# x86

x86 is an instruction set architecture used by software to communicate with CPUs and power computers, servers, and data centers.

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

## ELevate updates: upgrades to x86\_64\_v2 and from the installation ISO

DevFeed: [ELevate updates: upgrades to x86\_64\_v2 and from the installation ISO](<https://devfeed.tech/articles/elevate-updates-upgrades-to-x86-64-v2-and-from-the-installation-iso-146934.md>)

Original publisher: [Read original article](<https://almalinux.org/blog/2026-11-20-elevate-updates/>)

Author: Yuriy Kohut ELevate Project Engineer

Published: 2026-11-20T00:00:00Z

Content type: release

Language: en

Sources: [AlmaLinux](<https://devfeed.tech/sources/blog-on-almalinux.md>)

Topics: [project release](<https://devfeed.tech/topics/project-release.md>), [Deployment Strategies](<https://devfeed.tech/topics/deployment-strategies.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [air-gapped](<https://devfeed.tech/tags/air-gapped.md>), [almalinux](<https://devfeed.tech/tags/almalinux.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [enterprise-linux](<https://devfeed.tech/tags/enterprise-linux.md>), [epel](<https://devfeed.tech/tags/epel.md>), [framework](<https://devfeed.tech/tags/framework.md>), [iso](<https://devfeed.tech/tags/iso.md>), [release](<https://devfeed.tech/tags/release.md>), [upgrade](<https://devfeed.tech/tags/upgrade.md>), [upgrades](<https://devfeed.tech/tags/upgrades.md>), [upstream](<https://devfeed.tech/tags/upstream.md>), [v2](<https://devfeed.tech/tags/v2.md>), [x86-64](<https://devfeed.tech/tags/x86-64.md>)

### AI overview

ELevate Stable adds upgrades from AlmaLinux OS 9 to AlmaLinux OS 10 x86_64_v2 and AlmaLinux OS Kitten 10 x86_64_v2, using dedicated data packages and a downloaded x86_64_v2 rootfs; EPEL is the currently supported third-party repository for these paths. For air-gapped upgrades, `leapp preupgrade` and `leapp upgrade` accept `--iso` with a local target OS DVD image, which also serves the reboot phase. This applies to AlmaLinux 8-to-9 and 9-to-10 paths, including Kitten 10 and x86_64_v2. The ISO replaces only the target OS package source: ELevate must already be installed, and CRB and third-party packages must be handled after upgrading. The release syncs with leapp-repository 0.25.0 and framework 0.21.0, and fixes include an LVM-on-MD-RAID emergency-shell issue, custom repositories for Foreman/Katello or private mirrors, and a Secure Boot check for CentOS 7 upgrades to a different vendor. The article recommends backups or snapshots and a sandbox trial.

### Source excerpt

Hello everyone! We are happy to share that a new release of ELevate, the AlmaLinux project for in-place upgrades between major versions of Enterprise Linux distributions, is now available in ELevate Stable. It brings the upgrade path to AlmaLinux OS 10 x86_64_v2, the ability to upgrade from the installation ISO on air-gapped systems, and a sync with the current upstream leapp-repository version 0.25.0. Upgrade to AlmaLinux 10 x86_64_v2 AlmaLinux OS 10 is built for the x86_64_v3 architecture level by default, and we also provide a parallel x86_64_v2 build for older hardware. Earlier this year we asked you to help us test the upgrade to that build in ELevate NG. Thank you to everyone who tried it and reported results!

## Java4Shell: GitLab helps find and remediate a critical Java flaw

DevFeed: [Java4Shell: GitLab helps find and remediate a critical Java flaw](<https://devfeed.tech/articles/java4shell-gitlab-helps-find-and-remediate-a-critical-java-flaw-146875.md>)

Original publisher: [Read original article](<https://about.gitlab.com/blog/java4shell-critical-java-flaw-how-gitlab-helps/>)

Author: Daniel Abeles

Published: 2026-11-20T00:00:00Z

Content type: tutorial

Language: en

Sources: [GitLab](<https://devfeed.tech/sources/gitlab.md>)

Topics: [openjdk](<https://devfeed.tech/topics/openjdk.md>), [GitLab](<https://devfeed.tech/topics/gitlab.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Container Image Building](<https://devfeed.tech/topics/container-image-building.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [base64](<https://devfeed.tech/tags/base64.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [corruption](<https://devfeed.tech/tags/corruption.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cve](<https://devfeed.tech/tags/cve.md>), [cve-2026-114938](<https://devfeed.tech/tags/cve-2026-114938.md>), [cvss](<https://devfeed.tech/tags/cvss.md>), [gitlab](<https://devfeed.tech/tags/gitlab.md>), [hardening](<https://devfeed.tech/tags/hardening.md>), [java](<https://devfeed.tech/tags/java.md>), [java-flaw](<https://devfeed.tech/tags/java-flaw.md>), [java4shell](<https://devfeed.tech/tags/java4shell.md>), [jvm](<https://devfeed.tech/tags/jvm.md>), [november-17](<https://devfeed.tech/tags/november-17.md>), [openjdk](<https://devfeed.tech/tags/openjdk.md>), [optimized](<https://devfeed.tech/tags/optimized.md>), [option](<https://devfeed.tech/tags/option.md>), [remote-code-execution](<https://devfeed.tech/tags/remote-code-execution.md>), [security](<https://devfeed.tech/tags/security.md>), [security-labs](<https://devfeed.tech/tags/security-labs.md>), [security-research](<https://devfeed.tech/tags/security-research.md>), [upgrade](<https://devfeed.tech/tags/upgrade.md>)

### AI overview

Java4Shell is a memory corruption flaw in optimized Base64 decoding in recent x86-64 Java runtimes; researchers demonstrated unauthenticated remote code execution in several products' default configurations. The excerpt says GitLab assessed its own managed infrastructure as not exploitable, while proactively upgrading one component containing the affected bundle. It recommends upgrading Java runtimes from 17.0.6 onward to listed fixed builds or distribution patches; until then, `-XX:-UseBASE64Intrinsics` disables the vulnerable optimization with a slight performance cost and requires restarting Java processes. For discovery, it pairs static checks (package and optional binary container scanning, Orbit, and Java/Kotlin project filters) with runtime workload inventories, since each view can miss Java installations. It also outlines GitLab Duo agent workflows for proposing per-project fixes, with human review and merge.

### Source excerpt

GitLab has internally assessed the impact of Java4Shell, and concluded it is not exploitable in GitLab-managed infrastructure. Exploitation requires a specific combination of conditions, which we confirmed are not present in our production environment. A single component was found to contain the impacted bundle in its runtime environment, which we are proactively upgrading as a hardening measure. On November 17, 2026, OpenJDK, the project that most Java runtimes are built from, fixed a memory corruption flaw known as Java4Shell (CVE-2026-114938, CVSS 8.1) in the optimized java.util.Base64 decoding used on recent x86-64 CPUs. Web servers and frameworks routinely decode Base64 values from users, such as authentication headers and cookies, before the application sees the request. Researchers have demonstrated unauthenticated remote code execution in the default configurations of several widely used Java products. Upgrade Java to a fixed version now To mitigate this issue, upgrade every Java runtime from 17.0.6 onward, including unsupported releases such as Java 18 and 24, to a build based on OpenJDK 17.0.21.1, 21.0.13.1, 25.0.5.1, or 27.0.1.1, or to your distribution's patched package. If you can't upgrade right away, turn off the vulnerable optimization with the -XX:-UseBASE64Intrinsics JVM option. Here are fixed builds and packages as of November 19: Vendor or distributionFixed build or packageOpenJDK17.0.21.1, 21.0.13.1, 25.0.5.1, 27.0.1.1Eclipse Temurin17.0.21.1+2, 21.0.13.1+2, 25.0.5.1+2, 27.0.1.1+4Amazon Corretto17.0.21.1.2, 21.0.13.1.2, 25.0.5.1.2, 27.0.1.1.4Azul Zulu17.0.21.1, 21.0.13.1, 25.0.5.1, 27.0.1.1BellSoft Liberica17.0.21.1+5, 21.0.13.1+5, 25.0.5.1+5, 27.0.1.1+5SapMachine17.0.21.1, 21.0.13.1, 25.0.5.1, 27.0.1.1Microsoft Build of OpenJDK17.0.21.1, 21.0.13.1, 25.0.5.1Oracle Java SE 8 Performance Pack8u513-perf. Other Java 8 builds aren't affectedUbuntu 26.10, 26.04, 24.04, 22.04openjdk-17 17.0.21.1, openjdk-21 21.0.13.1, openjdk-25 25.0.5.1, and on 26.10

## Java4Shell: A critical flaw with a narrow reach

DevFeed: [Java4Shell: A critical flaw with a narrow reach](<https://devfeed.tech/articles/java4shell-a-critical-flaw-with-a-narrow-reach-140619.md>)

Original publisher: [Read original article](<https://www.malwarebytes.com/blog/bugs/2026/11/java4shell-a-critical-flaw-with-a-narrow-reach>)

