E8pds_v5 by Microsoft Azure

E8pds_v5 is a EPDSv5 family [ARM processor] [Local Disk] [Premium Storage capable] 8 vCPUs server offered by Microsoft Azure with 8 vCPUs, 64 GiB of memory and 307 GB of storage. The pricing starts at 0.0606 USD per hour.
8 vCPU
64 GiB Memory
307 GB Storage
Spare SCore
14,512
(All-cores)
1,823
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_E8pds_v5
Name
E8pds_v5
API Reference
Standard_E8pds_v5
Description
EPDSv5 family [ARM processor] [Local Disk] [Premium Storage capable] 8 vCPUs
Family
EPDSv5
Hw Virt
Average Time To Start
18
Status
active
Observed At
2026-10-27T21:24:32.154441

Availability

REGION / IDSPOTONDEMAND
Central India (IN) / centralindia
0.0606 USD/h 0.328 USD/h
Jio India Central (IN) / jioindiacentral
- 0.328 USD/h
Jio India West (IN) / jioindiawest
- 0.328 USD/h
East US 2 (US) / eastus2
0.0852 USD/h 0.461 USD/h
North Central US (US) / northcentralus
0.0852 USD/h 0.461 USD/h
West US 2 (US) / westus2
0.0852 USD/h 0.461 USD/h
West US 3 (US) / westus3
0.0852 USD/h 0.461 USD/h
East US (US) / eastus
0.0975 USD/h 0.461 USD/h
Sweden Central (SE) / swedencentral
0.0898 USD/h 0.486 USD/h
Canada Central (CA) / canadacentral
0.0935 USD/h 0.506 USD/h
North Europe (IE) / northeurope
0.0946 USD/h 0.512 USD/h
West US (US) / westus
0.0961 USD/h 0.52 USD/h
Central US (US) / centralus
0.0962 USD/h 0.521 USD/h
France Central (FR) / francecentral
0.0998 USD/h 0.54 USD/h
UK South (GB) / uksouth
0.0866 USD/h 0.542 USD/h
Germany West Central (DE) / germanywestcentral
0.102 USD/h 0.552 USD/h
West Europe (NL) / westeurope
0.102 USD/h 0.552 USD/h
South Central US (US) / southcentralus
0.1022 USD/h 0.553 USD/h
West Central US (US) / westcentralus
0.1022 USD/h 0.553 USD/h
Australia East (AU) / australiaeast
0.1027 USD/h 0.556 USD/h
Japan East (JP) / japaneast
0.1027 USD/h 0.556 USD/h
Southeast Asia (SG) / southeastasia
0.1027 USD/h 0.556 USD/h
East Asia (HK) / eastasia
0.1039 USD/h 0.562 USD/h
Switzerland North (CH) / switzerlandnorth
0.1129 USD/h 0.611 USD/h

Processor

vCPUs
8
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
8
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
512 KiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
512 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
8 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
8
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
64 GiB
Memory Amount Actual
64 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    307 GB
    Storage Type
    ssd
    Storages
    • 307 GB ssd (temp disk)
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    An ARM-powered virtual machine featuring a high memory-to-core ratio and local SSD storage for memory-intensive workloads.

    Memory OptimizedStorage & DatabaseGeneral Purpose

    Microsoft Azure E8pds_v5 is an ARM-based virtual machine from the EPDSv5 family, featuring 8 dedicated vCPUs on an 8-core Ampere ARMv8 Neoverse-N1 processor running at 3.0 GHz. It is equipped with 64.0 GB of RAM, providing a high 8.0 GB per core ratio, and includes a 307 GB local SSD with Premium Storage capability. Under benchmark testing, the server demonstrates average multi-core CPU and memory bandwidth performance, alongside average database and Redis operation speeds. However, single-core processing and LLM inference benchmarks fall into the lower performance tier. This hardware profile makes the instance qualitatively cost-effective for memory-optimized workloads, database hosting, caching, and web serving, while presenting tradeoffs in single-threaded compute efficiency.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.61Score
    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) 1,057,225 ops/sec 1,918,343 ops/sec 0.58 50.00% 50.00% -24.00%
    Redis RPS (pipeline=16, SET) 6,653,938 ops/sec 11,704,734 ops/sec 0.56 20.00% 20.00% -11.00%
    PassMark Memory Mark (composite) 1,867 2,416 0.79 10.00% 10.00% -2.30%
    Memory bandwidth (read, 16 MB ~ L3) 96,853 MB/sec 108,420 MB/sec 0.88 10.00% 10.00% -1.30%
    PassMark single-thread CPU 1,331 Mops/s 2,365 Mops/s 0.54 10.00% 10.00% -6.00%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,081

    Geekbench Multi-Core

    Score: 5,993

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 6,227
    Compression
    		 44,784
    Encryption
    		 1,305
    Extended Instructions
    		 5,964
    Floating Point Maths
    		 28,698
    Integer Maths
    		 37,684
    Physics
    		 1,166
    Prime Numbers
    		 67
    Single Threaded
    		 1,331
    String Sorting
    		 27,338

