(Go: >> BACK << -|- >> HOME <<)

SlideShare a Scribd company logo
Confidential
Confidential
Supermicro X13 Comprehensive Portfolio
Hyper and Hyper-E
Best-in-Class Performance and
Flexibility Rackmount Servers
for Enterprise Applications
Cloud DC
All-in-one Rackmount Platforms
for Cloud Data Centers
Mainstream
Versatile Entry Level and Volume
Servers for Enterprise Applications
BigTwin®
Highly Modular Multi-Node
Systems with Tool-less Design
FatTwin®
Advanced Multi-node 4U Twin
Architecture with 8 or 4 Nodes
Cost-effective 2U Multi-node
Platforms
TwinPro® SuperBlade®
High Density x86 Multi-node
Server for Enterprise Cloud, HPC
SuperStorage®
WIO (UP)
Industry’s Widest Variety of
I/O Optimized Servers
High Density Systems for Double-
width, Full Length PCIe GPUs
PCIe GPU Servers Universal GPU Servers
High Performance and Flexibility
with Advanced Architecture and
Thermal Design
Highest Performance and Flexibility
for Enterprise Applications
MP 4-Way Server
High-efficiency, High-performance Compact
Form Factor for 5G and Edge computing
IOT/Embedded
Top-loading Server Optimized for Field
Serviceability and Field Replacement
Workstations for High
Performance Workloads
SuperWorkstations
2 Better Faster Greener™ © 2022 Supermicro
GrandTwin®
Highly Modular Front Access
Multi-Node Systems with Tool-
less Design
Confidential
Supermicro Has the Most Genoa Options
2/8/2023 Better Faster Greener™ © 2022 Supermicro
3
AS –2115GT-HNTR (Rear IO)
GrandTwin
2U4Node
Hyper
DP Systems
CloudDC
UP Systems
GPU Systems
AS -1015CS-TNR
AS -1115CS-TNR
AS -2015CS-TNR
AS -1125HS-TNR
AS -2025HS-TNR
AS -2125HS-TNR
AS -4125GS-TNRT
8 PCIe 5.0 x16 GPUs
AS –2115GT-HNTF (Front IO)
Supermicro A+ Product Page
https://www.supermicro.com/en/products/aplus
Confidential
4th Generation Platform Overview (Max per socket)
• 3rd Generation Intel Xeon Scalable
• Core count: 40
• PCIe lane count: 64
• PCIe Generation: 4th
• Memory : DDR4/3200
• 8 channel
• 3rd Generation AMD EPYC
• Core count: 64
• PCIe lane count: 128
• PCIe Generation: 4th
• Memory : DDR4/3200
• 8 channel
• 4th Generation Intel Xeon Scalable
• Core count : 60
• PCIe lane count: 80
• PCIe Generation: 5th
• Memory : DDR5/4800
• 8 channel
• 4th Generation AMD EPYC (Genoa)
• Core count: 96
• PCIe lane count: 128
• PCIe Generation: 5th
• Memory : DDR5/4800
• 12 channel
Confidential
Memory and PCIe Bandwidth
24 x DIMM slots,
DDR5 -4800 memory
Supports up to 6 TB
32 DIMM slots
DDR5 -4800 memory
supports up to 8TB
Hyper
Hyper
CloudDC CloudDC
12 DIMM slots,
DDR5-4800
Supports up to 3TB
16 DIMM slots
DDR5-4800
Supports up to 4TB
Up to 160 Lanes of
Gen5 PCIe with DP
Up to 128 Lanes of
Gen5 PCIe with UP
H13
X13
• Micron Confidential
• Micron Confidential
The CPU/memory challenge
6
0.0
0.5
1.0
1.5
2.0
2.5
3.0
3.5
2012 2013 2014 2015 2016 2017 2018 2019 2020
Normalized growth rate
CPU core count Memory Channel BW per core
 Increasing core counts
drives memory demand
 Demanding more
bandwidth and capacity
 Memory is unable to
keep up, leading to
more DDR channels
 Year-over-year memory
cost per GB reductions
flatten
 Memory capacity scaling
challenges are expected
to persist
• Micron Confidential
• Micron Confidential
Memory
bandwidth
per
core
(GB/s)
CPU Core Count
24 32 48 64 96
DDR4 has reached its limit!
DDR5 increases memory bandwidth per CPU core
for next-generation, multi-core CPUs
128
Source: Micron estimates. System bandwidth simulated for x8 modules in 1DPC and dual-channel configuration.
DDR5 6400
DDR5 4800
DDR4 3200
DDR5 8800
0
2
4
6
8
10
12
14
40
16
18
• Micron Confidential
• Micron Confidential
DDR4 vs DDR5
Up to 3x
performance increase
Rank(s) left side A Rank(s) left side B
40 bits
independent channel A
40 bits
independent channel B
 Data rates (up to 8800 MT/s)
 2x burst length (BL16)
 2x bank groups (8)
 2x banks (32)
 Improved refresh granularity (same bank refresh)
 2 independent 40-bit channels per RDIMM
(64 bytes per channel)
Micron Simulation, Subject to change
Simulated Conditions
• Micron Confidential
• Micron Confidential
DDR4 vs DDR5
Simulated effective bandwidth
9
Simulated conditions
- BW normalized to x64 interface
- 64B random accesses
- 66% reads
- One dual rank x4 RDIMM
DDR4-3200 DDR5-3200
DDR4 3200 vs DDR5 3200
DDR4-3200 DDR5-4800
DDR4 3200 vs DDR5 4800
16.8 GB/s
34.2 GB/s
16.8 GB/s
23.4 GB/s
1.39x
2.03x
- 16Gb component addressing
- Same bank refresh enabled
- Auto-precharge enabled
• Micron Confidential
• Micron Confidential
DDR5 data bus efficiency improved
Micron Confidential
10
66%
efficiency
91%
efficiency
89%
efficiency
DDR4 3200
DDR5 3200
DDR5 4800
DDR4 3200 DDR5 3200 DDR5 4800
16.8 GB/s
25.6 GB/s
23.4 GB/s
25.6 GB/s
34.2 GB/s
38.4 GB/s
Simulation
Theoretical Theoretical
Theoretical
Simulated conditions
• Micron Confidential
• Micron Confidential
Application workload proof points
Micro-
benchmark
Stream
MLC
Data center
IMDB - REDIS
Cloud
provider
SPEC-jbb
SAP-SD
SAP-HANA
VMmark
HPC
OpenFoam
Cloverleaf
CP2K
POT3D
WRF
AI
ResNet
DLRM
BERT
• Micron Confidential
• Micron Confidential
Sensitivity of workloads to memory latency, bandwidth and capacity
12
Confidential
The User Perspective - Product Selection
• Single Node Systems
• Multi-Node Systems
• Blade Systems (Networking)
• Application Specific Systems
Confidential
Supermicro Solutions
• Micron Confidential
• Micron Confidential
Application workload demands in a data-centric world
Data center
Business applications
and real-time services
that include large in-
memory dB and OLTP
Cloud provider
Expanded number of
users and micro-
services that include
high-availability,
scaling and low
latency, virtualized and
containerized
environments
High-performance
computing
AI/ML and deep
learning algorithms
with real-time
processing and
analytics
• Micron Confidential
• Micron Confidential
Increased performance for in-memory execution of
database and analytics applications
23% 45%
9,756 Query
Executions
per Hour
DDR4-3200
3rd Gen Xeon platorm1
DDR5-4800
4th Gen Xeon platorm2
14,118 Query
Executions
per Hour
SAP HANA 2.0
3
Phase 1
Data Load Time (s)
Faster
1.3 billion records loaded
More efficient business intelligence for
online analytical systems
More concurrent
operations
SAP HANA 2.0
3
Phase 3
0 1 2 3 4 5 6 7
DDR5-4th Gen Xeon
platform2
DDR4-3rd Gen Xeon
platform1
8 9 10 11
10.49
8.05
Lower is better
1. 3rd Gen Intel Xeon Platinum 8380 processor with Micron DDR4 3200 MHz system
2. 4th Gen Intel Xeon Platinum 8490H processor with Micron DDR5 4800 MHz system
3. SAP Standard Application Benchmark testing the hardware and database performance of SAP applications and components.
• Micron Confidential
• Micron Confidential
Speed up your business application workloads
Meet Service Level Agreements (SLAs)
Improve business agility, scaling and efficiency
SPECjbb max-jOPS
3
1.40x
224,892
jOPS
DDR4-32001 DDR5-4800 2
315,663
jOPS
1.48x
135,269
jOPS
DDR4-32001
DDR5-48002
200,288
jOPS
SPECjbb critical-jOPS
3
1. 3rd Gen Intel Xeon Platinum 8380 processor with Micron DDR4 3200 MHz system
2. 4th Gen Intel Xeon Platinum 8480 processor with Micron DDR5 4800 MHz system
3. SPECjbb is registered trademark of Standard Performance Evaluation Corporation. Performance results are derived from detailed benchmark procedures available at http://www.spec.org
Increased transactional
throughput
Reduced latency and
response times
Better Quality of Service (QoS)
• Micron Confidential
• Micron Confidential
Improve HPC efficiency
Reduce overall runtime of HPC simulations
Increase design iterations to improve accuracy
Faster time-to-market
20
The memory bandwidth required for next-generation HPC servers
>3x HPC workload performance boost
2.96 3.16
2.56
3.24
2.60
Speed factor for HPC workloads
1. AMD DDR4 system is an AMD EPYC 7763 64 core with DDR4-3200 MHz fully populated with 64GB RDIMMs
2. AMD DDR5 system is an AMD EPYC 9654 96 core with DDR5-4800 MHz fully populated with 64GB RDIMMs
• Micron Confidential
• Micron Confidential
DDR5 for data-
intensive workloads
2xcapability
2x burst length
2x bank groups
2x banks
2x or higher bandwidth1
Increased bandwidth
More than 2x1
Higher bus efficiency
Greater than 80%1
Faster transfer speed
Up to 8800 MT/s2
Improving overall
workload performance3
Cloud
Data center
High-performance computing
22
34.2 GB/s
16.8 GB/s
23.4 GB/s
2.03x
1.39x
DDR4-3200 DDR5-4800
DDR5-3200
DDR4 3200 DDR5 4800
Virtualization
40%
HPC modeling
>200%
Business apps
45%
1. Benchmark simulation comparison of DDR5-4800 vs DDR4 -3200
2. Based on defined JEDEC specification
3. Results based on internal testing, 3rd party testing and/or industry workload benchmark
testing
• Micron Confidential
• Micron Confidential
© 2023 Micron Technology, Inc. All rights reserved. Information, products, and/or specifications are
subject to change without notice. Micron, the Micron logo, and all other Micron trademarks are the
property of Micron Technology, Inc. All other trademarks are the property of their respective owners.
24
Thank you!

