GPU-20xCPU-256GB-1xL40S by UpCloud

GPU-20xCPU-256GB-1xL40S is a GPU (20 vCPUs, 256 GiB RAM, 1x L40S) server offered by UpCloud with 20 vCPUs, 256 GiB of memory and 0 GB of storage. The pricing starts at 1.5111 USD per hour.
20 vCPU
256 GiB Memory
1 GPU
Spare SCore
84,015
(All-cores)
4,189
(Single-core)

Specifications

Server Metadata

Vendor ID
upcloud
Name
GPU-20xCPU-256GB-1xL40S
Description
GPU (20 vCPUs, 256 GiB RAM, 1x L40S)
Family
GPU
Hw Virt
Average Time To Start
50
Status
active
Observed At
2026-10-23T22:21:39.012310

Availability

REGION / IDSPOTONDEMAND
Helsinki #2 (FI) / fi-hel2
1.5111 USD/h 2.0204 USD/h

Processor

vCPUs
20
Hypervisor
KVM
CPU Allocation
Shared
CPU Cores
20
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9575F
CPU L1D Cache
64 KiB
CPU L1D Cache Total
1 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
1 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
10 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
16 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, ht, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, rep_good, nopl, cpuid, extd_apicid, 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, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, perfctr_core, ssbd, ibrs, ibpb, stibp, vmmcall, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, clzero, xsaveerptr, wbnoinvd, arat, avx512vbmi, umip, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, movdiri, movdir64b, avx512_vp2intersect, arch_capabilities
Ecpus
20.1
Scalability
100.5

System Resources and Accelerators

MEMORY
Memory Amount
256 GiB
Memory Amount Actual
256 GiB
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
48 GiB
Accelerator Memory Total
48 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ada Lovelace
Accelerator Model
L40S
Accelerators
  • NVIDIA Ada Lovelace NVIDIA L40S (Memory amount: 46068, Firmware version: 595.71.05, BIOS version: 95.02.66.00.02, Clock rate: 2520)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    32768 GB/month
    IPv4
    1

    CPU and System Topology

    Server Description

    A high-density GPU server combining AMD EPYC processing with NVIDIA Ada Lovelace acceleration for demanding AI and data science workloads.

    GPU AcceleratedMemory OptimizedCompute Optimized

    The UpCloud GPU-20xCPU-256GB-1xL40S is a high-performance, GPU-accelerated virtual server designed for resource-intensive workloads. Powered by an AMD EPYC 9575F processor with 20 physical cores and 256.0 GB of RAM, it integrates a single NVIDIA L40S GPU with 48 GB of VRAM. Operating on the KVM hypervisor, this server delivers top-tier single-core and multi-core CPU performance, alongside strong memory bandwidth. While it lacks local storage, its hardware profile is highly optimized for parallel processing. Benchmark data highlights exceptional efficiency in small-to-medium LLM inference, image processing, and software compilation. This instance is best suited for machine learning inference, data science, and GPU-accelerated rendering.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    3.6Score
    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) 8,047,500 ops/sec 1,919,289 ops/sec 4.2 50.00% 50.00% +100.00%
    Redis RPS (pipeline=16, SET) 51,941,216 ops/sec 11,728,058 ops/sec 4.3 20.00% 20.00% +34.00%
    PassMark Memory Mark (composite) 2,651 2,416 1.1 10.00% 10.00% +0.96%
    Memory bandwidth (read, 16 MB ~ L3) 786,403 MB/sec 108,466 MB/sec 7.2 10.00% 10.00% +22.00%
    PassMark single-thread CPU 4,188 Mops/s 2,365 Mops/s 1.8 10.00% 10.00% +6.10%

    GPU Bandwidth and Latency

    Node (all GPUs)
    Node baseline directional bandwidth
    		22.6 GB/s
    Node GPU-to-host bandwidth
    		26.4 GB/s
    Node host-to-GPU bandwidth
    		26.9 GB/s
    Single GPU slot
    Per-GPU GPU-to-host bandwidth
    		26.4 GB/s
    Per-GPU host-to-GPU bandwidth
    		26.9 GB/s
    Per-GPU host-device latency
    		611 ns
    Benchmark Environment
    Driver Version
    		 595.71.05
    CUDA Runtime Version
    		 13.2
    nvbandwidth Version
    		 v0.8
    GPU Count
    		 1
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		1.00

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 2,931

    Geekbench Multi-Core

    Score: 24,099

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 62,326
    Compression
    		 717,689
    Encryption
    		 35,467
    Extended Instructions
    		 64,373
    Floating Point Maths
    		 170,516
    Integer Maths
    		 170,427
    Physics
    		 11,018
    Prime Numbers
    		 670
    Single Threaded
    		 4,188
    String Sorting
    		 98,020

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,651
    Database Operations
    		 28,364
    Memory Latency
    		 97
    Memory Read Cached
    		 37,848
    Memory Read Uncached
    		 35,226
    Memory Write
    		 35,568

