x86
PulseAugur coverage of x86 — every cluster mentioning x86 across labs, papers, and developer communities, ranked by signal.
11 day(s) with sentiment data
-
vLLM Releases v0.27.1 with CI Adjustments
The v0.27.1 release of vLLM, a high-throughput serving engine for large language models, includes a change to its continuous integration process. This update specifically limits the Arctic import check to x86 test image…
-
Original Intel 8080 Rubylith Mask Seeks Restoration
An individual who claims to own the original engineering copy of the Intel 8080 Rubylith mask is seeking a restorer for the artifact. This handcrafted mask, used in the pre-digital era of chip design, details the layout…
-
Triton driver brings DirectX 11 support to QEMU emulator
A new driver named Triton has been developed to bring DirectX 11 compatibility to QEMU, a versatile emulator and virtualizer. This driver aims to enable broader graphics support across various operating systems, includi…
-
Researcher creates 'hall of shame' for slowest x86 CPU instructions
A hardware researcher named Christopher Domas has initiated a project to identify the slowest single x86 instruction, creating a leaderboard to rank these performance bottlenecks. The current top offender is the `fxrsto…
-
llama.cpp PRs boost Intel GPU and x86 CPU performance
A pull request for the llama.cpp project has introduced significant performance improvements for quantized KV cache decoding. One change targets Intel Battlemage GPUs, utilizing a SYCL kernel switch to achieve up to 169…
-
PS3 Emulation on ARM Achieves Major Speed Boosts After 6 Months of Optimization
Emulation of PlayStation 3 games on ARM processors has seen significant speed improvements after six months of optimization work. A new video details the progress made in closing the performance gap between ARM and x86 …
-
Intel licenses Atom-class x86 cores to RosaicLabs startup
Intel has reportedly licensed its Atom-class x86 processor cores to a new startup named RosaicLabs. This marks the first time in a decade that Intel has licensed its cores, granting RosaicLabs access to register-transfe…
-
Microsoft releases VibeVoice-ASR-BitNet for real-time CPU inference
Microsoft has released VibeVoice-ASR-BitNet, a highly compressed automatic speech recognition model designed for real-time inference on edge CPUs without requiring a GPU. This model achieves significant speedups over ex…
-
Project NOMAD aims to build a resilient, offline Library of Alexandria
Project NOMAD aims to create a modern-day Library of Alexandria, housing scholars and knowledge on an x86 system with a local LLM. This initiative is envisioned as a resilient archive for the future, with a focus on sel…
-
Enthusiast powers PC with 192 AA batteries, boots Hannah Montana Linux
A PC enthusiast, known as Uwoslab, has successfully powered a desktop computer using 192 AA alkaline batteries. This setup, comprising three wooden boxes each holding 64 batteries, was wired in series and parallel to pr…
-
New preprints detail processor security tool and federated learning efficiency
A new preprint on arXiv introduces Malcostume, a tool designed to automatically extract leakage contracts from black-box x86 and ARM processors. Separately, another unreviewed preprint proposes a novel two-layer secret …
-
TSMC boosts Arizona AI chip hub investment to $265B amid surging demand
TSMC is significantly expanding its Arizona manufacturing campus with an additional $100 billion investment, bringing the total to $265 billion. This expansion is driven by the surging demand for AI infrastructure, part…
-
Inspur Information launches AI infrastructure for 40,000+ agents and multi-model collaboration
Inspur Information has introduced new AI infrastructure solutions designed to support the growing demands of AI agents and complex multi-model collaborations. The company unveiled a CPU-native liquid-cooled server cabin…
-
mistral.rs v0.9.0 achieves 1.8x faster CPU decode speeds than llama.cpp
The mistral.rs project has released version 0.9.0, demonstrating significant performance improvements in CPU decoding for large language models. Benchmarks show that mistral.rs can be up to 1.8 times faster than llama.c…
-
AI adoption accelerates Arm server use, challenging x86 chips
Artificial intelligence is driving increased adoption of Arm-based servers, which offer superior efficiency and scalability. This trend is putting pressure on traditional x86 chips in data center environments.
-
Intel and AMD collaborate on new x86 AI instruction set
Intel and AMD have collaborated to develop and release the specifications for "AI Compute Extensions" (ACE), a new set of AI-specific matrix operation instructions for x86 processors. This initiative, developed through …
-
Intel and AMD collaborate on ACE CPU extensions for efficient AI on x86
Intel and AMD have collaborated on new ACE CPU extensions designed to enhance AI workloads on x86 processors. These extensions leverage existing AVX10 registers but incorporate dedicated silicon for matrix multiplicatio…
-
Intel and AMD Unveil ACE CPU Extensions for Efficient AI Workloads
Intel and AMD have jointly released the AI Compute Extensions (ACE) specification, designed to enhance AI workload performance on x86 processors. These extensions introduce dedicated silicon for matrix multiplication, a…
-
Intel's 8086 CPU launched, founding the dominant x86 architecture
On June 8, 1978, Intel launched the 16-bit 8086 microprocessor, establishing the x86 architecture that still dominates personal computing. This chip was developed as a temporary solution while Intel's more ambitious 32-…
-
NVIDIA Edge AI Hardware Lacks Energy Attribution Capabilities
A new paper highlights a significant energy observability gap in NVIDIA's flagship edge AI hardware, specifically the GB10 SoC found in ASUS Ascent GX10 systems. The research demonstrates that current hardware lacks the…