More Related Content

What's hot

Hardware & Software Platforms for HPC, AI and ML
Hardware & Software Platforms for HPC, AI and MLHardware & Software Platforms for HPC, AI and ML
Hardware & Software Platforms for HPC, AI and ML
inside-BigData.com
 
Delivering a new level of visual performance in an SoC AMD "Raven Ridge" APU
Delivering a new level of visual performance in an SoC AMD "Raven Ridge" APUDelivering a new level of visual performance in an SoC AMD "Raven Ridge" APU
Delivering a new level of visual performance in an SoC AMD "Raven Ridge" APU
AMD
 
Shared Memory Centric Computing with CXL & OMI
Shared Memory Centric Computing with CXL & OMIShared Memory Centric Computing with CXL & OMI
Shared Memory Centric Computing with CXL & OMI
Allan Cantle
 
10. GPU - Video Card (Display, Graphics, VGA)
10. GPU - Video Card (Display, Graphics, VGA)10. GPU - Video Card (Display, Graphics, VGA)
10. GPU - Video Card (Display, Graphics, VGA)
Akhila Dakshina
 
Modular by Design: Supermicro’s New Standards-Based Universal GPU Server
Modular by Design: Supermicro’s New Standards-Based Universal GPU ServerModular by Design: Supermicro’s New Standards-Based Universal GPU Server
Modular by Design: Supermicro’s New Standards-Based Universal GPU Server
Rebekah Rodriguez
 
한컴MDS_NVIDIA Jetson Platform
한컴MDS_NVIDIA Jetson Platform한컴MDS_NVIDIA Jetson Platform
한컴MDS_NVIDIA Jetson Platform
HANCOM MDS
 
Object Storage in a Cloud-Native Container Envirnoment
Object Storage in a Cloud-Native Container EnvirnomentObject Storage in a Cloud-Native Container Envirnoment
Object Storage in a Cloud-Native Container Envirnoment
Minio
 
Software development in ar mv8 m architecture - yiu
Software development in ar mv8 m architecture - yiuSoftware development in ar mv8 m architecture - yiu
Software development in ar mv8 m architecture - yiu
Arm
 
DDR, GDDR, HBM Memory : Presentation
DDR, GDDR, HBM Memory : PresentationDDR, GDDR, HBM Memory : Presentation
DDR, GDDR, HBM Memory : Presentation
Subhajit Sahu
 
AMD EPYC™ Microprocessor Architecture
AMD EPYC™ Microprocessor ArchitectureAMD EPYC™ Microprocessor Architecture
AMD EPYC™ Microprocessor Architecture
AMD
 
NVMe over Fabric
NVMe over FabricNVMe over Fabric
NVMe over Fabric
singh.gurjeet
 
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
 X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
Rebekah Rodriguez
 
Graphic Processing Unit (GPU)
Graphic Processing Unit (GPU)Graphic Processing Unit (GPU)
Graphic Processing Unit (GPU)
Jafar Khan
 
GPU Programming
GPU ProgrammingGPU Programming
GPU Programming
William Cunningham
 
Ceph Object Storage Performance Secrets and Ceph Data Lake Solution
Ceph Object Storage Performance Secrets and Ceph Data Lake SolutionCeph Object Storage Performance Secrets and Ceph Data Lake Solution
Ceph Object Storage Performance Secrets and Ceph Data Lake Solution
Karan Singh
 
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance ViewX13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
Rebekah Rodriguez
 
Introduction to DPDK
Introduction to DPDKIntroduction to DPDK
Introduction to DPDK
Kernel TLV
 
