# cpu

The central processing unit is the primary functional component of a computer, executing program instructions and coordinating computing operations.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Agentic AI puts the CPU back at center stage as Dell and AMD chase every watt

DevFeed: [Agentic AI puts the CPU back at center stage as Dell and AMD chase every watt](<https://devfeed.tech/articles/agentic-ai-puts-the-cpu-back-at-center-stage-as-dell-and-amd-chase-every-watt-140918.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/18/business-development-agentic-ai-era-puts-cpus-first-dellatsc26/>)

Author: Jonathan Anthony

Published: 2026-11-18T17:06:36Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>), [dell](<https://devfeed.tech/topics/dell.md>), [clean energy data centers](<https://devfeed.tech/topics/clean-energy-data-centers.md>)

Tags: [accelerated-computing](<https://devfeed.tech/tags/accelerated-computing.md>), [accelerators](<https://devfeed.tech/tags/accelerators.md>), [advanced-micro-devices](<https://devfeed.tech/tags/advanced-micro-devices.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-workloads](<https://devfeed.tech/tags/agentic-workloads.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-data-centers](<https://devfeed.tech/tags/ai-data-centers.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-supercomputers](<https://devfeed.tech/tags/ai-supercomputers.md>), [amd](<https://devfeed.tech/tags/amd.md>), [amd-epyc-9006-processor](<https://devfeed.tech/tags/amd-epyc-9006-processor.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [business](<https://devfeed.tech/tags/business.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cube-event-coverage](<https://devfeed.tech/tags/cube-event-coverage.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [david-schmidt](<https://devfeed.tech/tags/david-schmidt.md>), [dell](<https://devfeed.tech/tags/dell.md>), [dell-poweredge-r9825](<https://devfeed.tech/tags/dell-poweredge-r9825.md>), [dellatsc26](<https://devfeed.tech/tags/dellatsc26.md>), [demand](<https://devfeed.tech/tags/demand.md>), [development](<https://devfeed.tech/tags/development.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [epyc](<https://devfeed.tech/tags/epyc.md>), [gemma-allen](<https://devfeed.tech/tags/gemma-allen.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [graphics-processing-units](<https://devfeed.tech/tags/graphics-processing-units.md>), [hpc-infrastructure](<https://devfeed.tech/tags/hpc-infrastructure.md>), [john-furrier](<https://devfeed.tech/tags/john-furrier.md>), [nasdaq-amd](<https://devfeed.tech/tags/nasdaq-amd.md>), [news](<https://devfeed.tech/tags/news.md>), [nyse-dell](<https://devfeed.tech/tags/nyse-dell.md>), [power](<https://devfeed.tech/tags/power.md>), [poweredge](<https://devfeed.tech/tags/poweredge.md>), [r9825](<https://devfeed.tech/tags/r9825.md>), [sc26](<https://devfeed.tech/tags/sc26.md>), [sc26-2026](<https://devfeed.tech/tags/sc26-2026.md>), [sc26eventpage](<https://devfeed.tech/tags/sc26eventpage.md>), [scott-tease](<https://devfeed.tech/tags/scott-tease.md>), [server](<https://devfeed.tech/tags/server.md>), [supercomputing](<https://devfeed.tech/tags/supercomputing.md>), [sustainable-computing](<https://devfeed.tech/tags/sustainable-computing.md>), [thecube](<https://devfeed.tech/tags/thecube.md>)

### AI overview

The article reports that agentic AI could increase demand for CPUs alongside GPUs: CPUs feed accelerator data and support the speed and concurrency agent workloads require. Dell and AMD say data center power limits make efficiency central. Dell's PowerEdge R9825, a 3U server using AMD EPYC 9006 processors, is designed to improve power and cooling efficiency; Dell says one system can replace 13 legacy machines while reducing cooling power by 80%. The companies see reclaimed power as a way to support more compute, though the excerpt offers no independent verification of these figures.

### Source excerpt

Agentic AI is rewriting the business development playbook for chipmakers and server builders. Graphics processing units still grab the headlines, but as supercomputing and AI converge, the next wave of demand is landing on central processing units that must fit inside the power budgets data centers already have. The shift has been building for years. [...] The post Agentic AI puts the CPU back at center stage as Dell and AMD chase every watt appeared first on SiliconANGLE.

## How Two First-Timers Created the World's Most Popular Processor | Steve Furber

DevFeed: [How Two First-Timers Created the World's Most Popular Processor | Steve Furber](<https://devfeed.tech/articles/how-two-first-timers-created-the-world-s-most-popular-processor-steve-furber-135928.md>)

Original publisher: [Read original article](<https://www.developing.dev/p/e075-steve-furber>)

Author: Ryan Peterman

Published: 2026-11-16T14:05:41Z

Content type: article

Language: en

Sources: [The Developing Dev](<https://devfeed.tech/sources/the-developing-dev.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [Arm](<https://devfeed.tech/topics/arm.md>)

Tags: [arm](<https://devfeed.tech/tags/arm.md>), [chip](<https://devfeed.tech/tags/chip.md>), [created](<https://devfeed.tech/tags/created.md>), [designers](<https://devfeed.tech/tags/designers.md>), [first](<https://devfeed.tech/tags/first.md>), [popular](<https://devfeed.tech/tags/popular.md>), [processor](<https://devfeed.tech/tags/processor.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

Steve Furber describes how he and Sophie Wilson helped create ARM at Acorn despite having no prior processor-design experience. After testing 16-bit processors that handled real-time interrupts poorly and underused memory bandwidth, they drew on Berkeley and Stanford RISC research. Wilson designed the instruction set; Furber translated it into a microarchitecture and modeled it in 808 lines of BBC BASIC. Acorn's chip team turned that reference model into silicon about 18 months after work began. ARM's simple, pipelined, load-store design enabled faster memory use and a small, low-power processor. The interview also distinguishes the detailed microarchitecture model, useful for checking hardware behavior, from faster instruction-level emulators used to test larger programs and instruction functions. Furber credits Acorn's prior hardware experience and confidence, while noting that RISC's advantages were not widely adopted by industry for years.

### Source excerpt

In 1984, two first-time chip designers, Steve Furber and Sophie Wilson, created what would become the most popular processor in the world (ARM).

## Anatomy of a CPU: How Every Part of a Modern CPU Works Together

DevFeed: [Anatomy of a CPU: How Every Part of a Modern CPU Works Together](<https://devfeed.tech/articles/anatomy-of-a-cpu-how-every-part-of-a-modern-cpu-works-together-134713.md>)

Original publisher: [Read original article](<https://www.techspot.com/article/2000-anatomy-cpu/>)

Author: Julio Franco

Published: 2026-11-16T06:18:00Z

Content type: article

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [CPU Cache](<https://devfeed.tech/topics/cpu-cache.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>), [Cache Coherence](<https://devfeed.tech/topics/cache-coherence.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [accelerators](<https://devfeed.tech/tags/accelerators.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-accelerators](<https://devfeed.tech/tags/ai-accelerators.md>), [arm](<https://devfeed.tech/tags/arm.md>), [branch-prediction](<https://devfeed.tech/tags/branch-prediction.md>), [chiplets](<https://devfeed.tech/tags/chiplets.md>), [cpu](<https://devfeed.tech/tags/cpu.md>)

### AI overview

A modern CPU overlaps instruction work and predicts what it will need to keep its cores busy. It fetches instructions in blocks, decodes them into operations, and uses registers, execution units, and a cache hierarchy to process data. Branch prediction, pipelining, out-of-order execution, and prefetching improve throughput, while speculative execution can leave cache traces that create security risks. Modern processors also integrate GPUs, NPUs, and media or vector accelerators. Multiple cores communicate through an on-chip interconnect and coordinate shared data; hybrid cores and chiplets balance performance, efficiency, and manufacturing cost with scheduling and communication tradeoffs. The article presents these as general features, since manufacturers keep circuit details proprietary, and illustrates them with AMD Zen 5.

