- 42
- 206 836
CXL Consortium
United States
Приєднався 31 січ 2020
Compute Express Link (CXL) is a new breakthrough high-speed CPU interconnect that enables a high-speed, efficient performance between the CPU and platform enhancements and workload accelerators.
Industry leaders Alibaba, Cisco, Dell EMC, Facebook, Google, Hewlett Packard Enterprise, Huawei, Intel Corporation and Microsoft have teamed up to form an open industry standard group to develop technical specifications that facilitate breakthrough performance for emerging usage models while supporting an open ecosystem for data center accelerators and other high-speed enhancements.
Industry leaders Alibaba, Cisco, Dell EMC, Facebook, Google, Hewlett Packard Enterprise, Huawei, Intel Corporation and Microsoft have teamed up to form an open industry standard group to develop technical specifications that facilitate breakthrough performance for emerging usage models while supporting an open ecosystem for data center accelerators and other high-speed enhancements.
Exploring CXL® Use Cases and Implementations
CXL is an open coherent interconnect standard that enables heterogeneous computing, increases memory capacity and bandwidth, and optimizes performance for current workloads and emerging applications. CXL Consortium members are offering products based on the CXL 1.1 and 2.0 specifications and developing products based on the CXL 3.x specification.
Join CXL Consortium member companies Astera Labs, Samtec, and UniFabriX as they highlight their ongoing work to create CXL solutions that addresses emerging use cases and applications. The webinar will explore CXL feature capabilities, implementations, and future capabilities of CXL devices.
Presented by: Ahmed Medhioub (Astera Labs), Matthew Burns (Samtec), and Oren Benisty (UnifabriX)
Join CXL Consortium member companies Astera Labs, Samtec, and UniFabriX as they highlight their ongoing work to create CXL solutions that addresses emerging use cases and applications. The webinar will explore CXL feature capabilities, implementations, and future capabilities of CXL devices.
Presented by: Ahmed Medhioub (Astera Labs), Matthew Burns (Samtec), and Oren Benisty (UnifabriX)
Переглядів: 1 246
Відео
Introducing the CXL 3.1 Specification
Переглядів 3,1 тис.7 місяців тому
The CXL 3.1 Specification introduces enhancements to fabric capability and manager API definition for PBR switch, inter-host communication using Global Integrated Memory (GIM), Trusted-Execution-Environment Security Protocol (TSP), and memory expander improvements. These enhancements will enable composable and disaggregated systems to keep up with the demand for high-performance computational w...
Increasing Memory Utilization and Reducing Total Memory Cost Using CXL
Переглядів 8699 місяців тому
CXL’s advanced memory expansion and fabric management capabilities can be used to increase system scalability and flexibility across multiple compute domains, enabling resource sharing for higher performance, reduced software stack complexity, and lower overall datacenter memory cost. The fabric enhancements and memory expansion features included in CXL 3.0 deliver new levels of composability r...
Introduction to CXL
Переглядів 8 тис.Рік тому
In this tutorial session, CXL technology experts will review features in the CXL specification (CXL 1.1, 2.0, 3.0) specifically focusing on the following features: • Protocol for memory expansion, pooling, and sharing • Software and error reporting for CXL memory systems • CXL Fabric and Management Compute Express Link™ (CXL™) is a high-speed interconnect offering coherency and memory semantics...
CXL Consortium Compliance Program Overview: Integrators List & Feature Testing
Переглядів 868Рік тому
CXL Consortium member companies are developing a wide range of products and solutions including CXL memory solutions, IP, compliance testing, fabric implementations, switches, and software solutions. Compliance and interoperability between these products are essential to creating a technology standard that will be successfully deployed in commercially available systems across multiple vendors. ...
