Panmnesia's ML-driven Prefetching Technology for CXL-SSD Has Been Selected as KAIST Breakthroughs

Panmnesia’s machine learning-driven prefetching technology for CXL-SSD has been selected as KAIST Breakthroughs this year. KAIST Breakthroughs is a webzine that selectively highlights innovative technologies across various engineering disciplines, encompassing electrical engineering, biotechnology, environmental engineering, and industrial engineering. In this year, KAIST Breakthroughs has highlighted 31 technologies, including Panmnesia’s pioneering work. Panmnesia’s featured technology focuses on enhancing performance of systems that utilize CXL-SSDs. By utilizing the CXL interface, we can use SSD, which is commonly used as a block storage, as a huge memory device. The CXL-SSD harnesses host-side caching advantages while providing tremendous memory capacity. Therefore, it is garnering considerable attention from both industry and academia. However, systems employing CXL-SSDs may encounter long latency of SSD, when cache miss occurs. Panmnesia has addressed this challenge by developing machine learning-based prefetching techniques capable of predicting future memory access information and reading it prior to the actual request. With an in-depth understanding of CXL-based system hierarchies, Panmnesia has crafted a solution that accurately forecasts future access addresses and determines the optimal prefetching timing. If you are intrigued by this innovative work, you can access the original article featured in KAIST Breakthroughs through the following link. KAIST Breakthroughs

Panmnesia on Flash Memory Summit 2023

Panmnesia, the global frontrunner in CXL IP (Intellectual Property) advancement, is proud to unveil its groundbreaking, self-developed multi-terabyte, full-system CXL framework. This exciting development was launched during the 2023 Flash Memory Summit, held August 8-10 at the Santa Clara Convention Center, California. The Summit, a major annual event attracting over 3,000 participants, unites leading companies from around the globe, all specializing in memory and storage solutions. A brief on CXL Interface: The emergence of large-scale applications such as generative AI, Chat-GPT, and recommendation systems has fueled the demand for efficient large-capacity memory technologies and accelerators like GPUs in data centers. Amid this technological shift, the CXL (Compute eXpress Link, CXL) interface technology has gained prominence. CXL allows data centers to drastically expand their memory capacity and enables computing devices such as CPUs and accelerators to utilize this enlarged memory space efficiently, putting it in the industry spotlight. Panmnesia and CXL Technology: As the pioneer of the world's first CXL interface-based full-system framework, Panmnesia stands at the forefront of CXL IP development. Panmnesia design and supply all necessary CXL IPs to implement CXL solutions for data centers. Panmnesia's portfolio includes CXL Core IP and CXL IP for various CXL devices like CPU, NPU, switch, and device. The CXL Core IP supports all CXL devices to facilitate CXL cache communication (CXL.cache), CXL memory communication (CXL.mem), and CXL I/O communication (CXL.io), the primary communication protocols of the CXL interface. Additionally, Panmnesia provides CXL IPs tailored to specific hardware automation functions for each CXL device. Clients of Panmnesia can efficiently develop CXL devices by applying the company’s verified CXL IP to existing devices, thereby reducing additional costs and time associated with IP development and validation. "We're excited to introduce our innovative multi- terabyte full-system CXL framework at this year's Flash Memory Summit," says Dr. Myoungsoo Jung, CEO at Panmnesia. "Our commitment to pioneering cutting-edge solutions is demonstrated through our CXL IP, which we believe will significantly enhance memory and storage capabilities within data centers." At the 2023 Flash Memory Summit, Panmnesia exhibited a multi-terabyte memory pool framework powered by its proprietary CXL IP. Panmnesia also showcased a demonstration video of Meta’s large-scale AI application running within the memory pool framework. The Panmnesia Solution: Panmnesia showcased its multi-terabyte memory pool at the Flash Memory Summit 2023. This pool, consisting of CXL CPU, CXL Switch, and CXL Memory Expander, sets new benchmarks in performance, scalability, adaptability, and efficiency, distinguishing it from other existing memory expansion solutions. Panmnesia’s cutting-edge multi-terabyte memory pool framework encompasses both CXL hardware IP and corresponding software, ensuring high performance and substantial memory capacity expansion. By leveraging multiple CXL switches and CXL memory expanders, this complete solution can seamlessly integrate with existing data center ecosystems. Panmnesia’s innovative CXL Switch technology enables the memory pool framework to efficiently allocate expanded memory space based on user demand. Additionally, by employing a DIMM pooling method for memory module replacement, memory capacity can be increased without procuring extra memory expanders. This makes Panmnesia's memory pool framework a cost-effective memory expansion solution, balancing memory resource management with data center operational cost efficiency. Panmnesia’s CXL Demo - A Real-World Application Success: Panmnesia showcased a demonstration video featuring Meta’s recommendation system, a notable large-scale AI application, running on the implemented memory pool framework. This demonstration showed Panmnesia's solution could reduce the execution time of Meta’s recommendation system by 3.32 times compared to the existing RDMA-based memory expansion solutions used in data centers. Looking forward, Panmnesia is committed to continue pushing the boundaries of CXL technology. Panmnesia aim to further improve data center performance and efficiency through ongoing research, development, and implementation of advanced CXL solutions. The CXL IP and multi-terabyte memory pool framework presented by Panmnesia at the Flash Memory Summit 2023 embody a forward-thinking data center solution. It offers system-side benefits along with operational cost efficiency. Uniquely, Panmnesia is the only company to display the comprehensive use of CXL IP technology from the operating systems to real-world applications, giving them a significant edge over other data center solutions. To view Panmnesia’s CXL memory pool demonstration video again, visit the link below. Link - Demo Video (Youtube) Link - Article (Blocks and Files)