### Source excerpt

What actually happens inside a CPU? We break down the key parts of a modern processor, from fetching and decoding instructions to caches, branch prediction, chiplets and AI accelerators. Read Entire Article

## BF16 Component-Product Emulation of FP32 and FP64 GEMM on Intel AMX

DevFeed: [BF16 Component-Product Emulation of FP32 and FP64 GEMM on Intel AMX](<https://devfeed.tech/articles/bf16-component-product-emulation-of-fp32-and-fp64-gemm-on-intel-amx-131515.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.04663>)

Author: Bing Cui, Yu Liu

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [intel](<https://devfeed.tech/topics/intel.md>), [cpu](<https://devfeed.tech/topics/cpu.md>)

Tags: [bf16](<https://devfeed.tech/tags/bf16.md>), [component](<https://devfeed.tech/tags/component.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-ms](<https://devfeed.tech/tags/cs-ms.md>), [emulation](<https://devfeed.tech/tags/emulation.md>), [intel](<https://devfeed.tech/tags/intel.md>), [performance](<https://devfeed.tech/tags/performance.md>), [precision](<https://devfeed.tech/tags/precision.md>), [product](<https://devfeed.tech/tags/product.md>), [scientific-computing](<https://devfeed.tech/tags/scientific-computing.md>)

### AI overview

The paper emulates square FP32 and FP64 GEMM with BF16 products on Intel AMX. For FP32, it decomposes each input element into three BF16 components and evaluates six selected products, targeting accuracy comparable to oneMKL SGEMM. For FP64 values within the supported BF16 exponent range, a fixed six-slice Ozaki decomposition retains 6, 10, 15, or 21 products; each is computed in FP32, then widened and accumulated in FP64, trading speed for accuracy. The FP32 schedule reuses components and keeps partial sums in AMX tiles. In reported tests, AMX-FP32 beats oneMKL SGEMM at orders N >= 4096 on 64 threads and also gains on smaller matrices at lower thread counts. Some lower-product AMX-FP64 variants beat oneMKL DGEMM at sufficiently large orders, while retaining more products improves accuracy at added cost.

### Source excerpt

arXiv:2609.04663v2 Announce Type: replace-cross Abstract: Modern CPUs increasingly integrate high-throughput matrix engines optimized for low-precision AI workloads, while many scientific computing applications still rely on FP32 and FP64 GEMM to meet their numerical accuracy requirements. This paper presents a method that combines BF16 matrix products on Intel Advanced Matrix Extensions (AMX) to emulate real square FP32 and FP64 GEMM. For FP32 GEMM, each element in both input matrices is decomposed into three BF16 components, and six selected component products are evaluated to target FP32-level accuracy comparable to oneMKL SGEMM. For FP64 inputs within the supported BF16 exponent range, the method uses a simplified fixed six-slice Ozaki decomposition. Each retained BF16 product is first produced in FP32, then widened and accumulated in FP64. Four product-count settings retain 6, 10, 15, or 21 component products, exposing the accuracy-performance tradeoff relative to oneMKL DGEMM. The FP32 schedule reuses component data and retains partial sums in AMX tiles. AMX-FP32 outperforms oneMKL SGEMM at tested orders $N\ge4096$ on 64 threads and also achieves gains for smaller matrices at lower thread counts. AMX-FP64 variants retaining fewer component products can outperform oneMKL DGEMM at sufficiently large orders; more products improve accuracy at additional cost.

## A simple 8085 computer

DevFeed: [A simple 8085 computer](<https://devfeed.tech/articles/a-simple-8085-computer-129298.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/11/a-simple-8085-computer/>)

Author: Anne Barela

Published: 2026-11-11T17:16:28Z

Content type: article

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [Assembly](<https://devfeed.tech/topics/assembly.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [8085](<https://devfeed.tech/tags/8085.md>), [assembler](<https://devfeed.tech/tags/assembler.md>), [chips](<https://devfeed.tech/tags/chips.md>), [computer](<https://devfeed.tech/tags/computer.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [driver](<https://devfeed.tech/tags/driver.md>), [electronics](<https://devfeed.tech/tags/electronics.md>), [hackster](<https://devfeed.tech/tags/hackster.md>), [history](<https://devfeed.tech/tags/history.md>), [i-o](<https://devfeed.tech/tags/i-o.md>), [intel](<https://devfeed.tech/tags/intel.md>), [latch](<https://devfeed.tech/tags/latch.md>), [mandelbrot](<https://devfeed.tech/tags/mandelbrot.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-chips](<https://devfeed.tech/tags/memory-chips.md>), [microcontrollers](<https://devfeed.tech/tags/microcontrollers.md>), [octal](<https://devfeed.tech/tags/octal.md>), [port](<https://devfeed.tech/tags/port.md>), [processor](<https://devfeed.tech/tags/processor.md>), [ram](<https://devfeed.tech/tags/ram.md>), [rom](<https://devfeed.tech/tags/rom.md>), [simple](<https://devfeed.tech/tags/simple.md>), [small](<https://devfeed.tech/tags/small.md>), [tiny-basic](<https://devfeed.tech/tags/tiny-basic.md>), [vintage-computing](<https://devfeed.tech/tags/vintage-computing.md>)

### AI overview

mit41301's six-IC Intel 8085 computer runs at 4.9 MHz with 8 kB each of ROM and RAM, using plain logic for decoding instead of the PAL used in other designs mentioned. Its ROM contains a monitor and 8080-era Palo Alto Tiny BASIC, which runs on the 8085. Demonstrations include a text Mandelbrot program and an assembly version using undocumented 8085 instructions: replacing 12 instructions with ARHL and RDEL reduced its run time from 43.34 seconds to 40 seconds. The asmx 2.0 cross-assembler supports those instructions through the CPU 8085U directive. Another demo uses self-modifying code to reverse LED shift direction.

### Source excerpt

mit41301 built a small 8-bit computer around the Intel 8085, documented on Hackster.io. It runs at 4.9MHz with 8kB of ROM and 8kB of RAM, and the whole thing is six ICs: the processor, the two memory chips, an octal latch, a decoder, and a tristate bidirectional driver for the single I/O port. Other 8085 [...]

## IBM Quantum announces upcoming Nighthawk r3 processor designed to execute 10,000 operations

DevFeed: [IBM Quantum announces upcoming Nighthawk r3 processor designed to execute 10,000 operations](<https://devfeed.tech/articles/ibm-quantum-announces-upcoming-nighthawk-r3-processor-designed-to-execute-10-000-operations-129086.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/11/ibm-quantum-announces-upcoming-nighthawk-r3-processor-designed-to-execute-10000-operations/>)

Author: Kyt Dotson

Published: 2026-11-11T12:00:01Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Quantum Computing](<https://devfeed.tech/topics/quantum-computing.md>), [ibm](<https://devfeed.tech/topics/ibm.md>), [Parallelism](<https://devfeed.tech/topics/parallelism.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [Supercomputing](<https://devfeed.tech/topics/supercomputing.md>)

Tags: [advanced-micro-devices](<https://devfeed.tech/tags/advanced-micro-devices.md>), [ai](<https://devfeed.tech/tags/ai.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [amd](<https://devfeed.tech/tags/amd.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [complex](<https://devfeed.tech/tags/complex.md>), [emerging-tech](<https://devfeed.tech/tags/emerging-tech.md>), [generation](<https://devfeed.tech/tags/generation.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [ibm-quantum](<https://devfeed.tech/tags/ibm-quantum.md>), [link](<https://devfeed.tech/tags/link.md>), [news](<https://devfeed.tech/tags/news.md>), [nighthawk](<https://devfeed.tech/tags/nighthawk.md>), [operations](<https://devfeed.tech/tags/operations.md>), [processor](<https://devfeed.tech/tags/processor.md>), [processors](<https://devfeed.tech/tags/processors.md>), [quality](<https://devfeed.tech/tags/quality.md>), [quantum](<https://devfeed.tech/tags/quantum.md>), [quantum-computing](<https://devfeed.tech/tags/quantum-computing.md>), [quantum-processors](<https://devfeed.tech/tags/quantum-processors.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [speed](<https://devfeed.tech/tags/speed.md>), [system](<https://devfeed.tech/tags/system.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-5](<https://devfeed.tech/tags/top-story-5.md>)

### AI overview

IBM says its upcoming Nighthawk r3 will support 10,000 quantum operations on 520 programmable qubits, with 2,034 physical quantum components. In 2027, the company plans to connect two r3 processors into a system with 1,040 qubits. IBM reports earlier demonstrations of processor interconnects with 99.4% transfer fidelity toward a 99.9% target, and says it has connected cryogenic modules into one system. The article also describes IBM Quantum Platform's integration of quantum workflows with HPC and classical computing, plus new pulse-level access intended to help researchers investigate and correct errors. The announced capabilities and plans are IBM's claims; the excerpt does not establish their eventual performance.