Author: Pieter Arntz

Published: 2026-11-18T11:41:07Z

Content type: article

Language: en

Sources: [Malwarebytes](<https://devfeed.tech/sources/malwarebytes.md>)

Topics: [bug](<https://devfeed.tech/topics/bug.md>), [x86](<https://devfeed.tech/topics/x86.md>), [webservice](<https://devfeed.tech/topics/webservice.md>), [cybersecurity and infrastructure security agency](<https://devfeed.tech/topics/cybersecurity-and-infrastructure-security-agency.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [base64](<https://devfeed.tech/tags/base64.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [cve-2026-114938](<https://devfeed.tech/tags/cve-2026-114938.md>), [java](<https://devfeed.tech/tags/java.md>), [java4shell](<https://devfeed.tech/tags/java4shell.md>), [news](<https://devfeed.tech/tags/news.md>), [organizations](<https://devfeed.tech/tags/organizations.md>), [patch](<https://devfeed.tech/tags/patch.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

Java4Shell (CVE-2026-114938) is a memory-corruption bug in OpenJDK's hand-written x86-64 Base64 decoder fast path; malformed input can write 62 bytes past a buffer. Remote code execution requires an AVX-512 VBMI-capable x86-64 processor, an affected OpenJDK-based Java version (17.0.6 onward), an exposed application that decodes attacker-supplied data, and an application-specific exploit chain. Calif demonstrated unauthenticated code execution on default Keycloak, Jira, Confluence, Artifactory, Jenkins and PingFederate installations, and post-login execution on Kafka, Solr, Elasticsearch, Gerrit and Spinnaker. ARM64 is unaffected; Oracle says Java Web Start applications and applets cannot be used to exploit it. Oracle rates the flaw 8.1 (CVSS 3.1, difficult to exploit), while Calif rates it 9.2 (CVSS 4.0); no in-the-wild abuse was reported in the excerpt. Organizations using affected applications on vulnerable processors should patch promptly. Most home users are unlikely to be exposed.

### Source excerpt

Researchers used AI to find a Java vulnerability and named it Java4Shell. Here's why organizations need to patch.

## Java4Shell OpenJDK flaw: Exploitation is tricky and hinges on specific CPUs (CVE-2026-114938)

DevFeed: [Java4Shell OpenJDK flaw: Exploitation is tricky and hinges on specific CPUs (CVE-2026-114938)](<https://devfeed.tech/articles/java4shell-openjdk-flaw-exploitation-is-tricky-and-hinges-on-specific-cpus-cve-2026-114938-140371.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/11/18/java4shell-openjdk-vulnerability-cve-2026-114938/>)

Author: Zeljka Zorz

Published: 2026-11-18T11:12:12Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [openjdk](<https://devfeed.tech/topics/openjdk.md>), [cve remediation](<https://devfeed.tech/topics/cve-remediation.md>), [cybersecurity and infrastructure security agency](<https://devfeed.tech/topics/cybersecurity-and-infrastructure-security-agency.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [applications](<https://devfeed.tech/tags/applications.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [base64](<https://devfeed.tech/tags/base64.md>), [calif](<https://devfeed.tech/tags/calif.md>), [cisa](<https://devfeed.tech/tags/cisa.md>), [code](<https://devfeed.tech/tags/code.md>), [corruption](<https://devfeed.tech/tags/corruption.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cve](<https://devfeed.tech/tags/cve.md>), [cve-2026-114938](<https://devfeed.tech/tags/cve-2026-114938.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [cybersecurity-and-infrastructure-security-agency](<https://devfeed.tech/tags/cybersecurity-and-infrastructure-security-agency.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [don-t-miss](<https://devfeed.tech/tags/don-t-miss.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [hot-stuff](<https://devfeed.tech/tags/hot-stuff.md>), [java](<https://devfeed.tech/tags/java.md>), [java4shell](<https://devfeed.tech/tags/java4shell.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-corruption](<https://devfeed.tech/tags/memory-corruption.md>), [news](<https://devfeed.tech/tags/news.md>), [openjdk](<https://devfeed.tech/tags/openjdk.md>), [oracle](<https://devfeed.tech/tags/oracle.md>), [vulncheck](<https://devfeed.tech/tags/vulncheck.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [watchtowr](<https://devfeed.tech/tags/watchtowr.md>)

### AI overview

CVE-2026-114938 is a memory-corruption bug in OpenJDK's optimized Base64 decoder. Malformed input can corrupt adjacent memory; Calif reports unauthenticated remote code execution in default configurations of several products, while other tested products required authentication. Crashing an affected JVM is easier than achieving code execution, which VulnCheck says requires CPUs with AVX-512 VBMI and BW, heap grooming, and a separate memory leak to bypass ASLR; ARM64 is not affected. Oracle and OpenJDK have issued fixes, and vendors are releasing fixed Java builds. CISA advises inventorying Java installations and patching; if that cannot happen immediately, restrict and validate Base64 input, limit input sizes and unauthenticated access, and monitor for suspicious activity. The article reports no evidence of successful attacks so far.

### Source excerpt

CVE-2026-114938, a memory corruption flaw in Open Java Development Kit's Base64 decoder, can allow unauthenticated attackers to run code on servers hosting widely used Java applications. Nicknamed "Java4Shell" by Calif, the company whose researchers found it, CVE-2026-114938 was fixed by Oracle and the OpenJDK project on Tuesday. There is currently no evidence of successful attacks leveraging the flaw, but the US Cybersecurity and Infrastructure Security Agency (CISA) "strongly urges" organizations to patch immediately. About CVE-2026-114938 ... More -> The post Java4Shell OpenJDK flaw: Exploitation is tricky and hinges on specific CPUs (CVE-2026-114938) appeared first on Help Net Security.

## ElevatorII: High-Performance Fully-Static Cross-ISA Binary Translation

DevFeed: [ElevatorII: High-Performance Fully-Static Cross-ISA Binary Translation](<https://devfeed.tech/articles/elevatorii-high-performance-fully-static-cross-isa-binary-translation-139279.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.19577>)

Author: Hongyu Chen, James McGowan, Michael Franz

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [Cross-Compilation](<https://devfeed.tech/topics/cross-compilation.md>), [Compiler](<https://devfeed.tech/topics/compiler.md>), [x86](<https://devfeed.tech/topics/x86.md>), [obfuscation](<https://devfeed.tech/topics/obfuscation.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [binaries](<https://devfeed.tech/tags/binaries.md>), [branch](<https://devfeed.tech/tags/branch.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [code](<https://devfeed.tech/tags/code.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [control](<https://devfeed.tech/tags/control.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [data](<https://devfeed.tech/tags/data.md>), [execution](<https://devfeed.tech/tags/execution.md>), [faster](<https://devfeed.tech/tags/faster.md>), [flow](<https://devfeed.tech/tags/flow.md>), [functions](<https://devfeed.tech/tags/functions.md>), [high-performance](<https://devfeed.tech/tags/high-performance.md>), [isa](<https://devfeed.tech/tags/isa.md>), [performance](<https://devfeed.tech/tags/performance.md>), [static](<https://devfeed.tech/tags/static.md>), [translation](<https://devfeed.tech/tags/translation.md>)

### AI overview

ElevatorII is a fully static ahead-of-time translator from x86 to AArch64 that requires no target-side runtime support. It uses superset disassembly to pretranslate paths for every possible interpretation of input bytes, including computed jump destinations, then overlays optimized paths selected using observations. On 11 SPEC CPU 2026 Integer benchmarks without C++ exceptions, it runs at 2.5x native AArch64 time, matching Box64 and running 5x faster than QEMU. It also translates binaries obfuscated with virtualization and branch functions. The tradeoff is output code 51x the size of source-compiled code; moving cold code to a separate ELF section leaves 2-3% of hot code in the main section, while the rest is expected to remain unloaded.

### Source excerpt

arXiv:2611.19577v1 Announce Type: new Abstract: The established method for running software compiled for one instruction-set architecture (ISA) on a different ISA is by emulation in conjunction with just-in-time (JIT) compilation. This requires run-time support on the target that needs to be trusted and whose compilation decisions are hard to predict or reconstruct. We present ElevatorII, a fully static, ahead-of-time cross-ISA binary-to-binary compiler from x86 to AArch64 that challenges the established consensus. Our approach eliminates the need for run-time support on the target, removes the hard to reproduce effects of dynamic compilation, and provides the capability to exhaustively test the actual binary that is eventually executed. Our approach combines superset disassembly with observation-guided path selection. Superset disassembly overcomes the code vs. data differentiation problem by creating a separate control flow path for every possible interpretation of every byte in the input binary. It guarantees that there is pre-translated code for every possible jump destination in the original text segment, even for computed jumps that are not statically decidable. Static and observation-guided path selection then creates additional optimized "confirmed code paths" that overlay the regular grid. On the 11 SPEC CPU 2026 Integer benchmarks that do not use C++ exceptions, ElevatorII runs at 2.5x native AArch64 time, on par with Box64, the fastest dynamic translator, and 5x faster than QEMU. It also translates binaries obfuscated with virtualization and branch functions, which no static disassembler can follow. Our approach trades execution performance for space: our output code is 51x the size of code compiled from source. We alleviate this by separating cold code to a .text.unlikely ELF section: only 2-3% hot code winds up in the main ELF section, while the rest will likely never be loaded into memory.