Demo - Panmnesia's Authentic, Multi-Terabyte CXL Memory Disaggregation Framework

All set to explore the horizon of technological advancement at this year’s Flash Memory Summit (FMS)? Make sure you’ve got Panmnesia on your must-see list! This year at FMS 23, we’re beyond excited to present our live demo, entitled “Experience Reality, Not Blueprints: Panmnesia’s Authentic, Multi-Terabyte CXL Memory Disaggregation Framework.” We believe in the power of action over words, which is why we’re bringing you a fully-operational CXL solution. Panmnesia’s groundbreaking CXL system includes all the requisite hardware components, ranging from custom-designed CXL CPUs and switches, to our state-of-the-art DIMM pool devices. Our robust framework enables multi-terabyte capacity by integrating a myriad of memory devices via multi-tiered CXL switches. We can’t wait to showcase how CXL technology can supercharge real-world applications. As a part of our demo at FMS 23, we’ll demonstrate a deep learning recommendation system operating in harmony with LinuxOS and Panmnesia’s innovative CXL framework. Plus, you can gain deeper insights from the other demo videos we’ll be sharing. Intrigued by what real innovation looks like? Make sure to visit us at booth #655 during the Flash Memory Summit, and get up close with the future of technology, brought to life by Panmnesia! Link - Demo Video (Youtube)

Panmnesia will participate in Flash Memory Summit 2023

Panmnesia is excited to announce our participation in the Flash Memory Summit (FMS) 2023, taking place in Santa Clara, California, US, from August 8th to August 10th. This premier event is a global platform for industry leaders and innovative thinkers to showcase and discuss the latest advancements in flash memory technology. At this year’s FMS, Panmnesia will be in the spotlight with our groundbreaking full-system CXL (Compute Express Link) framework. This pioneering infrastructure consists of customized CXL CPUs, switches, and DIMM pools. Our innovation doesn’t stop there, though; we’ve designed the framework to offer multi-terabyte capacity by connecting a plethora of memory devices through multi-level CXL switches. One of the standout features of our system is the incorporation of DIMM pooling technology. By strategically utilizing this technology, we’ve made it possible to achieve substantial cost reductions, all the while maintaining the system’s high performance and reliability. Our team will demonstrate exactly how CXL technology can revolutionize real-world applications. Visitors will be treated to a live and captivating demo of recommendation systems running on a real deep learning framework with Linux OS. This example will provide a tangible glimpse into how our technologies can enhance and streamline systems in various sectors, from cloud computing to high-performance computing (HPC) to data centers and beyond. For everyone interested in learning more about Panmnesia’s innovative technologies, we extend a warm invitation to visit us at booth 655 at the Flash Memory Summit. Our team will be on hand to share insights, answer questions, and explore potential collaborations. We look forward to meeting fellow industry enthusiasts and exploring the future of memory technology together at FMS 2023! Link - Flash Memory Summit 2023

