cpu
56 stories and discussions about cpu, aggregated from every source we track.
CPU, memory, OS and Tetris, all running on the gates. Zoom in and watch the signals flow.
Unlocking _everything_ on the CPU with DRAM scrambling - xoreaxeaxeax/skitter-creek-bath-salts
This story begins, as they so often do, when I noticed that my machine was behaving poorly. My Windows 10 work machine has 24 cores (48 hyper-threads) and they were 50% idle. It has 64 GB of RAM an…
VSCode Version: 1.10.2 (8076a19) OS Version: macOS Sierra 10.12.3 VS Code uses 13% CPU when focused and idle, draining battery. This is likely due to the blinking cursor rendering. I think CPU usag...
Hackers can now reverse-engineer updates or write their own custom firmware.
Serving Gemma 4 E2B q4_0 through llama.cpp on one laptop, twice: CPU-only and on a 2021-era 4 GB GTX 1650 Ti. Same GGUF, same binary, same prompts, one flag apart. The card takes decode by 4.3x, and needs only 1598 MiB to do it.
Gemma 4 E2B q4_0 served by llama.cpp on one laptop, CPU-only and on a GTX 1650 Ti, rebuilt on CUDA 13.4 and re-measured in CPU, GPU, GPU, CPU order with a temperature gate. The card takes decode by 4.14x, and run order moves the answer by about 2%.
VUPEN Security provides vulnerability management and intelligence solutions (advisories, analysis, exploits).
It's a drop in replacement, it's faster, and it's cheap. What's not to like?
In the post I will cover: Configuring an ASRock H370M-ITX/ac to allow DCI DbC debugging Using Intel System Studio and System Debugger to single-step a Coffee Lake-S i7-8700 CPU Debugging an example exploitable UEFI…
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API. - kouhxp/gutsy
Inside every modern CPU since the Intel Pentium fdiv bug, assembly instructions aren’t a one-to-one mapping to what the CPU actually does. Inside the CPU, there is a decoder that turns assemb…
You write System.out.println("Hello World"); and hit Run. Something happens. Text appears on your...
grep for meaning: filter, score and classify lines with a plain-English question. Local CPU decision model (Laya, ONNX), single Rust binary. - sfmqrb/gutcheck
Why is x86 little-endian? Why are registers called AX, BX, CX, and DX, and why DOS uses addresses in the format A000:0000? The answers are in the story of how each chip was born.
Light the led unless both switches are on.
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API. - kouhxp/gutsy
Why a sorted array processes 6x faster than unsorted data: CPU pipelines, 2-bit counters, TAGE predictors, pipeline bubbles, and writing branchless code.
We Built a Game IDE in the Browser and Lived to Brag About It Hey, we're Evolved Tech —...
The last few days I spend some time on porting the beloved game DOOM to the ZPU CPU. For you who don't know what I am talking about, DOOM wa...
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API. - kouhxp/gutsy
The 12-core Zen 3 gaming and productivity monster that never was
What Matters Today is CPU and RAM Utilization (and infra costs) tl;dr: As agents take over writing code, the cost of validating generated code becomes a primary determinant of engineering throughput. Optimizing your…
Anti-cheat systems for online multiplayer games can flag individual PC parts, which can be a problem if you're trying to find a deal on secondhand hardware.
CPU-only LLM inference engine in pure Rust — 4-bit quantized models, hand-written AVX2 kernels, speculative decoding, and a local HTTP/MCP server. No GPU, no Python runtime. - Classevelabs/rai
Someone buys a used Ryzen 7 5800X3D. “Valorant” and other Riot games won’t start with it because the previous owner was a cheater.
A reading path for CPU performance engineering, from one instruction to production inference. Primary sources only, with a runnable benchmark for every section. - usamahz/cpu-performance-engineering
The return of AMD's ambidextrous strategy?
Snap any image, screenshot, or webpage into plaintext. No GPU. No cloud. One command. - kouhxp/textsnap
A new article series will examine the CPU caches that aren't called caches, but work similarly to transparently accelerate programs.
Sampling CPU and HEAP profiler for Java featuring AsyncGetCallTrace + perf_events - async-profiler/async-profiler
Making long-running CPU intensive processes not to suck every bit of CPU time from other processes in Linux.
An open speech recognition model that runs on the same CPU engine as Needle. It transcribes seven languages, reaches the first token in 11 ms, and loads beside Needle so one binary turns a clip straight into tool calls.
Processor pipeline visualization tools are routine inside industry CPU teams, but few of them are described or released publicly. As a result, students, researchers, and other practitioners rarely see the tooling that…
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
The Hutter Prize requires no validation data, so its scores cannot be inflated by data leaks. Three entries, each running on a single CPU core, just improved its record by nearly 10%.
No sound card driver. No audio library. Just the CPU and 44100 numbers a second. - whispem/asm.fm
Snap any image, screenshot, or webpage into plaintext. No GPU. No cloud. One command. - kouhxp/textsnap
Snap any image, screenshot, or webpage into plaintext. No GPU. No cloud. One command. - kouhxp/textsnap
Demonstrating offlineisbetter models. Contribute to offlineisbetter/offlinedemo development by creating an account on GitHub.
The LEDs are connected directly to the die, which is embedded in a glass substrate.
With over 2 million cores, 1% efficiency is worth millions. See how Uber tuned Go's runtime stack to boost CPU utilization for a service by 10%.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
The LEDs are connected directly to the die, which is embedded in a glass substrate.
A clean-sheet R4000-class CPU and SGI Indigo IP20 system running unmodified IRIX 5.3 on an FPGA.
A new X meme called "Jevops" (Jevon's Law meets DevOps) took off after someone asked "Can Jev emulate a CPU?" — prompting the punchline: "the end game…