## User-Schedulable Approximations for Quantized Tensor Programs

DevFeed: [User-Schedulable Approximations for Quantized Tensor Programs](<https://devfeed.tech/articles/user-schedulable-approximations-for-quantized-tensor-programs-135792.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17526>)

Author: Alex Reinking

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [ggml](<https://devfeed.tech/topics/ggml.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Functional programming](<https://devfeed.tech/topics/functional-programming.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [activation](<https://devfeed.tech/tags/activation.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [apple](<https://devfeed.tech/tags/apple.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [arm](<https://devfeed.tech/tags/arm.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [block](<https://devfeed.tech/tags/block.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [cases](<https://devfeed.tech/tags/cases.md>), [code](<https://devfeed.tech/tags/code.md>), [codec](<https://devfeed.tech/tags/codec.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [covering](<https://devfeed.tech/tags/covering.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-pf](<https://devfeed.tech/tags/cs-pf.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [devices](<https://devfeed.tech/tags/devices.md>), [user](<https://devfeed.tech/tags/user.md>)

### AI overview

The work extends Halide so quantization codecs--paired encoders and decoders built from reusable quantizers, integer representations, bit packers, and layouts--can be applied to program stages and scheduled like ordinary computation. Property-tested contracts can catch representation errors; a round-trip law exposed an inconsistent block sum in GGML's q8_1. One algorithm and schedule library generates 347 kernels for 31 GGML and KleidiAI formats on Arm CPUs and Apple GPUs, covering 38 weight-activation pairs without GGML kernels, using 3.7x less code than GGML and KleidiAI. On Apple M3 Max, the kernels reach at least 95% of GGML's format-specific kernel speed in 91.0% of comparable cases, with 1.13x median speedup; including Apple BLAS lowers the threshold share to 86.9% of CPU cases. An x86 port with Intel AMX adds 793 lines and matches GGML in 83.5% of its cases.

### Source excerpt

arXiv:2611.17526v1 Announce Type: cross Abstract: Quantization lets language models run on edge devices, but it sharply increases the number of tensor kernels a library must maintain: every weight format must be paired with every activation format on every instruction set and GPU, with an encoder and a decoder that agree on the stored bytes. In GGML, the tensor library used by llama.cpp, these kernels are written by hand, and only 8 of the 54 weight-activation pairs it runs on our Arm CPU have a tiled matrix-multiplication kernel. We extend Halide's separation of algorithm and schedule to the representation of values. Each approximation is a codec, an encoder paired with a decoder, composed from reusable units: quantizers, integer representations, bit packers and layouts. A new directive, approximate_by, applies a codec to one stage of a program and returns the encoder and decoder as ordinary stages that Halide can schedule, so both decoders fuse into the register tiles of a matrix product. Optional contracts, such as a round-trip law, are checked by property tests; the law exposed an inconsistent block sum in GGML's q8_1. One algorithm and one schedule library generate 347 kernels for 31 of GGML's and KleidiAI's formats on Arm CPUs and Apple GPUs, covering 38 weight-activation pairs for which GGML has no kernel, in 3.7x less code than GGML and KleidiAI. On an Apple M3 Max, our kernels reach at least 95% of the speed of GGML's format-specific kernels in 91.0% of the cases that have one, with a median speedup of 1.13x, and are faster still where GGML falls back to blocked dot products. Counting Apple's BLAS library, which is usually faster for larger f32 products, we still reach that threshold in 86.9% of CPU cases. A port to x86 with Intel's AMX adds 793 lines of code and matches GGML in 83.5% of its cases.

## The Hackintosh might be back, with macOS booting on Snapdragon and x86 PCs

DevFeed: [The Hackintosh might be back, with macOS booting on Snapdragon and x86 PCs](<https://devfeed.tech/articles/the-hackintosh-might-be-back-with-macos-booting-on-snapdragon-and-x86-pcs-134029.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114551-hackintosh-might-back-macos-booting-snapdragon-x86-pcs.html>)

Author: Daniel Sims

Published: 2026-11-14T14:26:00Z

Content type: news

Language: en

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

Topics: [macOS](<https://devfeed.tech/topics/macos.md>), [x86](<https://devfeed.tech/topics/x86.md>), [boot](<https://devfeed.tech/topics/boot.md>)

Tags: [amd](<https://devfeed.tech/tags/amd.md>), [apple](<https://devfeed.tech/tags/apple.md>), [apple-silicon](<https://devfeed.tech/tags/apple-silicon.md>), [arm](<https://devfeed.tech/tags/arm.md>), [asus-zenbook](<https://devfeed.tech/tags/asus-zenbook.md>), [audio](<https://devfeed.tech/tags/audio.md>), [beta](<https://devfeed.tech/tags/beta.md>), [bluetooth](<https://devfeed.tech/tags/bluetooth.md>), [displays](<https://devfeed.tech/tags/displays.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [github](<https://devfeed.tech/tags/github.md>), [graphics](<https://devfeed.tech/tags/graphics.md>), [graphics-card](<https://devfeed.tech/tags/graphics-card.md>), [hacking](<https://devfeed.tech/tags/hacking.md>), [hackintosh](<https://devfeed.tech/tags/hackintosh.md>), [intel](<https://devfeed.tech/tags/intel.md>), [laptop](<https://devfeed.tech/tags/laptop.md>), [macos](<https://devfeed.tech/tags/macos.md>), [modding](<https://devfeed.tech/tags/modding.md>), [operating-system](<https://devfeed.tech/tags/operating-system.md>), [qualcomm-snapdragon](<https://devfeed.tech/tags/qualcomm-snapdragon.md>), [snapdragon](<https://devfeed.tech/tags/snapdragon.md>), [software](<https://devfeed.tech/tags/software.md>), [tech-culture](<https://devfeed.tech/tags/tech-culture.md>), [translation](<https://devfeed.tech/tags/translation.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

Two projects are testing ways to run macOS on non-Apple PCs, with different hardware and maturity. Snapintosh has booted on an Asus Zenbook A16 with a Snapdragon X2 Elite, but requires a Mac host, does not run on battery, and lacks Wi-Fi, audio, cameras, Bluetooth, sleep, and external display support; performance also cannot sustain a stable 60 fps. Stela's open beta uses Arm-to-x86 translation and supports Intel Nehalem or newer and AMD Bulldozer or newer systems, with at least 8GB RAM and an Nvidia GTX 16-series or newer GPU. Installation starts by running its setup executable in Windows and choosing a USB stick; the online installer needs 8GB free, the offline version 32GB, and the target drive 60GB. Stela also lacks Wi-Fi and audio, though Bluetooth works. The excerpt gives no beta timing for Snapintosh.

### Source excerpt

Users can now try an early version of a new Arm-to-x86 translation layer that aims to support macOS on most recent Intel and AMD processors. Elsewhere, another project has booted the operating system on a Snapdragon-powered Asus Zenbook with basic functionality. Read Entire Article

## Wine 11.22 Introduces x86 AVX Emulation On ARM64

DevFeed: [Wine 11.22 Introduces x86 AVX Emulation On ARM64](<https://devfeed.tech/articles/wine-11-22-introduces-x86-avx-emulation-on-arm64-133503.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Wine-11.22-Released>)

Author: Michael Larabel

Published: 2026-11-14T01:35:04Z

Content type: release

Language: en

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

Topics: [WINE](<https://devfeed.tech/topics/wine.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [arm64](<https://devfeed.tech/tags/arm64.md>), [avx](<https://devfeed.tech/tags/avx.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [emulation](<https://devfeed.tech/tags/emulation.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>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [release](<https://devfeed.tech/tags/release.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [wine](<https://devfeed.tech/tags/wine.md>), [wine-11](<https://devfeed.tech/tags/wine-11.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

Wine 11.22 adds AVX emulation to Wine's x86 emulation path on ARM64, enabling modern Windows software that assumes AVX support to run through ARM64EC builds. The change follows initial NTDLL AVX support on ARM64EC and related XState work. Other listed updates include Unicode CLDR 49 locale data, address space randomization, improved Tahoma glyph metrics, reimplemented XML DTD validation, and 34 bug fixes, including fixes affecting Logos Bible Software, Guild Wars 2, and Star Citizen.

### Source excerpt

Wine 11.22 is out today as the latest bi-weekly development release and inching quite closely toward the Wine 12.0 stable release preparations...

