#amd #arm #intel #Pi4J #riscv #x64 #x86
https://foojay.io/today/java-on-single-board-computers-x86-vs-arm-vs-risc-v/
go-simd-softmax
Is a Go-oriented SIMD/avx softmax implementation with optimisations in amd64 / x64 assembler.
Up to 3.5x faster than equivalent function written using stdlib only. See benchmarks.
https://github.com/ha1tch/go-simd-softmax?tab=readme-ov-file#simd-accelerated-softmax
#go #foss #softmax #asm #assembler #x86_64 #x64 #amd64 #assembly #golang
TIL about `asmrepl`, a REPL (in ruby) for x64 assembly
#aarch64 builds of @binjr are coming, and I have proof!
But the amusing fact(*) about that screenshot, is that it shows an aarch64 Linux Java Virtual Machine running on an x64 Windows host and ultimately rendering in a native window on the host's desktop.
It's not very fast, obviously, but given the amount of layers it has to go through, it is kind of mind blowing that it actually works pretty much seamlessly:Windows 11 ➡️ WSL ➡️ Debian bookworm ➡️ qemu ➡️ OpenJDK-24 JVM ➡️ JavaFX ➡️ GTK3 ➡️ X11 ➡️ RemoteDesktop ➡️ GDI ➡️ Windows.
And why would you want to do that, I hear you ask? Well, that's the neat part: you don't! (Seriously it's pretty daft. Don't do that).
(*) It has been brought to my attention before that my personal notion of what constitutes an "amusing fact" isn't wildly shared amongst the general public. You have been warned.
NativeJIT: A C++ expression –> x64 JIT
https://github.com/BitFunnel/NativeJIT
#HackerNews #NativeJIT #C++ #JIT #x64 #Compiler #Programming #GitHub