ecs.gn5i-c8g1.2xlarge by Alibaba Cloud

ecs.gn5i-c8g1.2xlarge is a ecs.gn5i family (8 vCPUs, 32 GiB RAM, 0 GB storage, 1xP4 8192 GiB VRAM) server offered by Alibaba Cloud with 8 vCPUs, 32 GiB of memory and 0 GB of storage. The pricing starts at 0.3612 USD per hour.
8 vCPU
32 GiB Memory
1 GPU
Spare SCore
4,755
(All-cores)
953
(Single-core)

Specifications

Server Metadata

Vendor ID
alicloud
Name
ecs.gn5i-c8g1.2xlarge
Description
ecs.gn5i family (8 vCPUs, 32 GiB RAM, 0 GB storage, 1xP4 8192 GiB VRAM)
Family
ecs.gn5i
Hw Virt
Average Time To Start
15
Status
active
Observed At
2026-10-25T12:56:56.147503

Availability

REGION / IDSPOTONDEMAND
Beijing (CN) / cn-beijing
0.3612 USD/h 1.806 USD/h
Qingdao (CN) / cn-qingdao
0.903 USD/h 1.806 USD/h
Shenzhen (CN) / cn-shenzhen
0.903 USD/h 1.806 USD/h
Hangzhou (CN) / cn-hangzhou
- 1.806 USD/h
Shanghai (CN) / cn-shanghai
- 1.806 USD/h

Processor

vCPUs
8
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
4
CPU Speed
2.5 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
E5-2682 v4
CPU L1D Cache
32 KiB
CPU L1D Cache Total
128 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
128 KiB
CPU L2 Cache
256 KiB
CPU L2 Cache Total
1 MiB
CPU L3 Cache
40 MiB
CPU L3 Cache Total
40 MiB
CPU Flags
fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, nonstop_tsc, cpuid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, pti, ibrs, ibpb, stibp, fsgsbase, tsc_adjust, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, rdseed, adx, smap, xsaveopt, arat
Ecpus
5
Scalability
62.5

System Resources and Accelerators

MEMORY
Memory Amount
32 GiB
Memory Amount Actual
32 GiB
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
8 GiB
Accelerator Memory Total
8 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Pascal
Accelerator Model
P4
Accelerators
  • NVIDIA Pascal Tesla P4 (Memory amount: 7680, BIOS version: 86.04.8C.00.10, Clock rate: 1531)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Network Speed Baseline
    2 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    An entry-level GPU-accelerated server instance with an NVIDIA P4 GPU, 8 vCPUs, and 32 GB RAM for light inference and media workloads.

    GPU AcceleratedGeneral Purpose

    Alibaba Cloud ecs.gn5i-c8g1.2xlarge is a GPU-accelerated virtual machine featuring an Intel Xeon E5-2682 v4 processor running at 2.5 GHz with 8 vCPUs across 4 physical cores and 32 GB of system RAM. Hardware acceleration is delivered via a single integrated NVIDIA P4 GPU with 8 GB of VRAM based on the Pascal architecture. The instance offers 2 Gbps baseline network bandwidth and operates without onboard local storage. Performance testing highlights lower-tier CPU and memory scores, reflecting its older processor generation. The instance is designed for cost-conscious, low-density GPU workloads such as light machine learning inference, legacy media transcoding, and specialized computer vision pipelines where baseline hardware acceleration is needed without heavy compute throughput demands.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.35Score
    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) 542,475 ops/sec 1,919,289 ops/sec 0.28 50.00% 50.00% -47.00%
    Redis RPS (pipeline=16, SET) 3,503,992 ops/sec 11,728,058 ops/sec 0.29 20.00% 20.00% -22.00%
    PassMark Memory Mark (composite) 1,780 2,416 0.75 10.00% 10.00% -2.80%
    Memory bandwidth (read, 16 MB ~ L3) 37,823 MB/sec 108,466 MB/sec 0.35 10.00% 10.00% -10.00%
    PassMark single-thread CPU 1,843 Mops/s 2,365 Mops/s 0.75 10.00% 10.00% -2.80%

    GPU Bandwidth and Latency

    Node (all GPUs)
    Node baseline directional bandwidth
    		10.0 GB/s
    Node GPU-to-host bandwidth
    		13.2 GB/s
    Node host-to-GPU bandwidth
    		11.1 GB/s
    Single GPU slot
    Per-GPU GPU-to-host bandwidth
    		13.2 GB/s
    Per-GPU host-to-GPU bandwidth
    		11.1 GB/s
    Per-GPU host-device latency
    		782 ns
    Benchmark Environment
    Driver Version
    		 580.159.03
    CUDA Runtime Version
    		 13.0
    nvbandwidth Version
    		 v0.8
    GPU Count
    		 1
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		0.98

    Memory Bandwidth

    Compression

    OpenSSL

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 6,699
    Compression
    		 92,003
    Encryption
    		 2,025
    Extended Instructions
    		 4,266
    Floating Point Maths
    		 13,181
    Integer Maths
    		 20,842
    Physics
    		 819
    Prime Numbers
    		 55
    Single Threaded
    		 1,843
    String Sorting
    		 13,283

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 1,780
    Database Operations
    		 2,252
    Memory Latency
    		 70
    Memory Read Cached
    		 21,057
    Memory Read Uncached
    		 7,149
    Memory Write
    		 6,320

