Página 1 de 7 123 ... ÚltimoÚltimo
Resultados 1 a 10 de 67
  1. #1
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    €3 2xARMv8 2GB RAM 50GB SSD 200Mbit/s unmetered - Scaleway - Paris/Amsterdam

    ARM64-2GB
    ARM64-4GB
    ARM64-8GB
    Cores 2x ARMv8 4x ARMv8 8x ARMv8
    RAM 2GB 4GB 8GB
    SSD 50GB 100GB 200GB
    Bandwidth 200Mbit/s 200Mbit/s 200Mbit/s
    Price €3 or €0.006 per hour €6 or €0.012 per hour €12 or €0.024 per hour

    We currently offer Ubuntu 16.04 as base Operating System and are working to provide more OS and our InstantApps on these new servers.

    These three new servers are flagged as a preview as we're still deploying nodes to handle large scale and multi-site deployments. ARMv8 Servers will be available in AMS1 in the coming days.

    All of these cloud servers are backed by Cavium ThunderX SoCs, high end processors designed for the cloud. They come with 200Mbit/s of internet bandwidth with unlimited transfer. This means you won't pay any bandwidth fee.

    As all our cloud server, the new ARMv8 servers are billed by the hour.

    The new ARMv8 servers benefit from all the features of the Scaleway Cloud platform: flexible IPs, native IPv6, Snapshots and Images are all there.

    https://blog.online.net/2017/04/27/s...cloud-servers/

  2. #2
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    ARM64-2GB - Debian - Paris

    Código:
    :~# lscpu
    Architecture:          aarch64
    Byte Order:            Little Endian
    CPU(s):                2
    On-line CPU(s) list:   0,1
    Thread(s) per core:    1
    Core(s) per socket:    2
    Socket(s):             1
    NUMA node(s):          1
    NUMA node0 CPU(s):     0,1
    :~# cat /proc/version
    Linux version 4.9.23-std-1 (root@sad-chandrasekhar) (gcc version 5.4.0 20160609 (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.4) ) #1 SMP Mon Apr 24 13:18:14 UTC 2017
    Código:
    :~# lsb_release -a
    Distributor ID: Debian
    Description:    Debian GNU/Linux 8.7 (jessie)
    Release:        8.7
    Codename:       jessie
    :~# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
    16384+0 records in
    16384+0 records out
    1073741824 bytes (1.1 GB) copied, 6.10392 s, 176 MB/s

    :~# rm test

    :~# dd if=/dev/zero of=test bs=64k count=16k
    16384+0 records in
    16384+0 records out
    1073741824 bytes (1.1 GB) copied, 4.70153 s, 228 MB/s
    Código:
    :~#  free
                 total       used       free     shared    buffers     cached
    Mem:       2042700     458548    1584152      14576      41932     348960
    -/+ buffers/cache:      67656    1975044
    Swap:            0          0          0

    Código:
    :~# df -h
    Filesystem      Size  Used Avail Use% Mounted on
    udev            994M     0  994M   0% /dev
    tmpfs           200M   15M  186M   8% /run
    /dev/vda         46G  763M   43G   2% /
    tmpfs           998M     0  998M   0% /dev/shm
    tmpfs           5.0M     0  5.0M   0% /run/lock
    tmpfs           998M     0  998M   0% /sys/fs/cgroup
    
    :~# df -i
    Filesystem      Inodes IUsed   IFree IUse% Mounted on
    udev            254213   376  253837    1% /dev
    tmpfs           255337   689  254648    1% /run
    /dev/vda       3055616 29931 3025685    1% /
    tmpfs           255337     1  255336    1% /dev/shm
    tmpfs           255337     3  255334    1% /run/lock
    tmpfs           255337    16  255321    1% /sys/fs/cgroup
    :~# dmidecode --type 1
    # dmidecode 3.0
    Getting SMBIOS data from sysfs.
    SMBIOS 3.0.0 present.

    Handle 0x0100, DMI type 1, 27 bytes
    System Information
    Manufacturer: QEMU
    Product Name: KVM Virtual Machine
    Version: 1.0
    Código:
    :~# cat /proc/cpuinfo
    processor       : 0
    BogoMIPS        : 200.00
    Features        : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics
    CPU implementer : 0x43
    CPU architecture: 8
    CPU variant     : 0x1
    CPU part        : 0x0a1
    CPU revision    : 1
    
    processor       : 1
    BogoMIPS        : 200.00
    Features        : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics
    CPU implementer : 0x43
    CPU architecture: 8
    CPU variant     : 0x1
    CPU part        : 0x0a1
    CPU revision    : 1

