SlideShare a Scribd company logo
This document is Proprietary and Confidential. No part of this document may be disclosed in any
manner to a third party without the prior written consent of ZeroPoint Technologies AB.
Remove the waste.
Release the power.
Presenter: Nilesh Shah, VP Biz Dev
nilesh.shah@zptcorp.com
A portable, hardware IP portfolio solution for
lossless memory compression and compaction
Data centers: 20-25% TCO reduction
Consumers: Lower cost, better battery and UX
Boosts memory capacity 2-4x, bandwidth and
performance/watt by 50%, and 1,000x faster than
competitors
Security
(SphinX)
Product | Hardware accelerated memory compression
IP across the memory hierarchy
On-chip
memory
Off-chip
memory
Storage
Memory hierarchy
Cache
Register
Main memory
NVMe
CXL memory
SSD
Cache expansion
(CacheMX)
CXL expansion
(DenseMem)
Flash expansion
(FlashMX)
Memory expansion
(SuperRAM)
Bandwidth acceleration
(ZiptilionBW)
ZeroPoint applications and their product names
This document is Proprietary and Confidential. No part of this document may be disclosed in any
manner to a third party without the prior written consent of ZeroPoint Technologies AB.
Challenge
4.6%
3%
Hyperscalers spending significant $$ on
software based compression
CPU cycles used
for compression
Hyperscaler requirement:
hardware compression is a MUST-have
OCP Hyperscale CXL Tiered
Memory Expander Spec
Deploy New Tiers: Ordinary + Compressed DRAM memory on CXL
Removes barriers, enables diversity of Hyperscalers
+ Enterprise Customers
Benefit Spec Component
Reduction in total cost of
ownership
Standardization, Hardware accelerated,
Lossless Compressed Memory Tier
Energy Efficiency,
Sustainability
Transparent Hardware accelerated
Compression
Preserve Software
Investments
Support for legacy Compression
Algorithms
CXL
Controller
Opportunity| Add Compressed CXL Memory Tier
1
2
3
OCP Spec:
https://www.opencompute.org/documents/hyperscale-cxl-tiered-memory-expander-for-ocp-base-specification-1-pdf
Requirement: Hyperscale CXL Tiered Memory Expander Spec
Preserving Software Investment, without
compromising performance
● Support for Legacy Compression Algorithms
● Future Proof , supports Algorithm Innovation
● Stringent Latency & Bandwidth Specifications
Parameter Specification
Latency Uncompressed
Access
90 to 150ns
Latency Compressed
Access
250ns to <1us
Bandwidth Efficiency
Read only/ Write only
80% / 75%
Legacy
Room for Innovation
Compression Algorithms
https://www.opencompute.org/documents/hyperscale-cxl-tiered-memory-expander-for-ocp-base-specification-1-pdf
Stringent Requirements
Proposed Solution: Hyperscale CXL Tiered Memory Expander Spec
OS/HW
Application
FW
CPU
Compression/
Decompression
CXL interface
Host
CXL.io CXL.mem
Memory subsystem
Media
Configuration
Compressed
Tier
Uncompressed
Tier
CXL Type 3 Device
Address Space
CXL
Controller
CXL Controller with integrated Hardware Acceleration:
(De)Compression+ Compaction + Transparent memory management
The ZeroPoint Solution| DenseMem IP
OCP Spec Compliant, portable IP
Spec compliant Plug and Play
(De)Compression IP
CXL
Controller
● OCP Spec compliant Hardware Accelerated CXL memory
(De)Compression + Compaction + Transparent
memory management IP block
● 2-4x transparent (de)compression major Datacenter
workloads
● Protocol: CXL 2.0, 3.0, 3.1
● Compression Algorithms: LZ4, ZID (proprietary)
● Portable: AXI4, CHI, Leading process node support
ZeroPoint Solution | Reduce Data Center TCO 20-25%
Today With CXL only With our
compression only
With CXL & Our
compression
~850
~780
~700
~650
-20-25%
CAPEX:
CPU
CAPEX: Memory
CAPEX: Other
OPEX: Power
OPEX: Cooling
OPEX: Other
Waste: Compression tax
Total Cost of Ownership (TCO) for 40 server rack over 3y lifetime [kUSD]
DenseMem IP Demo| QEMU + FPGA
Link to Video
DenseMem | Performance across Datacenter workloads
Summary | Call To Action
● Summary
○ DenseMem IP: OCP Spec Compliant
○ Portable across process nodes, AXI/CHI interface
○ Production ready mid ‘24
○ Performance verified
● Call To Action
○ Controller manufacturers: Collaboratively address
Hyperscale OCP requirements
○ ISVs: Host software integration, target workloads