## AMD takes on Intel and Nvidia with new 256-core EPYC server CPUs

DevFeed: [AMD takes on Intel and Nvidia with new 256-core EPYC server CPUs](<https://devfeed.tech/articles/amd-takes-on-intel-and-nvidia-with-new-256-core-epyc-server-cpus-131101.md>)

Original publisher: [Read original article](<https://www.networkworld.com/article/4247802/amd-takes-on-intel-and-nvidia-with-new-256-core-epyc-server-cpus.html>)

Author: Nidhi Singal

Published: 2026-11-12T11:36:33Z

Content type: news

Language: en

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

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [systems](<https://devfeed.tech/topics/systems.md>), [ddr5](<https://devfeed.tech/topics/ddr5.md>), [x86](<https://devfeed.tech/topics/x86.md>), [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>), [Azure](<https://devfeed.tech/topics/azure.md>)

Tags: [accelerated](<https://devfeed.tech/tags/accelerated.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [amd](<https://devfeed.tech/tags/amd.md>), [amd-epyc](<https://devfeed.tech/tags/amd-epyc.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [azure](<https://devfeed.tech/tags/azure.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [business](<https://devfeed.tech/tags/business.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [core](<https://devfeed.tech/tags/core.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cpus-and-processors](<https://devfeed.tech/tags/cpus-and-processors.md>), [cpus-and-processors-data-center-servers](<https://devfeed.tech/tags/cpus-and-processors-data-center-servers.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [epyc](<https://devfeed.tech/tags/epyc.md>), [intel](<https://devfeed.tech/tags/intel.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [server](<https://devfeed.tech/tags/server.md>), [server-cpus](<https://devfeed.tech/tags/server-cpus.md>), [servers](<https://devfeed.tech/tags/servers.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

AMD's 6th Gen EPYC 9006 SP7 lineup spans 10 models with 64-256 cores, up to 512 threads, 16 DDR5 memory channels, and PCIe Gen 6; systems are shipping, with Azure and Oracle Cloud instances expected soon. AMD's comparisons claim up to 3.7x the performance of Nvidia Vera, up to 2.2x that of Intel Xeon 6980P, and higher agent capacity per CPU watt; these are company claims. The excerpt describes high-core-count models for cloud consolidation, VDI, and agent workloads, and high-frequency models for databases and enterprise applications sensitive to licensing costs. Nvidia Vera is positioned for integrated AI clusters, while Intel Xeon may suit enterprises retaining existing x86 infrastructure. CIOs are advised to assess workload performance, power, memory, compatibility, and total ownership costs over three to five years, including licensing and migration, since these can offset server-consolidation savings.

### Source excerpt

As enterprises race to deploy AI agents and expand AI infrastructure, AMD has launched a new generation of EPYC server processors built to challenge both Intel's dominance in enterprise CPUs and Nvidia's ambitions in data-center computing. The 6th Gen EPYC lineup offers up to 256 cores per socket and supports PCIe Gen 6 and DDR5 memory, with AMD touting major gains in performance, efficiency and AI throughput. "With 6th Gen AMD EPYC, customers can standardize on the proven x86 foundation while choosing a workload-optimized solution to run more agents, keep accelerated infrastructure fed and power the business-critical applications they depend on," Dan McNamara, senior vice president and general manager, Compute and Enterprise AI, AMD, said in a statement. Systems powered by the new CPUs are now shipping from leading server manufacturers and original design manufacturers (ODMs), while cloud instances from Microsoft Azure and Oracle Cloud Infrastructure (OCI) will be available soon. The hardware mechanics The EPYC 9006 SP7 range comprises 10 processor models, with configurations ranging from 64 to 256 cores and up to 512 threads per socket. The portfolio includes high-density processors for workloads requiring large numbers of simultaneous computing tasks, as well as high-frequency variants with boost speeds of up to 5.3GHz. Across the SP7 range, the processors support 16 channels of DDR5 memory and PCIe Gen 6 connectivity, offering twice the bandwidth per lane compared with PCIe Gen 5. "Rather than simply increasing core counts, AMD aims to deliver more computing power within existing power and infrastructure limits. This makes the platform particularly relevant for cloud computing, virtualization, high-performance computing (HPC), enterprise databases, data analytics and AI infrastructure," said Manish Rawat, semiconductor analyst at TechInsights. Benchmarking the competition AMD is pitching the new processors against Intel's Xeon and Nvidia's Vera CPUs, claiming si

## AMD Tunes Up CPUs For Agentic AI With "Venice" Epyc Processors

DevFeed: [AMD Tunes Up CPUs For Agentic AI With "Venice" Epyc Processors](<https://devfeed.tech/articles/amd-tunes-up-cpus-for-agentic-ai-with-venice-epyc-processors-126819.md>)

Original publisher: [Read original article](<https://www.nextplatform.com/compute/2026/11/10/amd-tunes-up-cpus-for-agentic-ai-with-venice-epyc-processors/5308850>)

Author: Jeff Burt

Published: 2026-11-10T17:06:06Z

Content type: news

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>), [x86](<https://devfeed.tech/topics/x86.md>), [Arm](<https://devfeed.tech/topics/arm.md>), [Graviton](<https://devfeed.tech/topics/graviton.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [1-5](<https://devfeed.tech/tags/1-5.md>), [1-6](<https://devfeed.tech/tags/1-6.md>), [2018](<https://devfeed.tech/tags/2018.md>), [2022](<https://devfeed.tech/tags/2022.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amd](<https://devfeed.tech/tags/amd.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [chatgpt-chatbot](<https://devfeed.tech/tags/chatgpt-chatbot.md>), [compute](<https://devfeed.tech/tags/compute.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [epyc](<https://devfeed.tech/tags/epyc.md>), [introduction](<https://devfeed.tech/tags/introduction.md>), [launch](<https://devfeed.tech/tags/launch.md>), [openai](<https://devfeed.tech/tags/openai.md>), [processors](<https://devfeed.tech/tags/processors.md>), [up](<https://devfeed.tech/tags/up.md>), [venice](<https://devfeed.tech/tags/venice.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

AMD presents its 6th Gen Epyc "Venice" CPUs as a fit for agentic AI, whose multi-step workflows involve orchestration, databases, APIs, enterprise tools and isolated code execution. The article says agentic AI could increase CPU demand relative to GPUs, though AMD did not design Venice specifically for it. AMD reports 1.9x throughput versus prior Turin processors; Venice scales to 96 cores at 5.3 GHz, with 16 DDR5 channels delivering 1.6 TB/s and PCIe Gen 6. AMD also claims a 256-core, 400-watt model achieves 3.3x Vera's agents per watt and higher agents per dollar than Intel's 6th Gen Xeons. These are company comparisons; the article notes ephemeral agent tools lack a well-defined benchmark and describes AMD's selected workloads as representative samples.

### Source excerpt

The introduction of the ChatGPT chatbot by OpenAI in late 2022 supercharged the launch of of the Gen ...

## x86 Ecosystem Advisory Group Posts ACE v2 & AVX10.3 Specs, GCC Patches Ready

DevFeed: [x86 Ecosystem Advisory Group Posts ACE v2 & AVX10.3 Specs, GCC Patches Ready](<https://devfeed.tech/articles/x86-ecosystem-advisory-group-posts-ace-v2-avx10-3-specs-gcc-patches-ready-126327.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/ACE-v2-AVX10.3-Posted>)

Author: Michael Larabel

Published: 2026-11-10T11:01:00Z

Content type: news

Language: en

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

Topics: [x86](<https://devfeed.tech/topics/x86.md>), [patches](<https://devfeed.tech/topics/patches.md>)

Tags: [ace](<https://devfeed.tech/tags/ace.md>), [advisory-group](<https://devfeed.tech/tags/advisory-group.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [avx](<https://devfeed.tech/tags/avx.md>), [bf16](<https://devfeed.tech/tags/bf16.md>), [builds](<https://devfeed.tech/tags/builds.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [gcc](<https://devfeed.tech/tags/gcc.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>), [patches](<https://devfeed.tech/tags/patches.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [posts](<https://devfeed.tech/tags/posts.md>), [processors](<https://devfeed.tech/tags/processors.md>), [specifications](<https://devfeed.tech/tags/specifications.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [v2](<https://devfeed.tech/tags/v2.md>), [with](<https://devfeed.tech/tags/with.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

The x86 Ecosystem Advisory Group has posted ACE v2 and AVX10.3 specifications for future processor development. ACE v2 adds 4-bit formats, expands 8-bit capabilities, and supports FP16, FP32, and FP64. AVX10.3 adds general vectorization improvements, including conversions between FP8 and BF16 and from FP16/BF16 to INT4. GCC patch series for the new ACE and AVX10.3 instructions are ready for review. The article says processors supporting these features are likely in the 2028-2029 timeframe.

### Source excerpt

While there aren't any processors released yet with AI Compute Extensions (ACE) or AVX10.2 quite yet, the x86 Ecosystem Advisory Group led by AMD and Intel have now posted their ACE v2 and AVX10.3 specifications...

