Instance Types

Learn about the full range of AWS and Azure instance types available on the DNAnexus Platform.

About Instance Types

Availability

This page provides a complete list of the AWS and Azure instance types that are available for use on the DNAnexus Platform.

Not all instance types are accessible to all customers. If you want to use an instance type listed here, but cannot access it when running an analysis, contact DNAnexus Support.

A list of instance types to which you have access is available via the command-line interface (CLI), by entering the command dx run --instance-type-help. When using the user interface (UI) to configure a tool to run an analysis, you can see this list in the Stage Settings pane of the Run Analysis screen.

GPU Instance Types

AWS and Azure GPU instance types are available for use on the Platform. See the full list below and learn how to specify NVIDIA driver version.

FPGA Instance Types

AWS FPGA instance types are available for use on the Platform. See the full list below and learn how to specify FPGA driver version.

OS Support

Ubuntu Linux 20.04 is supported on all instance types in all regions.

Resource Usage

When using any instance, note that some of the resources on that instance will be used by the Platform, to run processes that support your job and provide API services. Around 5% of the available storage, for example, will be used by the Platform; your job's virtual file system will be able to use the remainder as local scratch space. Some amount of available memory will also be used by the Platform.

New Versions of Existing Instance Types

DNAnexus regularly adds new versions of existing instance types, as AWS and Azure make them available. These new versions feature better hardware, such as a more powerful CPU, more memory, more local storage, or some combination of these elements.

On the Platform, each new instance type version has a version infix, such as _v2, in its name, to distinguish it from the original version of that instance type. See the Instance Names section for more information on version infixes.

While the latest version will deliver better performance, DNAnexus, as a rule, makes both the original and updated version of instance types available. So, for example, you can access both mem1_ssd1_x8 and mem1_ssd1_v2_x8. See the full list of available instance types for more information.

Instance Type Names

With the exception of GPU and FPGA instance types, instance type names are constructed according to the following scheme:

Cloud provider prefix		Memory infix		Storage infix		Version infix		Core suffix
∅ (AWS) azure: (Azure)	+	mem1_ (<=2GB/core) mem2_ (~4GB/core) mem3_ (>=7GB/core) mem4_ (~14GB/core) mem5_ (~28GB/core)	+	ssd1_ (<=20GB/core) ssd2_ (~32GB-128GB/core) ssd3_ (>600GB/core) hdd2_ (>100GB/core)	+	∅ (version1) v2_ (version2)	+	x1 x2 x4 x8 x16 x20 x32 x36 x40 x48 x64 x96 x128

Cloud provider prefix: Denotes the cloud provider.

Memory infix: Denotes the memory capacity (per core).

Storage infix: Denotes the local storage technology and capacity (per core). ssd represents a solid-state drive, whereas hdd represents a regular hard disk drive.

Version infix (optional): Denotes the version of the instance type.

Core suffix: Denotes the number of cores.

For example, mem1_ssd1_v2_x8 is the second version of an instance type available on AWS, featuring 8 cores, 16GB of memory (2GB/core), and 160GB of solid-state drive storage (20GB/core). Similarly, azure:mem1_ssd1_x8 is an instance type available on Azure, featuring 8 cores, 15.7GB of memory (~1.9GB/core), and 128GB of solid-state drive storage (16GB/core).

Not all name combinations are available as instance types. See the Available Instance Types section for full detail on available instance types.

GPU and FPGA Instance Type Names

GPU and FPGA instance type names following the schema described above, but with the inclusion of an additional infix. This infix is included before the version suffix, and provides information on the instance type (GPU or FPGA). Many such infixes also include a number, indicating the number of GPUs or FPGA included in the instance.

For example, the AWS FPGA instance typemem3_ssd2_fpga1_x8 includes 1 FPGA. The AWS GPU instance type mem2_ssd1_gpu4_x48, meanwhile, includes 4 GPUs.

For more information, see the detailed lists of GPU instances types and FPGA instances types.