    :~# wget -O /dev/null http://cachefly.cachefly.net/100mb.test
    --2017-04-27 15:49:30-- http://cachefly.cachefly.net/100mb.test
    Resolving cachefly.cachefly.net (cachefly.cachefly.net)... 62.210.187.96
    Connecting to cachefly.cachefly.net (cachefly.cachefly.net)|62.210.187.96|:80... connected.
    HTTP request sent, awaiting response... 200 OK
    Length: 104857600 (100M) [application/octet-stream]
    Saving to: ‘/dev/null’

    /dev/null 100%[===========>] 100.00M 25.8MB/s in 4.0s

    2017-04-27 15:49:34 (25.0 MB/s) - ‘/dev/null’ saved [104857600/104857600]
    Código:
    :~# ifconfig
    eth0      Link encap:Ethernet  HWaddr de:19:88:08:80:02
              inet addr:10.10.35.3  Bcast:10.255.255.255  Mask:255.255.255.254
              inet6 addr: xxxx/127 Scope:Global
              inet6 addr: fxxx/64 Scope:Link
              UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
              RX packets:149853 errors:0 dropped:0 overruns:0 frame:0
              TX packets:82596 errors:0 dropped:0 overruns:0 carrier:0
              collisions:0 txqueuelen:1000
              RX bytes:286196456 (272.9 MiB)  TX bytes:7200303 (6.8 MiB)
    
    lo        Link encap:Local Loopback
              inet addr:127.0.0.1  Mask:255.0.0.0
              inet6 addr: ::1/128 Scope:Host
              UP LOOPBACK RUNNING  MTU:65536  Metric:1
              RX packets:0 errors:0 dropped:0 overruns:0 frame:0
              TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
              collisions:0 txqueuelen:1
              RX bytes:0 (0.0 B)  TX bytes:0 (0.0 B)

  3. #3
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    Scaleway thinks the future of cloud hosting is ARM-based servers




    Romain Dillet
    2017/04/27

    Iliad’s cloud hosting division Scaleway is launching a new type of server today. In just a minute, you can launch your server with its own dedicated ARMv8 processor, 2GB of RAM, 50GB of SSD storage and unlimited bandwidth. And it only costs around $3.25 per month (€2.99).

    If you’re not familiar with processor atchitecture, your computer and your smartphone use two different chipsets. Your laptop uses an x86 CPU manufactured by Intel or AMD, while your smartphone uses an ARM-based system-on-a-chip.

    ARM-based devices don’t need a lot of cooling and are quite efficient when it comes to power usage. And they are also becoming increasingly powerful. That’s why it’s a smart bet to use those chips for servers.

    In many ways, using Scaleway as your cloud hosting provider feels like using DigitalOcean, Linode or any typical VPS provider. But there’s a big difference as Scaleway provides BareMetal servers (and a few virtual server options as well).

    For the past few years, the main trend in cloud computing is that you don’t rent actual physical servers if you don’t have insane needs. Cloud hosting companies run multiple virtual servers on the same physical server, and you can rent those virtual servers.

    By splitting up servers into tiny chunks and pooling resources, it has become much more flexible for developers. For instance, you can create a virtual server, install a VPN on it while you travel to China and destroy your server a few days later. You’ll only get billed for the hours of usage, making it much more flexible than signing up for servers with a 30-day commitment.

    Similarly, if you face big spikes of new users and traffic, you’ll be able to adjust your server infrastructure in no time. I’ve been using Scaleway for my weekend projects and it works well.

    Scaleway wants the best of both worlds — the reliability of physical servers with the flexibility of virtual private servers. So it means that you can create a server in just a few seconds, assign an IP address, load up an image and attach SSD storage to it.

    But you’re also the only one using your ARMv8 cores. You won’t get any performance surprise as you don’t share your CPU raw power with your server neighbor — you don’t have a neighbor.

    [As ofertas ARMv8 citadas abaixo são VPS KVM. ARMv7 é usado em servidor fisico com CPU/memória dedicada porém com armazenamento SSD compartilhado e volátil]

    Scaleway’s systems-on-a-chip are provided by Cavium ThunderX. For €2.99 per month, you get 2 ARMv8 cores and 2GB of RAM. You can also choose 4 cores with 4GB of RAM or 8 cores with 8GB of RAM for €5.99 and €11.99 respectively. Scaleway already had ARMv7 servers, so this is a major update of these options.

