E2pds_v5 by Microsoft Azure

E2pds_v5 is a EPDSv5 family [ARM processor] [Local Disk] [Premium Storage capable] 2 vCPUs server offered by Microsoft Azure with 2 vCPUs, 16 GiB of memory and 81 GB of storage. The pricing starts at 0.0152 USD per hour.
2 vCPU
16 GiB Memory
81 GB Storage
Spare SCore
3,552
(All-cores)
1,791
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_E2pds_v5
Name
E2pds_v5
API Reference
Standard_E2pds_v5
Description
EPDSv5 family [ARM processor] [Local Disk] [Premium Storage capable] 2 vCPUs
Family
Memory Optimized
Series
Epdsv5
Hw Virt
Average Time To Start
20.5
Status
active
Observed At
2026-11-13T10:56:36.375062

Availability

Region / IDSpotOndemand
Central India (IN) / centralindia
0.0152 USD/h
0.082 USD/h
Jio India Central (IN) / jioindiacentral
-
0.082 USD/h
Jio India West (IN) / jioindiawest
-
0.082 USD/h
East US 2 (US) / eastus2
0.0213 USD/h
0.115 USD/h
North Central US (US) / northcentralus
0.0213 USD/h
0.115 USD/h
West US 2 (US) / westus2
0.0213 USD/h
0.115 USD/h
West US 3 (US) / westus3
0.0213 USD/h
0.115 USD/h
East US (US) / eastus
0.0243 USD/h
0.115 USD/h
Sweden Central (SE) / swedencentral
0.0225 USD/h
0.122 USD/h
Canada Central (CA) / canadacentral
0.0235 USD/h
0.127 USD/h
North Europe (IE) / northeurope
0.0237 USD/h
0.128 USD/h
Central US (US) / centralus
0.024 USD/h
0.13 USD/h
West US (US) / westus
0.024 USD/h
0.13 USD/h
UK South (GB) / uksouth
0.0237 USD/h
0.135 USD/h
France Central (FR) / francecentral
0.0249 USD/h
0.135 USD/h
Germany West Central (DE) / germanywestcentral
0.0255 USD/h
0.138 USD/h
South Central US (US) / southcentralus
0.0255 USD/h
0.138 USD/h
West Central US (US) / westcentralus
0.0255 USD/h
0.138 USD/h
West Europe (NL) / westeurope
0.0255 USD/h
0.138 USD/h
Australia East (AU) / australiaeast
0.0257 USD/h
0.139 USD/h
Japan East (JP) / japaneast
0.0257 USD/h
0.139 USD/h
Southeast Asia (SG) / southeastasia
0.0257 USD/h
0.139 USD/h
East Asia (HK) / eastasia
0.0261 USD/h
0.141 USD/h
Switzerland North (CH) / switzerlandnorth
0.0283 USD/h
0.153 USD/h

Processor

vCPUs
2
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
2
CPU Speed
3 GHz
CPU Architecture
arm64
CPU Manufacturer
Ampere
CPU Family
ARMv8
CPU Model
Neoverse-N1
CPU L1D Cache
64 KiB
CPU L1D Cache Total
128 KiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
128 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
2 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
32 MiB
CPU Flags
fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, lrcpc, dcpop, asimddp
Ecpus
2
Scalability
100

System Resources and Accelerators

Memory
Memory Amount
16 GiB
Memory Amount Actual
16 GiB
Accelerators
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    Storage
    Storage Size
    81 GB
    Storage Type
    ssd
    Storages
    • 81 GB ssd (temp disk)
    Compatible Storage IDs
    PremiumV2_LRS, Premium_LRS, Premium_ZRS, StandardSSD_LRS, StandardSSD_ZRS, Standard_LRS, UltraSSD_LRS
    Network
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    An ARM64 virtual machine offering high memory density and local SSD storage for efficient, memory-bound scale-out workloads.

    Microsoft Azure E2pds_v5 is an ARM64-based virtual machine from the EPDSv5 family, powered by a 2-core Ampere Neoverse-N1 processor running at 3.0 GHz. It features 16.0 GB of RAM, yielding an 8.0 GB per vCPU ratio, alongside a 77 GB local SSD. Benchmarks show average single-core performance, with a stress-ng single-core score of 1791.39, but weaker multi-core and memory bandwidth results, such as a Geekbench multi-core score of 1978.0. Lacking advanced vector extensions like AVX and AMX, this instance is not designed for heavy compute or machine learning. Qualitatively, it provides a cost-effective, memory-dense profile for ARM-native applications. It is best suited for memory-optimized workloads, lightweight databases, caching layers like Redis, and general-purpose web serving.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.19Score
    Precomputed compound score for Cache Intensive workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x_i / m_i)^(w_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 50% Redis RPS (pipeline=1, SET), 20% Redis RPS (pipeline=16, SET), 10% PassMark Memory Mark (composite), 10% Memory bandwidth (read, 16 MB ~ L3), 10% PassMark single-thread CPU. Rationale for component selection: In-memory key-value store workload, mixing direct Redis performance metrics with memory speed and latency benchmarks, and single-core CPU performance profiles.
    Component Score Weight Impact
    Raw Reference Normalized Target Actual
    Redis RPS (pipeline=1, SET) 253,191 ops/sec 1,930,206 ops/sec 0.13 50.00% 50.00% -64.00%
    Redis RPS (pipeline=16, SET) 1,612,985 ops/sec 11,811,515 ops/sec 0.13 20.00% 20.00% -34.00%
    PassMark Memory Mark (composite) 1,517 2,408 0.62 10.00% 10.00% -4.70%
    Memory bandwidth (read, 16 MB ~ L3) 34,330 MB/sec 108,674 MB/sec 0.31 10.00% 10.00% -11.00%
    PassMark single-thread CPU 1,329 Mops/s 2,365 Mops/s 0.54 10.00% 10.00% -6.00%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,107