More Related Content

Similar to Q1 Memory Fabric Forum: ZeroPoint. Remove the waste. Release the power. (20)

PDF
WN Memory Tiering WP Mar2023.pdf
RochanSankar1
 
PDF
Q1 Memory Fabric Forum: Breaking Through the Memory Wall
Memory Fabric Forum
 
PDF
Q1 Memory Fabric Forum: Micron CXL-Compatible Memory Modules
Memory Fabric Forum
 
PPTX
CXL Memory Expansion, Pooling, Sharing, FAM Enablement, and Switching
Memory Fabric Forum
 
PPTX
Breaking the Memory Wall
Memory Fabric Forum
 
PDF
CXL Market Perspective: Get Ready for Adoption and Growth in 2025
AI Infra Forum
 
PPTX
Microchip: CXL Use Cases and Enabling Ecosystem
Memory Fabric Forum
 
PPTX
The State of CXL-related Activities within OCP
Memory Fabric Forum
 
PPTX
All Presentations during CXL Forum at Flash Memory Summit 22
Memory Fabric Forum
 
PPTX
Micron CXL product and architecture update
Memory Fabric Forum
 
PPTX
Q1 Memory Fabric Forum: CXL-Related Activities within OCP
Memory Fabric Forum
 
PPTX
SMART Modular: Memory Solutions with CXL
Memory Fabric Forum
 
PDF
intel-memverge-seminar-cxl-presentation-feb24-final-240214215332-ca83fba5.pdf
wonforest
 
PPTX
Q1 Memory Fabric Forum: Intel Enabling Compute Express Link (CXL)
Memory Fabric Forum
 
PPTX
Intel: Industry Enablement of IO Technologies
Memory Fabric Forum
 
PPTX
Intel: CXL Enabled Heterogeneous Active Memory Tiering
Memory Fabric Forum
 
PPTX
Astera Labs: Intelligent Connectivity for Cloud and AI Infrastructure
Memory Fabric Forum
 
PDF
OpenPOWER Summit 2020 - OpenCAPI Keynote
Allan Cantle
 
PDF
Q1 Memory Fabric Forum: CXL Controller by Montage Technology
Memory Fabric Forum
 
PPTX
Montage: MXC Memory Controller for Expansion & Pooling
Memory Fabric Forum
 
WN Memory Tiering WP Mar2023.pdf
RochanSankar1
 
Q1 Memory Fabric Forum: Breaking Through the Memory Wall
Memory Fabric Forum
 
Q1 Memory Fabric Forum: Micron CXL-Compatible Memory Modules
Memory Fabric Forum
 
CXL Memory Expansion, Pooling, Sharing, FAM Enablement, and Switching
Memory Fabric Forum
 
Breaking the Memory Wall
Memory Fabric Forum
 
CXL Market Perspective: Get Ready for Adoption and Growth in 2025
AI Infra Forum
 
Microchip: CXL Use Cases and Enabling Ecosystem
Memory Fabric Forum
 
The State of CXL-related Activities within OCP
Memory Fabric Forum
 
All Presentations during CXL Forum at Flash Memory Summit 22
Memory Fabric Forum
 
Micron CXL product and architecture update
Memory Fabric Forum
 
Q1 Memory Fabric Forum: CXL-Related Activities within OCP
Memory Fabric Forum
 
SMART Modular: Memory Solutions with CXL
Memory Fabric Forum
 
intel-memverge-seminar-cxl-presentation-feb24-final-240214215332-ca83fba5.pdf
wonforest
 
Q1 Memory Fabric Forum: Intel Enabling Compute Express Link (CXL)
Memory Fabric Forum
 
Intel: Industry Enablement of IO Technologies
Memory Fabric Forum
 
Intel: CXL Enabled Heterogeneous Active Memory Tiering
Memory Fabric Forum
 
Astera Labs: Intelligent Connectivity for Cloud and AI Infrastructure
Memory Fabric Forum
 