Moving to PCI Express based SSD with NVM Express
Moving to PCI Express based SSD with NVM ExpressMoving to PCI Express based SSD with NVM Express
Moving to PCI Express based SSD with NVM Express
Odinot Stanislas
 
Intel QLC: Cost-effective Ceph on NVMe
Intel QLC: Cost-effective Ceph on NVMeIntel QLC: Cost-effective Ceph on NVMe
Intel QLC: Cost-effective Ceph on NVMe
Ceph Community
 
Hot Chips: AMD Next Gen 7nm Ryzen 4000 APU
Hot Chips: AMD Next Gen 7nm Ryzen 4000 APUHot Chips: AMD Next Gen 7nm Ryzen 4000 APU
Hot Chips: AMD Next Gen 7nm Ryzen 4000 APU
AMD
 

What's hot (20)

Hardware & Software Platforms for HPC, AI and ML
Hardware & Software Platforms for HPC, AI and MLHardware & Software Platforms for HPC, AI and ML
Hardware & Software Platforms for HPC, AI and ML
 
Delivering a new level of visual performance in an SoC AMD "Raven Ridge" APU
Delivering a new level of visual performance in an SoC AMD "Raven Ridge" APUDelivering a new level of visual performance in an SoC AMD "Raven Ridge" APU
Delivering a new level of visual performance in an SoC AMD "Raven Ridge" APU
 
Shared Memory Centric Computing with CXL & OMI
Shared Memory Centric Computing with CXL & OMIShared Memory Centric Computing with CXL & OMI
Shared Memory Centric Computing with CXL & OMI
 
10. GPU - Video Card (Display, Graphics, VGA)
10. GPU - Video Card (Display, Graphics, VGA)10. GPU - Video Card (Display, Graphics, VGA)
10. GPU - Video Card (Display, Graphics, VGA)
 
Modular by Design: Supermicro’s New Standards-Based Universal GPU Server
Modular by Design: Supermicro’s New Standards-Based Universal GPU ServerModular by Design: Supermicro’s New Standards-Based Universal GPU Server
Modular by Design: Supermicro’s New Standards-Based Universal GPU Server
 
한컴MDS_NVIDIA Jetson Platform
한컴MDS_NVIDIA Jetson Platform한컴MDS_NVIDIA Jetson Platform
한컴MDS_NVIDIA Jetson Platform
 
Object Storage in a Cloud-Native Container Envirnoment
Object Storage in a Cloud-Native Container EnvirnomentObject Storage in a Cloud-Native Container Envirnoment
Object Storage in a Cloud-Native Container Envirnoment
 
Software development in ar mv8 m architecture - yiu
Software development in ar mv8 m architecture - yiuSoftware development in ar mv8 m architecture - yiu
Software development in ar mv8 m architecture - yiu
 
DDR, GDDR, HBM Memory : Presentation
DDR, GDDR, HBM Memory : PresentationDDR, GDDR, HBM Memory : Presentation
DDR, GDDR, HBM Memory : Presentation
 
AMD EPYC™ Microprocessor Architecture
AMD EPYC™ Microprocessor ArchitectureAMD EPYC™ Microprocessor Architecture
AMD EPYC™ Microprocessor Architecture
 
NVMe over Fabric
NVMe over FabricNVMe over Fabric
NVMe over Fabric
 
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
 X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
 
Graphic Processing Unit (GPU)
Graphic Processing Unit (GPU)Graphic Processing Unit (GPU)
Graphic Processing Unit (GPU)
 
GPU Programming
GPU ProgrammingGPU Programming
GPU Programming
 
Ceph Object Storage Performance Secrets and Ceph Data Lake Solution
Ceph Object Storage Performance Secrets and Ceph Data Lake SolutionCeph Object Storage Performance Secrets and Ceph Data Lake Solution
Ceph Object Storage Performance Secrets and Ceph Data Lake Solution
 
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance ViewX13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
X13 Products + Intel® Xeon® CPU Max Series–An Applications & Performance View
 
Introduction to DPDK
Introduction to DPDKIntroduction to DPDK
Introduction to DPDK
 
Moving to PCI Express based SSD with NVM Express
Moving to PCI Express based SSD with NVM ExpressMoving to PCI Express based SSD with NVM Express
Moving to PCI Express based SSD with NVM Express
 
Intel QLC: Cost-effective Ceph on NVMe
Intel QLC: Cost-effective Ceph on NVMeIntel QLC: Cost-effective Ceph on NVMe
Intel QLC: Cost-effective Ceph on NVMe
 
Hot Chips: AMD Next Gen 7nm Ryzen 4000 APU
Hot Chips: AMD Next Gen 7nm Ryzen 4000 APUHot Chips: AMD Next Gen 7nm Ryzen 4000 APU
Hot Chips: AMD Next Gen 7nm Ryzen 4000 APU
 

Similar to Supermicro Servers with Micron DDR5 & SSDs: Accelerating Real World Workloads

High-Density Top-Loading Storage for Cloud Scale Applications
High-Density Top-Loading Storage for Cloud Scale Applications High-Density Top-Loading Storage for Cloud Scale Applications
High-Density Top-Loading Storage for Cloud Scale Applications
Rebekah Rodriguez
 
Red Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super StorageRed Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super Storage
Red_Hat_Storage
 
Emerging Cloud Storage Trends for Enterprises
Emerging Cloud Storage Trends for EnterprisesEmerging Cloud Storage Trends for Enterprises
Emerging Cloud Storage Trends for Enterprises
Rebekah Rodriguez
 
System IBM x ivy bridge refresh
System IBM x ivy bridge refresh System IBM x ivy bridge refresh
System IBM x ivy bridge refresh
Anh Tuan
 
Optimize Content Delivery with Multi-Access Edge Computing
Optimize Content Delivery with Multi-Access Edge ComputingOptimize Content Delivery with Multi-Access Edge Computing
Optimize Content Delivery with Multi-Access Edge Computing
Rebekah Rodriguez
 
Evolution of Supermicro GPU Server Solution
Evolution of Supermicro GPU Server SolutionEvolution of Supermicro GPU Server Solution
Evolution of Supermicro GPU Server Solution
NVIDIA Taiwan
 
MWC Roundtable: Accelerating Innovation from the Intelligent Edge to Cloud
 MWC Roundtable: Accelerating Innovation from the Intelligent Edge to Cloud  MWC Roundtable: Accelerating Innovation from the Intelligent Edge to Cloud
MWC Roundtable: Accelerating Innovation from the Intelligent Edge to Cloud
Rebekah Rodriguez
 
Crossbar ARM TechCon 2016 presentation
Crossbar ARM TechCon 2016 presentation        Crossbar ARM TechCon 2016 presentation
Crossbar ARM TechCon 2016 presentation
Crossbarinc
 
Summit workshop thompto
Summit workshop thomptoSummit workshop thompto
Summit workshop thompto
Ganesan Narayanasamy
 
RedisConf18 - Re-architecting Redis-on-Flash with Intel 3DX Point™ Memory
RedisConf18 - Re-architecting Redis-on-Flash with Intel 3DX Point™ MemoryRedisConf18 - Re-architecting Redis-on-Flash with Intel 3DX Point™ Memory
RedisConf18 - Re-architecting Redis-on-Flash with Intel 3DX Point™ Memory
Redis Labs
 