### Source excerpt

IBM Corp. today announced the Quantum Nighthawk r3, its next-generation processor designed to tackle larger, more complex computations at high speed while maintaining quality. The company also said that in 2027, IBM plans to link two r3 quantum processors into a single system capable of running up to 10,000 quantum operations, scaling to more than [...] The post IBM Quantum announces upcoming Nighthawk r3 processor designed to execute 10,000 operations appeared first on SiliconANGLE.

## Intel Releases New CPU Microcode To Fix A Variety Of Functional Issues

DevFeed: [Intel Releases New CPU Microcode To Fix A Variety Of Functional Issues](<https://devfeed.tech/articles/intel-releases-new-cpu-microcode-to-fix-a-variety-of-functional-issues-128047.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Intel-CPU-Microcode-20261110>)

Author: Michael Larabel

Published: 2026-11-11T10:41:00Z

Content type: release

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [Intel Core](<https://devfeed.tech/topics/intel-core.md>), [intel](<https://devfeed.tech/topics/intel.md>)

Tags: [clearwater-forest](<https://devfeed.tech/tags/clearwater-forest.md>), [client](<https://devfeed.tech/tags/client.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [events](<https://devfeed.tech/tags/events.md>), [firmware](<https://devfeed.tech/tags/firmware.md>), [functional](<https://devfeed.tech/tags/functional.md>), [github](<https://devfeed.tech/tags/github.md>), [granite-rapids](<https://devfeed.tech/tags/granite-rapids.md>), [intel](<https://devfeed.tech/tags/intel.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [panther-lake](<https://devfeed.tech/tags/panther-lake.md>), [performance-monitoring](<https://devfeed.tech/tags/performance-monitoring.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [processor](<https://devfeed.tech/tags/processor.md>), [rapids](<https://devfeed.tech/tags/rapids.md>), [raptor](<https://devfeed.tech/tags/raptor.md>), [releases](<https://devfeed.tech/tags/releases.md>), [reporting](<https://devfeed.tech/tags/reporting.md>), [rom](<https://devfeed.tech/tags/rom.md>), [security](<https://devfeed.tech/tags/security.md>), [server](<https://devfeed.tech/tags/server.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

Intel's microcode-20261110 update addresses functional issues across recent Core and Xeon processors, with no new security issues reported in the excerpt. Client updates cover Raptor Lake, Wildcat Lake, and Panther Lake; server updates cover Sapphire Rapids, Emerald Rapids, Granite Rapids, Sierra Forest, and Clearwater Forest. Panther Lake fixes correct several performance-monitoring event counts, so the excerpt says the update is less pressing for users who do not use those events. Granite Rapids fixes address DICE AliasID Certificate DiceTcbInfo and incorrect core-count reporting in PIROM for certain SKUs; the latter affects BMC firmware and management tooling. Raptor Lake updates address existing errata.

### Source excerpt

Intel on Tuesday released the microcode-20261110 package that ships updated CPU microcode binaries for recent Intel Core (Ultra) and Xeon processors. The updated CPU microcode is for Core Gen 13 "Raptor Lake" and newer while on the Xeon server side is for Sapphire Rapids and newer. This is also the first time Clearwater Forest has seen microcode updates...

## World of Warcraft: Forever launched on 70,480 CPU cores and 251,136 GB of RAM

DevFeed: [World of Warcraft: Forever launched on 70,480 CPU cores and 251,136 GB of RAM](<https://devfeed.tech/articles/world-of-warcraft-forever-launched-on-70-480-cpu-cores-and-251-136-gb-of-ram-126645.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/10/world-of-warcraft-forever-launched-on-70480-cpu-cores-and-251136-gb-of-ram/>)

Author: Anne Barela

Published: 2026-11-10T16:21:39Z

Content type: news

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>), [cpu](<https://devfeed.tech/topics/cpu.md>)

Tags: [blizzard](<https://devfeed.tech/tags/blizzard.md>), [computers](<https://devfeed.tech/tags/computers.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [gaming](<https://devfeed.tech/tags/gaming.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [launch](<https://devfeed.tech/tags/launch.md>), [machines](<https://devfeed.tech/tags/machines.md>), [memory](<https://devfeed.tech/tags/memory.md>), [ram](<https://devfeed.tech/tags/ram.md>), [virtual-machines](<https://devfeed.tech/tags/virtual-machines.md>), [world-of-warcraft](<https://devfeed.tech/tags/world-of-warcraft.md>), [world-of-warcraft-forever](<https://devfeed.tech/tags/world-of-warcraft-forever.md>)

### AI overview

World of Warcraft: Forever opened on November 4 using 3,924 virtual machines, 70,480 CPU cores and 251,136 GB of memory. Blizzard said it broke the company's concurrent-player record, outdrew previous WoW launches, brought in more new players than any WoW release in 15 years, and set a franchise record for returning players. The launch was described as smooth, though Blizzard has not disclosed a current player count. Forever is an alternate version based on the 2004 game's settings and mechanics, with added content and storylines; it runs alongside the modern game and World of Warcraft: Classic.

### Source excerpt

Alfonso Maruccia writes at TechSpot about the hardware behind Blizzard's World of Warcraft: Forever, which opened on November 4. Blizzard posted the numbers on social media soon after launch: 3,924 virtual machines, 70,480 CPU cores, and 251,136 GB of memory. The spending seems to have worked. The launch went smoothly, Blizzard executives have talked up [...]

## Hidden in Plain Sight: Privacy-Enhanced Computing Through Register Renaming

DevFeed: [Hidden in Plain Sight: Privacy-Enhanced Computing Through Register Renaming](<https://devfeed.tech/articles/hidden-in-plain-sight-privacy-enhanced-computing-through-register-renaming-126988.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12570>)

Author: Ahmed Nematallah, Stefanos Kaxiras

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [Confidential Computing](<https://devfeed.tech/topics/confidential-computing.md>), [Parallelism](<https://devfeed.tech/topics/parallelism.md>), [FHE](<https://devfeed.tech/topics/fhe.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [all](<https://devfeed.tech/tags/all.md>), [applications](<https://devfeed.tech/tags/applications.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [area](<https://devfeed.tech/tags/area.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [but](<https://devfeed.tech/tags/but.md>), [code](<https://devfeed.tech/tags/code.md>), [compute](<https://devfeed.tech/tags/compute.md>), [compute-resources](<https://devfeed.tech/tags/compute-resources.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [data](<https://devfeed.tech/tags/data.md>), [encrypted](<https://devfeed.tech/tags/encrypted.md>), [encryption](<https://devfeed.tech/tags/encryption.md>), [hidden](<https://devfeed.tech/tags/hidden.md>), [privacy](<https://devfeed.tech/tags/privacy.md>)

### AI overview

HPS-PEC uses existing CPU infrastructure, with minor architectural changes, to provide Privacy-Enhanced Computing without a dedicated enclave that duplicates execution resources. Across 25 VIP-Bench benchmarks using a 7-cycle QARMA-64 cipher, encrypted code took 3.41x the execution time of unprotected native code on a geometric-mean basis; the data-oblivious code itself accounted for 1.03x. The authors report it was 1.26x faster than a Sequestered Encryption unit and used less than one-third of that unit's dedicated area. The security claim assumes a correctly functioning register renamer and register file, which the abstract says keep plaintext out of reach of instructions.

### Source excerpt

arXiv:2611.12570v1 Announce Type: cross Abstract: Privacy-Enhanced Computing (PEC) is a mechanism to hide program secrets from the outside world without paying the cost of fully-homomorphic encryption. Previous work has developed hardware mechanisms to achieve this goal but they require a dedicated processor enclave where all computations are done, requiring duplicate ALU resources and limiting the performance of PEC-utilizing applications due to not being able to access the full compute resources of the processor (e.g., multiple execution units and vector units), or not being able to execute PEC instructions in parallel and out-of-order. In this work, we introduce HPS-PEC (Hidden in Plain Sight PEC), a novel method of utilizing existing infrastructure in the CPU to achieve PEC with minor modifications to the architecture. We show that, across 25 VIP-Bench benchmarks and with a 7-cycle QARMA-64 cipher, HPS-PEC runs encrypted code at 3.41x the execution time of unprotected native code (geometric mean), of which 1.03x is the cost of data-oblivious code itself, and is 1.26x faster than a Sequestered Encryption (SE) unit while utilizing under a third of its dedicated area. Our method keeps plaintext out of reach of every instruction, as an enclave does given a correctly functioning renamer and register file, which every program already depends on.