OpenPOWER Summit 2020 - OpenCAPI Keynote
Allan Cantle
 
Q1 Memory Fabric Forum: CXL Controller by Montage Technology
Memory Fabric Forum
 
Montage: MXC Memory Controller for Expansion & Pooling
Memory Fabric Forum
 

More from Memory Fabric Forum (20)

PPTX
H3 Platform CXL Solution_Memory Fabric Forum.pptx
Memory Fabric Forum
 
PPTX
Q1 Memory Fabric Forum: Building Fast and Secure Chips with CXL IP
Memory Fabric Forum
 
PPTX
Q1 Memory Fabric Forum: Using CXL with AI Applications - Steve Scargall.pptx
Memory Fabric Forum
 
PPTX
Q1 Memory Fabric Forum: Memory expansion with CXL-Ready Systems and Devices
Memory Fabric Forum
 
PPTX
Q1 Memory Fabric Forum: About MindShare Training
Memory Fabric Forum
 
PDF
Q1 Memory Fabric Forum: Teledyne LeCroy | Austin Labs
Memory Fabric Forum
 
PDF
Q1 Memory Fabric Forum: SMART CXL Product Lineup
Memory Fabric Forum
 
PDF
Q1 Memory Fabric Forum: CXL Form Factor Primer
Memory Fabric Forum
 
PDF
Q1 Memory Fabric Forum: Memory Fabric in a Composable System
Memory Fabric Forum
 
PPTX
Q1 Memory Fabric Forum: Big Memory Computing for AI
Memory Fabric Forum
 
PPTX
Q1 Memory Fabric Forum: Compute Express Link (CXL) 3.1 Update
Memory Fabric Forum
 
PPTX
Q1 Memory Fabric Forum: XConn CXL Switches for AI
Memory Fabric Forum
 
PDF
Q1 Memory Fabric Forum: VMware Memory Vision
Memory Fabric Forum
 
PPTX
MemVerge: Memory Expansion Without Breaking the Budget
Memory Fabric Forum
 
PPTX
Micron - CXL Enabling New Pliability in the Modern Data Center.pptx
Memory Fabric Forum
 
PPTX
TE Connectivity: Card Edge Interconnects
Memory Fabric Forum
 
PPTX
Synopsys: Achieve First Pass Silicon Success with Synopsys CXL IP Solutions
Memory Fabric Forum
 
PPTX
Samsung: CMM-H Tiered Memory Solution with Built-in DRAM
Memory Fabric Forum
 
PPTX
XConn: Scalable Memory Expansion and Sharing for AI Computing with CXL Switches
Memory Fabric Forum
 
PPTX
MemVerge: Gismo (Global IO-free Shared Memory Objects)
Memory Fabric Forum
 
H3 Platform CXL Solution_Memory Fabric Forum.pptx
Memory Fabric Forum
 
Q1 Memory Fabric Forum: Building Fast and Secure Chips with CXL IP
Memory Fabric Forum
 
Q1 Memory Fabric Forum: Using CXL with AI Applications - Steve Scargall.pptx
Memory Fabric Forum
 
Q1 Memory Fabric Forum: Memory expansion with CXL-Ready Systems and Devices
Memory Fabric Forum
 
Q1 Memory Fabric Forum: About MindShare Training
Memory Fabric Forum
 
Q1 Memory Fabric Forum: Teledyne LeCroy | Austin Labs
Memory Fabric Forum
 
Q1 Memory Fabric Forum: SMART CXL Product Lineup
Memory Fabric Forum
 
Q1 Memory Fabric Forum: CXL Form Factor Primer
Memory Fabric Forum
 
Q1 Memory Fabric Forum: Memory Fabric in a Composable System
Memory Fabric Forum
 
Q1 Memory Fabric Forum: Big Memory Computing for AI
Memory Fabric Forum
 
Q1 Memory Fabric Forum: Compute Express Link (CXL) 3.1 Update
Memory Fabric Forum
 
Q1 Memory Fabric Forum: XConn CXL Switches for AI
Memory Fabric Forum
 
Q1 Memory Fabric Forum: VMware Memory Vision
Memory Fabric Forum
 
MemVerge: Memory Expansion Without Breaking the Budget
Memory Fabric Forum
 
Micron - CXL Enabling New Pliability in the Modern Data Center.pptx
Memory Fabric Forum
 
TE Connectivity: Card Edge Interconnects
Memory Fabric Forum
 
Synopsys: Achieve First Pass Silicon Success with Synopsys CXL IP Solutions
Memory Fabric Forum
 
