Jump to content

HMB2 Memory information release by Samsung.

Samsung Electronics, the world leader in advanced memory technology, today announced that it has developed the industry’s first High Bandwidth Memory (HBM) integrated with artificial intelligence (AI) processing power — the HBM-PIM. The new processing-in-memory (PIM) architecture brings powerful AI computing capabilities inside high-performance memory, to accelerate large-scale processing in data centers, high performance computing (HPC) systems and AI-enabled mobile applications.

 

Kwangil Park, senior vice president of Memory Product Planning at Samsung Electronics stated, “Our groundbreaking HBM-PIM is the industry’s first programmable PIM solution tailored for diverse AI-driven workloads such as HPC, training and inference. We plan to build upon this breakthrough by further collaborating with AI solution providers for even more advanced PIM-powered applications.”

 

Rick Stevens, Argonne’s Associate Laboratory Director for Computing, Environment and Life Sciences commented, “I’m delighted to see that Samsung is addressing the memory bandwidth/power challenges for HPC and AI computing. HBM-PIM design has demonstrated impressive performance and power gains on important classes of AI applications, so we look forward to working together to evaluate its performance on additional problems of interest to Argonne National Laboratory.”

 

Most of today’s computing systems are based on the von Neumann architecture, which uses separate processor and memory units to carry out millions of intricate data processing tasks. This sequential processing approach requires data to constantly move back and forth, resulting in a system-slowing bottleneck especially when handling ever-increasing volumes of data.

 

Instead, the HBM-PIM brings processing power directly to where the data is stored by placing a DRAM-optimized AI engine inside each memory bank — a storage sub-unit — enabling parallel processing and minimizing data movement. When applied to Samsung’s existing HBM2 Aquabolt solution, the new architecture is able to deliver over twice the system performance while reducing energy consumption by more than 70%. The HBM-PIM also does not require any hardware or software changes, allowing faster integration into existing systems.

 

Samsung’s paper on the HBM-PIM has been selected for presentation at the renowned International Solid-State Circuits Virtual Conference (ISSCC) held through Feb. 22. Samsung’s HBM-PIM is now being tested inside AI accelerators by leading AI solution partners, with all validations expected to be completed within the first half of this year

 

Summary

memory technology integrated with artificial intelligence (AI) processing power

 

Quotes

Quote

 The new architecture will deliver over twice the system performance
and reduce energy consumption by more than 70%

 

My thoughts

I had mentioned before that I believe machine learning will be integrated into displays within 1-4 years. I included some thoughts on that as to gaming, payloads and process. I believe this article is closest example of technology moving in that direction. I do not think these tasks should be handled on only the GPU level as our media is enjoyed on every level of display technology. An integrated AI ability on display should only advance to its limits, per pixel cpu/gpu threading. 

 

Sources

https://news.samsung.com/global/samsung-develops-industrys-first-high-bandwidth-memory-with-ai-processing-power

Link to comment
Share on other sites

Link to post
Share on other sites

Thread locked. Please check for existing discussions before posting. Do not copy and paste the entire article.

 

 

Quote

We've been receiving numerous complaints about duplicate threads in this subforum with some topics and articles being posted up to five times. Please check before posting to see if another thread already exists. 

If you post a duplicate thread, it will be deleted without warning.

 

Your thread should also include quotes from the cited source(s). While you shouldn't just copy the entire article, your quote should give the reader a summary of the article in a way that gives the key details, but also leaves room for them to read the full article on the linked website. Please use quote tags to show that you have copied this content from another site.

 

CPU: Intel i7 6700k  | Motherboard: Gigabyte Z170x Gaming 5 | RAM: 2x16GB 3000MHz Corsair Vengeance LPX | GPU: Gigabyte Aorus GTX 1080ti | PSU: Corsair RM750x (2018) | Case: BeQuiet SilentBase 800 | Cooler: Arctic Freezer 34 eSports | SSD: Samsung 970 Evo 500GB + Samsung 840 500GB + Crucial MX500 2TB | Monitor: Acer Predator XB271HU + Samsung BX2450

Link to comment
Share on other sites

Link to post
Share on other sites

Guest
This topic is now closed to further replies.

×