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 568.71 428.98 0.75×
    bitops
    		 253,194 5,019,595 19.83×
    branch
    		 195,871 3,877,838 19.80×
    funccall
    		 1,005 19,679 19.58×
    funcret
    		 29,892 588,433 19.69×
    hash
    		 240,954 4,766,473 19.78×
    intmath
    		 88,355 1,762,864 19.95×
    nop
    		 475,811 9,446,034 19.85×
    prime
    		 669,479 13,097,754 19.56×
    rotate
    		 156,817 3,097,542 19.75×
    str
    		 1,695,290 32,711,830 19.30×
    wcs
    		 1,087,086 21,885,393 20.13×
    CryptographySingleMultiScaling
    crypt
    		 5,975 118,028 19.75×
    CompressionSingleMultiScaling
    jpeg
    		 1,428 26,774 18.75×
    zlib
    		 86.74 1,631 18.81×
    HypervisorSingleMultiScaling
    clock
    		 84,851 264,501 3.12×
    clone
    		 457.74 7,455 16.29×
    context
    		 9,828 194,564 19.80×
    cpu-sched
    		 58.42 1,275 21.83×
    eventfd
    		 90,562 973,256 10.75×
    fault
    		 44,564 176,366 3.96×
    fork
    		 7,490 67,322 8.99×
    getrandom
    		 111,170 2,173,002 19.55×
    hrtimers
    		 756,805 4,283,003 5.66×
    mprotect
    		 732,260 9,704,775 13.25×
    mtx
    		 58,000,605 1,915,032,091 33.02×
    munmap
    		 5,558 53,795 9.68×
    null
    		 1,626,311 31,733,089 19.51×
    pipe
    		 1,100,818 13,992,475 12.71×
    priv-instr
    		 1,518,374 11,190,582 7.37×
    resched
    		 14,312,333 9,580,156 0.67×
    switch
    		 106,224 9,290,226 87.46×
    timermix
    		 361,686 6,924,074 19.14×
    tlb-shootdown
    		 25,320 177,379 7.01×
    tsc
    		 985,572 19,601,495 19.89×
    usersyscall
    		 1,229,716 11,469,007 9.33×
    vdso
    		 110,072,294 2,188,366,956 19.88×
    vfork
    		 40,035 193,935 4.84×
    x86syscall
    		 20,813,973 411,842,630 19.79×
    yield
    		 32,630,919 40,044,271 1.23×
    zero
    		 8,880,414 172,968,071 19.48×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 19,603 384,545 19.62×
    expmath
    		 4,451 87,895 19.75×
    fma
    		 1,728,662 34,226,347 19.80×
    fp
    		 213.6 4,620 21.63×
    fractal
    		 9.8 193.41 19.74×
    hyperbolic
    		 6,023 119,597 19.86×
    logmath
    		 6,332 124,466 19.66×
    matrix
    		 10,224 196,282 19.20×
    matrix-3d
    		 1,238 11,105 8.97×
    monte-carlo
    		 507.01 9,889 19.50×
    mpfr
    		 2,685 51,778 19.28×
    powmath
    		 2,030 40,434 19.92×
    trig
    		 2,666 52,853 19.83×
    veccmp
    		 33,565 648,730 19.33×
    vecfp
    		 2,743 53,032 19.34×
    vecmath
    		 5,283 104,071 19.70×
    vecshuf
    		 1,111 21,697 19.53×
    vecwide
    		 44,508 857,761 19.27×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 13.8 273.79 19.84×
    bsearch
    		 407.27 7,766 19.07×
    bubblesort
    		 1.4 27.8 19.86×
    fibsearch
    		 468.74 9,350 19.95×
    heapsort
    		 15.6 308.39 19.77×
    hsearch
    		 14,504 278,544 19.20×
    insertionsort
    		 17.6 344.4 19.57×
    malloc
    		 5,551,036 50,935,018 9.18×
    mcontend
    		 111.19 3,508 31.55×
    mergesort
    		 43.6 832.38 19.09×
    qsort
    		 29.6 570.59 19.28×
    skiplist
    		 9,426 183,037 19.42×
    tree
    		 2.8 52.77 18.85×
    MemorySingleMultiScaling
    cache
    		 1,322,537 1,443,640 1.09×
    cachehammer
    		 271,973 5,096,088 18.74×
    cacheline
    		 63.54 1,086 17.09×
    l1cache
    		 762.66 14,824 19.44×
    memcpy
    		 901.81 17,543 19.45×
    memrate
    		 1.17 15.06 12.87×
    memthrash
    		 146.67 1,183 8.06×
    ptr-chase
    		 82,935,066 529,843,243 6.39×
    spinmem
    		 459.78 2,074 4.51×
    stream
    		 494.25 38,629 78.16×
    vm
    		 260,565 294,382 1.13×

    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

    PostgreSQL heavy read-only throughput

    Alternatives

    Servers of the Same Family

    INSTANCEvCPUsMEMORYAccelerators
    GPU-8xCPU-64GB-1xL40S 864 GiB1
    GPU-12xCPU-128GB-1xL40S 12128 GiB1
    GPU-12xCPU-128GB-2xL40S 12128 GiB2
    GPU-16xCPU-80GB-1xRTXPRO6000 1680 GiB1
    GPU-16xCPU-192GB-1xL40S 16192 GiB1
    GPU-16xCPU-192GB-2xL40S 16192 GiB2
    GPU-16xCPU-192GB-3xL40S 16192 GiB3

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    GPU-20xCPU-256GB-1xL40S FAQs