Available Instance Types

Standard AWS Instance Types

Instance Type	Cores	Memory (GB)	Storage (GB)
mem1_hdd1_x2	2	3.75	200
mem1_hdd1_x4	4	7.5	400
mem1_hdd1_x8	8	15	800
mem1_hdd1_x16	16	30	1600
mem1_hdd1_x36	36	60	3200
mem1_hdd1_v2_x2	2	4	200
mem1_hdd1_v2_x4	4	8	400
mem1_hdd1_v2_x8	8	16	800
mem1_hdd1_v2_x16	16	32	1600
mem1_hdd1_v2_x36	36	72	3600
mem1_hdd1_v2_x72	72	144	7200
mem1_hdd1_v2_x96	96	192	9600
mem1_ssd1_x2	2	3.8	40
mem1_ssd1_x4	4	7.5	80
mem1_ssd1_x8	8	15	160
mem1_ssd1_x16	16	30	320
mem1_ssd1_x32	32	60	640
mem1_ssd1_x36	36	72	900
mem1_ssd1_v2_x2	2	4	50
mem1_ssd1_v2_x4	4	8	100
mem1_ssd1_v2_x8	8	16	200
mem1_ssd1_v2_x16	16	32	400
mem1_ssd1_v2_x36	36	72	900
mem1_ssd1_v2_x72	72	144	1,800
mem1_ssd2_x2	2	3.8	160
mem1_ssd2_x4	4	7.5	320
mem1_ssd2_x8	8	15	640
mem1_ssd2_x16	16	30	1,280
mem1_ssd2_x36	36	60	2,880
mem1_ssd2_v2_x2	2	4	160
mem1_ssd2_v2_x4	4	8	320
mem1_ssd2_v2_x8	8	16	640
mem1_ssd2_v2_x16	16	32	1,280
mem1_ssd2_v2_x36	36	72	2,880
mem1_ssd2_v2_x72	72	144	5,760
mem1_hdd2_x1	1	1.7	160
mem1_hdd2_x8	8	7	1,680
mem1_hdd2_x32	32	60.5	3,360
mem2_ssd1_x2	2	7.5	40
mem2_ssd1_x4	4	15	80
mem2_ssd1_x8	8	30	160
mem2_ssd1_v2_x2	2	8	75
mem2_ssd1_v2_x4	4	16	150
mem2_ssd1_v2_x8	8	32	300
mem2_ssd1_v2_x16	16	64	600
mem2_ssd1_v2_x32	32	128	1,200
mem2_ssd1_v2_x48	48	192	1,800
mem2_ssd1_v2_x64	64	256	2,400
mem2_ssd1_v2_x96	96	384	3,600
mem2_ssd2_x2	2	8	160
mem2_ssd2_x4	4	16	320
mem2_ssd2_x8	8	32	1280
mem2_ssd2_x16	16	64	2560
mem2_ssd2_x40	40	160	3200
mem2_ssd2_x64	64	256	5120
mem2_ssd2_v2_x2	2	8	160
mem2_ssd2_v2_x4	4	16	320
mem2_ssd2_v2_x8	8	32	640
mem2_ssd2_v2_x16	16	64	1280
mem2_ssd2_v2_x32	32	128	2560
mem2_ssd2_v2_x48	48	192	3840
mem2_ssd2_v2_x64	64	256	5120
mem2_ssd2_v2_x96	96	384	7480
mem2_hdd2_x1	1	3.8	410
mem2_hdd2_x2	2	7.5	840
mem2_hdd2_x4	4	15	1,680
mem2_hdd2_v2_x2	2	8	1,000
mem2_hdd2_v2_x4	4	16	2,000
mem3_ssd1_x2	2	15	40
mem3_ssd1_x4	4	30.5	80
mem3_ssd1_x8	8	61	160
mem3_ssd1_x16	16	122	320
mem3_ssd1_x32	32	244	640
mem3_ssd1_v2_x2	2	16	75
mem3_ssd1_v2_x4	4	32	150
mem3_ssd1_v2_x8	8	64	300
mem3_ssd1_v2_x16	16	128	600
mem3_ssd1_v2_x32	32	256	1,200
mem3_ssd1_v2_x48	48	384	1,800
mem3_ssd1_v2_x64	64	512	3,200
mem3_ssd1_v2_x96	96	768	3,600
mem3_ssd2_x4	4	30.5	800
mem3_ssd2_x8	8	61	1,600
mem3_ssd2_x16	16	122	3,200
mem3_ssd2_x32	32	244	6,400
mem3_ssd2_v2_x2	2	15.25	475
mem3_ssd2_v2_x4	4	30.5	950
mem3_ssd2_v2_x8	8	61	1,900
mem3_ssd2_v2_x16	16	122	3,800
mem3_ssd2_v2_x32	32	244	7,600
mem3_ssd2_v2_x64	64	488	15,200
mem3_ssd3_x2	2	16	1,250
mem3_ssd3_x4	4	32	2,500
mem3_ssd3_x8	8	64	5,000
mem3_ssd3_x12	12	96	7,500
mem3_ssd3_x24	24	192	15,000
mem3_ssd3_x48	48	384	30,000
mem3_ssd3_x96	96	768	60,000
mem3_hdd2_x2	2	17.1	420
mem3_hdd2_x4	4	34.2	850
mem3_hdd2_x8	8	68.4	1,680
mem3_hdd2_v2_x2	2	16	500
mem3_hdd2_v2_x4	4	32	1,000
mem3_hdd2_v2_x8	8	64	2,000
mem4_ssd1_x128	128	1,952	3,840