CXL Consortium Compliance Program Overview - Jim Pappas, CXL Consortium Chairman
Переглядів 138Рік тому
Learn more about CXL Consortium: www.computeexpresslink.org/ View the CXL Integrators List: www.computeexpresslink.org/integrators-list Follow us for updates! LinkedIn: www.linkedin.com/company/35690788
CXL Consortium Compliance Program Overview - Teledyne LeCroy
Переглядів 89Рік тому
Learn more about CXL Consortium: www.computeexpresslink.org/ View the CXL Integrators List: www.computeexpresslink.org/integrators-list Follow us for updates! LinkedIn: www.linkedin.com/company/35690788
CXL Consortium Compliance Program Overview - Keysight Technologies
Переглядів 92Рік тому
Learn more about CXL Consortium: www.computeexpresslink.org/ View the CXL Integrators List: www.computeexpresslink.org/integrators-list Follow us for updates! LinkedIn: www.linkedin.com/company/35690788
CXL Consortium Compliance Program Overview - Nathan White, CXL Consortium CWG Co-Chair
Переглядів 91Рік тому
Learn more about CXL Consortium: www.computeexpresslink.org/ View the CXL Integrators List: www.computeexpresslink.org/integrators-list Follow us for updates! LinkedIn: www.linkedin.com/company/35690788
CXL Consortium Compliance Program Overview - Kurt Lender, CXL Consortium MWG Co-Chair
Переглядів 102Рік тому
Learn more about CXL Consortium: www.computeexpresslink.org/ View the CXL Integrators List: www.computeexpresslink.org/integrators-list Follow us for updates! LinkedIn: www.linkedin.com/company/35690788
CXL Consortium Compliance Program Overview - VIAVI Solutions
Переглядів 213Рік тому
Learn more about CXL Consortium: www.computeexpresslink.org/ View the CXL Integrators List: www.computeexpresslink.org/integrators-list Follow us for updates! LinkedIn: www.linkedin.com/company/35690788
CXL Consortium Compliance Program Overview - Kurtis Bowman, CXL Consortium MWG Co-Chair
Переглядів 229Рік тому
Learn more about CXL Consortium: www.computeexpresslink.org/ View the CXL Integrators List: www.computeexpresslink.org/integrators-list Follow us for updates! LinkedIn: www.linkedin.com/company/35690788
A look into the CXL device ecosystem and the evolution of CXL use cases
Переглядів 3,9 тис.Рік тому
Compute Express Link™ (CXL™) is an industry supported cache-coherent interconnect for processors, memory expansion, and accelerators. CXL enables a high-speed, efficient interconnect between the CPU and platform enhancements and workload accelerators, such as GPUs, FPGAs, and other purpose-built accelerator solutions. At Supercomputing 2022 (SC’22), CXL Consortium members showcased CXL technolo...
CXL 3.0: Enabling composable systems with expanded fabric capabilities
Переглядів 9 тис.Рік тому
In August 2022, CXL Consortium released the CXL 3.0 specification. CXL 3.0 expands on previous technology generations to increase scalability and optimize system level flows with advanced switching and fabric capabilities, efficient peer-to-peer communications, and fine-grained resource sharing across multiple compute domains. It also doubles the data rate to 64 GT/s with no added latency over ...
Introducing Compute Express Link™ (CXL™) 3.0
Переглядів 9 тис.2 роки тому
Download the evaluation copy for the CXL 3.0 specification: www.computeexpresslink.org/download-the-specification Read the CXL 3.0 specification announcement: www.computeexpresslink.org/pressroom Download the CXL 3.0 white paper: www.computeexpresslink.org/resource-library
CXL 1.1 vs. CXL 2.0 - What’s the difference?
Переглядів 6 тис.2 роки тому
CXL 1.1 vs. CXL 2.0 - What’s the difference?
Exploring Compute Express Link™ (CXL™) Cache Coherency
Переглядів 8 тис.2 роки тому
Exploring Compute Express Link™ (CXL™) Cache Coherency
Introduction to the Compute Express Link™ (CXL™) Fabric Manager
Переглядів 6 тис.2 роки тому
Introduction to the Compute Express Link™ (CXL™) Fabric Manager
An Overview of the Compute Express Link™ (CXL™) 2.0 ECN
Переглядів 2,7 тис.2 роки тому
An Overview of the Compute Express Link™ (CXL™) 2.0 ECN
CXL™ Consortium, Gen-Z Consortium™, SNIA and End-Users - Is Disaggregation of Systems the Future?
Переглядів 8232 роки тому
CXL™ Consortium, Gen-Z Consortium™, SNIA and End-Users - Is Disaggregation of Systems the Future?
