Skip to content

Samsung Foundry plays an instrumental role in
offering unmatched expertise to our customers,
designing performance-intensive solutions that
are reshaping the industry.
Samsung Foundry plays an instrumental role in
offering unmatched expertise to our customers,
designing performance-intensive solutions that
are reshaping the industry.
Samsung Foundry plays an instrumental role in
offering unmatched expertise to our customers,
designing performance-intensive solutions that
are reshaping the industry.

A digital image of a glowing Samsung chip at the center of a futuristic data center, surrounded by illuminated servers with blue and purple lights.
Foundry Services
HPC solutions for tomorrow HPC solutions for tomorrow HPC solutions for tomorrow
Unmatched performance expertise Unmatched performance expertise Unmatched performance expertise
Scaling efficiently Scaling efficiently Scaling efficiently

In an era of accelerated global transformations, we see a dramatic rise in the deployment of AI and 5G technologies to tackle increasingly complex workloads and analytics.

 

To enable these requirements, enterprise and hyper-scale cloud data centers, communication and networking platforms have become the foundation of our global industries. As such, they need to scale efficiently without compromising computing power, performance, latency, bandwidth, and functionality.

In an era of accelerated global transformations, we see a dramatic rise in the deployment of AI and 5G technologies to tackle increasingly complex workloads and analytics.

 

To enable these requirements, enterprise and hyper-scale cloud data centers, communication and networking platforms have become the foundation of our global industries. As such, they need to scale efficiently without compromising computing power, performance, latency, bandwidth, and functionality.

In an era of accelerated global transformations, we see a dramatic rise in the deployment of AI and 5G technologies to tackle increasingly complex workloads and analytics.

 

To enable these requirements, enterprise and hyper-scale cloud data centers, communication and networking platforms have become the foundation of our global industries. As such, they need to scale efficiently without compromising computing power, performance, latency, bandwidth, and functionality.

An isometric illustration of a black data server with orange arrows indicating airflow or connectivity, representing scalable data infrastructure.
An isometric illustration of a stacked semiconductor chip package, featuring a blue outlined die on the top layer and a minimalist design.
Trusted foundry supplier Trusted foundry supplier Trusted foundry supplier

Samsung Foundry plays an instrumental role in providing unmatched expertise and innovation to our customers designing performance and compute-intensive solutions that are reshaping this industry. Our commitment to technology innovation and manufacturing excellence are driven by our goal to become the most trusted foundry supplier in the rapidly evolving Mobile, AI, Networking, Performance and Storage segments. We are committed to providing robust, reliable and innovative technologies that integrate seamlessly to produce next-generation enhanced SOCs and Multi-Chip Module platforms.

Samsung Foundry plays an instrumental role in providing unmatched expertise and innovation to our customers designing performance and compute-intensive solutions that are reshaping this industry. Our commitment to technology innovation and manufacturing excellence are driven by our goal to become the most trusted foundry supplier in the rapidly evolving Mobile, AI, Networking, Performance and Storage segments. We are committed to providing robust, reliable and innovative technologies that integrate seamlessly to produce next-generation enhanced SOCs and Multi-Chip Module platforms.

Samsung Foundry plays an instrumental role in providing unmatched expertise and innovation to our customers designing performance and compute-intensive solutions that are reshaping this industry. Our commitment to technology innovation and manufacturing excellence are driven by our goal to become the most trusted foundry supplier in the rapidly evolving Mobile, AI, Networking, Performance and Storage segments. We are committed to providing robust, reliable and innovative technologies that integrate seamlessly to produce next-generation enhanced SOCs and Multi-Chip Module platforms.

Meeting customer demands Meeting customer demands Meeting customer demands

Our high volume manufacturing capability and commitment to excellence puts us in a unique position to scale our production to meet our customer's demand at all stages of their product life cycle. Our regular investment in new production lines ensures adequate capacity on our advanced EUV nodes.

Our high volume manufacturing capability and commitment to excellence puts us in a unique position to scale our production to meet our customer's demand at all stages of their product life cycle. Our regular investment in new production lines ensures adequate capacity on our advanced EUV nodes.

Our high volume manufacturing capability and commitment to excellence puts us in a unique position to scale our production to meet our customer's demand at all stages of their product life cycle. Our regular investment in new production lines ensures adequate capacity on our advanced EUV nodes.

