Data Centers and Hardware#

The resources offered by CONVERGE Horizon are managed by different cloud providers at various data centers around the world. These resources include cloud storage, compute nodes for running jobs, and visualization nodes for workstations.

Node Types#

Nodes provisioned by CONVERGE Horizon are based on node types, which describe the hardware configurations users can choose from when creating a file system, job, or workstation.

Node types labeled as bare metal (BM) are allocated to one user at a time, meaning there is no shared use of processing cores, memory, or other hardware resources. Some BM nodes may run a hypervisor on top of the physical hardware, making them virtual machines in the strict sense. They are still classified as bare metal on CONVERGE Horizon if the hardware resources are dedicated to a single user.

Virtual machine (VM) nodes are allocated with the number of cores and the amount of memory requested by the user, allowing the remaining cores and memory to be allocated to other users. The cores allocated to a VM on CONVERGE Horizon are physical cores, not execution threads. For example, if you request a 30-core VM based on the VM-AMD-TURIN node type, you will have 30 physical cores dedicated to your simulation, and these cores will not be split for the duration of your simulation. The processor’s remaining 226 cores and other hardware resources are shared with other users. Performance of VMs can vary due to the use of shared resources, although the dedication of physical cores does help stabilize performance.

Hardware specifications for CONVERGE Horizon node types are listed below. For file systems, the Standard and Performance node types are supported at all data centers. For jobs and workstations, the list of supported node types is different for each data center; refer to Oracle Cloud Data Centers and Google Cloud Data Centers for details.

Node Types for File Systems#

Node Type

Processor

Number of Cores

Memory (GB)

Storage (TB)
Standard
(VM-AMD-FILESYSTEM-2)
Oracle Cloud: AMD Turin or Genoa
Google Cloud: AMD Milan

2

16

Configurable
Performance*
(VM-AMD-FILESYSTEM-4)
Oracle Cloud: AMD Turin or Genoa
Google Cloud: AMD Milan

4

32

Configurable

*Optimized for heavy concurrent use of the file system by multiple users and/or multiple jobs.

Node Types for Jobs#

Node Type

Processor

Cores per Node

Memory (GB)

Network

Maximum Number of Nodes per Job

BM-AMD-GENOA-192

AMD EPYC 9J14

192

2304

Ethernet

1

BM-AMD-TURIN-192

AMD EPYC 9B45

192

720

Falcon

20

BM-AMD-TURIN-192-AX*

AMD EPYC 9J45

192

1536

Ethernet

1

BM-AMD-TURIN-192-HM*

AMD EPYC 9B45

192

1488

Falcon

20

BM-AMD-TURIN-256

AMD EPYC 9J45

256

3072

Ethernet

1

BM-INTEL-ICELAKE-36

Intel Xeon 6354

36

512

RDMA

25

BM-INTEL-SAPPHIRE-88

Intel Xeon 8481C

88

352

Ethernet

1

VM-AMD†

AMD EPYC 9J45 or AMD EPYC 9J14

1-94

16-512‡

Ethernet

1

VM-AMD-TURIN

AMD EPYC 9J45

1-126

16-512‡

Ethernet

1

VM-AMD-TURIN-AX*

AMD EPYC 9J45

1-94

16-512‡

Ethernet

1

*AX indicates faster memory. HM indicates high memory.

†High-availability VM based on either AMD Turin or AMD Genoa. AMD Turin will be requested first. If no AMD Turin nodes are available, AMD Genoa will be requested.

‡VM nodes require at least 1 GB of memory per core and cannot exceed 64 GB per core.

Node Types for Workstations#

Node Type

Processor

Cores

Memory (GB)

GPU

VM-INTEL-GPU-15

Intel Xeon Platinum 8358

15

240

NVIDIA A10 24 GB RAM

VM-INTEL-GPU-30

Intel Xeon Platinum 8358

30

480

NVIDIA A10 24 GB RAM

Hardware Recommendations#

The optimal number of cores for a CONVERGE simulation depends on the number of computational cells, the type of calculation being performed, and the hardware configuration of the cluster running the simulation. For the hardware configurations available on CONVERGE Horizon, a reasonable starting point for no-chemistry simulations is 5,000 cells per core for single-node jobs or 10,000 cells per core for multi-node jobs. These are baseline numbers intended to optimize scaling for the CONVERGE solver. The number of cells per core can be much higher if you choose to optimize cost instead of scaling.