## Sem86 full-system x86 emulator

DevFeed: [Sem86 full-system x86 emulator](<https://devfeed.tech/articles/sem86-full-system-x86-emulator-123800.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/09/sem86-full-system-x86-emulator/>)

Author: Anne Barela

Published: 2026-11-09T16:01:37Z

Content type: article

Language: en

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

Topics: [Emulator](<https://devfeed.tech/topics/emulator.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [emulation](<https://devfeed.tech/tags/emulation.md>), [emulator](<https://devfeed.tech/tags/emulator.md>), [full](<https://devfeed.tech/tags/full.md>), [history](<https://devfeed.tech/tags/history.md>), [llvm](<https://devfeed.tech/tags/llvm.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-analysis](<https://devfeed.tech/tags/malware-analysis.md>), [microprocessors](<https://devfeed.tech/tags/microprocessors.md>), [sem86](<https://devfeed.tech/tags/sem86.md>), [system](<https://devfeed.tech/tags/system.md>), [vintage-computing](<https://devfeed.tech/tags/vintage-computing.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

Sem86 is a full-system x86 emulator whose instruction semantics are loaded from a file and can be changed during execution. This lets it model chip-specific behavior for undefined or undocumented instructions; the team demonstrated using mid-run changes and bisection to locate where a toy malware sample's behavior diverges, a technique relevant to malware analysis. Sem86 uses LLVM rather than a custom JIT and is reported as 1.9x Bochs' speed and about 42% of QEMU's. It implements enough Pentium-era hardware to boot Windows 3.1, 98, XP, 7, and Debian 8, with optional ES1370 audio, VBE video, and NE2k networking. It also runs on Android, though LLVM memory use can crash it on an 8 GiB phone.

### Source excerpt

Sem86 is an x86 full-system emulator that loads instruction behavior from a file at runtime, so undefined or undocumented instructions can be changed by editing the file. That makes it possible to emulate undefined behavior and undocumented instructions the way a particular chip handles them. It uses LLVM rather than a custom JIT, and it's [...]

## Linux x86 32-bit Patches Clean Old Kernel Code After Recently Removing Vintage CPUs

DevFeed: [Linux x86 32-bit Patches Clean Old Kernel Code After Recently Removing Vintage CPUs](<https://devfeed.tech/articles/linux-x86-32-bit-patches-clean-old-kernel-code-after-recently-removing-vintage-cpus-121293.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Linux-2026-x86-32-bit-Cleanup>)

Author: Michael Larabel

Published: 2026-11-06T14:11:31Z

Content type: news

Language: en

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

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [x86](<https://devfeed.tech/topics/x86.md>), [patches](<https://devfeed.tech/topics/patches.md>)

Tags: [32-bit](<https://devfeed.tech/tags/32-bit.md>), [amd](<https://devfeed.tech/tags/amd.md>), [cache](<https://devfeed.tech/tags/cache.md>), [can](<https://devfeed.tech/tags/can.md>), [code](<https://devfeed.tech/tags/code.md>), [compare](<https://devfeed.tech/tags/compare.md>), [counter](<https://devfeed.tech/tags/counter.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [developer](<https://devfeed.tech/tags/developer.md>), [exchange](<https://devfeed.tech/tags/exchange.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/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>), [other](<https://devfeed.tech/tags/other.md>), [patches](<https://devfeed.tech/tags/patches.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [support](<https://devfeed.tech/tags/support.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [vintage](<https://devfeed.tech/tags/vintage.md>), [with](<https://devfeed.tech/tags/with.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

After older 32-bit CPUs were removed from Linux support, Arnd Bergmann proposed x86 32-bit cleanup patches. They remove lingering AMD Elan code and other obsolete dependencies, make Time Stamp Counter (TSC) and CX8 support unconditional, require at least 64-byte cache lines, and simplify instruction-set selection. The stated aim is to remove unnecessary code and bring 32-bit x86 code closer to x86_64; the excerpt describes a patch series, not whether it was merged.

### Source excerpt

With the Linux kernek having phased out i486 CPU support and dropping old AMD Elan SoC code along with removing other obsolete and stagnate 32-bit x86 hardware support, some x86 32-bit clean-ups are proceeding along with being able to make the kernel depend unconditionally now on some features...

## AMD on track to overtake Intel as biggest x86 outfit

DevFeed: [AMD on track to overtake Intel as biggest x86 outfit](<https://devfeed.tech/articles/amd-on-track-to-overtake-intel-as-biggest-x86-outfit-117102.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/04/amd-on-track-to-overtake-intel-as-biggest-x86-outfit/>)

Author: Anne Barela

Published: 2026-11-04T16:04:46Z

Content type: news

Language: en

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

Topics: [x86](<https://devfeed.tech/topics/x86.md>), [intel](<https://devfeed.tech/topics/intel.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [advanced-packaging](<https://devfeed.tech/tags/advanced-packaging.md>), [amd](<https://devfeed.tech/tags/amd.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [client](<https://devfeed.tech/tags/client.md>), [computers](<https://devfeed.tech/tags/computers.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [gaming](<https://devfeed.tech/tags/gaming.md>), [growth](<https://devfeed.tech/tags/growth.md>), [history](<https://devfeed.tech/tags/history.md>), [intel](<https://devfeed.tech/tags/intel.md>), [lisa-su](<https://devfeed.tech/tags/lisa-su.md>), [memory](<https://devfeed.tech/tags/memory.md>), [microprocessors](<https://devfeed.tech/tags/microprocessors.md>), [q3](<https://devfeed.tech/tags/q3.md>), [results](<https://devfeed.tech/tags/results.md>), [revenue](<https://devfeed.tech/tags/revenue.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

AMD expects to surpass Intel in chip sales next quarter, with guidance of about $17 billion in revenue versus Intel's $15 billion to $16 billion. Its Q3 revenue rose 45 percent year over year to $13.4 billion, led by Data Center, up 97 percent to $8.5 billion. Client and gaming revenue fell 8 percent, although PC chip sales within it rose 7 percent to $2.9 billion. CEO Lisa Su forecast more than 80 percent company growth in 2027 and roughly doubled data center CPU business, saying AMD had secured the wafers, substrates, advanced packaging and memory needed. Intel would still have higher total revenue because of its foundry business.

### Source excerpt

Simon Sharwood, writing for The Register, reports that AMD expects to bring in more revenue than Intel next quarter. That would make AMD the biggest vendor whose main product is the x86 processor, after years of trailing its rival. AMD's Q3 2026 results showed revenue up 45 percent year over year to $13.4 billion, with [...]

## AMD Q3 2026 Earnings Data Center Growth Drives Record Quarter

DevFeed: [AMD Q3 2026 Earnings Data Center Growth Drives Record Quarter](<https://devfeed.tech/articles/amd-q3-2026-earnings-data-center-growth-drives-record-quarter-117159.md>)

Original publisher: [Read original article](<https://www.servethehome.com/amd-q3-2026-earnings-data-center-growth/>)

Author: Cliff Robinson

Published: 2026-11-04T05:24:08Z

Content type: article

Language: en

Sources: [ServeTheHome](<https://devfeed.tech/sources/servethehome.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [x86](<https://devfeed.tech/topics/x86.md>), [ddr5](<https://devfeed.tech/topics/ddr5.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [acceleration](<https://devfeed.tech/tags/acceleration.md>), [aerospace](<https://devfeed.tech/tags/aerospace.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [amd](<https://devfeed.tech/tags/amd.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-center-growth](<https://devfeed.tech/tags/data-center-growth.md>), [data-center-revenue](<https://devfeed.tech/tags/data-center-revenue.md>), [defense](<https://devfeed.tech/tags/defense.md>), [demand](<https://devfeed.tech/tags/demand.md>), [earnings](<https://devfeed.tech/tags/earnings.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [growth](<https://devfeed.tech/tags/growth.md>), [leadership](<https://devfeed.tech/tags/leadership.md>), [news](<https://devfeed.tech/tags/news.md>), [q3](<https://devfeed.tech/tags/q3.md>), [q3-2026-earnings](<https://devfeed.tech/tags/q3-2026-earnings.md>), [venice](<https://devfeed.tech/tags/venice.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

AMD reported Q3 2026 revenue of $13.377 billion, up 45% year over year, with Data Center revenue nearly doubling to $8.546 billion. AMD attributes the segment's growth to strong EPYC demand and the launch of Instinct MI450 GPUs; it says major clients are running workloads on Helios rack-scale systems. The article compares AMD's Data Center growth of 97% with Intel's 78% on $7.3 billion in quarterly revenue. Client and Gaming revenue fell 8% to $3.722 billion, while Embedded rose 29% to $1.109 billion. AMD forecast Q4 revenue of about $17 billion, plus or minus 3%, implying roughly 66% year-over-year growth at the midpoint. The article's expectations about Venice's future x86 performance leadership and Intel's Diamond Rapids timing are projections, not reported results.

### Source excerpt

AMD Q3 2026 earnings were massive with the data center and embedded segments seeing big uplift with the clear Venice x86 leadership looming The post AMD Q3 2026 Earnings Data Center Growth Drives Record Quarter appeared first on ServeTheHome.

