Login
Roast topics
Find topics
Find it!
From:
The LLVM Project Blog
(Uncensored)
subscribe
GSoC 2025: Bfloat16 in LLVM libc - The LLVM Project Blog
https://blog.llvm.org/posts/2025-09-10-bfloat16-in-llvm-libc/
links
backlinks
Tagged with:
math
gsoc
c++23
libc
Roast topics
Find topics
Roast it!
Introduction BFloat16 is a 16-bit floating-point format, introduced by Google and standardized in C++23 as std::bfloat16_t. It uses 1 sign bit, 8 exponent bits (the same as float), and 7 mantissa bits.