When you have identified the target number of cores for your job, select a node type with the following recommendations in mind:

  • Use a single VM node for cases that require 126 or fewer cores. The VM nodes are very cost-effective because they offer the option to customize the number of cores and memory.

  • Use a single BM-AMD node for small and medium-sized cases with high memory requirements. Node types based on Turin processors offer the best performance for most cases.

  • Use multiple BM-INTEL-ICELAKE-36 or BM-AMD-TURIN-192 nodes for large cases that require more than 256 cores. BM-AMD-TURIN-192 is recommended only for CONVERGE 6.

Pricing information for each node type is available at convergecfd.com.

Oracle Cloud Data Centers#

The Standard and Performance node types are supported for file systems at all Oracle Cloud data centers. The node types offered for jobs and workstations at each data center are listed below.

The availability of a given node type at a given data center fluctuates throughout the day. Check the Node Availability page for real-time availability details.

Oracle Cloud Data Centers and Supported Node Types#

Data Center

Supported Node Types for Jobs

Supported Node Types for Workstations

Australia East (Sydney)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-INTEL-GPU-15
VM-INTEL-GPU-30

Canada Southeast (Toronto)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN

Germany Central (Frankfurt)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-INTEL-GPU-15
VM-INTEL-GPU-30

India West (Mumbai)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-INTEL-GPU-15
VM-INTEL-GPU-30

India South (Hyderabad)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
VM-AMD
VM-AMD-TURIN

Italy North (Turin)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
VM-AMD
VM-AMD-TURIN

Italy Northwest (Milan)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-INTEL-GPU-15
VM-INTEL-GPU-30

Japan Central (Osaka)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-INTEL-GPU-15
VM-INTEL-GPU-30

Japan East (Tokyo)
BM-AMD-GENOA-192
BM-AMD-TURIN-192-AX
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-AMD-TURIN-AX
VM-INTEL-GPU-15
VM-INTEL-GPU-30

Netherlands Northwest (Amsterdam)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN

South Korea Central (Seoul)
BM-AMD-GENOA-192
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-INTEL-GPU-15
VM-INTEL-GPU-30

UK South (London)
BM-AMD-GENOA-192
BM-AMD-TURIN-192-AX
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-AMD-TURIN-AX
VM-INTEL-GPU-15
VM-INTEL-GPU-30

US East (Ashburn)
BM-AMD-GENOA-192
BM-AMD-TURIN-192-AX
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-AMD-TURIN-AX
VM-INTEL-GPU-15
VM-INTEL-GPU-30

US West (Phoenix)
BM-AMD-GENOA-192
BM-AMD-TURIN-192-AX
BM-AMD-TURIN-256
BM-INTEL-ICELAKE-36
VM-AMD
VM-AMD-TURIN
VM-AMD-TURIN-AX
VM-INTEL-GPU-15
VM-INTEL-GPU-30

Google Cloud Data Centers#

The Standard and Performance node types are supported for file systems at all Google Cloud data centers. The supported node types for jobs are listed below.

The availability of a given node type at a given data center fluctuates throughout the day. Check the Node Availability page for real-time availability details.

Google Cloud Data Centers and Supported Node Types#

Data Center

Supported Node Types for Jobs

Netherlands (Eemshaven)

BM-AMD-TURIN-192, BM-AMD-TURIN-192-HM, BM-INTEL-SAPPHIRE-88

US Central (Council Bluffs)

BM-AMD-TURIN-192, BM-AMD-TURIN-192-HM, BM-INTEL-SAPPHIRE-88

US Southeast (Moncks Corner)

BM-AMD-TURIN-192, BM-AMD-TURIN-192-HM