


Reaching the top of the OpenCL list, AMD MI300X becomes the 'big brother': 7.7% faster than NVIDIA L40S and 18.8% faster than RTX 4090
According to news from this site on June 26, AMD’s MI300X graphics card appeared in GeekBench6’s OpenCL benchmark library, with a score of 379660, reaching the top of GeekBench’s OpenCL benchmark rankings, and having the highest score on the list Graphics card .
7.7%.
The above is the detailed content of Reaching the top of the OpenCL list, AMD MI300X becomes the 'big brother': 7.7% faster than NVIDIA L40S and 18.8% faster than RTX 4090. For more information, please follow other related articles on the PHP Chinese website!

Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

Notepad++7.3.1
Easy-to-use and free code editor

SublimeText3 Chinese version
Chinese version, very easy to use

Zend Studio 13.0.1
Powerful PHP integrated development environment

Dreamweaver CS6
Visual web development tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

Hot Topics



OneXGPU 2 is the first eGPUto feature the Radeon RX 7800M, a GPU that even AMD hasn't announced yet. As revealed by One-Netbook, the manufacturer of the external graphics card solution, the new AMD GPU is based on RDNA 3 architecture and has the Navi

Even though AMD tailor-made the Ryzen Z1 Extreme (and its non-Extreme variant) for handheld consoles, the chip only ever found itself in two mainstream handhelds, the Asus ROG Ally (curr. $569 on Amazon) and Lenovo Legion Go (three if you count the R

Many students are going back to school these days, and some may notice that their old laptop isn't up to the task anymore. Some college students might even be in the market for a high-end business notebook with a gorgeous OLED screen, in which case t

According to news from this site on August 10, AMD officially confirmed that some EPYC and Ryzen processors have a new vulnerability called "Sinkclose" with the code "CVE-2023-31315", which may involve millions of AMD users around the world. So, what is Sinkclose? According to a report by WIRED, the vulnerability allows intruders to run malicious code in "System Management Mode (SMM)." Allegedly, intruders can use a type of malware called a bootkit to take control of the other party's system, and this malware cannot be detected by anti-virus software. Note from this site: System Management Mode (SMM) is a special CPU working mode designed to achieve advanced power management and operating system independent functions.

Beelink continues to introduce new mini-PCs and accompanying accessories at a rate of knots. To recap, little over a month has passed since it released the EQi12, EQR6 and the EX eGPU dock. Now, the company has turned its attention to AMD's new Strix

Aoostar was among the first to announce a Strix Point mini PC, and later, Beelink launched the SER9with a soaring starting price tag of $999. Minisforum joined the party by teasingthe EliteMini AI370, and as the name suggests, it will be the company'

Asus had the first round of AMD Strix Point laptop launches, and now Lenovo has joined the party. Among the newly launched laptops is the Yoga Pro 7, which packs the Ryzen AI 9 365. Compared to the Hawk Point option launched earlier this year, the ne

The rise of small models. Last month, Meta released the Llama3.1 series of models, which includes Meta’s largest model to date, the 405B model, and two smaller models with 70 billion and 8 billion parameters respectively. Llama3.1 is considered to usher in a new era of open source. However, although the new generation models are powerful in performance, they still require a large amount of computing resources when deployed. Therefore, another trend has emerged in the industry, which is to develop small language models (SLM) that perform well enough in many language tasks and are also very cheap to deploy. Recently, NVIDIA research has shown that structured weight pruning combined with knowledge distillation can gradually obtain smaller language models from an initially larger model. Turing Award Winner, Meta Chief A