Samsung: CMM-H Tiered Memory Solution with Built-in DRAM
Memory Fabric Forum
 
XConn: Scalable Memory Expansion and Sharing for AI Computing with CXL Switches
Memory Fabric Forum
 
MemVerge: Gismo (Global IO-free Shared Memory Objects)
Memory Fabric Forum
 
Ad

Recently uploaded (20)

PPTX
Agentic AI in Healthcare Driving the Next Wave of Digital Transformation
danielle hunter
 
PDF
Make GenAI investments go further with the Dell AI Factory
Principled Technologies
 
PPTX
Agile Chennai 18-19 July 2025 | Workshop - Enhancing Agile Collaboration with...
AgileNetwork
 
PPTX
IT Runs Better with ThousandEyes AI-driven Assurance
ThousandEyes
 
PDF
Tea4chat - another LLM Project by Kerem Atam
a0m0rajab1
 
PDF
Data_Analytics_vs_Data_Science_vs_BI_by_CA_Suvidha_Chaplot.pdf
CA Suvidha Chaplot
 
PDF
A Strategic Analysis of the MVNO Wave in Emerging Markets.pdf
IPLOOK Networks
 
PDF
NewMind AI Weekly Chronicles – July’25, Week III
NewMind AI
 
PDF
Presentation about Hardware and Software in Computer
snehamodhawadiya
 
PDF
State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification
Ivan Ruchkin
 
PDF
Generative AI vs Predictive AI-The Ultimate Comparison Guide
Lily Clark
 
PDF
How Open Source Changed My Career by abdelrahman ismail
a0m0rajab1
 
PDF
Market Insight : ETH Dominance Returns
CIFDAQ
 
PDF
Per Axbom: The spectacular lies of maps
Nexer Digital
 
PDF
AI Unleashed - Shaping the Future -Starting Today - AIOUG Yatra 2025 - For Co...
Sandesh Rao
 
PDF
Researching The Best Chat SDK Providers in 2025
Ray Fields
 
PPTX
OA presentation.pptx OA presentation.pptx
pateldhruv002338
 
PPTX
AI Code Generation Risks (Ramkumar Dilli, CIO, Myridius)
Priyanka Aash
 
PDF
Google I/O Extended 2025 Baku - all ppts
HusseinMalikMammadli
 
PDF
Brief History of Internet - Early Days of Internet
sutharharshit158
 
Agentic AI in Healthcare Driving the Next Wave of Digital Transformation
danielle hunter
 
Make GenAI investments go further with the Dell AI Factory
Principled Technologies
 
Agile Chennai 18-19 July 2025 | Workshop - Enhancing Agile Collaboration with...
AgileNetwork
 
IT Runs Better with ThousandEyes AI-driven Assurance
ThousandEyes
 
Tea4chat - another LLM Project by Kerem Atam
a0m0rajab1
 
Data_Analytics_vs_Data_Science_vs_BI_by_CA_Suvidha_Chaplot.pdf
CA Suvidha Chaplot
 
A Strategic Analysis of the MVNO Wave in Emerging Markets.pdf
IPLOOK Networks
 
NewMind AI Weekly Chronicles – July’25, Week III
NewMind AI
 
Presentation about Hardware and Software in Computer
snehamodhawadiya
 
State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification
Ivan Ruchkin
 
Generative AI vs Predictive AI-The Ultimate Comparison Guide
Lily Clark
 
How Open Source Changed My Career by abdelrahman ismail
a0m0rajab1
 
Market Insight : ETH Dominance Returns
CIFDAQ
 
Per Axbom: The spectacular lies of maps
Nexer Digital
 
AI Unleashed - Shaping the Future -Starting Today - AIOUG Yatra 2025 - For Co...
Sandesh Rao
 
Researching The Best Chat SDK Providers in 2025
Ray Fields
 
OA presentation.pptx OA presentation.pptx
pateldhruv002338
 
AI Code Generation Risks (Ramkumar Dilli, CIO, Myridius)
Priyanka Aash
 
Google I/O Extended 2025 Baku - all ppts
HusseinMalikMammadli
 
Brief History of Internet - Early Days of Internet
sutharharshit158
 
Ad

Q1 Memory Fabric Forum: ZeroPoint. Remove the waste. Release the power.