## The CPU and Memory Economics of vSAN

DevFeed: [The CPU and Memory Economics of vSAN](<https://devfeed.tech/articles/the-cpu-and-memory-economics-of-vsan-124133.md>)

Original publisher: [Read original article](<https://www.verge.io/blog/vmwareexit/vsan-overhead-cpu-memory-economics/>)

Author: George Crump

Published: 2026-11-09T16:27:33Z

Content type: article

Language: en

Sources: [VergeIO](<https://devfeed.tech/sources/vergeio.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [DRAM price increase](<https://devfeed.tech/topics/dram-price-increase.md>), [Memory Heirarchy](<https://devfeed.tech/topics/memory-heirarchy.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>)

Tags: [applications](<https://devfeed.tech/tags/applications.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data](<https://devfeed.tech/tags/data.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [deduplication](<https://devfeed.tech/tags/deduplication.md>), [economics](<https://devfeed.tech/tags/economics.md>), [hci](<https://devfeed.tech/tags/hci.md>), [memory](<https://devfeed.tech/tags/memory.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [ram](<https://devfeed.tech/tags/ram.md>), [servers](<https://devfeed.tech/tags/servers.md>), [storage](<https://devfeed.tech/tags/storage.md>), [vergeos](<https://devfeed.tech/tags/vergeos.md>), [vmware](<https://devfeed.tech/tags/vmware.md>), [vmware-exit](<https://devfeed.tech/tags/vmware-exit.md>), [vmwareexit](<https://devfeed.tech/tags/vmwareexit.md>), [vsan](<https://devfeed.tech/tags/vsan.md>)

### AI overview

The excerpt argues that three-tier infrastructure and legacy vSAN both consume resources beyond application workloads: a midsize enterprise's six application servers plus two x86 array controllers make eight servers, while vSAN shifts storage overhead onto host CPU and RAM and often requires NSX or network appliances for routing, firewall, and microsegmentation. It claims VergeOS combines compute, storage, and networking in one codebase, runs the same workloads on five servers, and includes VergeFS shared storage and virtual networking. Inline deduplication is presented as a way to reduce disk and RAM use, and support for servers up to ten years old may let organizations reuse existing vSAN hosts. The excerpt also claims unified management simplifies operations; it provides no numerical vSAN overhead estimates or independent validation of the five-server comparison.

### Source excerpt

vSAN overhead takes host CPU and RAM from your apps. See how VergeOS runs a midsize data center on five servers instead of eight. The post The CPU and Memory Economics of vSAN appeared first on VergeIO.

## 520 MHz STM32H7P4/STM32H7P5 Arm Cortex-M7 MCUs feature Hardware Signal Processor (HSP), optional Neural-ART NPU

DevFeed: [520 MHz STM32H7P4/STM32H7P5 Arm Cortex-M7 MCUs feature Hardware Signal Processor (HSP), optional Neural-ART NPU](<https://devfeed.tech/articles/520-mhz-stm32h7p4-stm32h7p5-arm-cortex-m7-mcus-feature-hardware-signal-processor-hsp-optional-neural-art-npu-121109.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/11/06/520-mhz-stm32h7p4-stm32h7p5-arm-cortex-m7-mcus-feature-hardware-signal-processor-hsp-optional-neural-art-npu/>)

Author: Debashis Das

Published: 2026-11-06T11:04:55Z

Content type: news

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [Embedded Systems](<https://devfeed.tech/topics/embedded-systems.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [tinyml](<https://devfeed.tech/topics/tinyml.md>), [fourier analysis](<https://devfeed.tech/topics/fourier-analysis.md>)

Tags: [accelerators](<https://devfeed.tech/tags/accelerators.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [arm](<https://devfeed.tech/tags/arm.md>), [can-fd](<https://devfeed.tech/tags/can-fd.md>), [cortex-m7](<https://devfeed.tech/tags/cortex-m7.md>), [development-board](<https://devfeed.tech/tags/development-board.md>), [dsp](<https://devfeed.tech/tags/dsp.md>), [edge-ai](<https://devfeed.tech/tags/edge-ai.md>), [flash](<https://devfeed.tech/tags/flash.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [hsp](<https://devfeed.tech/tags/hsp.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [mcu](<https://devfeed.tech/tags/mcu.md>), [mcus](<https://devfeed.tech/tags/mcus.md>), [motor-control](<https://devfeed.tech/tags/motor-control.md>), [npu](<https://devfeed.tech/tags/npu.md>), [optional](<https://devfeed.tech/tags/optional.md>), [power](<https://devfeed.tech/tags/power.md>), [pwm](<https://devfeed.tech/tags/pwm.md>), [sensing](<https://devfeed.tech/tags/sensing.md>), [sensors](<https://devfeed.tech/tags/sensors.md>), [signal-processing](<https://devfeed.tech/tags/signal-processing.md>), [sram](<https://devfeed.tech/tags/sram.md>), [stm32](<https://devfeed.tech/tags/stm32.md>), [stmicro](<https://devfeed.tech/tags/stmicro.md>), [stmicro-stm32](<https://devfeed.tech/tags/stmicro-stm32.md>), [tinyml](<https://devfeed.tech/tags/tinyml.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

The STM32H7P4 and STM32H7P5 are 520 MHz Cortex-M7 MCUs aimed at digital power, motor control, industrial sensing, and edge AI. Both include an HSP for matrix, vector, FFT/IFFT, and filtering work; ST says it runs FFT operations up to five times faster than Cortex-M7 software. The H7P5 adds a 520 MHz Neural-ART NPU rated at 85 GOPS, and ST says its AFCI model runs up to 40 times faster than a software implementation on the Cortex-M7. Both offer up to 2 MB flash, 736 KB SRAM, high-resolution timers with up to 24 PWM outputs, four 12-bit ADCs, and broad connectivity. Software includes STM32CubeH7P and motor-control and digital-power packages; two development boards were also announced. The MCUs are sampling for OEMs, with mass production planned for January 2027. Listed starting price is $4.43 for a 1 MB LQFP100 device at 10,000 units.

### Source excerpt

STMicroelectronics has introduced the STM32H7P4 and STM32H7P5, two 520 MHz Arm Cortex-M7 MCUs part of STM32H7P family designed for digital power, motor control, industrial sensing, and edge AI applications. Both feature a Hardware Signal Processor (HSP) for accelerating mathematical and signal-processing operations, while the STM32H7P5 also includes an 85 GOPS Neural-ART NPU for Edge AI inference/TinyML. The MCUs feature up to 2MB dual-bank flash, 736KB SRAM, two high-resolution timers with up to 24 PWM outputs, three advanced motor-control timers, and four 12-bit ADCs. Other features include CORDIC and FMAC mathematical accelerators, three CAN FD interfaces, USB OTG Full-Speed, and support for external memory through Octo-SPI and FMC interfaces. STM32H7P4 and STM32H7P5 specifications: MCU Core 32-bit Arm Cortex-M7 CPU @ up to 520 MHz with double-precision FPU, DSP instructions, and MPU 32 KB instruction cache and 32 KB data cache Performance - 2773 CoreMark (5.33 CoreMark/MHz) Mathematical coprocessors Hardware Signal Processor [...] The post 520 MHz STM32H7P4/STM32H7P5 Arm Cortex-M7 MCUs feature Hardware Signal Processor (HSP), optional Neural-ART NPU appeared first on CNX Software - Embedded Systems News.

## Agentic AI boom expected to reshape CPU market

DevFeed: [Agentic AI boom expected to reshape CPU market](<https://devfeed.tech/articles/agentic-ai-boom-expected-to-reshape-cpu-market-119667.md>)

Original publisher: [Read original article](<https://www.networkworld.com/article/4245292/agentic-ai-boom-expected-to-reshape-cpu-market.html>)

Author: Andy Patrizio

Published: 2026-11-05T18:47:51Z

Content type: article

Language: en

Sources: [Network World](<https://devfeed.tech/sources/network-world.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-data-centers](<https://devfeed.tech/tags/ai-data-centers.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-cpus-and-processors](<https://devfeed.tech/tags/artificial-intelligence-cpus-and-processors.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-ai-agents](<https://devfeed.tech/tags/autonomous-ai-agents.md>), [balance](<https://devfeed.tech/tags/balance.md>), [code](<https://devfeed.tech/tags/code.md>), [computing](<https://devfeed.tech/tags/computing.md>), [core](<https://devfeed.tech/tags/core.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cpus-and-processors](<https://devfeed.tech/tags/cpus-and-processors.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [databases](<https://devfeed.tech/tags/databases.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Agentic AI could raise data center CPU core requirements from about 30 million to 120 million per gigawatt, according to Arm estimates cited by TrendForce. Unlike conventional LLM inference, agents rely on CPUs to plan and schedule tasks, call tools, coordinate agents, evaluate results, and run code or process data. TrendForce says deployments could shift from roughly one CPU per four to eight GPUs toward one per one to two GPUs. CPU tool processing can account for up to 90.6% of latency in some workloads, and CPU energy use can also be substantial, so adding GPUs alone may leave coordination tasks as bottlenecks. Nvidia's Vera CPUs, designed to work with its GPU platforms and also offered in dedicated CPU racks, are cited as evidence of growing demand for CPU capacity.