IBM Power9 Features and Specifications
IBM Power9 Features and SpecificationsIBM Power9 Features and Specifications
IBM Power9 Features and Specifications
inside-BigData.com
 
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red_Hat_Storage
 
Hybrid Memory Cube: Developing Scalable and Resilient Memory Systems
Hybrid Memory Cube: Developing Scalable and Resilient Memory SystemsHybrid Memory Cube: Developing Scalable and Resilient Memory Systems
Hybrid Memory Cube: Developing Scalable and Resilient Memory Systems
MicronTechnology
 
New Generation of IBM Power Systems Delivering value with Red Hat Enterprise ...
New Generation of IBM Power Systems Delivering value with Red Hat Enterprise ...New Generation of IBM Power Systems Delivering value with Red Hat Enterprise ...
New Generation of IBM Power Systems Delivering value with Red Hat Enterprise ...
Filipe Miranda
 
[OpenStack Days Korea 2016] Track3 - OpenStack on 64-bit ARM with X-Gene
[OpenStack Days Korea 2016] Track3 - OpenStack on 64-bit ARM with X-Gene[OpenStack Days Korea 2016] Track3 - OpenStack on 64-bit ARM with X-Gene
[OpenStack Days Korea 2016] Track3 - OpenStack on 64-bit ARM with X-Gene
OpenStack Korea Community
 
Heterogeneous Computing : The Future of Systems
Heterogeneous Computing : The Future of SystemsHeterogeneous Computing : The Future of Systems
Heterogeneous Computing : The Future of Systems
Anand Haridass
 
Drive Data Center Efficiency with SuperBlade, Powered by AMD EPYC™ and Instinct™
Drive Data Center Efficiency with SuperBlade, Powered by AMD EPYC™ and Instinct™Drive Data Center Efficiency with SuperBlade, Powered by AMD EPYC™ and Instinct™
Drive Data Center Efficiency with SuperBlade, Powered by AMD EPYC™ and Instinct™
Rebekah Rodriguez
 
Exadata_X10M-Hardware-Overview.pdf
Exadata_X10M-Hardware-Overview.pdfExadata_X10M-Hardware-Overview.pdf
Exadata_X10M-Hardware-Overview.pdf
Koko842772
 
Introduction to HPC & Supercomputing in AI
Introduction to HPC & Supercomputing in AIIntroduction to HPC & Supercomputing in AI
Introduction to HPC & Supercomputing in AI
Tyrone Systems
 
How AI and ML are driving Memory Architecture changes
How AI and ML are driving Memory Architecture changesHow AI and ML are driving Memory Architecture changes
How AI and ML are driving Memory Architecture changes
Danny Sabour
 

Similar to Supermicro Servers with Micron DDR5 & SSDs: Accelerating Real World Workloads (20)

High-Density Top-Loading Storage for Cloud Scale Applications
High-Density Top-Loading Storage for Cloud Scale Applications High-Density Top-Loading Storage for Cloud Scale Applications
High-Density Top-Loading Storage for Cloud Scale Applications
 
Red Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super StorageRed Hat Storage Day Boston - Supermicro Super Storage
Red Hat Storage Day Boston - Supermicro Super Storage
 
Emerging Cloud Storage Trends for Enterprises
Emerging Cloud Storage Trends for EnterprisesEmerging Cloud Storage Trends for Enterprises
Emerging Cloud Storage Trends for Enterprises
 
System IBM x ivy bridge refresh
System IBM x ivy bridge refresh System IBM x ivy bridge refresh
System IBM x ivy bridge refresh
 
Optimize Content Delivery with Multi-Access Edge Computing
Optimize Content Delivery with Multi-Access Edge ComputingOptimize Content Delivery with Multi-Access Edge Computing
Optimize Content Delivery with Multi-Access Edge Computing
 
Evolution of Supermicro GPU Server Solution
Evolution of Supermicro GPU Server SolutionEvolution of Supermicro GPU Server Solution
Evolution of Supermicro GPU Server Solution
 
MWC Roundtable: Accelerating Innovation from the Intelligent Edge to Cloud
 MWC Roundtable: Accelerating Innovation from the Intelligent Edge to Cloud  MWC Roundtable: Accelerating Innovation from the Intelligent Edge to Cloud
MWC Roundtable: Accelerating Innovation from the Intelligent Edge to Cloud
 
Crossbar ARM TechCon 2016 presentation
Crossbar ARM TechCon 2016 presentation        Crossbar ARM TechCon 2016 presentation
Crossbar ARM TechCon 2016 presentation
 
Summit workshop thompto
Summit workshop thomptoSummit workshop thompto
Summit workshop thompto
 
RedisConf18 - Re-architecting Redis-on-Flash with Intel 3DX Point™ Memory
RedisConf18 - Re-architecting Redis-on-Flash with Intel 3DX Point™ MemoryRedisConf18 - Re-architecting Redis-on-Flash with Intel 3DX Point™ Memory
RedisConf18 - Re-architecting Redis-on-Flash with Intel 3DX Point™ Memory
 
IBM Power9 Features and Specifications
IBM Power9 Features and SpecificationsIBM Power9 Features and Specifications
IBM Power9 Features and Specifications
 
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
Red Hat Storage Day Seattle: Supermicro Solutions for Red Hat Ceph and Red Ha...
 
Hybrid Memory Cube: Developing Scalable and Resilient Memory Systems
Hybrid Memory Cube: Developing Scalable and Resilient Memory SystemsHybrid Memory Cube: Developing Scalable and Resilient Memory Systems
Hybrid Memory Cube: Developing Scalable and Resilient Memory Systems
 
New Generation of IBM Power Systems Delivering value with Red Hat Enterprise ...
New Generation of IBM Power Systems Delivering value with Red Hat Enterprise ...New Generation of IBM Power Systems Delivering value with Red Hat Enterprise ...
New Generation of IBM Power Systems Delivering value with Red Hat Enterprise ...
 
[OpenStack Days Korea 2016] Track3 - OpenStack on 64-bit ARM with X-Gene
[OpenStack Days Korea 2016] Track3 - OpenStack on 64-bit ARM with X-Gene[OpenStack Days Korea 2016] Track3 - OpenStack on 64-bit ARM with X-Gene
[OpenStack Days Korea 2016] Track3 - OpenStack on 64-bit ARM with X-Gene
 
Heterogeneous Computing : The Future of Systems
Heterogeneous Computing : The Future of SystemsHeterogeneous Computing : The Future of Systems
Heterogeneous Computing : The Future of Systems
 
Drive Data Center Efficiency with SuperBlade, Powered by AMD EPYC™ and Instinct™
Drive Data Center Efficiency with SuperBlade, Powered by AMD EPYC™ and Instinct™Drive Data Center Efficiency with SuperBlade, Powered by AMD EPYC™ and Instinct™
Drive Data Center Efficiency with SuperBlade, Powered by AMD EPYC™ and Instinct™
 
Exadata_X10M-Hardware-Overview.pdf
Exadata_X10M-Hardware-Overview.pdfExadata_X10M-Hardware-Overview.pdf
Exadata_X10M-Hardware-Overview.pdf
 
Introduction to HPC & Supercomputing in AI
Introduction to HPC & Supercomputing in AIIntroduction to HPC & Supercomputing in AI
Introduction to HPC & Supercomputing in AI
 