  • 1. This document is Proprietary and Confidential. No part of this document may be disclosed in any manner to a third party without the prior written consent of ZeroPoint Technologies AB. Remove the waste. Release the power. Presenter: Nilesh Shah, VP Biz Dev [email protected]
  • 2. A portable, hardware IP portfolio solution for lossless memory compression and compaction Data centers: 20-25% TCO reduction Consumers: Lower cost, better battery and UX Boosts memory capacity 2-4x, bandwidth and performance/watt by 50%, and 1,000x faster than competitors
  • 3. Security (SphinX) Product | Hardware accelerated memory compression IP across the memory hierarchy On-chip memory Off-chip memory Storage Memory hierarchy Cache Register Main memory NVMe CXL memory SSD Cache expansion (CacheMX) CXL expansion (DenseMem) Flash expansion (FlashMX) Memory expansion (SuperRAM) Bandwidth acceleration (ZiptilionBW) ZeroPoint applications and their product names
  • 4. This document is Proprietary and Confidential. No part of this document may be disclosed in any manner to a third party without the prior written consent of ZeroPoint Technologies AB. Challenge 4.6% 3% Hyperscalers spending significant $$ on software based compression CPU cycles used for compression Hyperscaler requirement: hardware compression is a MUST-have OCP Hyperscale CXL Tiered Memory Expander Spec
  • 5. Deploy New Tiers: Ordinary + Compressed DRAM memory on CXL Removes barriers, enables diversity of Hyperscalers + Enterprise Customers Benefit Spec Component Reduction in total cost of ownership Standardization, Hardware accelerated, Lossless Compressed Memory Tier Energy Efficiency, Sustainability Transparent Hardware accelerated Compression Preserve Software Investments Support for legacy Compression Algorithms CXL Controller Opportunity| Add Compressed CXL Memory Tier 1 2 3 OCP Spec: https://www.opencompute.org/documents/hyperscale-cxl-tiered-memory-expander-for-ocp-base-specification-1-pdf
  • 6. Requirement: Hyperscale CXL Tiered Memory Expander Spec Preserving Software Investment, without compromising performance ● Support for Legacy Compression Algorithms ● Future Proof , supports Algorithm Innovation ● Stringent Latency & Bandwidth Specifications Parameter Specification Latency Uncompressed Access 90 to 150ns Latency Compressed Access 250ns to <1us Bandwidth Efficiency Read only/ Write only 80% / 75% Legacy Room for Innovation Compression Algorithms https://www.opencompute.org/documents/hyperscale-cxl-tiered-memory-expander-for-ocp-base-specification-1-pdf Stringent Requirements
  • 7. Proposed Solution: Hyperscale CXL Tiered Memory Expander Spec OS/HW Application FW CPU Compression/ Decompression CXL interface Host CXL.io CXL.mem Memory subsystem Media Configuration Compressed Tier Uncompressed Tier CXL Type 3 Device Address Space CXL Controller CXL Controller with integrated Hardware Acceleration: (De)Compression+ Compaction + Transparent memory management
  • 8. The ZeroPoint Solution| DenseMem IP OCP Spec Compliant, portable IP Spec compliant Plug and Play (De)Compression IP CXL Controller ● OCP Spec compliant Hardware Accelerated CXL memory (De)Compression + Compaction + Transparent memory management IP block ● 2-4x transparent (de)compression major Datacenter workloads ● Protocol: CXL 2.0, 3.0, 3.1 ● Compression Algorithms: LZ4, ZID (proprietary) ● Portable: AXI4, CHI, Leading process node support
  • 9. ZeroPoint Solution | Reduce Data Center TCO 20-25% Today With CXL only With our compression only With CXL & Our compression ~850 ~780 ~700 ~650 -20-25% CAPEX: CPU CAPEX: Memory CAPEX: Other OPEX: Power OPEX: Cooling OPEX: Other Waste: Compression tax Total Cost of Ownership (TCO) for 40 server rack over 3y lifetime [kUSD]
  • 10. DenseMem IP Demo| QEMU + FPGA Link to Video
  • 11. DenseMem | Performance across Datacenter workloads
  • 12. Summary | Call To Action ● Summary ○ DenseMem IP: OCP Spec Compliant ○ Portable across process nodes, AXI/CHI interface ○ Production ready mid ‘24 ○ Performance verified ● Call To Action ○ Controller manufacturers: Collaboratively address Hyperscale OCP requirements ○ ISVs: Host software integration, target workloads