## AMD Ryzen Zen 6 Looks Like It Will Be In Good Shape With Linux 7.4, Laptop Improvements

DevFeed: [AMD Ryzen Zen 6 Looks Like It Will Be In Good Shape With Linux 7.4, Laptop Improvements](<https://devfeed.tech/articles/amd-ryzen-zen-6-looks-like-it-will-be-in-good-shape-with-linux-7-4-laptop-improvements-108938.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Linux-7.4-x86-Platform-Driver>)

Author: Michael Larabel

Published: 2026-10-30T15:24:46Z

Content type: news

Language: en

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

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [7-4](<https://devfeed.tech/tags/7-4.md>), [added](<https://devfeed.tech/tags/added.md>), [amd](<https://devfeed.tech/tags/amd.md>), [amd-ryzen](<https://devfeed.tech/tags/amd-ryzen.md>), [arm](<https://devfeed.tech/tags/arm.md>), [asus](<https://devfeed.tech/tags/asus.md>), [battery](<https://devfeed.tech/tags/battery.md>), [changes](<https://devfeed.tech/tags/changes.md>), [client](<https://devfeed.tech/tags/client.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [driver](<https://devfeed.tech/tags/driver.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [it](<https://devfeed.tech/tags/it.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [laptop](<https://devfeed.tech/tags/laptop.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-7-4](<https://devfeed.tech/tags/linux-7-4.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>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [platform](<https://devfeed.tech/tags/platform.md>), [ryzen](<https://devfeed.tech/tags/ryzen.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [x86](<https://devfeed.tech/tags/x86.md>), [zen-6](<https://devfeed.tech/tags/zen-6.md>)

### AI overview

Linux 7.4 adds early platform-driver support for upcoming AMD Ryzen Zen 6 systems: the AMD HSMP and PMC drivers gain Zen 6 support, and the PMF driver adds the AMDI0112 ID, described as presumably for Zen 6. The excerpt also lists hardware and control support across laptop vendors, including Acer hardware monitoring, fan and battery controls; additional Alienware, MSI, HP, ASUS and Uniwill device support; and Ayaneo and OneXPlayer handhelds. Snapdragon X laptop changes include ASUS Glymur EC support and a Lenovo Yoga Slim 7x Gen 11 EC driver. These are driver additions and IDs; the excerpt does not establish broader compatibility or describe testing outcomes.

### Source excerpt

The x86 platform driver changes were merged this week to the Linux 7.4 kernel ahead of the merge window closing this weekend...

## Quantized Edge Inference of a Self-Supervised SAR-Optical Encoder on Commodity x86 Hardware

DevFeed: [Quantized Edge Inference of a Self-Supervised SAR-Optical Encoder on Commodity x86 Hardware](<https://devfeed.tech/articles/quantized-edge-inference-of-a-self-supervised-sar-optical-encoder-on-commodity-x86-hardware-104039.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.37056>)

Author: Christian Sanchez-Leon, Dongming Chen

Published: 2026-10-28T04:00:00Z

Content type: news

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [quantization](<https://devfeed.tech/topics/quantization.md>), [x86](<https://devfeed.tech/topics/x86.md>), [On-device AI](<https://devfeed.tech/topics/on-device-ai.md>), [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [avx2](<https://devfeed.tech/tags/avx2.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [device](<https://devfeed.tech/tags/device.md>), [earth](<https://devfeed.tech/tags/earth.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-inference](<https://devfeed.tech/tags/edge-inference.md>), [eess-iv](<https://devfeed.tech/tags/eess-iv.md>), [energy](<https://devfeed.tech/tags/energy.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [inference](<https://devfeed.tech/tags/inference.md>), [int8](<https://devfeed.tech/tags/int8.md>), [latency](<https://devfeed.tech/tags/latency.md>), [linear](<https://devfeed.tech/tags/linear.md>), [low-power](<https://devfeed.tech/tags/low-power.md>), [node](<https://devfeed.tech/tags/node.md>), [optical](<https://devfeed.tech/tags/optical.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

On three commodity x86 nodes, INT8 inference of a pretrained SAR-optical masked-autoencoder encoder reduced CPU cost while preserving linear-probe accuracy: micro-mAP changed by only +0.0006, within seed spread. INT8 lowered CPU latency on every node, including a 1.45x gain on the CPU without AVX2, and reduced CPU energy wherever measured; the AVX2+VNNI reference showed a 1.53x latency gain. The best device depended on the CPU: the integrated GPU was 4.38x faster on the weakest node, while the Pareto-optimal choice shifted to the CPU as CPU capability improved. The excerpt describes measurements at FP32, FP16, and INT8, but does not provide full methods or results.

### Source excerpt

arXiv:2610.37056v1 Announce Type: cross Abstract: Self-supervised vision transformers are increasingly used as reusable encoders for Earth observation, but their inference cost on the hardware available in the field is rarely characterized. We deploy a pretrained SAR-optical masked-autoencoder encoder on three commodity x86 nodes, from a low-power CPU without AVX2 to an AVX2+VNNI reference, at FP32, FP16 and INT8 on the CPU and, where present, the integrated GPU, and report latency, energy (RAPL and wall plug) and linear-probe accuracy. Quantization is accuracy-neutral: INT8 changes micro-mAP by only +0.0006, within the seed spread, so precision becomes a pure cost decision. INT8 lowers CPU latency on every node, by 1.45x even on the CPU without AVX2, and CPU energy wherever it is measured, and the VNNI reference (1.53x) suggests a further gain beyond AVX2. The Pareto-optimal device shifts from the integrated GPU, which is 4.38x faster than the CPU on the weakest node, to the CPU as the CPU class improves.

## v21.2.0 Umbrella released

DevFeed: [v21.2.0 Umbrella released](<https://devfeed.tech/articles/v21-2-0-umbrella-released-105503.md>)

Original publisher: [Read original article](<https://ceph.io/en/news/blog/2026/v21-2-0-umbrella-released/>)

Author: Yuri Weinstein

Published: 2026-10-28T00:00:00Z

Content type: release

Language: en

Sources: [Ceph Blog](<https://devfeed.tech/sources/ceph-blog.md>)

Topics: [radosgw](<https://devfeed.tech/topics/radosgw.md>), [container images](<https://devfeed.tech/topics/container-images.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [health check](<https://devfeed.tech/topics/health-check.md>), [rocksdb](<https://devfeed.tech/topics/rocksdb.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [4k](<https://devfeed.tech/tags/4k.md>), [added](<https://devfeed.tech/tags/added.md>), [aes](<https://devfeed.tech/tags/aes.md>), [aggregates](<https://devfeed.tech/tags/aggregates.md>), [all](<https://devfeed.tech/tags/all.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [authentication-bypass](<https://devfeed.tech/tags/authentication-bypass.md>), [availability](<https://devfeed.tech/tags/availability.md>), [backup](<https://devfeed.tech/tags/backup.md>), [based](<https://devfeed.tech/tags/based.md>), [blog-post](<https://devfeed.tech/tags/blog-post.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [can](<https://devfeed.tech/tags/can.md>), [cases](<https://devfeed.tech/tags/cases.md>), [ceph](<https://devfeed.tech/tags/ceph.md>), [changes](<https://devfeed.tech/tags/changes.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [en-article](<https://devfeed.tech/tags/en-article.md>), [en-blog-post](<https://devfeed.tech/tags/en-blog-post.md>), [release](<https://devfeed.tech/tags/release.md>), [umbrella](<https://devfeed.tech/tags/umbrella.md>)

### AI overview

Ceph v21.2.0 Umbrella is the project's first stable Umbrella release. Its container images use Rocky Linux 10 and require x86-64-v3-capable CPUs; cephadm requires Python 3.9 or newer on every host. Major changes include a new optimized erasure-coding I/O path with related health warnings and alignment constraints, stronger CephX defaults and online key rotation, and optional monitor RocksDB backup and restore. The release also raises PG autoscaler defaults, which may increase PG counts after upgrade; the text describes a pacing option and cautions some deployments to retain the previous settings. Other highlights span RGW logging, cloud restore and encryption, expanded NVMe-oF and SMB management, cephadm certificate support and CRUSH-aware upgrades, CephFS mirroring, and Crimson erasure coding and PG splitting.