A 3D graphic representation of passive electronic components in different sizes, featuring black casings and red, yellow, and blue color codes.
A hierarchical flowchart diagram on a dark background, illustrating the structure from Wired Infrastructure to Cloud Data Centers, Enterprise Networks, and End Devices.
A categorized diagram showing key components in five technology domains: Compute, AI, Networking, Storage, and Memory, arranged vertically by function.
A minimalist flow diagram on a dark background showing interconnected semiconductor development pillars: Process, IP, Packaging, Services, and Eco-system.

Your ultimate foundry partner for
performance-intensive applications

Samsung Foundry continues to power HPC, AI and advanced networking platforms through
technologies that deliver CPU and GPU engines, neural networks, storage and memory chips
as well as a broad range of interfaces and connectivity solutions.

  • FPGA Controllers
  • CPU Peripherals
  • SSD Controllers
  • Network Switch and Router
  • HBM
  • GPU
  • 5G Infrastructure
We’re ready for you. We’re ready for you. We’re ready for you. Samsung Foundry's core technologies to fuel your next platform consist of: Samsung Foundry's core technologies to fuel your next platform consist of: Samsung Foundry's core technologies to fuel your next platform consist of:

Leading edge, cost-effective process node technologies

Leading edge, cost-effective process node technologies

Leading edge, cost-effective process node technologies

Advanced Packaging and Chiplet integrations

Advanced Packaging and Chiplet integrations

Advanced Packaging and Chiplet integrations

Flexible business engagement models for designs services & OSATs

Flexible business engagement models for designs services & OSATs

Flexible business engagement models for designs services & OSATs

Silicon-proven IPs built with industry-leading partners

Silicon-proven IPs built with industry-leading partners

Silicon-proven IPs built with industry-leading partners

Connectivity solutions

Connectivity solutions

Connectivity solutions

Advanced storage and memory solutions

Advanced storage and memory solutions

Advanced storage and memory solutions

HPC Solutions HPC Solutions HPC Solutions

A technical diagram illustrating Samsung's advanced chiplet architecture, including dies, cubes, and interconnects, supported by high-speed PHYs and CUBE technology.

Process node technology Process node technology Process node technology

A technology roadmap graph showing the evolution of semiconductor process nodes from 14nm to 2nm, highlighting transitions from FinFET to EUV to GAA technology.

To guarantee higher performance, many Samsung Foundry processes have undergone additional optimizations at the transistor and standard cell level. They also include flexible metal stack options and higher-track libraries with performance boost kits. Additionally, these process nodes come with complete foundry services and supply chain support as you ramp up silicon.

To guarantee higher performance, many Samsung Foundry processes have undergone additional optimizations at the transistor and standard cell level. They also include flexible metal stack options and higher-track libraries with performance boost kits. Additionally, these process nodes come with complete foundry services and supply chain support as you ramp up silicon.

To guarantee higher performance, many Samsung Foundry processes have undergone additional optimizations at the transistor and standard cell level. They also include flexible metal stack options and higher-track libraries with performance boost kits. Additionally, these process nodes come with complete foundry services and supply chain support as you ramp up silicon.

Broad portfolio of process technologies Broad portfolio of process technologies Broad portfolio of process technologies