    Scaleway is launching its new ARM-based servers in its French data center first with Amsterdam following course in a few days. I hope the company is also planning to launch new data centers in the U.S. and Asia to make it more compelling for users outside of Europe.

    https://techcrunch.com/2017/04/27/sc...based-servers/

  4. #4
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    Exclamation ARM64-2GB (VPS KVM) - BYTE UNIX Benchmarks (Version 5.1.3)

    O benchmark não identificou 2 cores

    System: fr81: GNU/Linux
    OS: GNU/Linux -- 4.9.23-std-1 -- #1 SMP Mon Apr 24 13:18:14 UTC 2017
    Machine: aarch64 (unknown)
    Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
    16:38:50 up 1:22, 1 user, load average: 0.00, 0.10, 0.07; runlevel 3

    ------------------------------------------------------------------------
    Benchmark Run: Thu Apr 27 2017 16:38:50 - 16:59:36
    0 CPUs in system; running 1 parallel copy of tests

    Código:
    Dhrystone 2 using register variables        9006897.0 lps   (10.0 s, 7 samples)
    Double-Precision Whetstone                      998.8 MWIPS (10.0 s, 7 samples)
    Execl Throughput                               1255.6 lps   (29.9 s, 2 samples)
    Pipe Throughput                              485328.0 lps   (10.0 s, 7 samples)
    Pipe-based Context Switching                  32255.2 lps   (10.0 s, 7 samples)
    Process Creation                               2139.6 lps   (30.0 s, 2 samples)
    Shell Scripts (1 concurrent)                   2915.9 lpm   (60.0 s, 2 samples)
    Shell Scripts (8 concurrent)                    537.9 lpm   (60.2 s, 2 samples)
    System Call Overhead                         956725.5 lps   (10.0 s, 7 samples)
    
    System Benchmarks Partial Index              BASELINE       RESULT    INDEX
    Dhrystone 2 using register variables         116700.0    9006897.0    771.8
    Double-Precision Whetstone                       55.0        998.8    181.6
    Execl Throughput                                 43.0       1255.6    292.0
    Pipe Throughput                               12440.0     485328.0    390.1
    Pipe-based Context Switching                   4000.0      32255.2     80.6
    Process Creation                                126.0       2139.6    169.8
    Shell Scripts (1 concurrent)                     42.4       2915.9    687.7
    Shell Scripts (8 concurrent)                      6.0        537.9    896.4
    System Call Overhead                          15000.0     956725.5    637.8
                                                                       ========
    System Benchmarks Index Score (Partial Only)                          353.4

  5. #5
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    ICYMI: ARMv7 Scaleway (3€)

    System: fr50: GNU/Linux
    OS: GNU/Linux -- 4.1.6-249 -- #1 SMP Mon Aug 31 12:34:47 UTC 2015
    Machine: armv7l (unknown)
    Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
    CPU 0: ARMv7 Processor rev 2 (v7l) (0.0 bogomips)

    CPU 1: ARMv7 Processor rev 2 (v7l) (0.0 bogomips)

    CPU 2: ARMv7 Processor rev 2 (v7l) (0.0 bogomips)

    CPU 3: ARMv7 Processor rev 2 (v7l) (0.0 bogomips)

    21:31:11 up 40 min, 1 user, load average: 0.04, 0.50, 0.52; runlevel 3

    Código:
    Benchmark Run: Fri Oct 02 2015 21:31:11 - 21:52:11
    4 CPUs in system; running 1 parallel copy of tests
    
    Dhrystone 2 using register variables        3710342.7 lps   (10.0 s, 7 samples)
    Double-Precision Whetstone                      553.0 MWIPS (10.0 s, 7 samples)
    Execl Throughput                                935.2 lps   (29.9 s, 2 samples)
    Pipe Throughput                              230813.4 lps   (10.0 s, 7 samples)
    Pipe-based Context Switching                  56017.1 lps   (10.0 s, 7 samples)
    Process Creation                               1591.9 lps   (30.0 s, 2 samples)
    Shell Scripts (1 concurrent)                   1481.7 lpm   (60.0 s, 2 samples)
    Shell Scripts (8 concurrent)                    519.7 lpm   (60.1 s, 2 samples)
    System Call Overhead                         736947.8 lps   (10.0 s, 7 samples)
    
    System Benchmarks Partial Index              BASELINE       RESULT    INDEX
    Dhrystone 2 using register variables         116700.0    3710342.7    317.9
    Double-Precision Whetstone                       55.0        553.0    100.5
    Execl Throughput                                 43.0        935.2    217.5
    Pipe Throughput                               12440.0     230813.4    185.5
    Pipe-based Context Switching                   4000.0      56017.1    140.0
    Process Creation                                126.0       1591.9    126.3
    Shell Scripts (1 concurrent)                     42.4       1481.7    349.5
    Shell Scripts (8 concurrent)                      6.0        519.7    866.1
    System Call Overhead                          15000.0     736947.8    491.3
                                                                       ========
    System Benchmarks Index Score (Partial Only)                          246.8
    