### Source excerpt

Growing use of autonomous AI agents could drive a four-fold increase in data center CPU core requirements. CPUs have been declared all but irrelevant in the era of artificial intelligence, but they are receiving a new lease on life thanks to agentic AI creating a new source of demand. According to semiconductor research firm TrendForce, the growing computational requirements of autonomous AI agents could force operators to substantially increase CPU deployments and reconsider the balance between CPUs and GPUs in their server infrastructure. TrendForce said AI agents introduce a more CPU-intensive workload than conventional large language model (LLM) inference. While GPUs remain essential for executing the training portion of AI models, CPUs are responsible for coordinating the complex sequences of actions that enable AI agents to operate autonomously, steps that a GPU simply can't do. These activities include planning tasks, scheduling subtasks, calling external tools, managing interactions between multiple agents and evaluating results. Agents also rely on conventional computing resources to execute Python code, search databases, crawl websites and process information, according to TrendForce. As a result, the CPU is enjoying a new lease on life and becoming a more significant component of AI infrastructure rather than simply serving as a supporting processor for GPUs, according to TrendForce. TrendForce notes that traditional AI data centers have typically deployed approximately one CPU for every four to eight GPUs, reflecting the industry's emphasis on accelerating computationally intensive AI workloads. But agentic AI could change all that. TrendForce cited estimates from Arm indicating that CPU core requirements could increase from approximately 30 million cores per gigawatt of data center capacity to 120 million cores per gigawatt as agentic AI workloads become more prevalent. That represents a potential fourfold increase in CPU core demand. TrendForce expects

## A cheap FPGA board becomes retro-style computer

DevFeed: [A cheap FPGA board becomes retro-style computer](<https://devfeed.tech/articles/a-cheap-fpga-board-becomes-retro-style-computer-114866.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/03/a-cheap-fpga-board-becomes-retro-style-computer/>)

Author: Anne Barela

Published: 2026-11-03T17:12:59Z

Content type: news

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [Computing](<https://devfeed.tech/topics/computing.md>), [CPU Cache](<https://devfeed.tech/topics/cpu-cache.md>)

Tags: [audio](<https://devfeed.tech/tags/audio.md>), [board](<https://devfeed.tech/tags/board.md>), [cache](<https://devfeed.tech/tags/cache.md>), [chip](<https://devfeed.tech/tags/chip.md>), [clocks](<https://devfeed.tech/tags/clocks.md>), [computer](<https://devfeed.tech/tags/computer.md>), [core](<https://devfeed.tech/tags/core.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [fpga](<https://devfeed.tech/tags/fpga.md>), [gaming](<https://devfeed.tech/tags/gaming.md>), [github](<https://devfeed.tech/tags/github.md>), [gowin](<https://devfeed.tech/tags/gowin.md>), [hdmi](<https://devfeed.tech/tags/hdmi.md>), [history](<https://devfeed.tech/tags/history.md>), [inside](<https://devfeed.tech/tags/inside.md>), [logic](<https://devfeed.tech/tags/logic.md>), [psram](<https://devfeed.tech/tags/psram.md>), [retro](<https://devfeed.tech/tags/retro.md>), [risc-v](<https://devfeed.tech/tags/risc-v.md>), [sd](<https://devfeed.tech/tags/sd.md>), [sipeed](<https://devfeed.tech/tags/sipeed.md>), [tang-nano-9k](<https://devfeed.tech/tags/tang-nano-9k.md>), [vintage-computing](<https://devfeed.tech/tags/vintage-computing.md>)

### AI overview

The m9b project fits a retro-style computer into a $15 Sipeed Tang Nano 9K by building its 36 MHz RISC-V CPU and peripherals in the Gowin FPGA's logic, which has 8,640 lookup tables and 52 KB of block RAM but no hard CPU core. The system adds 24 KB of cache, 8 MB of PSRAM, HDMI output at 720x480 and 60 Hz, 48 kHz stereo audio, two USB ports, and SD storage. Its HDMI encoder, audio path, and USB host are also implemented in logic, with all clocks derived from the board's 27 MHz crystal. The author reports porting Doom, Descent, Tyrian, System Shock, and Ultima VII. Place and route uses 7,560 of 8,640 logic cells, 97% of slices, and 25 of 26 block RAMs. This is part one of a six-part write-up, focused on the FPGA, system around the CPU, and clocking.

### Source excerpt

The Parts Bin has built a complete retro-style computer inside a $15 Sipeed Tang Nano 9K board, and posted it at the-parts-bin.github.io. The Gowin FPGA on the board has 8,640 lookup tables and 52 KB of block RAM. It doesn't have a hard CPU core, so the processor had to be built from the same [...]

## Hardwired Distributed Processing Units at the Sensor: Truly Parallel Vision Pre-Processing that Frees the Host CPU

DevFeed: [Hardwired Distributed Processing Units at the Sensor: Truly Parallel Vision Pre-Processing that Frees the Host CPU](<https://devfeed.tech/articles/hardwired-distributed-processing-units-at-the-sensor-truly-parallel-vision-pre-processing-that-frees-the-host-cpu-107573.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.38752>)

Author: Raj Mali

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [cpu](<https://devfeed.tech/tags/cpu.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [processing](<https://devfeed.tech/tags/processing.md>), [sensor](<https://devfeed.tech/tags/sensor.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

Hardwired distributed processing units (HDPUs) attach fixed, always-on vision datapaths to a camera sensor, process the pixel stream in parallel, and send compact results to the host without waiting for a full frame. The authors implement Canny edge, Harris corner, and line-tracking units on an Artix-7 FPGA using 2,568 LUTs and an estimated 0.318 W; their stages are bit-exact with software models. In simulation, decisions emerge within 11.03 camera lines of their source pixels, reported as 22-67 times sooner than a frame-based host response. The units return 18-30% of a core at 640x480 and 63% of the frame period at 1080p. Their hardware cost scales with frame width through line buffers. In a closed-loop vehicle model, the line-tracking unit raises the highest speed for holding the line from 4.75 to 10.00 m/s. These are abstract-level results, including simulation and modeling.

### Source excerpt

arXiv:2610.38752v1 Announce Type: new Abstract: Conventional vision pipelines route every pixel to a host processor, which must then wait for a complete frame before it can act and devote part of each frame period to routine pre-processing. We examine an alternative organisation in which this work is distributed across hardwired distributed processing units (HDPUs): small, fixed datapaths attached directly to the sensor, each committed to a single always-on task, operating truly in parallel on the same pixel stream and delivering compact results to the host. From one library of 3x3 operators sharing a common two-clock latency, we construct three HDPUs (Canny edges, Harris corners, and a line tracker that issues a steering decision) and run them side by side on a single camera stream in a low-cost Artix-7 FPGA, at a cost of 2,568 LUTs and an estimated 0.318 W. Every stage of every unit is bit-exact with its software model. In a full-system simulation with a datasheet camera model, each decision leaves its HDPU within 11.03 camera lines of the pixel that produced it, 22-67x sooner than the earliest moment at which a frame-based program on the host could respond; the HDPU latency varies by no more than 17 ns, whereas the host's own run times reached 12.5x their median. Offloading the three tasks returns 18-30% of a core to the host in every frame period at 640x480, and 63% of the frame period, with all threads in use, at 1080p. The cost of the units grows with frame width only through their line buffers, and in a closed-loop model of a line-following vehicle the HDPU raises the highest speed at which the line is held from 4.75 to 10.00 m/s.