### Source excerpt

Umbrella is the 21st stable release of Ceph. This is the first stable release of Ceph Umbrella. We recommend all users update to this release. Warning: Umbrella container images are based on Rocky Linux 10 (el10), which requires a CPU supporting the x86-64-v3 microarchitecture level. Deployments on hosts with older CPUs will not be able to run the containerized daemons. Warning: Python 3.9 or newer is required on all hosts for cephadm support. Release Date ¶ October 28, 2026 Notable Changes ¶ RADOS / OSD / Erasure Coding ¶ Optimized ("Fast") Erasure Coding: a substantial new EC I/O path. EC Direct Reads CLS support for EC reads EC OMAP support Add Fast EC CRC-checking for data and first parity Numerous correctness fixes to the new path (truncate+write planning, PDW vs RMW selection, snapshot scrub handling, peering/recovery corner cases) Ships with health warnings for deprecated EC plugins/techniques and for Blaum-Roth EC profiles whose w+1 isn't prime; non-4k-aligned chunk sizes are now rejected for optimized EC. Security: CephX authentication hardening -- new AES256KRB5 cipher (replacing weaker legacy key types as the default), online key rotation for mon/OSD/MDS daemons during upgrades, and fixes for CVE-2025-30156 (AES-CBC misuse enabling authentication bypass), CVE-2026-39944, CVE-2026-50152, and CVE-2026-54330 (pr#71172). Monitor: new optional RocksDB backup/restore mechanism (mon_backup_interval, ceph tell mon.* backup, offline restore via ceph-mon --restore-backup). New availability score feature for Monitor/OSD (tracking + health warnings config toggle), off by default. Stretch clusters: tiebreaker mon can now be optional, added a max bucket-weight-diff threshold, a health warning for colocated monitors, and a restriction on changing the election strategy after stretch mode is enabled. mgr/DaemonServer: ok-to-upgrade now aggregates and globally sorts OSDs across CRUSH child buckets (fixing inaccurate per-chassis/rack ordering), and upgrades can now be scope

## Windows is preparing for Intel's biggest x86 change in years, but only Xeon chips will use it at first

DevFeed: [Windows is preparing for Intel's biggest x86 change in years, but only Xeon chips will use it at first](<https://devfeed.tech/articles/windows-is-preparing-for-intel-s-biggest-x86-change-in-years-but-only-xeon-chips-will-use-it-at-first-100717.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114337-windows-preparing-intel-biggest-x86-change-years-but.html>)

Author: Alfonso Maruccia

Published: 2026-10-26T19:06:00Z

Content type: news

Language: en

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

Topics: [Windows](<https://devfeed.tech/topics/windows.md>), [x86](<https://devfeed.tech/topics/x86.md>), [intel](<https://devfeed.tech/topics/intel.md>), [Xeon 600](<https://devfeed.tech/topics/xeon-600.md>)

Tags: [advanced](<https://devfeed.tech/tags/advanced.md>), [but](<https://devfeed.tech/tags/but.md>), [change](<https://devfeed.tech/tags/change.md>), [changes](<https://devfeed.tech/tags/changes.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [enthusiast](<https://devfeed.tech/tags/enthusiast.md>), [extensions](<https://devfeed.tech/tags/extensions.md>), [first](<https://devfeed.tech/tags/first.md>), [future](<https://devfeed.tech/tags/future.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [insider](<https://devfeed.tech/tags/insider.md>), [intel](<https://devfeed.tech/tags/intel.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [offer](<https://devfeed.tech/tags/offer.md>), [option](<https://devfeed.tech/tags/option.md>), [os](<https://devfeed.tech/tags/os.md>), [performance](<https://devfeed.tech/tags/performance.md>), [releases](<https://devfeed.tech/tags/releases.md>), [software](<https://devfeed.tech/tags/software.md>), [windows](<https://devfeed.tech/tags/windows.md>), [windows-11](<https://devfeed.tech/tags/windows-11.md>), [windows-insider](<https://devfeed.tech/tags/windows-insider.md>), [x86](<https://devfeed.tech/tags/x86.md>), [xeon](<https://devfeed.tech/tags/xeon.md>)

### AI overview

Windows Insider build 29695 contains a manually enabled APX setting that requires a reboot, but Xeno says it is currently for developers and has no practical effect on the OS. APX doubles x86-64 general-purpose registers from 16 to 32; Intel says APX-compiled code has 10% fewer loads and over 20% fewer stores than its baseline, and developers can adopt it by recompiling. Those figures suggest potential performance and dynamic-power benefits, but actual gains depend on software and workload and remain unproven. Initial compatible processors are expected to be Diamond Rapids Xeon chips; the excerpt suggests Windows support could arrive in a 2027 update.

### Source excerpt

Windows enthusiast Xeno recently uncovered what could be one of the most interesting changes coming to future Windows releases. Microsoft's OS may soon offer an option to enable Advanced Performance Extensions (APX) support on compatible hardware, the self-described "Windows Insider since day one" said. In turn, APX could deliver a... Read Entire Article

## Reading temperature of Intel CPUs by (carefully) making a hole in the Matrix

DevFeed: [Reading temperature of Intel CPUs by (carefully) making a hole in the Matrix](<https://devfeed.tech/articles/reading-temperature-of-intel-cpus-by-carefully-making-a-hole-in-the-matrix-99108.md>)

Original publisher: [Read original article](<https://xcp-ng.org/blog/2026/10/25/intel-cpu-temperature-xcp-ng/>)

Author: Teddy Astie

Published: 2026-10-25T09:00:08Z

Content type: article

Language: en

Sources: [XCP-ng](<https://devfeed.tech/sources/xcp-ng-blog.md>)

Topics: [Xen](<https://devfeed.tech/topics/xen.md>), [Intel Core](<https://devfeed.tech/topics/intel-core.md>), [x86](<https://devfeed.tech/topics/x86.md>)

Tags: [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [devblog](<https://devfeed.tech/tags/devblog.md>), [intel](<https://devfeed.tech/tags/intel.md>), [temperature](<https://devfeed.tech/tags/temperature.md>), [xen](<https://devfeed.tech/tags/xen.md>)

### AI overview

Intel core temperature can be calculated from the per-core `IA32_THERM_STATUS` digital readout and `MSR_TEMPERATURE_TARGET`'s `tjmax`; package temperature uses `MSR_PACKAGE_THERM_STATUS`. Under Xen, Dom0's virtual CPUs may not map consistently to physical cores, Dom0 may expose fewer CPUs than the hardware has, and `rdmsr` access is restricted, so Linux's `coretemp` driver cannot reliably provide readings. Xen exposes selected MSRs through the `XENPF_resource_op` hypercall; after Xen's allowed-register list is updated, `xenpm get-core-temp` reads them for specific physical CPUs and computes temperatures. AMD uses Northbridge/System Management Unit registers accessible through PCI MMIO from Dom0, so it does not require this Xen-specific support and can use `k10temp` or `zenpower`; some recent AMD CPUs may need `k10temp` recognition patches.

### Source excerpt

CPU temperature readings break under Xen on Intel. Teddy Astie explains why, and how XCP-ng now reads them with xenpm get-core-temp.

## AMD and Intel Make oneDNN the Default x86 Path in PyTorch, Folding ZenDNN In and Lining Up AI Compute Extensions

DevFeed: [AMD and Intel Make oneDNN the Default x86 Path in PyTorch, Folding ZenDNN In and Lining Up AI Compute Extensions](<https://devfeed.tech/articles/amd-and-intel-make-onednn-the-default-x86-path-in-pytorch-folding-zendnn-in-and-lining-up-ai-compute-extensions-95988.md>)

Original publisher: [Read original article](<https://www.storagereview.com/news/amd-intel-onednn-default-x86-pytorch-zendnn-ai-compute-extensions>)

Author: Harold Fritts

Published: 2026-10-22T16:44:09Z

Content type: news

Language: en

Sources: [StorageReview.com](<https://devfeed.tech/sources/storagereview-com.md>)

Topics: [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [x86](<https://devfeed.tech/topics/x86.md>), [intel](<https://devfeed.tech/topics/intel.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [accelerate](<https://devfeed.tech/tags/accelerate.md>), [advisory-group](<https://devfeed.tech/tags/advisory-group.md>), [ai-compute](<https://devfeed.tech/tags/ai-compute.md>), [amd](<https://devfeed.tech/tags/amd.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [compute-density](<https://devfeed.tech/tags/compute-density.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpu-optimization](<https://devfeed.tech/tags/cpu-optimization.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [epyc](<https://devfeed.tech/tags/epyc.md>), [extensions](<https://devfeed.tech/tags/extensions.md>), [intel](<https://devfeed.tech/tags/intel.md>), [library](<https://devfeed.tech/tags/library.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [optimizations](<https://devfeed.tech/tags/optimizations.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [software](<https://devfeed.tech/tags/software.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

AMD and Intel are consolidating their PyTorch CPU optimizations for x86 in oneDNN, which they identify as PyTorch's default open-source x86 acceleration library. AMD is folding ZenDNN's EPYC-tuned primitives into oneDNN while continuing processor-specific optimization, aiming to put both vendors' kernels behind the same PyTorch calls and simplify access to optimized inference and training. They also plan to expose jointly defined AI Compute Extensions (ACE) through future oneDNN updates. The excerpt describes ACE's matrix instructions and supported data types, but says neither the consolidated implementation's release timeline or performance nor the processor generations that will support ACE have been announced; the claimed 16x compute density is from the ACE specification.

### Source excerpt

AMD and Intel announced that they will combine their x86 CPU optimization work for PyTorch in oneDNN, the open-source deep learning library governed by the Unified Acceleration Foundation (UXL), and have aligned on it as the default open-source library for x86 acceleration inside PyTorch. AMD is folding its ZenDNN optimizations into oneDNN and has joined The post AMD and Intel Make oneDNN the Default x86 Path in PyTorch, Folding ZenDNN In and Lining Up AI Compute Extensions appeared first on StorageReview.com.