    ------------------------------------------------------------------------
    Benchmark Run: Fri Oct 02 2015 21:52:11 - 22:13:13
    4 CPUs in system; running 4 parallel copies of tests
    
    Dhrystone 2 using register variables       14877535.2 lps   (10.0 s, 7 samples)
    Double-Precision Whetstone                     2220.7 MWIPS (10.0 s, 7 samples)
    Execl Throughput                               2782.2 lps   (29.9 s, 2 samples)
    Pipe Throughput                             1159512.4 lps   (10.0 s, 7 samples)
    Pipe-based Context Switching                 228719.6 lps   (10.0 s, 7 samples)
    Process Creation                               5241.2 lps   (30.0 s, 2 samples)
    Shell Scripts (1 concurrent)                   4472.1 lpm   (60.0 s, 2 samples)
    Shell Scripts (8 concurrent)                    577.9 lpm   (60.2 s, 2 samples)
    System Call Overhead                        2582491.4 lps   (10.0 s, 7 samples)
    
    System Benchmarks Partial Index              BASELINE       RESULT    INDEX
    Dhrystone 2 using register variables         116700.0   14877535.2   1274.9
    Double-Precision Whetstone                       55.0       2220.7    403.8
    Execl Throughput                                 43.0       2782.2    647.0
    Pipe Throughput                               12440.0    1159512.4    932.1
    Pipe-based Context Switching                   4000.0     228719.6    571.8
    Process Creation                                126.0       5241.2    416.0
    Shell Scripts (1 concurrent)                     42.4       4472.1   1054.7
    Shell Scripts (8 concurrent)                      6.0        577.9    963.1
    System Call Overhead                          15000.0    2582491.4   1721.7
                                                                       ========
    System Benchmarks Index Score (Partial Only)                          796.6

  6. #6
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966
    Infelizmente, matérias "entusiasmadas" nem sempre correspondem à realidade. Os desenvolvedores da Scaleway recoheceram que o "pacote IP (Intellectual Property)" que acompanhava o ARMv7 que tinham selecionado era inadequado para servidores e devem ter aprendido a lição. Entretanto, a versão do Debian disponivel neste lançamento para o ARMv8 apresenta problemas semelhantes ao processador anterior. Talvez seja uma questão de ajustes por parte da Scaleway mas como está é imprestável para desenvolvimento e possivelmente para rodar inúmeros pacotes. Dito isso, o desempenho do processador no benchmark da Byte foi pifio. Se não estou enganado, o VPS deles utilizando ATOM C2750 também oferece "core dedicado" e custa o mesmo. Não tem problemas de compatibilidade e o desempenho é muito melhor.

  7. #7
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    Sysbench - Checking out Scaleway's new ARM servers


    sysbench --test=cpu --cpu-max-prime=100000 --num-threads=4 run

    This was not a very scientific test, just a quick comparison of a new product. However, the results are quite interesting, especially considering that the prices for the products in this chart vary from €5.99 to $80 per month!

    https://www.opsdash.com/blog/arm-mon...-scaleway.html

  8. #8
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    Sysbench

    cpu
    The cpu is one of the most simple benchmarks in SysBench. In this mode each request consists in calculation of prime numbers up to a value specified by the --cpu-max-primes option. All calculations are performed using 64-bit integers.

    Each thread executes the requests concurrently until either the total number of requests or the total execution time exceed the limits specified with the common command line options.




    This was not a very scientific test
    Mas foi very asinino.


    Aqui o resultado para o VPS ARMv8 com 2 cores

    Código:
    root@fr81:~# sysbench --test=cpu --cpu-max-prime=100000 --num-threads=2 run
    sysbench 0.4.12:  multi-threaded system evaluation benchmark
    
    Running the test with following options:
    Number of threads: 2
    
    Doing CPU performance benchmark
    
    Threads started!
    Done.
    
    Maximum prime number checked in CPU test: 100000
    
    
    Test execution summary:
        total time:                          129.2867s
        total number of events:              10000
        total time taken by event execution: 258.5453
        per-request statistics:
             min:                                 25.58ms
             avg:                                 25.85ms
             max:                                 31.94ms
             approx.  95 percentile:              26.61ms
    
    Threads fairness:
        events (avg/stddev):           5000.0000/1.00
        execution time (avg/stddev):   129.2726/0.01

    E os resultados para um C2750 utilizando 2 cores:


    Código:
    root@fr80:~# sysbench --test=cpu --cpu-max-prime=100000 --num-threads=2 run
    sysbench 0.4.12:  multi-threaded system evaluation benchmark
    
    Running the test with following options:
    Number of threads: 2
    
    Doing CPU performance benchmark
    
    Threads started!
    Done.
    
