[4, byte] | ||
| r_bytes.marshal(r, cpuEndian) | ||
| let new_r = cast[uint32](r_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == r) | ||
| # Check equality when converting back to natural domain | ||
| new_r == 144'u32 | ||
|
|
||
| block: | ||
| var x, y, z, r: Fp[KoalaBear] | ||
|
|
||
| x.fromUint(0x10000'u32) | ||
| y.fromUint(0x20000'u32) | ||
| z.fromUint(uint32((0x10000'u64 * 0x20000'u64) mod 0x7f000001'u64)) | ||
|
|
||
| r.prod(x, y) | ||
|
|
||
| var r_bytes: array[4, byte] | ||
| r_bytes.marshal(r, cpuEndian) | ||
| let new_r = cast[uint32](r_bytes) | ||
|
|
||
| check: | ||
| # Check equality in the Montgomery domain | ||
| bool(z == r) | ||
| # Check equality when converting back to natural domain | ||
| new_r == uint32((0x10000'u64 * 0x20000'u64) mod 0x7f000001'u64) | ||
|
|
There was a problem hiding this comment.
This is a valid suggestion by Gemini
Comment on lines
+49
to
+138
| # BabyBear --------------------------------- | ||
| block: | ||
| # "Little-endian" - 0 | ||
| let x = 0'u64 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[BabyBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - 1 | ||
| let x = 1'u64 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[BabyBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - 2^15 | ||
| let x = 1'u64 shl 15 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[BabyBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - p-1 | ||
| let x = 2013265921'u64 - 1 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[BabyBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| # KoalaBear --------------------------------- | ||
| block: | ||
| # "Little-endian" - 0 | ||
| let x = 0'u64 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[KoalaBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - 1 | ||
| let x = 1'u64 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[KoalaBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - 2^15 | ||
| let x = 1'u64 shl 15 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[KoalaBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
||
| block: | ||
| # "Little-endian" - p-1 | ||
| let x = 2130706433'u64 - 1 | ||
| let x_bytes = cast[array[8, byte]](x) | ||
| var f: Fp[KoalaBear] | ||
| f.fromUint(x) | ||
|
|
||
| var r_bytes: array[8, byte] | ||
| marshal(r_bytes, f, littleEndian) | ||
| check: x_bytes == r_bytes | ||
|
|
There was a problem hiding this comment.
This is a valid suggestion by gemini
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Addressing #573
Consists tests for :