Industry Trends

HPC Development Trends

HPC Development Trends

To meet the processing demands of HPC applications, enterprises are faced with the decision to build local HPC clusters or leverage the scalability, performance, and price offerings of the cloud. In-cloud HPC enables nearly unlimited computing capacity that scales with demand, reduces unnecessary investment and costs, and allows customers to focus on their own business development.

Business Challenges

  • Asset-heavy, Time-intensive Builds

    High construction costs and long rollouts that quite often fail to meet requirements for service flexibility.

  • Heavy Maintenance Workloads

    Heavy maintenance workloads consume manpower and time.

  • Rapid Hardware Iterations

    New technology emerges and evolves so quickly that enterprises can barely keep up with computing requirements.

  • High OPEX

    High operating costs including rent, electricity, water, system management, service consultation, and device O&M.

Typical Scenarios

Industrial Design

Industrial and manufacturing enterprises typically use design simulation software, including CAD and CAE, to improve efficiency. Huawei HPC Cloud provides powerful computing services for a wide range of simulation software, helping enterprises shorten service rollouts and improve product quality.

Benefits

  • Scalable HPC ECS

    C6 (general computing-plus) and M6 (memory-optimized) computing-intensive ECSs are provided. These ECSs use second-generation Intel® Xeon® Scalable processors with technologies optimized and Huawei-proprietary high-speed intelligent NICs to offer powerful and stable computing performance, including ultra-high network bandwidth and ultra-low latency.

  • Excellent-Performance BMS

    H2 BMSs (dedicated physical servers) with 100 Gbit/s EDR Infiniband networks are provided, avoiding losses due to virtualization and offering high performance. You are allowed to automatically provision BMSs on the management console, fully meeting scalability and flexibility requirements for HPC services.

  • High-Performance Lustre Parallel File System

    Optimized and dedicated ECSs and EVS disks provide up to 4.5 GB/s throughput for each OSS and up to 2 TB/s throughput in total. Each file supports up to 32 PB capacity. Lustre file systems fully meet HPC requirements.

  • Distributed, Scalable Block Storage Service

    EVS disks can be attached to each ECS based on demand to offer storage space for HPC computing and storage nodes. Each disk provides up to 32 TB capacity, 33,000 IOPS, and 350 MB/s throughput.

Biomedicine

Biomedicine relies heavily on HPC for molecular modeling, data management, medicine molecular design, and next-generation gene sequencing. Huawei HPC Cloud provides biopharmaceutical companies with industry-leading computing and storage services.

Benefits

  • Scalable HPC ECS

    Various ECSs and BMSs are provided to meet different HPC application requirements for computing and memory capacity. ECS types include C6 (general computing-plus), P2v (AI-accelerated), and M6 (memory-optimized). 

  • Distributed, Scalable Block Storage Service

    EVS disks can be attached to each ECS based on demand to offer storage space for HPC computing and storage nodes. Each disk provides up to 32 TB capacity, 33,000 IOPS, and 350 MB/s throughput.

  • Excellent VPC Network

    A secure, isolated virtual network environment is built on HUAWEI CLOUD for HPC users. HPC networks connect to each other using high-speed intelligent NICs or Direct Connect, providing high bandwidth for the users on your network.

  • Massive OBS

    A huge amount of storage space is provided for HPC applications. You can flexibly upload and download HPC data.

Energy Exploration

Energy exploration is a computing-intensive industry. Huawei HPC Cloud provides powerful computing services for data collection, seismic data processing, and oil reservoir modeling to deliver unprecedented levels of accuracy and productivity.

Benefits

  • Scalable HPC ECS

    D3 ECSs provide optimized data processing capabilities and attach enforced SAS disks as local storage (supporting up to 28 local disks). D3 ECSs provide HPC applications with high I/O speed and rapid data processing capabilities to meet requirements for data-intensive computing applications. P2v ECSs provide superb dual-precision computing power of up to 62.4 TeraFLOPS and use GPU NVLink for direct communication between GPUs, thereby improving data transmission efficiency. C6 ECSs use second-generation Intel® Xeon® Scalable processors with technologies optimized and Huawei-proprietary high-speed intelligent NICs to offer powerful and stable computing performance, including ultra-high network bandwidth and ultra-low latency.

  • Excellent-Performance BMS

    BMSs (dedicated physical servers) with 100 Gbit/s EDR Infiniband networks are provided, avoiding losses due to virtualization and offering high performance. You are allowed to automatically provision BMSs on the management console, fully meeting scalability and flexibility requirements for HPC services.

  • High-Performance Lustre Parallel File System

    Optimized and dedicated ECSs and EVS disks provide up to 4.5 GB/s throughput for each OSS and up to 2 TB/s throughput in total. Each file supports up to 32 PB capacity. Lustre file systems fully meet HPC requirements.

  • Distributed, Scalable Block Storage Service

    EVS disks can be attached to each ECS based on demand to offer storage space for HPC computing and storage nodes. Each disk provides up to 32 TB capacity, 33,000 IOPS, and 350 MB/s throughput.

Graphics Rendering and Heterogeneous Computing

HPC nodes use heterogeneous computing to accelerate computing for various HPC applications including AI, deep learning, neural networking, and 3D rendering. Huawei HPC Cloud greatly improves application program execution efficiency.