How AI and ML are driving Memory Architecture changes
How AI and ML are driving Memory Architecture changesHow AI and ML are driving Memory Architecture changes
How AI and ML are driving Memory Architecture changes
 

More from Rebekah Rodriguez

Supermicro and The Green Grid (TGG)
Supermicro and The Green Grid (TGG)Supermicro and The Green Grid (TGG)
Supermicro and The Green Grid (TGG)
Rebekah Rodriguez
 
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super Affordable
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super AffordableSupermicro AI Pod that’s Super Simple, Super Scalable, and Super Affordable
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super Affordable
Rebekah Rodriguez
 
Building Efficient Edge Nodes for Content Delivery Networks
Building Efficient Edge Nodes for Content Delivery NetworksBuilding Efficient Edge Nodes for Content Delivery Networks
Building Efficient Edge Nodes for Content Delivery Networks
Rebekah Rodriguez
 
Innovative Solutions for Cloud Gaming, Media, Transcoding, & AI Inferencing
Innovative Solutions for Cloud Gaming, Media, Transcoding, & AI InferencingInnovative Solutions for Cloud Gaming, Media, Transcoding, & AI Inferencing
Innovative Solutions for Cloud Gaming, Media, Transcoding, & AI Inferencing
Rebekah Rodriguez
 
Zero Trust for Private 5G and Edge
Zero Trust for Private 5G and EdgeZero Trust for Private 5G and Edge
Zero Trust for Private 5G and Edge
Rebekah Rodriguez
 
Benefits of Operating an On-Premises Infrastructure
Benefits of Operating an On-Premises InfrastructureBenefits of Operating an On-Premises Infrastructure
Benefits of Operating an On-Premises Infrastructure
Rebekah Rodriguez
 
Tackling Retail Technology Management Challenges at the Edge
Tackling Retail Technology Management Challenges at the EdgeTackling Retail Technology Management Challenges at the Edge
Tackling Retail Technology Management Challenges at the Edge
Rebekah Rodriguez
 
Delivering Breakthrough Performance Per Core with AMD EPYC
Delivering Breakthrough Performance Per Core with AMD EPYCDelivering Breakthrough Performance Per Core with AMD EPYC
Delivering Breakthrough Performance Per Core with AMD EPYC
Rebekah Rodriguez
 
Delivering Breakthrough Performance Per Core with AMD EPYC
Delivering Breakthrough Performance Per Core with AMD EPYCDelivering Breakthrough Performance Per Core with AMD EPYC
Delivering Breakthrough Performance Per Core with AMD EPYC
Rebekah Rodriguez
 
Accelerating Innovation from Edge to Cloud
Accelerating Innovation from Edge to CloudAccelerating Innovation from Edge to Cloud
Accelerating Innovation from Edge to Cloud
Rebekah Rodriguez
 
Consumption Based On-Demand Private Cloud in a Box
Consumption Based On-Demand Private Cloud in a BoxConsumption Based On-Demand Private Cloud in a Box
Consumption Based On-Demand Private Cloud in a Box
Rebekah Rodriguez
 
High Performance Object Storage in 30 Minutes with Supermicro and MinIO
High Performance Object Storage in 30 Minutes with Supermicro and MinIOHigh Performance Object Storage in 30 Minutes with Supermicro and MinIO
High Performance Object Storage in 30 Minutes with Supermicro and MinIO
Rebekah Rodriguez
 
Rack Cluster Deployment for SDSC Supercomputer
Rack Cluster Deployment for SDSC SupercomputerRack Cluster Deployment for SDSC Supercomputer
Rack Cluster Deployment for SDSC Supercomputer
Rebekah Rodriguez
 
Simplify Data Management and Go Green with Supermicro & Qumulo
Simplify Data Management and Go Green with Supermicro & QumuloSimplify Data Management and Go Green with Supermicro & Qumulo
Simplify Data Management and Go Green with Supermicro & Qumulo
Rebekah Rodriguez
 
The Power of One: Supermicro’s High-Performance Single-Processor Blade Systems
The Power of One: Supermicro’s High-Performance Single-Processor Blade SystemsThe Power of One: Supermicro’s High-Performance Single-Processor Blade Systems
The Power of One: Supermicro’s High-Performance Single-Processor Blade Systems
Rebekah Rodriguez
 

More from Rebekah Rodriguez (15)

Supermicro and The Green Grid (TGG)
Supermicro and The Green Grid (TGG)Supermicro and The Green Grid (TGG)
Supermicro and The Green Grid (TGG)
 
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super Affordable
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super AffordableSupermicro AI Pod that’s Super Simple, Super Scalable, and Super Affordable
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super Affordable
 
Building Efficient Edge Nodes for Content Delivery Networks
Building Efficient Edge Nodes for Content Delivery NetworksBuilding Efficient Edge Nodes for Content Delivery Networks
Building Efficient Edge Nodes for Content Delivery Networks
 
Innovative Solutions for Cloud Gaming, Media, Transcoding, & AI Inferencing
Innovative Solutions for Cloud Gaming, Media, Transcoding, & AI InferencingInnovative Solutions for Cloud Gaming, Media, Transcoding, & AI Inferencing
Innovative Solutions for Cloud Gaming, Media, Transcoding, & AI Inferencing
 
Zero Trust for Private 5G and Edge
Zero Trust for Private 5G and EdgeZero Trust for Private 5G and Edge
Zero Trust for Private 5G and Edge
 
Benefits of Operating an On-Premises Infrastructure
Benefits of Operating an On-Premises InfrastructureBenefits of Operating an On-Premises Infrastructure
Benefits of Operating an On-Premises Infrastructure
 
Tackling Retail Technology Management Challenges at the Edge
Tackling Retail Technology Management Challenges at the EdgeTackling Retail Technology Management Challenges at the Edge
Tackling Retail Technology Management Challenges at the Edge
 
Delivering Breakthrough Performance Per Core with AMD EPYC
Delivering Breakthrough Performance Per Core with AMD EPYCDelivering Breakthrough Performance Per Core with AMD EPYC
Delivering Breakthrough Performance Per Core with AMD EPYC
 
Delivering Breakthrough Performance Per Core with AMD EPYC
Delivering Breakthrough Performance Per Core with AMD EPYCDelivering Breakthrough Performance Per Core with AMD EPYC
Delivering Breakthrough Performance Per Core with AMD EPYC
 
Accelerating Innovation from Edge to Cloud
Accelerating Innovation from Edge to CloudAccelerating Innovation from Edge to Cloud
Accelerating Innovation from Edge to Cloud
 
Consumption Based On-Demand Private Cloud in a Box
Consumption Based On-Demand Private Cloud in a BoxConsumption Based On-Demand Private Cloud in a Box
Consumption Based On-Demand Private Cloud in a Box
 
High Performance Object Storage in 30 Minutes with Supermicro and MinIO
High Performance Object Storage in 30 Minutes with Supermicro and MinIOHigh Performance Object Storage in 30 Minutes with Supermicro and MinIO
High Performance Object Storage in 30 Minutes with Supermicro and MinIO
 
Rack Cluster Deployment for SDSC Supercomputer
Rack Cluster Deployment for SDSC SupercomputerRack Cluster Deployment for SDSC Supercomputer
Rack Cluster Deployment for SDSC Supercomputer
 
