#CPUArchitecture
September 17, 2026 at 9:20 AM
August 17, 2026 at 11:35 AM
M6 base chip finally gets Pro-level super + performance cores—Pro features bleeding down. #AppleSilicon #M6 #MacMini #CPUArchitecture #TechNews #Performance thedailytechfeed.com/apple-m6-bri...
August 28, 2026 at 3:19 PM
📰 Intel dan AMD Umumkan Peningkatan Besar pada Arsitektur x86 untuk Masa Depan Komputasi Modern

👉 Baca artikel lengkap di sini: https://ahmandonk.com/2025/10/14/intel-amd-x86-chktag-avx10/

#ace
##ace##amd##arm0#avx10a#chktagr#cpuarchitecture #fredl#intel##isa-#risc6#x86
October 14, 2025 at 10:29 AM
Saw an article comparing the #amd "#am4 Platform" lasting 9 years and counting to "#powerpc" lasting 12, and I got the impression this person didn't realize that the comparison they are comparing a #cpusocket to a #cpuarchitecture, because as fas as I know, you couldn't upgrade an early #ppc […]
Original post on techhub.social
techhub.social
September 29, 2025 at 10:16 AM
TREVEX: Black-Box CPU Fuzzing Finds FP-DSS, New FPVI Variants, and Zero-at-ret
TREVEX is a post-silicon black-box CPU fuzzer from CISPA designed to discover data-flow transient execution vulnerabilities without needing RTL access, an ISA emulator, or a leakage contract. The framework runs across 20 microarchitectures from Intel, AMD, and Zhaoxin and uncovers a new TEA — Floating Point Divider State Sampling (FP-DSS, CVE-2025-54505) — on AMD Zen and Zen+, a new FPVI variant on AMD that does not need denormal inputs, three instances of Zero-at-ret on Intel, and FPVI on Zhaoxin. The authors weaponise FP-DSS from native code, the Linux kernel, and a Chrome JavaScript exploit. {"_yoast_wpseo_title": "TREVEX: Black-Box CPU Fuzzer Finds FP-DSS (CVE-2025-54505)", "_yoast_wpseo_metadesc": "TREVEX black-box CPU fuzzer (CISPA, S&P 2026) finds FP-DSS (CVE-2025-54505), new FPVI variants, and Zero-at-ret across 20 Intel, AMD, Zhaoxin microarchitectures.", "rank_math_title": "TREVEX: Black-Box CPU Fuzzer Finds FP-DSS (CVE-2025-54505)", "rank_math_description": "TREVEX black-box CPU fuzzer (CISPA, S&P 2026) finds FP-DSS (CVE-2025-54505), new FPVI variants, and Zero-at-ret across 20 Intel, AMD, Zhaoxin microarchitectures."}
core-jmp.org
May 23, 2026 at 6:46 PM
#Intel #CoreUltra200 #ArrowLakeS #Pcore #Ecore #IPC #TechNews #CPUArchitecture #LionCove #Skymont #NextGenCPU

Intel、Core Ultra 200「Arrow Lake-S」はPコアで9%、Eコアで32%のIPC向上と主張

Intel claims Core Ultra 200 "Arrow Lake-S" improves IPC by 9% on P cores and 32% on E cores
youtu.be/LZy2Wt0674E
Intel、Core Ultra 200「Arrow Lake-S」はPコアで9%、Eコアで32%のIPC向上と主張
YouTube video by 情報の灯台
youtu.be
October 8, 2024 at 8:09 AM
#intel #pantherlake #coreultra300 #npu5 #ai #edgeai #deeplearning #cpuarchitecture

Intel、Panther Lake「Core Ultra 300」CPUを発表。次世代NPU5アーキテクチャを搭載しAI性能を強化

Intel announces Panther Lake "Core Ultra 300" CPU. Equipped with next-generation NPU5 architecture to enhance AI performance
youtu.be/hj0fVk2f2xA
Intel、Panther Lake「Core Ultra 300」CPUを発表。次世代NPU5アーキテクチャを搭載しAI性能を強化
YouTube video by 情報の灯台
youtu.be
October 5, 2024 at 9:57 PM
Many argued that VLIW's core limitations, especially with unpredictable latencies, made it a less viable choice than Out-of-Order (OoO) execution. While flawed for general CPUs, VLIW concepts still find relevance in modern GPUs. #CPUArchitecture 5/6
August 4, 2025 at 10:00 PM
Critiques hit Intel hard for removing AVX-512 from consumer CPUs. While gains were small in this CSV test, the move hinders broader software development & adoption of powerful SIMD features. Seen as a strategic misstep. #CPUArchitecture 2/6
May 10, 2025 at 12:00 PM
ECSのWindowsコンテナをデプロイするには、サービスとタスク両方でWindowsを統一して指定する必要がある。

サービス
"platformFamily": "WINDOWS_SERVER_2022_FULL",

タスク
"runtimePlatform": {
"cpuArchitecture": "X86_64",
"operatingSystemFamily": "WINDOWS_SERVER_2022_FULL"
},
December 6, 2024 at 12:30 PM
Performance is an architectural decision.

Explore the science behind it:
flow-computing.com/science

#FlowComputing #PPU #CPU #HPC #DeepTech #Semiconductor #Semiconductors #CPUArchitecture
Modern CPUs aren’t just limited by core counts. They’re limited by how well memory, synchronization, & #parallelexecution are handled at the architectural level. #FlowPPU combines decades of parallel computing research, w/ a design that emphasizes scalable throughput & simpler parallel programming.
January 26, 2026 at 3:30 PM
We walk you through the super-pipelined, Superscalar #VLIW architecture inside each Processing Element of our PPU. Watch how this design achieves high-throughput execution with low latency and deterministic performance.👇
#FlowComputing #ParallelProcessing #DeepTech #Semiconductors #HPC #PPU #CPU
November 17, 2025 at 12:52 PM
👉 Request full demo + poster: flow-computing.com/hot-chips-20...
👉 Catch up on Part 1: lnkd.in/eyKJzV8M

Next week: PPU as part of a CPU system 101

Tomorrow: hear directly from the engineers behind these results.

#FlowComputing #PPU #ParallelProcessing #CPUArchitecture #Semiconductors
How does the #PPUt work? Pt 4
Scalability isn’t theoretical. It’s measurable. The PPU delivers 2x performance out of the box, & scales to extreme levels when optimized. This is what perfect linear scalability looks like in practice.

#FlowComputing #ParallelProcessing #CPU #Semiconductors
October 20, 2025 at 5:58 AM
👉 Missed Parts 1 & 2? Start here: lnkd.in/eyKJzV8M
👉 Request full demo + poster: flow-computing.com/hot-chips-20...

Next up: Pt. 4, Perfect Linear Scalability.

#FlowComputing #PPU #ParallelProcessing #CPUArchitecture #Semiconductor
October 14, 2025 at 4:01 AM
Optimizing `asin()` sounds simple, but hardware & compiler differences are causing chaos in distributed systems. Unpredictable latency, uneven loads – your system's efficiency is at stake!

#performanceoptimization #distributedsystems #cpuarchitecture
March 16, 2026 at 6:16 PM
New in my vintage computing book shelf. #vintagecomputing #risc #parisc #powerpc #cpu #cpuarchitecture
September 23, 2024 at 10:33 AM