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 180.15 188.75 1.05×
    bitops
    		 100,692 435,017 4.32×
    branch
    		 131,878 777,791 5.90×
    funccall
    		 456.37 1,816 3.98×
    funcret
    		 9,340 51,604 5.53×
    hash
    		 107,539 639,947 5.95×
    intmath
    		 18,171 108,820 5.99×
    nop
    		 154,377 536,055 3.47×
    prime
    		 265,381 1,140,364 4.30×
    rotate
    		 83,452 432,550 5.18×
    str
    		 599,698 2,591,555 4.32×
    wcs
    		 376,103 1,599,772 4.25×
    CryptographySingleMultiScaling
    crypt
    		 1,984 7,618 3.84×
    CompressionSingleMultiScaling
    jpeg
    		 420.66 2,113 5.02×
    zlib
    		 51.32 291.73 5.68×
    HypervisorSingleMultiScaling
    clock
    		 25,281 123,869 4.90×
    clone
    		 436.3 1,404 3.22×
    context
    		 2,645 17,073 6.45×
    cpu-sched
    		 58.31 520.37 8.92×
    eventfd
    		 27,252 422,445 15.50×
    fault
    		 7,808 45,238 5.79×
    fork
    		 3,280 16,665 5.08×
    getrandom
    		 38,254 181,178 4.74×
    hrtimers
    		 134,979 795,775 5.90×
    mprotect
    		 837,001 1,452,685 1.74×
    mtx
    		 10,345,555 184,435,106 17.83×
    munmap
    		 2,295 12,404 5.40×
    null
    		 309,755 1,957,311 6.32×
    pipe
    		 833,802 2,478,987 2.97×
    priv-instr
    		 519,868 2,875,100 5.53×
    resched
    		 1,888,271 857,239 0.45×
    switch
    		 48,686 922,903 18.96×
    timermix
    		 207,182 1,275,421 6.16×
    tlb-shootdown
    		 9,406 16,317 1.73×
    tsc
    		 870,190 6,289,518 7.23×
    usersyscall
    		 365,712 2,122,494 5.80×
    vdso
    		 71,197,447 362,210,565 5.09×
    vfork
    		 14,557 76,204 5.23×
    x86syscall
    		 3,663,831 23,642,193 6.45×
    yield
    		 4,233,578 4,196,058 0.99×
    zero
    		 1,866,225 10,125,957 5.43×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 12,544 63,137 5.03×
    expmath
    		 2,189 12,458 5.69×
    fma
    		 484,676 3,008,058 6.21×
    fp
    		 104.97 546.85 5.21×
    fractal
    		 4.4 22.4 5.09×
    hyperbolic
    		 2,464 14,777 6.00×
    logmath
    		 3,900 22,400 5.74×
    matrix
    		 3,034 13,840 4.56×
    matrix-3d
    		 647.02 1,273 1.97×
    monte-carlo
    		 139.88 858.52 6.14×
    mpfr
    		 991 4,054 4.09×
    powmath
    		 1,333 7,542 5.66×
    trig
    		 1,561 6,856 4.39×
    veccmp
    		 11,972 48,816 4.08×
    vecfp
    		 721.88 3,577 4.96×
    vecmath
    		 1,882 11,113 5.90×
    vecshuf
    		 471.84 1,989 4.21×
    vecwide
    		 19,555 83,678 4.28×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 6 27.8 4.63×
    bsearch
    		 193.93 944.96 4.87×
    bubblesort
    		 0.6 1.6 2.67×
    fibsearch
    		 231.07 1,111 4.81×
    heapsort
    		 6.8 31.8 4.68×
    hsearch
    		 3,646 16,605 4.55×
    insertionsort
    		 6.8 26.6 3.91×
    malloc
    		 1,704,139 14,553,768 8.54×
    mcontend
    		 153.92 1,754 11.39×
    mergesort
    		 22.4 120 5.36×
    qsort
    		 15.6 75 4.81×
    skiplist
    		 5,006 26,435 5.28×
    tree
    		 1 5.2 5.20×
    MemorySingleMultiScaling
    cache
    		 219,810 489,556 2.23×
    cachehammer
    		 445,990 3,091,230 6.93×
    cacheline
    		 33.34 268.91 8.07×
    l1cache
    		 165.26 646.42 3.91×
    memcpy
    		 361.07 1,493 4.14×
    memrate
    		 0.98 4.59 4.68×
    memthrash
    		 99.27 248.04 2.50×
    ptr-chase
    		 31,680,320 76,302,869 2.41×
    spinmem
    		 222.59 252.97 1.14×
    stream
    		 31.36 1,024 32.65×
    vm
    		 51,848 272,329 5.25×

    Stress-ng Raw Scores

    Stress-ng Relative Multicore Performance

    Static Web Server

    Redis

    Alternatives

    Servers of the Same Family

    INSTANCEvCPUsMEMORYAccelerators
    ecs.gn5i-c2g1.large 28 GiB1
    ecs.gn5i-c4g1.xlarge 416 GiB1
    ecs.gn5i-c16g1.4xlarge 1664 GiB1
    ecs.gn5i-c16g1.8xlarge 32128 GiB2
    ecs.gn5i-c28g1.14xlarge 56224 GiB2

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    ecs.gn5i-c8g1.2xlarge FAQs