## How to Evaluate CPU Performance for Agentic AI

DevFeed: [How to Evaluate CPU Performance for Agentic AI](<https://devfeed.tech/articles/how-to-evaluate-cpu-performance-for-agentic-ai-106193.md>)

Original publisher: [Read original article](<https://www.nextplatform.com/compute/2026/10/29/sponsored-how-to-evaluate-cpu-performance-for-agentic-ai/5305779>)

Author: Timothy Pricket-Morgan

Published: 2026-10-29T09:00:00Z

Content type: article

Language: en

Sources: [The Next Platform: In-depth coverage of high end computing](<https://devfeed.tech/sources/the-next-platform-in-depth-coverage-of-high-end-computing.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-testing](<https://devfeed.tech/tags/agentic-ai-testing.md>), [ai](<https://devfeed.tech/tags/ai.md>), [arm](<https://devfeed.tech/tags/arm.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [capacity-planning](<https://devfeed.tech/tags/capacity-planning.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpu-performance](<https://devfeed.tech/tags/cpu-performance.md>), [performance](<https://devfeed.tech/tags/performance.md>)

### AI overview

Arm argues that CPU performance for agentic AI should be evaluated through both component benchmarks and end-to-end task completion, since workflows chain dependent model, retrieval, database, tool, and state operations. It recommends measuring critical-path latency and per-thread performance at the core level; throughput, concurrency, memory behavior, and sustained performance under load at the system level; and completed work, energy, power, cooling, and density at the rack level. Existing benchmarks such as InferenceX and TPCx-AI cover parts of the workflow, but not the full orchestration and tool-execution path. The article says CPU performance can affect accelerator utilization and that concurrency shifts the balance toward core count, memory bandwidth, cache, and scheduling. Arm reports an independently evaluated AGI CPU result of approximately 2x performance per rack versus AMD EPYC 9755 on selected CPU-visible workflow workloads, based on server measurements and rack-level modeling.

### Source excerpt

A funny thing happened on the way from machine learning to chatbots to agentic AI: the central proce ...

## CVE-2026-118664 - decode-uri-component: Denial of service via quadratic replacement of percent-encoded runs

DevFeed: [CVE-2026-118664 - decode-uri-component: Denial of service via quadratic replacement of percent-encoded runs](<https://devfeed.tech/articles/cve-2026-118664-decode-uri-component-denial-of-service-via-quadratic-replacement-of-percent-encoded-runs-105592.md>)

Original publisher: [Read original article](<https://cvefeed.io/vuln/detail/CVE-2026-118664>)

Author: CVEFEED.io; github.com

Published: 2026-10-28T21:16:56Z

Content type: news

Language: en

Sources: [Latest High/Critical Vulnerabilitiy Feed](<https://devfeed.tech/sources/latest-high-critical-vulnerabilitiy-feed.md>)

Topics: [декодер](<https://devfeed.tech/topics/tag-db5a2ccdff76.md>), [Decoding](<https://devfeed.tech/topics/decoding.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [blocking](<https://devfeed.tech/tags/blocking.md>), [body](<https://devfeed.tech/tags/body.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cve](<https://devfeed.tech/tags/cve.md>), [cve-2026-118664](<https://devfeed.tech/tags/cve-2026-118664.md>), [cvss](<https://devfeed.tech/tags/cvss.md>), [denial-of-service](<https://devfeed.tech/tags/denial-of-service.md>), [event-loop](<https://devfeed.tech/tags/event-loop.md>), [fallback](<https://devfeed.tech/tags/fallback.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [header](<https://devfeed.tech/tags/header.md>), [input](<https://devfeed.tech/tags/input.md>), [issue](<https://devfeed.tech/tags/issue.md>), [js](<https://devfeed.tech/tags/js.md>), [native](<https://devfeed.tech/tags/native.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [regular](<https://devfeed.tech/tags/regular.md>), [url](<https://devfeed.tech/tags/url.md>), [version](<https://devfeed.tech/tags/version.md>)

### AI overview

Before version 0.5.1, decode-uri-component's custom fallback runs after native decoding fails. It gathers distinct percent-encoded runs, then scans the full input once per run with regular-expression replacements. Malformed input with many distinct runs can therefore cause quadratic CPU use and block Node.js's event loop. Request bodies can reach the demonstrated size, while ordinary URL header limits reduce the practical delay. The issue is fixed in version 0.5.1.

### Source excerpt

CVE ID :CVE-2026-118664 Published : Oct. 28, 2026, 9:16 p.m. | 2 hours, 12 minutes ago Description :decode-uri-component provides a more robust alternative to decodeURIComponent. Prior to 0.5.1, decodeUriComponent in index.js falls back to customDecodeURIComponent after native decoding throws, and the fallback collects every distinct percent-encoded run before performing a full-string regular-expression replacement for each entry. Malformed input containing many distinct runs can therefore make both the number of replacements and the scanned input length grow together, causing quadratic CPU consumption and blocking the Node.js event loop; request-body inputs can reach the demonstrated size, while ordinary URL header limits reduce the practical delay. This issue is fixed in version 0.5.1. Severity: 8.2 | HIGH Visit the link for more details, such as CVSS details, affected products, timeline, and more...

## Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall

DevFeed: [Speeding up Log-Sum-Exp: Kernel Fusion at the Memory Wall, Integer Arithmetic at the Compute Wall](<https://devfeed.tech/articles/speeding-up-log-sum-exp-kernel-fusion-at-the-memory-wall-integer-arithmetic-at-the-compute-wall-101608.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33647>)

Author: Lingyun Yao, Martin Andraud, Niki Loppi, Andrea Pilzer, Anji Liu, Guy Van den Broeck, Martin Trapp

Published: 2026-10-27T04:00:00Z

Content type: news

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [GPU optimization](<https://devfeed.tech/topics/gpu-optimization.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [Performance Testing](<https://devfeed.tech/topics/performance-testing.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [accelerate](<https://devfeed.tech/tags/accelerate.md>), [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bottlenecks](<https://devfeed.tech/tags/bottlenecks.md>), [call](<https://devfeed.tech/tags/call.md>), [compute](<https://devfeed.tech/tags/compute.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [exp](<https://devfeed.tech/tags/exp.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-wall](<https://devfeed.tech/tags/memory-wall.md>), [up](<https://devfeed.tech/tags/up.md>)

### AI overview

The paper reports two drop-in kernels for faster Log-Sum-Exp (LSE): FuseLSE uses a single-pass GPU kernel to reduce launch overhead and high-bandwidth memory traffic, evaluating exp and log on the GPU's Special Function Unit; IntLSE replaces LSE computation with approximated integer arithmetic for CPUs, where exp and log are costly. Benchmarks across workload sizes and hardware platforms report GPU speedups over PyTorch of about 10-11x for small workloads and 6x for larger ones. On CPUs, IntLSE is reported to run about 3-6x faster than FuseLSE. These are abstract-level reported results; no further benchmark details are supplied.

### Source excerpt

arXiv:2610.33647v1 Announce Type: new Abstract: While the Log-Sum-Exp (LSE) function is a foundational numerical primitive for stable log-domain computation in modern machine learning, its fast and efficient computation on generic platforms (\ie, CPUs and GPUs) has been underexplored, potentially creating execution bottlenecks for large workloads. On GPU, the de facto implementation torch.logsumexp dispatches a chain of nine sub-kernels per call, incurring redundant High Bandwidth Memory (HBM) traffic and launch overhead. On CPU, exp and log operations are hardware-hungry, limiting the computing efficiency. To address these bottlenecks, we propose two drop-in kernels to significantly accelerate LSE computation on both GPUs and CPUs: FuseLSE, a single-pass fused kernel that evaluates LSE's exp and log functions on the GPU's Special Function Unit (SFU); and IntLSE, which further replaces the LSE computation with approximated integer arithmetic for CPU computation. Our experiments, validated by benchmarks across workload sizes and hardware platforms, show that both kernels are ${\sim}10-11\times$ faster than PyTorch at small workloads and ${\sim}6\times$ faster on larger ones on GPUs, where the speed-up is attributed to reduced launch overhead and HBM traffic. On CPU, where no SFU is available, LSE computation dominates the cost, allowing IntLSE to gain ${\sim}3-6\times$ execution speed over FuseLSE.