Simplify Data Management and Go Green with Supermicro & Qumulo
Simplify Data Management and Go Green with Supermicro & QumuloSimplify Data Management and Go Green with Supermicro & Qumulo
Simplify Data Management and Go Green with Supermicro & Qumulo
 
The Power of One: Supermicro’s High-Performance Single-Processor Blade Systems
The Power of One: Supermicro’s High-Performance Single-Processor Blade SystemsThe Power of One: Supermicro’s High-Performance Single-Processor Blade Systems
The Power of One: Supermicro’s High-Performance Single-Processor Blade Systems
 

Recently uploaded

The Increasing Use of the National Research Platform by the CSU Campuses
The Increasing Use of the National Research Platform by the CSU CampusesThe Increasing Use of the National Research Platform by the CSU Campuses
The Increasing Use of the National Research Platform by the CSU Campuses
Larry Smarr
 
What’s New in Teams Calling, Meetings and Devices May 2024
What’s New in Teams Calling, Meetings and Devices May 2024What’s New in Teams Calling, Meetings and Devices May 2024
What’s New in Teams Calling, Meetings and Devices May 2024
Stephanie Beckett
 
Scaling Connections in PostgreSQL Postgres Bangalore(PGBLR) Meetup-2 - Mydbops
Scaling Connections in PostgreSQL Postgres Bangalore(PGBLR) Meetup-2 - MydbopsScaling Connections in PostgreSQL Postgres Bangalore(PGBLR) Meetup-2 - Mydbops
Scaling Connections in PostgreSQL Postgres Bangalore(PGBLR) Meetup-2 - Mydbops
Mydbops
 
this resume for sadika shaikh bca student
this resume for sadika shaikh bca studentthis resume for sadika shaikh bca student
this resume for sadika shaikh bca student
SadikaShaikh7
 
K2G - Insurtech Innovation EMEA Award 2024
K2G - Insurtech Innovation EMEA Award 2024K2G - Insurtech Innovation EMEA Award 2024
K2G - Insurtech Innovation EMEA Award 2024
The Digital Insurer
 
STKI Israeli Market Study 2024 final v1
STKI Israeli Market Study 2024 final  v1STKI Israeli Market Study 2024 final  v1
STKI Israeli Market Study 2024 final v1
Dr. Jimmy Schwarzkopf
 
UiPath Community Day Kraków: Devs4Devs Conference
UiPath Community Day Kraków: Devs4Devs ConferenceUiPath Community Day Kraków: Devs4Devs Conference
UiPath Community Day Kraków: Devs4Devs Conference
UiPathCommunity
 
What Not to Document and Why_ (North Bay Python 2024)
What Not to Document and Why_ (North Bay Python 2024)What Not to Document and Why_ (North Bay Python 2024)
What Not to Document and Why_ (North Bay Python 2024)
Margaret Fero
 
一比一原版(msvu毕业证书)圣文森山大学毕业证如何办理
一比一原版(msvu毕业证书)圣文森山大学毕业证如何办理一比一原版(msvu毕业证书)圣文森山大学毕业证如何办理
一比一原版(msvu毕业证书)圣文森山大学毕业证如何办理
uuuot
 
5G bootcamp Sep 2020 (NPI initiative).pptx
5G bootcamp Sep 2020 (NPI initiative).pptx5G bootcamp Sep 2020 (NPI initiative).pptx
5G bootcamp Sep 2020 (NPI initiative).pptx
SATYENDRA100
 
Knowledge and Prompt Engineering Part 2 Focus on Prompt Design Approaches
Knowledge and Prompt Engineering Part 2 Focus on Prompt Design ApproachesKnowledge and Prompt Engineering Part 2 Focus on Prompt Design Approaches
Knowledge and Prompt Engineering Part 2 Focus on Prompt Design Approaches
Earley Information Science
 
Calgary MuleSoft Meetup APM and IDP .pptx
Calgary MuleSoft Meetup APM and IDP .pptxCalgary MuleSoft Meetup APM and IDP .pptx
Calgary MuleSoft Meetup APM and IDP .pptx
ishalveerrandhawa1
 
AI_dev Europe 2024 - From OpenAI to Opensource AI
AI_dev Europe 2024 - From OpenAI to Opensource AIAI_dev Europe 2024 - From OpenAI to Opensource AI
AI_dev Europe 2024 - From OpenAI to Opensource AI
Raphaël Semeteys
 
DealBook of Ukraine: 2024 edition
DealBook of Ukraine: 2024 editionDealBook of Ukraine: 2024 edition
DealBook of Ukraine: 2024 edition
Yevgen Sysoyev
 
Running a Go App in Kubernetes: CPU Impacts
Running a Go App in Kubernetes: CPU ImpactsRunning a Go App in Kubernetes: CPU Impacts
Running a Go App in Kubernetes: CPU Impacts
ScyllaDB
 
Why do You Have to Redesign?_Redesign Challenge Day 1
Why do You Have to Redesign?_Redesign Challenge Day 1Why do You Have to Redesign?_Redesign Challenge Day 1
Why do You Have to Redesign?_Redesign Challenge Day 1
FellyciaHikmahwarani
 
Lessons Of Binary Analysis - Christien Rioux
Lessons Of Binary Analysis - Christien RiouxLessons Of Binary Analysis - Christien Rioux
Lessons Of Binary Analysis - Christien Rioux
crioux1
 
“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...
“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...
“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...
Edge AI and Vision Alliance
 
How Netflix Builds High Performance Applications at Global Scale
How Netflix Builds High Performance Applications at Global ScaleHow Netflix Builds High Performance Applications at Global Scale
How Netflix Builds High Performance Applications at Global Scale
ScyllaDB
 
Quantum Communications Q&A with Gemini LLM
Quantum Communications Q&A with Gemini LLMQuantum Communications Q&A with Gemini LLM
Quantum Communications Q&A with Gemini LLM
Vijayananda Mohire
 

Recently uploaded (20)

The Increasing Use of the National Research Platform by the CSU Campuses
The Increasing Use of the National Research Platform by the CSU CampusesThe Increasing Use of the National Research Platform by the CSU Campuses
The Increasing Use of the National Research Platform by the CSU Campuses
 
What’s New in Teams Calling, Meetings and Devices May 2024
What’s New in Teams Calling, Meetings and Devices May 2024What’s New in Teams Calling, Meetings and Devices May 2024
What’s New in Teams Calling, Meetings and Devices May 2024
 
Scaling Connections in PostgreSQL Postgres Bangalore(PGBLR) Meetup-2 - Mydbops
Scaling Connections in PostgreSQL Postgres Bangalore(PGBLR) Meetup-2 - MydbopsScaling Connections in PostgreSQL Postgres Bangalore(PGBLR) Meetup-2 - Mydbops
Scaling Connections in PostgreSQL Postgres Bangalore(PGBLR) Meetup-2 - Mydbops
 
this resume for sadika shaikh bca student
this resume for sadika shaikh bca studentthis resume for sadika shaikh bca student
this resume for sadika shaikh bca student
 
K2G - Insurtech Innovation EMEA Award 2024
K2G - Insurtech Innovation EMEA Award 2024K2G - Insurtech Innovation EMEA Award 2024
K2G - Insurtech Innovation EMEA Award 2024
 
