升息緊縮, 其實玩金融遊戲都要爆, 只要是槓桿的.

舉最簡單例子: 買房如果現金付清, 不爆正常, 但大量貸款, 理論要爆.
還不爆, 就兩個支撐: 要不是自己口袋很有可以應付, 要不就是有權的人幫忙應付.

升息, 代表槓桿另一端會變重.
緊縮, 代表沒人要幫你出錢救.

重點就是看敢不敢進行到底, 戒毒(QE毒).

是USB要出APPLE了

Armv9較難理解的是SVE2！

# SVE2讓開發人員編寫和構建一次程式，就能用在不同AArch64硬體之上。
《轉貼》Why use SVE2?
The SVE2 design concept enables developers to write and build software once, then run the same binaries on different AArch64 hardware with various SVE2 vector length implementations, as the name suggests. Since some laptop and mobile devices have different vector lengths, SVE2 can reduce the cost of cross-platform support by sharing code. Removing the requirement to rebuild binaries allows software to be ported more easily. The scalability and portability of the binaries means that developers do not have to know and care about the vector length for their target devices. This particular benefit of SVE2 is more effective when the software is shared across platforms or used over an extended period of time.

# 四種使用SVE2的方法
How to use SVE2
So, how can you make the most of SVE2? There are several ways to write or generate SVE2 code:
1) A library that uses SVE2
2) SVE2-enabled Compiler
3) SVE2 Intrinsics in C/C++
4) SVE2 Assembly
https://community.arm.com/arm-commu...blog/posts/sve2

# Arm合作夥伴可在 128∼2048位元之間且以 128位為增量去設計向量長度
《轉貼》Introducing SVE2
SVE2 is a superset of SVE and Neon. SVE2 allows for more function domains in data-level parallelism. SVE2 inherits the concept, vector registers, and operation principles of SVE. SVE and SVE2 define 32 scalable vector registers. Silicon partners can choose a suitable vector length design implementation for hardware that varies between 128 bits and 2048 bits, at 128-bit increments. The advantage of SVE and SVE2 is that only one vector instruction set uses the scalable variables.

# SVE2讓開發人員編寫和構建一次程式，就能用在不同AArch64硬體之上。
The SVE design concept enables developers to write and build software once, then run the same binaries on different AArch64 hardware with various SVE vector length implementations. The portability of the binaries means that developers do not have to know the vector length implementation for their system. Removing the requirement to rebuild binaries allows software to be ported more easily.

# SVE2 指令集還可以加速以下應用
The main difference between SVE2 and SVE is the functional coverage of the instruction set. SVE was designed for HPC and ML applications. SVE2 extends the SVE instruction set to enable data-processing domains beyond HPC and ML. The SVE2 instruction set can also accelerate the common algorithms that are used in the following applications:
Computer vision
Multimedia
Long-Term Evolution (LTE) baseband processing
Genomics
In-memory database
Web serving
General-purpose software
https://developer.arm.com/documenta...ntroducing-SVE2

# Avx512也對電信營運幫助極大！
# 我猜，台積電、日月光、京元電、載板三雄能吃到電信大餅！

《轉貼快科技》Intel就推出了適合電信運營商的至強EE系列處理器，支持vRAN Boost加速，基於AVX512指令集優化而來的，在芯片內部集成了VRAN模塊。

與前一代處理器相比，第四代Intel至強處理器的基礎算力提升了53%，人工智能性能提升10倍，5G vRAN性能提升了2倍，網絡&存儲性能提升了2倍，數據分析性能提升了3倍，科學計算性能提升了3.7倍。

https://news.mydrivers.com/1/894/894032.htm

我意思是Arm、X86-64、Broadcom（Avgo）爭奪電信大餅，則台積電、日月光、京元電、載板三雄等等就有滿滿訂單。

# 國泰3/22公佈股利多寡，自行判斷是否逢低買入！
## 國泰金明揭股利，股價會跌至3字頭?

《轉貼》國泰金去年第4季舉辦史上最大現金增資，每股申購價僅35元，對照今股價面臨40元保衛戰，存股族很心動，加上國泰金早已跌破10年線46.95元，難怪網友會說「甜還有更甜，天天都便宜」、「越來越香了」、「我等全糖價」、「放著賠都舒服」、「國泰坐等跌破增資價」、「國泰金不可能倒，保險土地多到炸掉」。

