Видео с ютуба Peter Cordes

How to run bitwise OR on big vectors of u64 in the most performant manner?

How to run bitwise OR on big vectors of u64 in the most performant manner?
#lessing20 - Vision Menschmaschine - Vortrag Dr. Peter Cordes

#lessing20 - Vision Menschmaschine - Vortrag Dr. Peter Cordes
Why do none of the major compilers optimize this conditional store that checks if the value is al...

Why do none of the major compilers optimize this conditional store that checks if the value is al...
Is synchronization relationship necessary to avoid the duplicate invocation of a function?

Is synchronization relationship necessary to avoid the duplicate invocation of a function?
Why are functions b and f called *twice* in this code after b overwrites its return address with ...

Why are functions b and f called *twice* in this code after b overwrites its return address with ...
Why do none of the major compilers optimize this conditional move of != the value to assign?

Why do none of the major compilers optimize this conditional move of != the value to assign?
Why do compilers miss vectorization here?

Why do compilers miss vectorization here?
How to run bitwise OR on big vectors of u64 in the most performant manner?

How to run bitwise OR on big vectors of u64 in the most performant manner?
Is it necessary to call load() before compare_exchange_strong()？

Is it necessary to call load() before compare_exchange_strong()？
How to interpret the code produced by the .ascii directive in x86 assembly?

How to interpret the code produced by the .ascii directive in x86 assembly?
Fastest way to perform an atomic read in this *very* specific situation?

Fastest way to perform an atomic read in this *very* specific situation?
Using = operator on atomic variable?

Using = operator on atomic variable?
Converting u64 to f64 between 0..1

Converting u64 to f64 between 0..1
What makes numpy.sum faster than an optimized (auto-vectorized) C loop?

What makes numpy.sum faster than an optimized (auto-vectorized) C loop?