A comparison chart of semiconductor process nodes from 14nm FinFET to 2nm GAA, illustrating their scalability, performance, and wafer processing maturity.
Technology Compute / Graphics Datacenter & Enterprise
N/W AI Storage
Ent D/C Training Interface Ent D/C
Process
(recommended)
5nm, 4nm,
3nm GAA
14/11nm,
10/8nm
5nm, 4nm,
3nm GAA
5nm, 4nm,
3nm GAA
8nm, 5nm 14/11nm
10/8nm, 5nm
Technology Compute / Graphics Datacenter & Enterprise
N/W AI Storage
Ent D/C Training Interface Ent D/C
Process
(recommended)
5nm, 4nm,
3nm GAA
14/11nm,
10/8nm
5nm, 4nm,
3nm GAA
5nm, 4nm,
3nm GAA
8nm, 5nm 14/11nm
10/8nm, 5nm
Best-in-class IP for intensive HPC Best-in-class IP for intensive HPC Best-in-class IP for intensive HPC Samsung Foundry provides a broad portfolio of best in class IPs optimized for your performance needs. Our portfolio consists of dedicated as well as foundation IPs designed for your performance-intensive applications. Furthermore, our foundation IP is optimized to best meet your performance needs. Samsung Foundry provides a broad portfolio of best in class IPs optimized for your performance needs. Our portfolio consists of dedicated as well as foundation IPs designed for your performance-intensive applications. Furthermore, our foundation IP is optimized to best meet your performance needs. Samsung Foundry provides a broad portfolio of best in class IPs optimized for your performance needs. Our portfolio consists of dedicated as well as foundation IPs designed for your performance-intensive applications. Furthermore, our foundation IP is optimized to best meet your performance needs.
    • High performance
    • Low Latency
    • Optimized power/energy
    • Multi-protocol (MP) SERDES
    • D2D
    • PCIe
    • Ethernet
    • LPDDR
    • DDR
    • GDDR
    • HBM
    • Chip to Chip (C2C): CXL, CCIX
    • Die to Die (D2D): Serial & Parallel
IP 14nm/1nm 10/8nm 5nm 4nm
SerDes Shape Shape Shape Shape
D2D     Shape Shape
PCle Shape Shape Shape Shape
Ethernet Shape Shape Shape Shape
LPDDR Shape Shape Shape Shape
DDR Shape Shape Shape Shape
GDDR Shape Shape Shape Shape
HBM Shape Shape Shape Shape
Analog IP Shape Shape Shape Shape
SRAM, TCQM Shape Shape Shape Shape
IP 14nm/1nm 10/8nm 5nm 4nm
SerDes Shape Shape Shape Shape
D2D     Shape Shape
PCle Shape Shape Shape Shape
Ethernet Shape Shape Shape Shape
LPDDR Shape Shape Shape Shape
DDR Shape Shape Shape Shape
GDDR Shape Shape Shape Shape
HBM Shape Shape Shape Shape
Analog IP Shape Shape Shape Shape
SRAM, TCQM Shape Shape Shape Shape
Design enablement Design enablement Design enablement In a fast pace market, speed and productivity are key. Our customers measure our effectiveness through our ability to help them accelerate adoption, and ensure rapid integration while reducing design cycle times and increasing the productivity and success of their tape-outs and silicon. For this, we’ve established a design enablement platform to facilitate their designs and optimize their cycle time. In a fast pace market, speed and productivity are key. Our customers measure our effectiveness through our ability to help them accelerate adoption, and ensure rapid integration while reducing design cycle times and increasing the productivity and success of their tape-outs and silicon. For this, we’ve established a design enablement platform to facilitate their designs and optimize their cycle time. In a fast pace market, speed and productivity are key. Our customers measure our effectiveness through our ability to help them accelerate adoption, and ensure rapid integration while reducing design cycle times and increasing the productivity and success of their tape-outs and silicon. For this, we’ve established a design enablement platform to facilitate their designs and optimize their cycle time.

Samsung Foundry design enablement platform encompasses:

Samsung Foundry design enablement platform encompasses:

Samsung Foundry design enablement platform encompasses:

A complete set of PDK files

A complete set of PDK files

A complete set of PDK files

A full suite of libraries and IPs

A full suite of libraries and IPs

A full suite of libraries and IPs

Robust design flow methodologies that are node specific and downloadable for rapid design start

Robust design flow methodologies that are node specific and downloadable for rapid design start

Robust design flow methodologies that are node specific and downloadable for rapid design start

Samsung Foundry works closely with key design enablement and IP partners to optimize the tools and allow for higher design productivity. In addition, our SAFE-QEDA or EDA certification program allows for higher design and silicon success by ensuring that IP and customer designs meet Samsung Foundry process and packaging technology requirements. Furthermore, our design enablement partners have entered a new era of computational software where the convergence of System Level Design, Artificial Intelligence, and Electronic Design Automation offers enhancements for even greater design optimizations.

All these optimizations provide a robust and reliable design enablement platform which is essential, especially for early adoptions of more recent technologies such as Samsung Foundry 5nm EUV, 3D IC and soon-to-be available GAA.