## x86 Kernel Shadow Stacks Being Worked On For Linux As Powerful Control Flow Protection

DevFeed: [x86 Kernel Shadow Stacks Being Worked On For Linux As Powerful Control Flow Protection](<https://devfeed.tech/articles/x86-kernel-shadow-stacks-being-worked-on-for-linux-as-powerful-control-flow-protection-95729.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Linux-Kernel-Shadow-Stacks>)

Author: Michael Larabel

Published: 2026-10-22T13:22:56Z

Content type: news

Language: en

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

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [Kernel](<https://devfeed.tech/topics/kernel.md>), [x86](<https://devfeed.tech/topics/x86.md>), [eBPF](<https://devfeed.tech/topics/ebpf.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [amd](<https://devfeed.tech/tags/amd.md>), [but](<https://devfeed.tech/tags/but.md>), [code](<https://devfeed.tech/tags/code.md>), [control](<https://devfeed.tech/tags/control.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [dave](<https://devfeed.tech/tags/dave.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [flow](<https://devfeed.tech/tags/flow.md>), [intel](<https://devfeed.tech/tags/intel.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/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>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [powerful](<https://devfeed.tech/tags/powerful.md>), [protection](<https://devfeed.tech/tags/protection.md>), [return](<https://devfeed.tech/tags/return.md>), [stack](<https://devfeed.tech/tags/stack.md>), [support](<https://devfeed.tech/tags/support.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [x86](<https://devfeed.tech/tags/x86.md>)

### AI overview

An RFC from Intel engineer Dave Hansen proposes running the Linux kernel with x86 shadow stacks, a protected parallel stack for return addresses intended to help defend against control-flow attacks. The proposal is proof of concept and seeks discussion about what an initial merge could include; Hansen says parts may be reusable while others need substantial rework. The current RFC requires Flexible Return Event Delivery (FRED), limiting support to Intel Panther Lake and newer or AMD Zen 6 and beyond. It is incompatible with several features, including Retpolines, function graph tracing, BPF trampolines, Kexec, EFI mixed mode, KVM, and Xen PV. Initial testing has been done on Intel Panther Lake.

### Source excerpt

Linux user-space for several years had shadow stack support for hardware-enforced control-flow enforcement in defending against return oriented programming (ROP) attacks. Intel Tigerlake and newer CPUs or AMD Zen 3 and newer have the necessary hardware shadow stacks support. Shadow stacks have been effective for helping user-space software fend ROP attacks while now there is new work toward bringing shadow stack support for kernel space on Linux...

## Linux 7.4 Kernel Crypto Library Enjoying Optimized AES Implementations On x86 & RISC-V

DevFeed: [Linux 7.4 Kernel Crypto Library Enjoying Optimized AES Implementations On x86 & RISC-V](<https://devfeed.tech/articles/linux-7-4-kernel-crypto-library-enjoying-optimized-aes-implementations-on-x86-risc-v-93155.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Linux-7.4-Crypto-Library>)

Author: Michael Larabel

Published: 2026-10-21T20:11:03Z

Content type: news

Language: en

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

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [x86](<https://devfeed.tech/topics/x86.md>), [Library](<https://devfeed.tech/topics/library.md>), [RISC-V](<https://devfeed.tech/topics/riscv.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [7-4](<https://devfeed.tech/tags/7-4.md>), [accelerated](<https://devfeed.tech/tags/accelerated.md>), [acceleration](<https://devfeed.tech/tags/acceleration.md>), [aes](<https://devfeed.tech/tags/aes.md>), [crypto](<https://devfeed.tech/tags/crypto.md>), [cryptographic](<https://devfeed.tech/tags/cryptographic.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [faster](<https://devfeed.tech/tags/faster.md>), [google](<https://devfeed.tech/tags/google.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [library](<https://devfeed.tech/tags/library.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-7-4](<https://devfeed.tech/tags/linux-7-4.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-kernel](<https://devfeed.tech/tags/linux-kernel.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>), [optimized](<https://devfeed.tech/tags/optimized.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>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>), [x86](<https://devfeed.tech/tags/x86.md>), [x86-64](<https://devfeed.tech/tags/x86-64.md>)

### AI overview

Merged for Linux 7.4, optimized AES implementations for ECB, CBC, CBC-CTS, CTR, XCTR and XTS were moved into the kernel crypto library for x86/x86_64 and RISC-V. This accelerates the library APIs on those architectures while preserving acceleration for crypto_skcipher; x86_64 uses AVX-optimized code and AES-NI. The change also removes duplicated glue code. Separately, SPARC64 gains an optimized AES-XTS implementation using its crypto opcodes.

### Source excerpt

The latest Linux kernel cryptographic subsystem performance work carried out by Google engineer Eric Biggers is migrating x86/x86_64 and RISC-V optimized implementations of different AES modes into the lib/crypto kernel crypto library to enjoy faster performance there...

## CAFS: A Cache-Aware Frequency Sort for Low-Cardinality Integer Data on x86-64

DevFeed: [CAFS: A Cache-Aware Frequency Sort for Low-Cardinality Integer Data on x86-64](<https://devfeed.tech/articles/cafs-a-cache-aware-frequency-sort-for-low-cardinality-integer-data-on-x86-64-93870.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.25040>)

Author: Vasiliy S. Shlyk

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [vectorization techniques](<https://devfeed.tech/topics/vectorization-techniques.md>), [Cache](<https://devfeed.tech/topics/cache.md>), [CPU Cache](<https://devfeed.tech/topics/cpu-cache.md>), [x86](<https://devfeed.tech/topics/x86.md>), [olap](<https://devfeed.tech/topics/olap.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [array](<https://devfeed.tech/tags/array.md>), [avx2](<https://devfeed.tech/tags/avx2.md>), [cache](<https://devfeed.tech/tags/cache.md>), [cardinality](<https://devfeed.tech/tags/cardinality.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-ds](<https://devfeed.tech/tags/cs-ds.md>), [olap](<https://devfeed.tech/tags/olap.md>), [open-addressing](<https://devfeed.tech/tags/open-addressing.md>), [operational](<https://devfeed.tech/tags/operational.md>), [pdqsort](<https://devfeed.tech/tags/pdqsort.md>), [radix-sort](<https://devfeed.tech/tags/radix-sort.md>), [simd](<https://devfeed.tech/tags/simd.md>), [ska-sort](<https://devfeed.tech/tags/ska-sort.md>), [sort](<https://devfeed.tech/tags/sort.md>), [throughput](<https://devfeed.tech/tags/throughput.md>), [x86-64](<https://devfeed.tech/tags/x86-64.md>)

### AI overview

CAFS targets integer arrays with many values but low cardinality, common in OLAP workloads. On x86-64 with AVX2, it combines a cache-line-sized SIMD bucket, a Chao1 estimator using 1,024 strided samples, and an adaptive dispatcher with a spill safety guard; its branchless hot loop uses cmpeq, movemask, and tzcnt. Across 592,770 benchmark runs, CAFS reached 1.7-3.1x pdqsort, 1.7-3.5x IPS4o, and 1.2-2.3x vqsort throughput when K was much smaller than N. The reported crossover is about K=130,000 for pdqsort and 670,000 for vqsort; only vqsort overtook CAFS beyond its crossover, making that threshold the stated limit of CAFS's operational range. The evidence is an abstract-level summary of benchmarks, not full paper coverage.

### Source excerpt

arXiv:2605.25040v2 Announce Type: replace-cross Abstract: Integer sorts in OLAP engines often run on columns whose cardinality $K$ is much smaller than the array length $N$. After a group-by stage the intermediate key column has $K$ bounded by the number of distinct group keys, and even a column-store scan typically operates on dictionary-encoded categorical fields where $K$ never exceeds a few thousand. A comparison sort on such a column still pays $\Theta(N \log N)$ comparisons, and a radix sort still pays $\Theta(N \cdot B/b)$ byte passes, irrespective of $K$. This paper describes CAFS, an integer sort that does exploit it on x86-64 with AVX2. The algorithm combines a SIMD bucket sized to one cache line, a Chao1 cardinality estimator over 1024 strided samples (kept in a heap-allocated 40 KB open-addressing table), and an adaptive dispatcher backed by a spill safety guard. The hot loop is branchless and uses AVX2 cmpeq together with movemask and tzcnt to locate the matching lane. We benchmarked CAFS on a full-factorial grid of 58 array sizes $N$ from $10^3$ to $3 \cdot 10^7$ with dense $K$ schedules per $N$, producing 592770 timed runs against pdqsort, IPS4o, vqsort, ska_sort, and std::sort. In the $K \ll N$ band the throughput is 1.7 to 3.1x that of pdqsort, 1.7 to 3.5x IPS4o, and 1.2 to 2.3x vqsort. The operational crossover against pdqsort is at $K \approx 1.3 \cdot 10^5$; against ska_sort, $K \approx 8.14 \cdot 10^5$; against vqsort, $K \approx 6.7 \cdot 10^5$; and against IPS4o the curves only converge near $K = N$. Of the five baselines, only vqsort actually overtakes CAFS once the crossover is passed, which makes the vqsort threshold at $K \approx 6.7 \cdot 10^5$ the binding constraint on the operational range of CAFS.

[Next page](<https://devfeed.tech/topics/x86.md?cursor=WyIyMDI2LTEwLTIxVDA0OjAwOjAwKzAwOjAwIiwgIjgyMTc3OWRlLTMyZTAtNDI3ZS04ZjVkLWNjMWI3YmFkZDRhMyJd>)