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 1,867
    Database Operations
    		 5,719
    Memory Latency
    		 72
    Memory Read Cached
    		 11,369
    Memory Read Uncached
    		 8,766
    Memory Write
    		 14,818

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 88.91 43.81 0.49×
    bitops
    		 108,480 866,319 7.99×
    branch
    		 220,869 1,762,704 7.98×
    funccall
    		 1,339 10,675 7.97×
    funcret
    		 20,805 165,943 7.98×
    hash
    		 128,138 1,021,230 7.97×
    intmath
    		 31,732 250,554 7.90×
    nop
    		 173,608 1,384,682 7.98×
    prime
    		 336,804 2,685,205 7.97×
    rotate
    		 96,531 769,684 7.97×
    str
    		 514,933 4,106,330 7.97×
    wcs
    		 119,298 949,534 7.96×
    CryptographySingleMultiScaling
    crypt
    		 2,896 23,214 8.02×
    CompressionSingleMultiScaling
    jpeg
    		 521 4,166 8.00×
    zlib
    		 34.3 275.62 8.04×
    HypervisorSingleMultiScaling
    clock
    		 23,959 144,193 6.02×
    clone
    		 209.59 1,143 5.45×
    context
    		 2,594 20,795 8.02×
    cpu-sched
    		 65.26 503.38 7.71×
    eventfd
    		 54,800 740,799 13.52×
    fault
    		 13,152 83,885 6.38×
    fork
    		 4,021 24,680 6.14×
    getrandom
    		 48,972 390,268 7.97×
    hrtimers
    		 360,400 998,687 2.77×
    mprotect
    		 828,615 2,663,241 3.21×
    mtx
    		 6,564,960 386,761,757 58.91×
    munmap
    		 2,832 18,645 6.58×
    null
    		 460,309 3,674,160 7.98×
    pipe
    		 932,925 4,712,629 5.05×
    priv-instr
    		 751,088 5,343,326 7.11×
    resched
    		 3,103,565 1,237,777 0.40×
    switch
    		 80,145 2,605,880 32.51×
    timermix
    		 393,734 3,168,091 8.05×
    tlb-shootdown
    		 5,410 7,585 1.40×
    vdso
    		 46,823,294 373,308,198 7.97×
    vfork
    		 28,252 121,138 4.29×
    yield
    		 6,373,972 6,516,886 1.02×
    zero
    		 2,065,806 16,476,682 7.98×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 1,336 10,648 7.97×
    expmath
    		 240.14 1,915 7.97×
    fma
    		 641,172 5,108,476 7.97×
    fp
    		 103.16 825.45 8.00×
    fractal
    		 6.6 51.6 7.82×
    hyperbolic
    		 244.33 1,949 7.98×
    logmath
    		 293.61 2,341 7.97×
    matrix
    		 5,347 42,602 7.97×
    matrix-3d
    		 529.36 3,385 6.40×
    monte-carlo
    		 193.07 1,544 8.00×
    mpfr
    		 641.91 5,117 7.97×
    powmath
    		 176.53 1,408 7.98×
    trig
    		 329.61 2,629 7.98×
    veccmp
    		 17,144 136,922 7.99×
    vecfp
    		 744.17 5,948 7.99×
    vecmath
    		 3,090 24,645 7.97×
    vecshuf
    		 671.91 5,361 7.98×
    vecwide
    		 18,398 146,676 7.97×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 5.4 43.2 8.00×
    bsearch
    		 258.37 2,054 7.95×
    bubblesort
    		 0.8 6.4 8.00×
    fibsearch
    		 273.59 2,181 7.97×
    heapsort
    		 8.2 65.6 8.00×
    hsearch
    		 4,919 39,122 7.95×
    insertionsort
    		 4.6 36.8 8.00×
    malloc
    		 2,870,092 17,549,691 6.11×
    mcontend
    		 216.33 15,724 72.68×
    mergesort
    		 28 222.99 7.96×
    qsort
    		 19.4 155.39 8.01×
    skiplist
    		 5,355 42,733 7.98×
    tree
    		 1.2 8 6.67×
    MemorySingleMultiScaling
    cache
    		 383,424 639,639 1.67×
    cachehammer
    		 167,076 555,607 3.33×
    cacheline
    		 48.77 355.4 7.29×
    l1cache
    		 182.3 1,454 7.98×
    memcpy
    		 443.76 3,537 7.97×
    memrate
    		 3.15 18.07 5.74×
    memthrash
    		 164.6 192.08 1.17×
    ptr-chase
    		 21,037,108 87,057,901 4.14×
    spinmem
    		 867.96 1,306 1.50×
    stream
    		 66.93 2,969 44.35×
    vm
    		 63,088 542,404 8.60×

    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
    E2pds_v5 216 GiB0
    E4pds_v5 432 GiB0
    E16pds_v5 16128 GiB0
    E20pds_v5 20160 GiB0
    E32pds_v5 32208 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    E8pds_v5 FAQs