Samsung Foundry works closely with key design enablement and IP partners to optimize the tools and allow for higher design productivity. In addition, our SAFE-QEDA or EDA certification program allows for higher design and silicon success by ensuring that IP and customer designs meet Samsung Foundry process and packaging technology requirements. Furthermore, our design enablement partners have entered a new era of computational software where the convergence of System Level Design, Artificial Intelligence, and Electronic Design Automation offers enhancements for even greater design optimizations.

All these optimizations provide a robust and reliable design enablement platform which is essential, especially for early adoptions of more recent technologies such as Samsung Foundry 5nm EUV, 3D IC and soon-to-be available GAA.

Samsung Foundry works closely with key design enablement and IP partners to optimize the tools and allow for higher design productivity. In addition, our SAFE-QEDA or EDA certification program allows for higher design and silicon success by ensuring that IP and customer designs meet Samsung Foundry process and packaging technology requirements. Furthermore, our design enablement partners have entered a new era of computational software where the convergence of System Level Design, Artificial Intelligence, and Electronic Design Automation offers enhancements for even greater design optimizations.

All these optimizations provide a robust and reliable design enablement platform which is essential, especially for early adoptions of more recent technologies such as Samsung Foundry 5nm EUV, 3D IC and soon-to-be available GAA.

Design enablement files for EDA venders Design enablement files for EDA venders Design enablement files for EDA venders
DK/PDK Datacenter & Enterprise
ANSYS Cadence Siemens EDA Synopsys Other
SPICE   Shape Shape Shape  
P-Cell   Shape   Shape  
DRC/Antenna   Shape Shape Shape  
Dummy Insertion   Shape Shape Shape  
LVS   Shape Shape Shape  
RC Extraction   Shape Shape Shape  
IR/EM Shape Shape   Shape  
DFM   Shape Shape Shape  
DK/PDK Datacenter & Enterprise
ANSYS Cadence Siemens EDA Synopsys Other
SPICE   Shape Shape Shape  
P-Cell   Shape   Shape  
DRC/Antenna   Shape Shape Shape  
Dummy Insertion   Shape Shape Shape  
LVS   Shape Shape Shape  
RC Extraction   Shape Shape Shape  
IR/EM Shape Shape   Shape  
DFM   Shape Shape Shape  
Design implementation ASIC steps Design implementation ASIC steps Design implementation ASIC steps
DK/PDK Datacenter & Enterprise
ANSYS Cadence Siemens EDA Synopsys Other
RTL       Shape Arteris IP
Synthesis   Shape   Shape  
DFT   Shape Shape Shape  
PD/STA   Shape   Shape  
PV/Sign-off   Shape Shape Shape  
IR/EM Shape Shape   Shape  
DK/PDK Datacenter & Enterprise
ANSYS Cadence Siemens EDA Synopsys Other
RTL       Shape Arteris IP
Synthesis   Shape   Shape  
DFT   Shape Shape Shape  
PD/STA   Shape   Shape  
PV/Sign-off   Shape Shape Shape  
IR/EM Shape Shape   Shape  
SAFE™ ecosystem SAFE™ ecosystem SAFE™ ecosystem Ease of adoption, and rapid integration are essential in all high-performance designs. Samsung Foundry offers customers access to a comprehensive ecosystem of IP, design services, design enablement and implementation partners. Our SAFE™ program provides a framework for these partnerships. Ease of adoption, and rapid integration are essential in all high-performance designs. Samsung Foundry offers customers access to a comprehensive ecosystem of IP, design services, design enablement and implementation partners. Our SAFE™ program provides a framework for these partnerships. Ease of adoption, and rapid integration are essential in all high-performance designs. Samsung Foundry offers customers access to a comprehensive ecosystem of IP, design services, design enablement and implementation partners. Our SAFE™ program provides a framework for these partnerships.

A broad ecosystem of services with our SAFE™ partners includes:

A broad ecosystem of services with our SAFE™ partners includes:

A broad ecosystem of services with our SAFE™ partners includes:

Best-in-class reference flows from major electronic design automation (EDA) vendors.

Best-in-class reference flows from major electronic design automation (EDA) vendors.

Best-in-class reference flows from major electronic design automation (EDA) vendors.

Comprehensive libraries of standard cells, memory compilers, and I/O interfaces.