Functional Integration of SAP HANA In-Memory-Database on Samsung's CXL Memory Expander - Samsung
Переглядів 1,2 тис.2 роки тому
Functional Integration of SAP HANA In-Memory-Database on Samsung's CXL Memory Expander - Samsung
Cadence IP for CXL Interop Demonstration
Переглядів 1,3 тис.2 роки тому
Cadence IP for CXL Interop Demonstration
Proof of Concept: Memory Disaggregation Local, Expanded, and Remote Memory - Elastics.cloud
Переглядів 1,6 тис.2 роки тому
Proof of Concept: Memory Disaggregation Local, Expanded, and Remote Memory - Elastics.cloud
Astera Labs Aries CXL™ Smart Retimers
Переглядів 1,9 тис.2 роки тому
Astera Labs Aries CXL™ Smart Retimers
GigaIO: The Future of Composability with CXL
Переглядів 1,1 тис.2 роки тому
GigaIO: The Future of Composability with CXL
CXL Type 3 Memory Device Demo - Meta
Переглядів 7 тис.2 роки тому
CXL Type 3 Memory Device Demo - Meta
Demonstration of a CXL Interconnect on a FPGA-based Design - Rambus
Переглядів 2,5 тис.2 роки тому
Demonstration of a CXL Interconnect on a FPGA-based Design - Rambus
MXC + Retimer Video - Montage Technology
Переглядів 1,1 тис.2 роки тому
MXC Retimer Video - Montage Technology
CXL Fabric Adaptor Bridge Demo - IntelliProp
Переглядів 7972 роки тому
CXL Fabric Adaptor Bridge Demo - IntelliProp
Synopsys DesignWare CXL IP Showing Successful Data Transfer Using a Teledyne LeCroy CXL Analyzer
Переглядів 1,1 тис.2 роки тому
Synopsys DesignWare CXL IP Showing Successful Data Transfer Using a Teledyne LeCroy CXL Analyzer
46680 Towne Drive
88145 Rutherford Meadows
64319 Bobby Fall
442 Cole Underpass
Williams William Harris Patricia Hernandez Kevin
5612 Audrey Knoll
0925 Ratke Parkways
Marc Lights
Leilani Squares
Hermiston Island
Garcia Kimberly White Larry Martinez Helen
Cummings Parkways
54731 Kshlerin Shores
034 Ricky Point
Davis Brian Lewis Christopher Harris Eric
Anderson Deborah Hall Jennifer Rodriguez Edward
Norene Plains
Wanda Plains
Leannon Harbors
Jones George Martin Helen Thompson Nancy
Wow... Spelled FPGAs wrong im not gonna trust this
So many details in the slides. It's easy to get lost
I'd love the presentation material as well. Great session!
Is there any chance for me to get the presentation material? :)
How can be the credits exchange mechanism work without LLCRD flit in CXL 3.0? I mean which flit should carry credit information after INIT.Pram Flit being sent.
Will these Micron memory expansion cards be available for Workstations platforms as well, like the Threadripper and Threadripper Pro? Or will there only be support for the Epic 9004 series? If there will be workstation support, are there plans for these cards being available as PCIe5 x16 slot variant add-in boards? With Intel Optane gone, I really hope CXL and Micron will include support for Workstation users as well.
I think it'll be a while before we see CXL support for HEDT's.
Promo-SM
and the gpu processor, can control a cxl port, how caché memory?
I'm trying to learn what problem CXL is designed to solve? How is this any different than standard system memory?
why blur the text, it's pretty much obvious this is a 96-thread × 2 cpu system.
how do i install cxl to help reduce Texture Memory usage in RAM ?
Why do you think the CXL devices' cache size should be around 1MB? I'm curious about this because there are many GPUs that have a cache larger than 1MB
Can I have a pdf of this video please since your explanation is very I want to go through this
Will it go point to point over chassis
I wonder if CXL 2.0 would be able to be used to create a virtual machine that runs a single kernel that runs on all hardware as though it were one giant system. Not that I can think of a use case for this, it is just fascinating.
I wonder when the CXL 3.0 Drafts would be allowed to be previewed by the public :/
Last month they released the first public version for 3.0 and efforts are now on 3.1
The graphic in the beginning misspells "FPGA".
Very informative!
Thanks for the great video. I have a few questions about the video. In the case of Multiple Logical Device (MLD), one CXL Memory Node is likely to consist of 1 ~ 4 channels. Is the host assigned to each channel? Or, if this memory node is E3.S form factor, there will be 20 or 40 DRAM packages, are the hosts allocated in units of packages?
Does a CXL Device support hotplug?
32:51
29:50 The hosts and devices are attached and removed from the CXL switch via hotplug. More detail is given from 32:50 onward
How about the memory latency behind the CXL?
= Latency of the attached memory device + latency of the PCIe interconnect.
It seems the fabric manager manages system memory for all those hosts. In this case, the fabric manager has higher exception level than hypervisors. What exactly is this piece of SW?
It will be either be either a kernel module in the Host OS of a host (exception level = 0) like device drivers, or (for some CXL-compliant devices) implemented in hardware itself. The spec does not specify this, so it is left to the implementer. This is what I think, pls refer to spec to confirm.
Buy NLST = NLST = CXL = Winner
Which version of ubuntu is this which understands CXL ?
Very informative
Thanks a lot for the presentation. It clarifies many of my questions.
main question - what is the speed?
Excellent presentation, Rick