## SpacemiT Announces The V100 Server-Class RISC-V Processor

DevFeed: [SpacemiT Announces The V100 Server-Class RISC-V Processor](<https://devfeed.tech/articles/spacemit-announces-the-v100-server-class-risc-v-processor-90247.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/SpacemiT-V100>)

Author: Michael Larabel

Published: 2026-10-19T12:00:00Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [RISC-V](<https://devfeed.tech/topics/riscv.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [Intel 12th Gen](<https://devfeed.tech/topics/intel-12th-gen.md>), [DRAM price increase](<https://devfeed.tech/topics/dram-price-increase.md>)

Tags: [ddr5](<https://devfeed.tech/tags/ddr5.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [pcie](<https://devfeed.tech/tags/pcie.md>), [performance](<https://devfeed.tech/tags/performance.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [risc-v](<https://devfeed.tech/tags/risc-v.md>), [server-cpus](<https://devfeed.tech/tags/server-cpus.md>), [spacemit](<https://devfeed.tech/tags/spacemit.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

SpacemiT announced the V100, a server-class RISC-V processor with 46 hybrid cores, support for two-socket servers, DDR5-4800 memory, and PCIe 5.0. The article describes its specifications and says its performance remains to be seen.

### Source excerpt

Following the interesting SpacemiT K3 RVA23 RISC-V SoC, SpacemiT today announced the V100 server-class RISC-V processor...

## Agentic AI Alters The CPU-GPU Balance

DevFeed: [Agentic AI Alters The CPU-GPU Balance](<https://devfeed.tech/articles/agentic-ai-alters-the-cpu-gpu-balance-87823.md>)

Original publisher: [Read original article](<https://semiengineering.com/agentic-ai-alters-the-cpu-gpu-balance/>)

Author: Bryon Moyer

Published: 2026-10-15T07:01:24Z

Content type: article

Language: en

Sources: [Semiconductor Engineering](<https://devfeed.tech/sources/semiconductor-engineering.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>)

Tags: [acceleration](<https://devfeed.tech/tags/acceleration.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-accelerators](<https://devfeed.tech/tags/ai-accelerators.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-reasoning](<https://devfeed.tech/tags/ai-reasoning.md>), [apis](<https://devfeed.tech/tags/apis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arm](<https://devfeed.tech/tags/arm.md>), [cadence](<https://devfeed.tech/tags/cadence.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [delos-data](<https://devfeed.tech/tags/delos-data.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [low-power-high-performance](<https://devfeed.tech/tags/low-power-high-performance.md>), [mixture-of-experts](<https://devfeed.tech/tags/mixture-of-experts.md>), [moe](<https://devfeed.tech/tags/moe.md>), [qci](<https://devfeed.tech/tags/qci.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [reasoning-models](<https://devfeed.tech/tags/reasoning-models.md>), [reservoir-computing](<https://devfeed.tech/tags/reservoir-computing.md>), [semiconductor](<https://devfeed.tech/tags/semiconductor.md>), [semiconductor-engineering](<https://devfeed.tech/tags/semiconductor-engineering.md>), [synopsys](<https://devfeed.tech/tags/synopsys.md>), [top-stories](<https://devfeed.tech/tags/top-stories.md>)

### AI overview

The article describes how agentic AI workloads increase CPU work because agents orchestrate models and make sequential, branching decisions, potentially moving CPU-to-GPU ratios closer to parity. It also surveys reasoning models, mixture-of-experts architectures, and reservoir computing, which continue to rely largely on GPUs or other accelerators, and discusses their distinct characteristics and tradeoffs.

### Source excerpt

Agentic workloads increase CPU demand, while reasoning models, MoE architectures, and reservoir computing fuel AI acceleration. The post Agentic AI Alters The CPU-GPU Balance appeared first on Semiconductor Engineering.

## Agentic AI puts the CPU back in play as Dell touts 13-to-1 server consolidation

DevFeed: [Agentic AI puts the CPU back in play as Dell touts 13-to-1 server consolidation](<https://devfeed.tech/articles/agentic-ai-puts-the-cpu-back-in-play-as-dell-touts-13-to-1-server-consolidation-87338.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/14/server-consolidation-gets-new-life-agentic-ai-strains-cpus-aidatapipelineforum/>)

Author: Sloane Kali Faye

Published: 2026-10-14T20:59:23Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [data centers](<https://devfeed.tech/topics/data-centers.md>), [dell](<https://devfeed.tech/topics/dell.md>), [systems](<https://devfeed.tech/topics/systems.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-data-pipeline-forum-2026](<https://devfeed.tech/tags/ai-data-pipeline-forum-2026.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [aidatapipelineforum](<https://devfeed.tech/tags/aidatapipelineforum.md>), [amd](<https://devfeed.tech/tags/amd.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cube-event-coverage](<https://devfeed.tech/tags/cube-event-coverage.md>), [data-center-efficiency](<https://devfeed.tech/tags/data-center-efficiency.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [dell](<https://devfeed.tech/tags/dell.md>), [dell-technologies](<https://devfeed.tech/tags/dell-technologies.md>), [idrac](<https://devfeed.tech/tags/idrac.md>), [infra](<https://devfeed.tech/tags/infra.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [john-furrier](<https://devfeed.tech/tags/john-furrier.md>), [news](<https://devfeed.tech/tags/news.md>), [nyse-dell](<https://devfeed.tech/tags/nyse-dell.md>), [open-compute-project](<https://devfeed.tech/tags/open-compute-project.md>), [openmanage-enterprise](<https://devfeed.tech/tags/openmanage-enterprise.md>), [power](<https://devfeed.tech/tags/power.md>), [poweredge](<https://devfeed.tech/tags/poweredge.md>), [pradyumna-narendra](<https://devfeed.tech/tags/pradyumna-narendra.md>), [scaleflux](<https://devfeed.tech/tags/scaleflux.md>), [server-consolidation](<https://devfeed.tech/tags/server-consolidation.md>), [servers](<https://devfeed.tech/tags/servers.md>), [silicon-diversity](<https://devfeed.tech/tags/silicon-diversity.md>), [thecube](<https://devfeed.tech/tags/thecube.md>)

### AI overview

The article describes Dell's server-consolidation pitch as demand for agentic AI increases the need for general-purpose compute. Dell says upcoming PowerEdge systems using AMD processors can replace as many as 13 older servers with one, while a rack-focused design and management tools aim to increase compute density and simplify fleet management. The segment was sponsored by Dell.

### Source excerpt

Server consolidation is getting a second look as agentic AI drives a surge in demand for general-purpose compute. Graphics processing units dominate the AI infrastructure conversation, but the agents running on those systems lean heavily on central processing units, and data centers are short on the power and space to keep adding servers. Dell Technologies [...] The post Agentic AI puts the CPU back in play as Dell touts 13-to-1 server consolidation appeared first on SiliconANGLE.

## Why x86 processors still start in 16-bit real mode

DevFeed: [Why x86 processors still start in 16-bit real mode](<https://devfeed.tech/articles/your-cpu-still-boots-up-pretending-to-be-a-1978-intel-chip-and-intel-gave-up-on-removing-it-86149.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/10/13/your-cpu-still-boots-up-pretending-to-be-a-1978-intel-chip-and-intel-gave-up-on-removing-it/>)

Author: Anne Barela

Published: 2026-10-13T14:50:34Z

Content type: article

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [cpu](<https://devfeed.tech/topics/cpu.md>), [Chip design](<https://devfeed.tech/topics/chip-design.md>), [Linux](<https://devfeed.tech/topics/linux.md>)

Tags: [8086](<https://devfeed.tech/tags/8086.md>), [code](<https://devfeed.tech/tags/code.md>), [compatibility](<https://devfeed.tech/tags/compatibility.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [history](<https://devfeed.tech/tags/history.md>), [intel](<https://devfeed.tech/tags/intel.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [microprocessors](<https://devfeed.tech/tags/microprocessors.md>), [operating-system](<https://devfeed.tech/tags/operating-system.md>), [qemu](<https://devfeed.tech/tags/qemu.md>), [real-mode](<https://devfeed.tech/tags/real-mode.md>), [uefi](<https://devfeed.tech/tags/uefi.md>), [windows-11](<https://devfeed.tech/tags/windows-11.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

x86 processors begin execution in 16-bit real mode, a startup state inherited from the Intel 8086. Firmware quickly switches to protected mode, but additional CPU cores repeat the process, and operating systems retain startup stubs for it. Intel abandoned its 2023 proposal to start directly in 64-bit mode; a possible alternative was later discussed, though the processor described was unnamed.

### Source excerpt

Adam Conway, writing at XDA Developers, lays out how every x86 processor still starts in real mode, the 16-bit execution environment of the Intel 8086 from June 1978. Intel's documentation says its 64-bit designs come out of reset in the same state as the original 8086, and AMD says its chips always enter real mode [...]