    Geekbench Multi-Core

    Score: 1,978

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 1,591
    Compression
    		 10,533
    Encryption
    		 323
    Extended Instructions
    		 1,480
    Floating Point Maths
    		 7,147
    Integer Maths
    		 9,385
    Physics
    		 284
    Prime Numbers
    		 14
    Single Threaded
    		 1,329
    String Sorting
    		 6,688

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 1,517
    Database Operations
    		 1,363
    Memory Latency
    		 73
    Memory Read Cached
    		 11,342
    Memory Read Uncached
    		 8,787
    Memory Write
    		 14,807

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 231.36 223 0.96×
    bitops
    		 108,488 215,051 1.98×
    branch
    		 220,873 438,127 1.98×
    funccall
    		 1,339 2,643 1.97×
    funcret
    		 20,778 41,029 1.97×
    hash
    		 128,082 252,783 1.97×
    intmath
    		 30,479 60,982 2.00×
    nop
    		 173,620 342,966 1.98×
    prime
    		 336,817 665,034 1.97×
    rotate
    		 96,524 190,659 1.98×
    str
    		 512,249 1,015,431 1.98×
    wcs
    		 119,158 235,344 1.98×
    CryptographySingleMultiScaling
    crypt
    		 2,899 5,748 1.98×
    CompressionSingleMultiScaling
    jpeg
    		 525.52 1,028 1.96×
    zlib
    		 47.44 88.73 1.87×
    HypervisorSingleMultiScaling
    clock
    		 23,426 45,170 1.93×
    clone
    		 235.95 287.25 1.22×
    context
    		 2,609 5,143 1.97×
    cpu-sched
    		 63.27 127.48 2.01×
    eventfd
    		 60,192 181,221 3.01×
    fault
    		 13,904 25,165 1.81×
    fork
    		 4,975 9,109 1.83×
    getrandom
    		 48,979 96,688 1.97×
    hrtimers
    		 515,534 253,716 0.49×
    mprotect
    		 705,100 744,895 1.06×
    mtx
    		 8,551,388 98,190,068 11.48×
    munmap
    		 2,824 5,346 1.89×
    null
    		 460,394 907,838 1.97×
    pipe
    		 904,995 1,366,237 1.51×
    priv-instr
    		 749,532 1,408,617 1.88×
    resched
    		 373,507 241,827 0.65×
    switch
    		 105,786 511,624 4.84×
    timermix
    		 396,247 781,940 1.97×
    tlb-shootdown
    		 3,809 3,793 1.00×
    vdso
    		 46,805,479 92,460,754 1.98×
    vfork
    		 30,472 43,746 1.44×
    yield
    		 1,658,063 1,640,498 0.99×
    zero
    		 2,065,849 4,078,003 1.97×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 1,336 2,636 1.97×
    expmath
    		 240.14 473.77 1.97×
    fma
    		 641,157 1,265,232 1.97×
    fp
    		 103.2 205.28 1.99×
    fractal
    		 6.6 12.8 1.94×
    hyperbolic
    		 244.34 482.44 1.97×
    logmath
    		 293.68 580.42 1.98×
    matrix
    		 5,347 10,525 1.97×
    matrix-3d
    		 498.49 953.93 1.91×
    monte-carlo
    		 193.07 376.13 1.95×
    mpfr
    		 641.82 1,266 1.97×
    powmath
    		 176.55 348.15 1.97×
    trig
    		 329.56 650.6 1.97×
    veccmp
    		 17,194 33,843 1.97×
    vecfp
    		 745.26 1,472 1.97×
    vecmath
    		 3,090 6,101 1.97×
    vecshuf
    		 670.57 1,327 1.98×
    vecwide
    		 18,407 35,983 1.95×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 5.4 10.8 2.00×
    bsearch
    		 258.36 512.18 1.98×
    bubblesort
    		 0.8 1.6 2.00×
    fibsearch
    		 273.51 539.8 1.97×
    heapsort
    		 8.2 16.4 2.00×
    hsearch
    		 4,911 9,686 1.97×
    insertionsort
    		 4.6 8.8 1.91×
    malloc
    		 2,534,996 5,398,991 2.13×
    mcontend
    		 675.14 1,858 2.75×
    mergesort
    		 28 55.2 1.97×
    qsort
    		 19.4 38.4 1.98×
    skiplist
    		 5,360 10,577 1.97×
    tree
    		 1 2 2.00×
    MemorySingleMultiScaling
    cache
    		 334,799 354,076 1.06×
    cachehammer
    		 144,445 253,588 1.76×
    cacheline
    		 31.31 61.04 1.95×
    l1cache
    		 182.43 359.74 1.97×
    memcpy
    		 444.37 875.64 1.97×
    memrate
    		 3.35 5.91 1.76×
    memthrash
    		 69.38 66.13 0.95×
    ptr-chase
    		 11,297,365 21,633,992 1.91×
    spinmem
    		 670.57 4.4 0.01×
    stream
    		 68.5 261.97 3.82×
    vm
    		 60,952 209,309 3.43×

    Stress-ng Raw Scores

    Stress-ng Relative Multicore Performance

    LLM Inference Speed for Prompt Processing

    LLM Inference Speed for Text Generation

    Static Web Server

    Redis

    Alternatives

    Servers of the Same Family

    INSTANCEvCPUsMEMORYAccelerators
    E2_v4 216 GiB0
    E2_v5 216 GiB0
    E2a_v4 216 GiB0
    E2ads_v5 216 GiB0
    E2ads_v6 216 GiB0
    E2ads_v7 216 GiB0
    E2as_v4 216 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    E2pds_v5 FAQs