Benefits

  • Excellent-Performance BMS

    Excellent computing performance is provided using dedicated physical servers. Each BMS uses up to eight GPU accelerators to support parallel acceleration and attaches local SSDs to provide storage acceleration. You are allowed to automatically provision BMSs on the management console to meet the flexibility and scalability requirements for services like AI and deep learning.

  • Scalable HPC ECS

    General computing-plus C6 and memory-optimized M6 ECSs are provided to comply with scalable computing requirements for rendering.

Solution Architecture

Description

Huawei HPC Cloud provides high-performance, reliable, secure, and easy-to-use simulation services, fully satisfying parts manufacturing requirements, shortening service rollouts, and boosting enterprise revenue.

Highlights

  • Excellent performance

    100 Gbit/s computing network, 1.6 TB local SSDs

  • Rich instances

    Deployment of both ECSs and BMSs

  • Open architecture

    OpenStack-based

  • All-around protection

    7-layer security protection

Solution Advantages

  • Excellent Performance

    Industry-leading performance is achieved using 100 Gbit/s computing networks and 1.6 TB enterprise-level SSDs (local high-speed cache disks for cloud services).

    Industry-leading performance is achieved using 100 Gbit/s computing networks and 1.6 TB enterprise-level SSDs (local high-speed cache disks for cloud services).

  • Comprehensive Security Protection

    End-to-end security solutions protect user data from leakage and ensure a reliable HPC platform.

    End-to-end security solutions protect user data from leakage and ensure a reliable HPC platform.

  • Strong Scalability

    Full OpenStack architecture provides openness and heterogeneous capabilities while avoiding vendor lock-in.

    Full OpenStack architecture provides openness and heterogeneous capabilities while avoiding vendor lock-in.

  • Extensive Ecosystem

    Integration with advanced HPC applications ensures HPC Cloud service reliability.

    Integration with advanced HPC applications ensures HPC Cloud service reliability.

Recommended Configurations

Recommended Configurations

Terms & Conditions

活动对象:华为云电销客户及渠道伙伴客户可参与消费满送活动,其他客户参与前请咨询客户经理

活动时间: 2020年8月12日-2020年9月11日

活动期间,华为云用户通过活动页面购买云服务,或使用上云礼包优惠券在华为云官网新购云服务,累计新购实付付费金额达到一定额度,可兑换相应的实物礼品。活动优惠券可在本活动页面中“上云礼包”等方式获取,在华为云官网直接购买(未使用年中云钜惠活动优惠券)或参与其他活动的订单付费金额不计入统计范围内;

活动对象:华为云电销客户及渠道伙伴客户可参与消费满送活动,其他客户参与前请咨询客户经理

Industrial Design
Pre- and post-simulation scenarios
Cloud Service
Specifications
Quantity
ECS
P2vs | NVIDIA V100-SXM2-32G
2
EVS
High I/O data disk | 100 GB
--
VPC
--
--
AS
--
--
IMS
--
--
Cloud Eye
--
--
Pre- and post-simulation scenarios
ECS
P2vs | NVIDIA V100-SXM2-32G
2
EVS
High I/O data disk | 100 GB
VPC
AS
IMS
Cloud Eye

Industrial Simulation
Calculation scenarios
Cloud Service
Specifications
Quantity
BMS
H2 | 36 cores, 192 GB | 1.6 TB SSD | 100 Gbit/s high-speed network
10
SFS
Capacity | 4 TB
--
VPC
--
--
AS
--
--
IMS
--
--
Cloud Eye
--
--
Industrial Simulation
Calculation scenarios
BMS
H2 | 36 cores, 192 GB | 1.6 TB SSD | 100 Gbit/s high-speed network
10
SFS
Capacity | 4 TB
VPC
AS
IMS
Cloud Eye

Biomedicine
Gene conversion
Cloud Service
Specifications
Quantity
ECS
C6 | 32 vCPUs, 128 GB
10
SFS
Capacity | 4 TB
--
VPC
--
--
AS
--
--
IMS
--
--
Cloud Eye
--
--
Gene conversion
ECS
C6 | 32 vCPUs, 128 GB
10
SFS
Capacity | 4 TB
VPC
AS
IMS
Cloud Eye

Energy Exploration
Cloud Service
Specifications
Quantity
BMS
H2 | 36 cores, 192 GB | 1.6 TB SSD | 100 Gbit/s high-speed network
10
SFS
Capacity | 4 TB
--
VPC
--
--
AS
--
--
IMS
--
--
Cloud Eye
--
--
BMS
H2 | 36 cores, 192 GB | 1.6 TB SSD | 100 Gbit/s high-speed network
10
SFS
Capacity | 4 TB
VPC
AS
IMS
Cloud Eye

Heterogeneous Computing
Cloud Service
Specifications
Quantity
GACS
P2vs | NVIDIA V100-SXM2-32G
2
SFS
Capacity | 4 TB
--
VPC
--
--
AS
--
--
IMS
--
--
Cloud Eye
--
--
Heterogeneous Computing
GACS
P2vs | NVIDIA V100-SXM2-32G
2
SFS
Capacity | 4 TB
VPC
AS
IMS
Cloud Eye