## A 16-bit relay computer runs Pi and Dijkstra

DevFeed: [A 16-bit relay computer runs Pi and Dijkstra](<https://devfeed.tech/articles/a-16-bit-relay-computer-runs-pi-and-dijkstra-85388.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/10/12/a-16-bit-relay-computer-runs-pi-and-dijkstra/>)

Author: Anne Barela

Published: 2026-10-12T16:17:51Z

Content type: article

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [Computing](<https://devfeed.tech/topics/computing.md>), [cpu](<https://devfeed.tech/topics/cpu.md>)

Tags: [analog](<https://devfeed.tech/tags/analog.md>), [code](<https://devfeed.tech/tags/code.md>), [computer](<https://devfeed.tech/tags/computer.md>), [computers](<https://devfeed.tech/tags/computers.md>), [computing](<https://devfeed.tech/tags/computing.md>), [digital](<https://devfeed.tech/tags/digital.md>), [dijkstra](<https://devfeed.tech/tags/dijkstra.md>), [electronics](<https://devfeed.tech/tags/electronics.md>), [fpga](<https://devfeed.tech/tags/fpga.md>), [pi](<https://devfeed.tech/tags/pi.md>), [relay](<https://devfeed.tech/tags/relay.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [square](<https://devfeed.tech/tags/square.md>)

### AI overview

A 16-bit relay computer uses a 19-command accumulator instruction set and self-holding relays. It computes Pi to two decimal places, finds the integer square root of 60000, and runs Dijkstra's shortest-path algorithm. Its memory and clock use Arduino boards, and its design was simulated before construction.

### Source excerpt

Open Electronics covered a 16-bit relay computer built by Peter, running on self-holding relays at 24 V. The CPU is an accumulator design, so all math and load/store work passes through an ACCUmulator. The instruction set has 19 commands and three addressing modes, including indirect, which gives the programmer pointers and tables. Computing Pi to [...]

## Oxide Computer raises $445M to step up data center rack production

DevFeed: [Oxide Computer raises $445M to step up data center rack production](<https://devfeed.tech/articles/oxide-computer-raises-445m-to-step-up-data-center-rack-production-84406.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/09/oxide-computer-raises-445m-to-step-up-data-center-rack-production/>)

Author: Maria Deutscher

Published: 2026-10-10T00:47:34Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Software-Defined Data Center](<https://devfeed.tech/topics/software-defined-data-center.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [Software](<https://devfeed.tech/topics/software.md>)

Tags: [amd](<https://devfeed.tech/tags/amd.md>), [aws](<https://devfeed.tech/tags/aws.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [energy](<https://devfeed.tech/tags/energy.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [funding](<https://devfeed.tech/tags/funding.md>), [funding-round](<https://devfeed.tech/tags/funding-round.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [infra](<https://devfeed.tech/tags/infra.md>), [investment](<https://devfeed.tech/tags/investment.md>), [networking](<https://devfeed.tech/tags/networking.md>), [news](<https://devfeed.tech/tags/news.md>), [oxide-computer](<https://devfeed.tech/tags/oxide-computer.md>), [series-d](<https://devfeed.tech/tags/series-d.md>), [startup](<https://devfeed.tech/tags/startup.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-5](<https://devfeed.tech/tags/top-story-5.md>)

### AI overview

Oxide Computer raised $445 million in a Series D round led by returning backer Eclipse Capital. The company sells pre-integrated data center racks with computing, storage and networking equipment, and says funding will support expanded materials and manufacturing capacity. It also plans to upgrade the rack design to host a graphics card.

### Source excerpt

Data center hardware startup Oxide Computer Inc. today announced that it has raised $445 million in funding. Returning backer Eclipse Capital led the Series D round. It was joined by AMD Ventures, Riot Ventures, Jane Street, Atreides Management and USIT, which led Oxide's previous $200 million raise in February. Oxide sells a data center rack [...] The post Oxide Computer raises $445M to step up data center rack production appeared first on SiliconANGLE.

## Row-Parallel DRAM Computing Cuts Data-Reorganization Overhead (Syracuse, FAU, TU Dresden)

DevFeed: [Row-Parallel DRAM Computing Cuts Data-Reorganization Overhead (Syracuse, FAU, TU Dresden)](<https://devfeed.tech/articles/row-parallel-dram-computing-cuts-data-reorganization-overhead-syracuse-fau-tu-dresden-64922.md>)

Original publisher: [Read original article](<https://semiengineering.com/row-parallel-dram-computing-cuts-data-reorganization-overhead-syracuse-fau-tu-dresden/>)

Author: Technical Paper Link

Published: 2026-10-05T18:16:28Z

Content type: article

Language: en

Sources: [Semiconductor Engineering](<https://devfeed.tech/sources/semiconductor-engineering.md>)

Topics: [Computing](<https://devfeed.tech/topics/computing.md>), [Memory Heirarchy](<https://devfeed.tech/topics/memory-heirarchy.md>), [cpu](<https://devfeed.tech/topics/cpu.md>), [ddr5](<https://devfeed.tech/topics/ddr5.md>)

Tags: [accelerators](<https://devfeed.tech/tags/accelerators.md>), [alex](<https://devfeed.tech/tags/alex.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [bit-parallel-arithmetic](<https://devfeed.tech/tags/bit-parallel-arithmetic.md>), [computing](<https://devfeed.tech/tags/computing.md>), [data](<https://devfeed.tech/tags/data.md>), [data-movement](<https://devfeed.tech/tags/data-movement.md>), [ddr4](<https://devfeed.tech/tags/ddr4.md>), [dram](<https://devfeed.tech/tags/dram.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [friedrich-alexander-universitat-erlangen-nurnberg](<https://devfeed.tech/tags/friedrich-alexander-universitat-erlangen-nurnberg.md>), [in-memory-computing](<https://devfeed.tech/tags/in-memory-computing.md>), [inversion-cells](<https://devfeed.tech/tags/inversion-cells.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-architecture](<https://devfeed.tech/tags/memory-architecture.md>), [memory-bandwidth](<https://devfeed.tech/tags/memory-bandwidth.md>), [migration-cells](<https://devfeed.tech/tags/migration-cells.md>), [mlperf](<https://devfeed.tech/tags/mlperf.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [pim](<https://devfeed.tech/tags/pim.md>), [power-performance](<https://devfeed.tech/tags/power-performance.md>), [processing-in-memory](<https://devfeed.tech/tags/processing-in-memory.md>), [processing-using-memory](<https://devfeed.tech/tags/processing-using-memory.md>), [pum](<https://devfeed.tech/tags/pum.md>), [rapid](<https://devfeed.tech/tags/rapid.md>), [row-parallel-computing](<https://devfeed.tech/tags/row-parallel-computing.md>), [semiconductor](<https://devfeed.tech/tags/semiconductor.md>), [semiconductor-research](<https://devfeed.tech/tags/semiconductor-research.md>), [spice-simulation](<https://devfeed.tech/tags/spice-simulation.md>), [syracuse-university](<https://devfeed.tech/tags/syracuse-university.md>), [technical-papers](<https://devfeed.tech/tags/technical-papers.md>), [tu-dresden](<https://devfeed.tech/tags/tu-dresden.md>), [volatile-memory](<https://devfeed.tech/tags/volatile-memory.md>)

### AI overview

Researchers from Syracuse University, Friedrich-Alexander-Universität Erlangen-Nürnberg, and TU Dresden present RAPID, a processing-in-DRAM architecture. It uses migration cells for movement between neighboring bitlines and inversion cells for in-array logical inversion, enabling row-parallel, bit-parallel computation while preserving CPU-compatible data layouts.

### Source excerpt

Researchers at Syracuse University, Friedrich-Alexander-Universität Erlangen-Nürnberg, and TU Dresden published a technical paper titled "RAPID: Row-Parallel Arithmetic Processing in DRAM." Abstract Excerpt: "Processing-using-memory (PUM) architectures perform computation directly within DRAM to reduce costly data movement between memory and processors. Because charge-sharing operations are confined to individual bitlines, existing DRAM-PUM architectures reorganize data into column-oriented, bit-serial... " read more The post Row-Parallel DRAM Computing Cuts Data-Reorganization Overhead (Syracuse, FAU, TU Dresden) appeared first on Semiconductor Engineering.

[Next page](<https://devfeed.tech/topics/cpu.md?cursor=WyIyMDI2LTEwLTA1VDE4OjE2OjI4KzAwOjAwIiwgImJlNjFmODUxLTQ1ZjYtNDZhOS05YjgwLWJjMzQyNzUzZjdiNyJd>)