Standard Azure Instance Types

Instance Type	Cores	Memory (GB)	Storage (GB)
azure:mem1_ssd1_x2	2	3.9	32
azure:mem1_ssd1_x4	4	7.8	64
azure:mem1_ssd1_x8	8	15.7	128
azure:mem1_ssd1_x16	16	31.4	254
azure:mem2_ssd1_x1	1	3.5	128
azure:mem2_ssd1_x2	2	7	128
azure:mem2_ssd1_x4	4	14	128
azure:mem2_ssd1_x8	8	28	256
azure:mem2_ssd1_x16	16	56	512
azure:mem3_ssd1_x2	2	14	128
azure:mem3_ssd1_x4	4	28	128
azure:mem3_ssd1_x8	8	56	256
azure:mem3_ssd1_x16	16	112	512
azure:mem3_ssd1_x20	20	140	640
azure:mem4_ssd1_x2	2	28	128
azure:mem4_ssd1_x4	4	56	128
azure:mem4_ssd1_x8	8	112	256
azure:mem4_ssd1_x16	16	224	512
azure:mem4_ssd1_x32	32	448	1024
azure:mem5_ssd2_x64*	64	1,792	8,192
azure:mem5_ssd2_x128*	128	3,892	16,384

* - These high memory instance types are expensive, use them with caution.

GPU Instance Types

The following table shows all the GPU instance types available on AWS and Azure.

Instance Type	GPU	Cores	Memory (GB)	Storage (GB)
mem1_ssd1_gpu2_x8	1	8	15	60
mem1_ssd1_gpu2_x32	4	32	60	240
mem2_ssd1_gpu_x16	1	16	64	225
mem2_ssd1_gpu_x32	1	32	128	900
mem2_ssd1_gpu_x48	4	48	192	900
mem2_ssd1_gpu_x64	1	64	256	900
mem2_ssd1_gpu1_x32	1	32	128	900
mem2_ssd1_gpu1_x64	1	64	256	900
mem2_ssd1_gpu4_x48	4	48	192	900
mem3_ssd1_gpu_x8	1	8	61	160
mem3_ssd1_gpu_x32 *	4	32	244	640
mem3_ssd1_gpu_x64 *	8	64	488	1,280
azure:mem3_ssd2_gpu4_x64 *	4	64	488	2,048

* - These GPU instance types are costly to use. Use them with caution.

FPGA Instance Types

The following table shows all the FPGA instance types available on AWS.

Instance Type	FPGA	Cores	Memory (GB)	Storage (GB)
mem3_ssd2_fpga1_x8	1	8	122	470
mem3_ssd2_fpga1_x16	1	16	244	940
mem3_ssd2_fpga1_x64	1	64	976	3760