key concepts in cuda
key concepts Warps: In CUDA, a warp is a fundamental execution unit in the GPU. It represents a group of threads that are executed together in a SIMD (Single Instruction, Multiple Data) fas…
Read article
Explore
cpp key workds
decltypedecltype is a keyword that is used to obtain the type of an expression or an entity friendIn C++, the friend keyword is used to grant non-member functions or other classes access to…
Read articlecpp generics
genericsvariadic template parameter macrosexamples __cplusplus macro is a predefined macro in C++ that is used to indicate the version of the C++ standard being used by the compiler. The va…
Read articlecpp std
snprintfsnprintf is a function that formats a string and writes the resulting characters to a character array. str: A pointer to the destination buffer where the resulting string is stored.…
Read articlegoldilocks field
properties\( p = \phi^2 - \phi + 1\)\( \epsilon = \phi -1\) Goldilocks Additionlet \( a = a_0 + a_1 \cdot \phi, b = b_0 + b_1 \cdot \phi\) (c, carry) = a + b; if carry = 0 && c > p, result …
Read articleinline ptx assembly in cuda
introductionPTX, a low-level parallel thread execution virtual machine and instruction set architecture (ISA). PTX exposes the GPU as a data-parallel computing device.The PTX Instruction Se…
Read articlecpp types
Conversion Operator
Read articleplonky2 code analysis
introductionthis post is a source code analysis of https://github.com/0xPolygonZero/plonky2 0. fieldthe lde in proving stage is conducted on extension field 1. Config1.1 CircuitConfigthe de…
Read articlestark 101
trace and low degree extensionthe objective is to develop a STARK prover for the FibonacciSq sequence over a finite field. The FibonacciSq sequence is defined by the recurrence relation\[ a…
Read articleunderstanding plonk
introductionPLONK, standing for the unwieldy quasi-backronym “Permutations over Lagrange-bases for Oecumenical Noninteractive arguments of Knowledge”. PLONK still requires a “universal and …
Read article