國泰金明天法說，是否會動用資本公積配息備受囑目，去年配息3.5元創新高，殖利率高達6.86％。去年因防疫險慘賠及投資帳面虧損，僅賺380億元、年減逾7成，每股僅賺2.58元。

國泰金總經理李長庚日前表示，感謝金管會放寬可用資本公積或法定盈餘公積配息，業界認為，國泰金勢必會動用公積配息，且因Fed暴力升息，使歐美銀行危機連環爆，股利配發率縮水可期。
https://ctee.com.tw/news/stocks/829099.html

黃仁勳：AI的iPhone時刻來臨
https://ctee.com.tw/news/tech/830337.html

GTC 2023 Keynote with NVIDIA CEO Jensen Huang
https://www.youtube.com/watch?v=DiG...MzAzMjAyMw&t=2s

GTC 2023主題演講簡報檔
https://images.nvidia.com/nvimages/...C2023_FINAL.pdf

《轉貼》財務長陳妟如表示，目前金控資本公積 2153 億元、法定公積 737 億元，金額充沛，但實際配發金額仍待 4 月底董事會決議，但確實會比去 (2022) 年來得少，針對市場傳言今年股利會在每股 0.5 元至 1 元區間，「這的確會是考量的區間。」
https://news.cnyes.com/news/id/5122476

# Tenstorrent的RISC-V CPU用網路通訊，而非用記憶體。雖然此舉效能較差，但卻能降低成本，而吃下中小企業市場

「晶片之神」Jim Keller正式出任AI公司CEO，自研RISC-V架構全新CPU已經在路上
https://www.techbang.com/posts/1034...-becomes-ceo-of

Tenstorrent RISC-V
https://tenstorrent.com/risc-v/

《轉貼》What is Tenstorrent doing differently than GPUs?
Tenstorrent processors comprise a grid of cores known as Tensix cores. Our processors are capable of executing small and large tensor computations efficiently. Network communication hardware is present in each processor, and they talk with one another directly over networks, instead of through DRAM. Compared to GPUs, our processors are easier to program, scale better, and excel at handling run-time sparsity and conditional computation.
https://tenstorrent.com/faq/

NV這波又站上AI風頭真的屌

什麼GPT背後就是靠他家的硬體

又跟台積電等廠商合作2nm加速流程

GTC 2023 ： NVIDIA 攜手 ASML 、台積電與 Synopsys
將 NVIDIA cuLitho 加速運算技術導入半導體運算式微影技術
https://www.cool3c.com/article/190916/amp

以當前的實質效益而言，使用 NVIDIA cuLitho 技術進行運算微影的晶圓廠能夠提升 3 到 5 倍的光阻層產量，比當前的技術還少了 9 倍的能耗，可將過去需要兩周才能完成的作業在一個晚上完成

三星最近很慘，大客戶被搶光
就算擁有世界第二先進製程也沒用
大客戶要的是第一，小客戶則是連第二都用不起
靠中客戶去攤先進製程研發費？那輸慘了
Intel磨刀霍霍要搶食晶圓代工市場
可以觀察幾年看看

每日八大公股銀行買賣超排行
https://www.pttweb.cc/user/q1a1?t=article

作者q1a1 (一問一答)
標題[情報] 112/03/23 八大公股銀行買賣超排行
https://www.ptt.cc/bbs/Stock/M.1679566735.A.267.html

八大公股銀行最近大買《元大台灣５０反１》！