Comprehensive libraries of standard cells, memory compilers, and I/O interfaces.

Comprehensive libraries of standard cells, memory compilers, and I/O interfaces.

An extensive IP portfolio including mixed-signal, peripheral, multimedia cores, and interfaces.

An extensive IP portfolio including mixed-signal, peripheral, multimedia cores, and interfaces.

An extensive IP portfolio including mixed-signal, peripheral, multimedia cores, and interfaces.

Predictive design-for-manufacturing solutions to address yield upstream in the design flow.

Predictive design-for-manufacturing solutions to address yield upstream in the design flow.

Predictive design-for-manufacturing solutions to address yield upstream in the design flow.

Advanced packaging and testing.

Advanced packaging and testing.

Advanced packaging and testing.

Design Service Partners

Design Service Partners

Design Service Partners

Cloud design support

Cloud design support

Cloud design support

OSATS

OSATS

OSATS

We work very closely with every customer from the initial design concept to high-volume manufacturing, with transparency, and exceptionally flawless execution while delivering the highest quality product. We work very closely with every customer from the initial design concept to high-volume manufacturing, with transparency, and exceptionally flawless execution while delivering the highest quality product. We work very closely with every customer from the initial design concept to high-volume manufacturing, with transparency, and exceptionally flawless execution while delivering the highest quality product.
Packaging for HPC and networking chip designs Packaging for HPC and networking chip designs Packaging for HPC and networking chip designs In this new era of high-performance computing and networking, designers are confronted with greater SOC integration challenges to meet system performance requirements. As a result, new packaging technologies and business models are being developed and deployed to overcome these limitations while offering customers a broader portfolio breadth for the optimal cost of ownership (or price/performance ratios). In this new era of high-performance computing and networking, designers are confronted with greater SOC integration challenges to meet system performance requirements. As a result, new packaging technologies and business models are being developed and deployed to overcome these limitations while offering customers a broader portfolio breadth for the optimal cost of ownership (or price/performance ratios). In this new era of high-performance computing and networking, designers are confronted with greater SOC integration challenges to meet system performance requirements. As a result, new packaging technologies and business models are being developed and deployed to overcome these limitations while offering customers a broader portfolio breadth for the optimal cost of ownership (or price/performance ratios).

Customers can choose one of our flexible business models to procure the package solution
that best meets their chip design:

Customers can choose one of our flexible business models to procure the package solution
that best meets their chip design:

Customers can choose one of our flexible business models to procure the package solution
that best meets their chip design:

Handoff Model: COT (Customer Owned Tooling), COPD (Customer Owned Physical Design)

Handoff Model: COT (Customer Owned Tooling), COPD (Customer Owned Physical Design)

Handoff Model: COT (Customer Owned Tooling), COPD (Customer Owned Physical Design)

Customers can choose from Samsung Foundry packaging offerings or those offered by our performance OSAT partners such as Amkor

Customers can choose from Samsung Foundry packaging offerings or those offered by our performance OSAT partners such as Amkor

Customers can choose from Samsung Foundry packaging offerings or those offered by our performance OSAT partners such as Amkor

Customers can choose one of our flexible business models to procure the package solution that best meets their chip design:

Customers can choose one of our flexible business models to procure the package solution that best meets their chip design:

Customers can choose one of our flexible business models to procure the package solution that best meets their chip design:

I-Cube S: 2.5D Si-Interposer

I-Cube S: 2.5D Si-Interposer

I-Cube S: 2.5D Si-Interposer

I-Cube E: 2.3D RDL-Interposer with Si-Bridge

I-Cube E: 2.3D RDL-Interposer with Si-Bridge

I-Cube E: 2.3D RDL-Interposer with Si-Bridge

X-Cube: 3DIC

X-Cube: 3DIC

X-Cube: 3DIC

A technical diagram illustrating Samsung’s I-Cube S 2.5D Si interposer technology, connecting an SoC and HBM via a silicon interposer.