Panmnesia's Invited Presentation at SIGARCH Korea Workshop

Panmnesia delivered an invited presentation (title: Breaking Down CXL: Why It’s Crucial and What’s Next) at the SIGARCH Korea Workshop 2023 held in SNU(Seoul National University). During this presentation, we extensively dissected the ins and outs of Compute Express Link (CXL) technology, highlighting its relevance and the present status of its advancement. CXL is a potent interconnect standard offering high-speed, low-latency communication between CPUs and diverse accelerators such as FPGAs and GPUs. It allows these devices to share memory space and maintain cache coherence, resulting in swift data access and efficient processing of intricate tasks. Our exploration of CXL began from its genesis, the CXL 1.0 specification, and continued through its successive iterations, including the recently launched CXL 3.0. We emphasized the unique features of each iteration, differences among them, and the advantages of CXL compared to other interconnect standards. Beyond just the technicalities of CXL, we also navigated its real-world impact. We specifically addressed how CXL is deployed in large-scale data centers and its role in fostering innovation in areas like artificial intelligence and machine learning. Overall, this talk served as a platform to share a thorough understanding of CXL technology, from its fundamental principles to its practical applications. It was truly delightful discussing CXL technology with a number of professors and students who are passionate about computer architecture. Thank you for the invitation!

Panmnesia's Invited Talk at OCP APAC Tech Day

Panmnesia had the privilege of leading a talk at the OCP (Open Compute Project) APAC Tech Day, staged at COEX in Seoul. Our presentation, “Memory Pooling over CXL and Go Beyond with AI,” highlighted the importance and fundamentals of CXL(Compute Express Link), along with its potential to propel large-scale AI applications forward. Specifically, we first provided a comprehensive overview of CXL technology and examined why it matters. We then explored the different versions of CXL, starting with the original CXL 1.0 specification and its subsequent updates, including the recently released CXL 3.0. We also delved into the real-world implications of this technology, such as artificial intelligence and machine learning. We’re incredibly grateful to our engaged audience for their interest and to the event organizers for hosting such a successful day. We look forward to participating in future OCP events! Link - OCP APAC Tech Day

Panmnesia will present at OCP APAC Tech Day

Panmnesia will be delivering an invited talk at OCP(Open Compute Project) APAC Tech Day. Our talk will provide a comprehensive overview of CXL(Compute Express Link) technology, from its foundational principles to its practical applications, such as machine learning. We cordially invite you to join us at OCP APAC Tech Day on July 4th at COEX, Seoul. If you’re interested in delving into the intricacies of CXL technology and widening your understanding, this event is perfect for you. Link - OCP APAC Tech Day

Panmnesia's Groundbreaking AI Vector Search System based on CXL 3.0

Panmnesia’s groundbreaking AI vector search solution has been highlighted in recent ‘Blocks and Files’ and ‘New Electronics’ articles. The core innovation of our CXL-augmented AI vector search solution is its ability to separate memory from the central processing unit, achieved through the implementation of CXL 3.0. This strategic decoupling allows for substantial AI search data to be accommodated within the memory pool, potentially reaching a staggering 4 Petabytes per CPU’s root complex. Notably, our CXL-augmented AI vector search solution boosts the rate of query processing by a whopping 111.1 times, outstripping existing strategies, including those employed by Microsoft’s production service. For an in-depth exploration of the AI vector search solution, please refer to the links below. Link - Article (Blocks and Files) Link - Article (New Electronics)

Special Seminar on Harnessing the Potential of CXL with Panmnesia

Panmnesia had the pleasure of being invited by Professor Byung-Gon Chun, the CEO of FriendliAI at Seoul National University, to present at his seminar. During our presentation, we shed light on two significant applications of the advanced Compute Express Link (CXL) technology. Firstly, we discussed a combined software-hardware system that enhances search capabilities for approximate nearest neighbors. This solution uses CXL to separate memory from host resources and optimize search performance despite CXL’s distant memory characteristics. It employs innovative strategies and utilizes all available hardware, outperforming current platforms in query latency. Secondly, we presented a robust system for managing large recommendation datasets. It harnesses CXL to integrate persistent memory and graphics processing units seamlessly, enabling direct memory access without software intervention. With a sophisticated checkpointing technique that updates model parameters and embeddings across training batches, we’ve seen a significant boost in training performance and energy savings. We’re looking forward to more such opportunities! Keep an eye out for our future endeavors! Link - Seminar Information