STKI Israeli Market Study 2024 final v1
STKI Israeli Market Study 2024 final  v1STKI Israeli Market Study 2024 final  v1
STKI Israeli Market Study 2024 final v1
 
UiPath Community Day Kraków: Devs4Devs Conference
UiPath Community Day Kraków: Devs4Devs ConferenceUiPath Community Day Kraków: Devs4Devs Conference
UiPath Community Day Kraków: Devs4Devs Conference
 
What Not to Document and Why_ (North Bay Python 2024)
What Not to Document and Why_ (North Bay Python 2024)What Not to Document and Why_ (North Bay Python 2024)
What Not to Document and Why_ (North Bay Python 2024)
 
一比一原版(msvu毕业证书)圣文森山大学毕业证如何办理
一比一原版(msvu毕业证书)圣文森山大学毕业证如何办理一比一原版(msvu毕业证书)圣文森山大学毕业证如何办理
一比一原版(msvu毕业证书)圣文森山大学毕业证如何办理
 
5G bootcamp Sep 2020 (NPI initiative).pptx
5G bootcamp Sep 2020 (NPI initiative).pptx5G bootcamp Sep 2020 (NPI initiative).pptx
5G bootcamp Sep 2020 (NPI initiative).pptx
 
Knowledge and Prompt Engineering Part 2 Focus on Prompt Design Approaches
Knowledge and Prompt Engineering Part 2 Focus on Prompt Design ApproachesKnowledge and Prompt Engineering Part 2 Focus on Prompt Design Approaches
Knowledge and Prompt Engineering Part 2 Focus on Prompt Design Approaches
 
Calgary MuleSoft Meetup APM and IDP .pptx
Calgary MuleSoft Meetup APM and IDP .pptxCalgary MuleSoft Meetup APM and IDP .pptx
Calgary MuleSoft Meetup APM and IDP .pptx
 
AI_dev Europe 2024 - From OpenAI to Opensource AI
AI_dev Europe 2024 - From OpenAI to Opensource AIAI_dev Europe 2024 - From OpenAI to Opensource AI
AI_dev Europe 2024 - From OpenAI to Opensource AI
 
DealBook of Ukraine: 2024 edition
DealBook of Ukraine: 2024 editionDealBook of Ukraine: 2024 edition
DealBook of Ukraine: 2024 edition
 
Running a Go App in Kubernetes: CPU Impacts
Running a Go App in Kubernetes: CPU ImpactsRunning a Go App in Kubernetes: CPU Impacts
Running a Go App in Kubernetes: CPU Impacts
 
Why do You Have to Redesign?_Redesign Challenge Day 1
Why do You Have to Redesign?_Redesign Challenge Day 1Why do You Have to Redesign?_Redesign Challenge Day 1
Why do You Have to Redesign?_Redesign Challenge Day 1
 
Lessons Of Binary Analysis - Christien Rioux
Lessons Of Binary Analysis - Christien RiouxLessons Of Binary Analysis - Christien Rioux
Lessons Of Binary Analysis - Christien Rioux
 
“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...
“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...
“Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” a Pres...
 
How Netflix Builds High Performance Applications at Global Scale
How Netflix Builds High Performance Applications at Global ScaleHow Netflix Builds High Performance Applications at Global Scale
How Netflix Builds High Performance Applications at Global Scale
 
Quantum Communications Q&A with Gemini LLM
Quantum Communications Q&A with Gemini LLMQuantum Communications Q&A with Gemini LLM
Quantum Communications Q&A with Gemini LLM
 