The 300-mm TSV-bearing Silicon (Si) interposer wafer is manufactured by Samsung Foundry. There are two assembly processes depending on what format of Si interposer is being used: Chip on Substrate (CoS) or Chip on Wafer (CoW). In CoS, the Si interposer chip comes from a back-grinded and sawed Si interposer wafer. The chip is assembled on the package substrate. And then, the logic devices and HBM modules are mounted on top of it. In CoW, the logic devices and HBM modules are mounted on the back-grinded Si interposer wafer by following the wafer-level molding, grinding and sawing, and then the molded Si interposer die with devices is mounted on the package substrate. There is a major benefit with CoS: interim testing. Interim testing is for helping not to mount any faulted interposer or logic chips before HBM modules are mounted. There is a major benefit with CoW: larger. A larger Si interposer can be used for CoW. CoS helps to develop low-cost 2.5D packages and CoW helps to develop 2.5D packages with more HBM modules. Samsung Foundry has successfully qualified I-Cube S which is available in a wide range of interposer sizes, HBM modules, and package sizes. Today, the 2.5D packages with 2x (1,600mm2) Si interposer integrating advanced logic chip and up to four HBM modules are fully qualified and available for production. Larger 2.5D packages with larger Si interposer integrating more than 4 HBM modules and 2000nF/mm2 ISC™ (Integrated Stack Capacitor) is in development.

The 300-mm TSV-bearing Silicon (Si) interposer wafer is manufactured by Samsung Foundry. There are two assembly processes depending on what format of Si interposer is being used: Chip on Substrate (CoS) or Chip on Wafer (CoW). In CoS, the Si interposer chip comes from a back-grinded and sawed Si interposer wafer. The chip is assembled on the package substrate. And then, the logic devices and HBM modules are mounted on top of it. In CoW, the logic devices and HBM modules are mounted on the back-grinded Si interposer wafer by following the wafer-level molding, grinding and sawing, and then the molded Si interposer die with devices is mounted on the package substrate. There is a major benefit with CoS: interim testing. Interim testing is for helping not to mount any faulted interposer or logic chips before HBM modules are mounted. There is a major benefit with CoW: larger. A larger Si interposer can be used for CoW. CoS helps to develop low-cost 2.5D packages and CoW helps to develop 2.5D packages with more HBM modules. Samsung Foundry has successfully qualified I-Cube S which is available in a wide range of interposer sizes, HBM modules, and package sizes. Today, the 2.5D packages with 2x (1,600mm2) Si interposer integrating advanced logic chip and up to four HBM modules are fully qualified and available for production. Larger 2.5D packages with larger Si interposer integrating more than 4 HBM modules and 2000nF/mm2 ISC™ (Integrated Stack Capacitor) is in development.

The 300-mm TSV-bearing Silicon (Si) interposer wafer is manufactured by Samsung Foundry. There are two assembly processes depending on what format of Si interposer is being used: Chip on Substrate (CoS) or Chip on Wafer (CoW). In CoS, the Si interposer chip comes from a back-grinded and sawed Si interposer wafer. The chip is assembled on the package substrate. And then, the logic devices and HBM modules are mounted on top of it. In CoW, the logic devices and HBM modules are mounted on the back-grinded Si interposer wafer by following the wafer-level molding, grinding and sawing, and then the molded Si interposer die with devices is mounted on the package substrate. There is a major benefit with CoS: interim testing. Interim testing is for helping not to mount any faulted interposer or logic chips before HBM modules are mounted. There is a major benefit with CoW: larger. A larger Si interposer can be used for CoW. CoS helps to develop low-cost 2.5D packages and CoW helps to develop 2.5D packages with more HBM modules. Samsung Foundry has successfully qualified I-Cube S which is available in a wide range of interposer sizes, HBM modules, and package sizes. Today, the 2.5D packages with 2x (1,600mm2) Si interposer integrating advanced logic chip and up to four HBM modules are fully qualified and available for production. Larger 2.5D packages with larger Si interposer integrating more than 4 HBM modules and 2000nF/mm2 ISC™ (Integrated Stack Capacitor) is in development.

A cross-sectional diagram illustrating Samsung's I-Cube E™ packaging, combining RDL interposer and silicon bridge for TSV-less logic integration.

I-Cube E gets more cost-effective over a silicon interposer as the size of the interposer becomes much larger but still be able to take the advantage of small L/S from silicon bridges embedded in the RDL interposer based on PLP technology and used as interfaces between silicon dies. Superior warpage control and power integrity in I-Cube E enables the next generation chiplet architectures possible for many years to come.

There is a major benefit to an RDL interposer in that it is a low cost option as it a Si-Bridge solution. Also, RDL interposer provides more design flexibility for less routing interference with fine line width and line spacing. Samsung Foundry is developing a 2.3D RDL interposer technology with a line and space width of 2/2um and a large interposer (~1600mm2) integrating 4 HBM modules.

I-Cube E gets more cost-effective over a silicon interposer as the size of the interposer becomes much larger but still be able to take the advantage of small L/S from silicon bridges embedded in the RDL interposer based on PLP technology and used as interfaces between silicon dies. Superior warpage control and power integrity in I-Cube E enables the next generation chiplet architectures possible for many years to come.

There is a major benefit to an RDL interposer in that it is a low cost option as it a Si-Bridge solution. Also, RDL interposer provides more design flexibility for less routing interference with fine line width and line spacing. Samsung Foundry is developing a 2.3D RDL interposer technology with a line and space width of 2/2um and a large interposer (~1600mm2) integrating 4 HBM modules.

I-Cube E gets more cost-effective over a silicon interposer as the size of the interposer becomes much larger but still be able to take the advantage of small L/S from silicon bridges embedded in the RDL interposer based on PLP technology and used as interfaces between silicon dies. Superior warpage control and power integrity in I-Cube E enables the next generation chiplet architectures possible for many years to come.

There is a major benefit to an RDL interposer in that it is a low cost option as it a Si-Bridge solution. Also, RDL interposer provides more design flexibility for less routing interference with fine line width and line spacing. Samsung Foundry is developing a 2.3D RDL interposer technology with a line and space width of 2/2um and a large interposer (~1600mm2) integrating 4 HBM modules.

A cross-sectional diagram of Samsung's X-Cube 3DIC technology, illustrating vertically stacked logic dies connected via Through Silicon Via (TSV).

X-Cube leverages three key technologies: Chip on Wafer (CoW), Wafer on Wafer (WoW) and Through Silicon Via (TSV).
CoW stacks thin chips on top of a thinned wafer.
WoW stacks a wafer on a thinned wafer.
TSV vertically interconnects top and bottom chips and wafers.

The combination of these three technologies allows for higher density integration, greater scaling in size, improved power efficiency and lower latency. Samsung is in a leading position to offer highly reliable and competitive micro-bump 3DIC products such as High Bandwidth Memory (HBM) and CMOS Image Sensor (CIS) products.. In addition our expertise and rapid high volume manufacturing allows us to secure high yield production at an early stage. We are ready for mass production based on micro-bump CoW and TSV for low power 3DIC applications. A bumpless hybrid Die to Wafer (D2W) technology is in development.

X-Cube leverages three key technologies: Chip on Wafer (CoW), Wafer on Wafer (WoW) and Through Silicon Via (TSV).
CoW stacks thin chips on top of a thinned wafer.
WoW stacks a wafer on a thinned wafer.
TSV vertically interconnects top and bottom chips and wafers.

The combination of these three technologies allows for higher density integration, greater scaling in size, improved power efficiency and lower latency. Samsung is in a leading position to offer highly reliable and competitive micro-bump 3DIC products such as High Bandwidth Memory (HBM) and CMOS Image Sensor (CIS) products.. In addition our expertise and rapid high volume manufacturing allows us to secure high yield production at an early stage. We are ready for mass production based on micro-bump CoW and TSV for low power 3DIC applications. A bumpless hybrid Die to Wafer (D2W) technology is in development.

X-Cube leverages three key technologies: Chip on Wafer (CoW), Wafer on Wafer (WoW) and Through Silicon Via (TSV).
CoW stacks thin chips on top of a thinned wafer.
WoW stacks a wafer on a thinned wafer.
TSV vertically interconnects top and bottom chips and wafers.

The combination of these three technologies allows for higher density integration, greater scaling in size, improved power efficiency and lower latency. Samsung is in a leading position to offer highly reliable and competitive micro-bump 3DIC products such as High Bandwidth Memory (HBM) and CMOS Image Sensor (CIS) products.. In addition our expertise and rapid high volume manufacturing allows us to secure high yield production at an early stage. We are ready for mass production based on micro-bump CoW and TSV for low power 3DIC applications. A bumpless hybrid Die to Wafer (D2W) technology is in development.