Supermicro Servers with Micron DDR5 & SSDs: Accelerating Real World Workloads

  • 2. Confidential Supermicro X13 Comprehensive Portfolio Hyper and Hyper-E Best-in-Class Performance and Flexibility Rackmount Servers for Enterprise Applications Cloud DC All-in-one Rackmount Platforms for Cloud Data Centers Mainstream Versatile Entry Level and Volume Servers for Enterprise Applications BigTwin® Highly Modular Multi-Node Systems with Tool-less Design FatTwin® Advanced Multi-node 4U Twin Architecture with 8 or 4 Nodes Cost-effective 2U Multi-node Platforms TwinPro® SuperBlade® High Density x86 Multi-node Server for Enterprise Cloud, HPC SuperStorage® WIO (UP) Industry’s Widest Variety of I/O Optimized Servers High Density Systems for Double- width, Full Length PCIe GPUs PCIe GPU Servers Universal GPU Servers High Performance and Flexibility with Advanced Architecture and Thermal Design Highest Performance and Flexibility for Enterprise Applications MP 4-Way Server High-efficiency, High-performance Compact Form Factor for 5G and Edge computing IOT/Embedded Top-loading Server Optimized for Field Serviceability and Field Replacement Workstations for High Performance Workloads SuperWorkstations 2 Better Faster Greener™ © 2022 Supermicro GrandTwin® Highly Modular Front Access Multi-Node Systems with Tool- less Design
  • 3. Confidential Supermicro Has the Most Genoa Options 2/8/2023 Better Faster Greener™ © 2022 Supermicro 3 AS –2115GT-HNTR (Rear IO) GrandTwin 2U4Node Hyper DP Systems CloudDC UP Systems GPU Systems AS -1015CS-TNR AS -1115CS-TNR AS -2015CS-TNR AS -1125HS-TNR AS -2025HS-TNR AS -2125HS-TNR AS -4125GS-TNRT 8 PCIe 5.0 x16 GPUs AS –2115GT-HNTF (Front IO) Supermicro A+ Product Page https://www.supermicro.com/en/products/aplus
  • 4. Confidential 4th Generation Platform Overview (Max per socket) • 3rd Generation Intel Xeon Scalable • Core count: 40 • PCIe lane count: 64 • PCIe Generation: 4th • Memory : DDR4/3200 • 8 channel • 3rd Generation AMD EPYC • Core count: 64 • PCIe lane count: 128 • PCIe Generation: 4th • Memory : DDR4/3200 • 8 channel • 4th Generation Intel Xeon Scalable • Core count : 60 • PCIe lane count: 80 • PCIe Generation: 5th • Memory : DDR5/4800 • 8 channel • 4th Generation AMD EPYC (Genoa) • Core count: 96 • PCIe lane count: 128 • PCIe Generation: 5th • Memory : DDR5/4800 • 12 channel
  • 5. Confidential Memory and PCIe Bandwidth 24 x DIMM slots, DDR5 -4800 memory Supports up to 6 TB 32 DIMM slots DDR5 -4800 memory supports up to 8TB Hyper Hyper CloudDC CloudDC 12 DIMM slots, DDR5-4800 Supports up to 3TB 16 DIMM slots DDR5-4800 Supports up to 4TB Up to 160 Lanes of Gen5 PCIe with DP Up to 128 Lanes of Gen5 PCIe with UP H13 X13
  • 6. • Micron Confidential • Micron Confidential The CPU/memory challenge 6 0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5 2012 2013 2014 2015 2016 2017 2018 2019 2020 Normalized growth rate CPU core count Memory Channel BW per core  Increasing core counts drives memory demand  Demanding more bandwidth and capacity  Memory is unable to keep up, leading to more DDR channels  Year-over-year memory cost per GB reductions flatten  Memory capacity scaling challenges are expected to persist
  • 7. • Micron Confidential • Micron Confidential Memory bandwidth per core (GB/s) CPU Core Count 24 32 48 64 96 DDR4 has reached its limit! DDR5 increases memory bandwidth per CPU core for next-generation, multi-core CPUs 128 Source: Micron estimates. System bandwidth simulated for x8 modules in 1DPC and dual-channel configuration. DDR5 6400 DDR5 4800 DDR4 3200 DDR5 8800 0 2 4 6 8 10 12 14 40 16 18
  • 8. • Micron Confidential • Micron Confidential DDR4 vs DDR5 Up to 3x performance increase Rank(s) left side A Rank(s) left side B 40 bits independent channel A 40 bits independent channel B  Data rates (up to 8800 MT/s)  2x burst length (BL16)  2x bank groups (8)  2x banks (32)  Improved refresh granularity (same bank refresh)  2 independent 40-bit channels per RDIMM (64 bytes per channel) Micron Simulation, Subject to change Simulated Conditions
  • 9. • Micron Confidential • Micron Confidential DDR4 vs DDR5 Simulated effective bandwidth 9 Simulated conditions - BW normalized to x64 interface - 64B random accesses - 66% reads - One dual rank x4 RDIMM DDR4-3200 DDR5-3200 DDR4 3200 vs DDR5 3200 DDR4-3200 DDR5-4800 DDR4 3200 vs DDR5 4800 16.8 GB/s 34.2 GB/s 16.8 GB/s 23.4 GB/s 1.39x 2.03x - 16Gb component addressing - Same bank refresh enabled - Auto-precharge enabled
  • 10. • Micron Confidential • Micron Confidential DDR5 data bus efficiency improved Micron Confidential 10 66% efficiency 91% efficiency 89% efficiency DDR4 3200 DDR5 3200 DDR5 4800 DDR4 3200 DDR5 3200 DDR5 4800 16.8 GB/s 25.6 GB/s 23.4 GB/s 25.6 GB/s 34.2 GB/s 38.4 GB/s Simulation Theoretical Theoretical Theoretical Simulated conditions
  • 11. • Micron Confidential • Micron Confidential Application workload proof points Micro- benchmark Stream MLC Data center IMDB - REDIS Cloud provider SPEC-jbb SAP-SD SAP-HANA VMmark HPC OpenFoam Cloverleaf CP2K POT3D WRF AI ResNet DLRM BERT
  • 12. • Micron Confidential • Micron Confidential Sensitivity of workloads to memory latency, bandwidth and capacity 12
  • 13. Confidential The User Perspective - Product Selection • Single Node Systems • Multi-Node Systems • Blade Systems (Networking) • Application Specific Systems
  • 15. • Micron Confidential • Micron Confidential Application workload demands in a data-centric world Data center Business applications and real-time services that include large in- memory dB and OLTP Cloud provider Expanded number of users and micro- services that include high-availability, scaling and low latency, virtualized and containerized environments High-performance computing AI/ML and deep learning algorithms with real-time processing and analytics
  • 16. • Micron Confidential • Micron Confidential Increased performance for in-memory execution of database and analytics applications 23% 45% 9,756 Query Executions per Hour DDR4-3200 3rd Gen Xeon platorm1 DDR5-4800 4th Gen Xeon platorm2 14,118 Query Executions per Hour SAP HANA 2.0 3 Phase 1 Data Load Time (s) Faster 1.3 billion records loaded More efficient business intelligence for online analytical systems More concurrent operations SAP HANA 2.0 3 Phase 3 0 1 2 3 4 5 6 7 DDR5-4th Gen Xeon platform2 DDR4-3rd Gen Xeon platform1 8 9 10 11 10.49 8.05 Lower is better 1. 3rd Gen Intel Xeon Platinum 8380 processor with Micron DDR4 3200 MHz system 2. 4th Gen Intel Xeon Platinum 8490H processor with Micron DDR5 4800 MHz system 3. SAP Standard Application Benchmark testing the hardware and database performance of SAP applications and components.
  • 17. • Micron Confidential • Micron Confidential Speed up your business application workloads Meet Service Level Agreements (SLAs) Improve business agility, scaling and efficiency SPECjbb max-jOPS 3 1.40x 224,892 jOPS DDR4-32001 DDR5-4800 2 315,663 jOPS 1.48x 135,269 jOPS DDR4-32001 DDR5-48002 200,288 jOPS SPECjbb critical-jOPS 3 1. 3rd Gen Intel Xeon Platinum 8380 processor with Micron DDR4 3200 MHz system 2. 4th Gen Intel Xeon Platinum 8480 processor with Micron DDR5 4800 MHz system 3. SPECjbb is registered trademark of Standard Performance Evaluation Corporation. Performance results are derived from detailed benchmark procedures available at http://www.spec.org Increased transactional throughput Reduced latency and response times Better Quality of Service (QoS)
  • 18. • Micron Confidential • Micron Confidential Improve HPC efficiency Reduce overall runtime of HPC simulations Increase design iterations to improve accuracy Faster time-to-market 20 The memory bandwidth required for next-generation HPC servers >3x HPC workload performance boost 2.96 3.16 2.56 3.24 2.60 Speed factor for HPC workloads 1. AMD DDR4 system is an AMD EPYC 7763 64 core with DDR4-3200 MHz fully populated with 64GB RDIMMs 2. AMD DDR5 system is an AMD EPYC 9654 96 core with DDR5-4800 MHz fully populated with 64GB RDIMMs
  • 19. • Micron Confidential • Micron Confidential DDR5 for data- intensive workloads 2xcapability 2x burst length 2x bank groups 2x banks 2x or higher bandwidth1 Increased bandwidth More than 2x1 Higher bus efficiency Greater than 80%1 Faster transfer speed Up to 8800 MT/s2 Improving overall workload performance3 Cloud Data center High-performance computing 22 34.2 GB/s 16.8 GB/s 23.4 GB/s 2.03x 1.39x DDR4-3200 DDR5-4800 DDR5-3200 DDR4 3200 DDR5 4800 Virtualization 40% HPC modeling >200% Business apps 45% 1. Benchmark simulation comparison of DDR5-4800 vs DDR4 -3200 2. Based on defined JEDEC specification 3. Results based on internal testing, 3rd party testing and/or industry workload benchmark testing
  • 20. • Micron Confidential • Micron Confidential
  • 21. © 2023 Micron Technology, Inc. All rights reserved. Information, products, and/or specifications are subject to change without notice. Micron, the Micron logo, and all other Micron trademarks are the property of Micron Technology, Inc. All other trademarks are the property of their respective owners. 24 Thank you!

Editor's Notes

  1. X13 Intel -Optimized, Open Architectures More than 15 server categories -Resourcing saving architecture to reduce material and energy usage -Enhanced thermal capacity – supporting next-gen CPUs, GPUs and other components Flexible networking with Advanced I/O Modules (AIOM), up to 400G/s speeds High ambient temperature operations up to 40C with liquid cooling options Support for open and industry standards including OCP 3.0, OAM, ORV2, OSF, Open BMC and EDSFF
  2. H13 AMD (Genoa) 4 Family/categories utilizing SMCI innovative system designs