    Maximum prime number checked in CPU test: 100000
    
    
    Test execution summary:
        total time:                          209.0351s
        total number of events:              10000
        total time taken by event execution: 418.0401
        per-request statistics:
             min:                                 41.78ms
             avg:                                 41.80ms
             max:                                 42.11ms
             approx.  95 percentile:              41.81ms
    
    Threads fairness:
        events (avg/stddev):           5000.0000/1.00
        execution time (avg/stddev):   209.0201/0.01

    ARMv8 129s vs 209s C2750

    Vamos ver como ambos se saem quando usarem o processador

  9. #9
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    Cavium

    Online is deploying dual socket 96 core ThunderX based platforms as part of their Scaleway IaaS cloud offering.



    PR: Online Launches ARMv8-Based Scaleway Public Cloud Service Powered by Cavium’s ThunderX® Workload Optimized Processors


    SAN JOSE, Calif., April 27, 2017 –Online, a wholly-owned subsidiary of the leading French Telecom company Iliad Group and one of the leading web hosting providers, announced today the commercial deployment of server platforms based on Cavium’s (NASDAQ: CAVM) ThunderX® workload optimized processors as part of their Scaleway® cloud service offering.

    Online offers a range of services to Internet customers worldwide including domain names, web hosting, dedicated servers and hosting in their datacenter. With several hundred thousand servers deployed in their datacenter, Online is one of the largest web hosting providers in Europe.

    The ThunderX product family is Cavium’s 64-bit ARMv8-A server processor for Datacenter and Cloud applications, and features high performance custom cores, single and dual socket configurations, high memory bandwidth and large memory capacity. The product family also includes integrated hardware accelerators, integrated feature rich high bandwidth network and storage IO, fully virtualized core and IO, and scalable high bandwidth, low latency Ethernet fabric, which affords ThunderX best-in-class performance per dollar. They are fully compliant with ARMv8-A architecture specifications as well as ARM’s SBSA and SBBR standards, and widely supported by industry leading OS, Hypervisor and Software tool and application vendors.

    Online is deploying dual socket 96 core ThunderX based platforms as part of their Scaleway IaaS cloud offering. As part of this deployment, Online.net is introducing three starter ARMv8 servers at an attractive starting price of €0.006 per hour, which is less than one third of their current offering. Scaleway cloud platform is fully supported by Ubuntu 16.04 OS, including LAMP stack, Docker, Puppet, Juju, Hadoop, MAAS, and more. The platforms also support all standard features of the Scaleway Cloud including flexible IPs, native IPv6, Snapshots and images.

    “Online success in the hosting server industry is built on providing disruptive technology with best-in-class customer experience. This requires us to deploy the most advanced, highest performance and highly scalable servers in our infrastructure,” said Yann Léger, VP Cloud Computing at Online. “Cavium’s ThunderX workload optimized servers provide an ideal vehicle to enable highly optimized platforms for scalable cloud workloads. We expect ThunderX based servers to deliver significant benefits in performance and TCO, thereby providing better performance and cost-efficiency than all existing solutions in the industry.”

    “ThunderX ARMv8 CPUs were designed to deliver best-in-class performance and TCO for targeted workloads and are being deployed at multiple hosting datacenters,” said Gopal Hegde, VP/GM, Datacenter Processor Group at Cavium. “We are pleased to partner with one of Europe’s elite hosting providers on server platforms for their next generation cloud datacenters. This partnership demonstrates continued acceptance of ThunderX platforms across largest and most demanding datacenters.”

    About Cavium
    Cavium, Inc. (NASDAQ: CAVM), offers a broad portfolio of infrastructure solutions for compute, security, storage, switching, connectivity and baseband processing. Cavium’s highly integrated multi-core SoC products deliver software compatible solutions across low to high performance points enabling secure and intelligent functionality in Enterprise, Datacenter and Service Provider Equipment. Cavium processors and solutions are supported by an extensive ecosystem of operating systems, tools, application stacks, hardware reference designs and other products. Cavium is headquartered in San Jose, CA with design centers in California, Massachusetts, India, Israel, China and Taiwan.

    http://cavium.com/newsevents_Online-...rocessors.html

  10. #10
    WHT-BR Top Member
    Data de Ingresso
    Dec 2010
    Posts
    17,966

    ThunderX_CP™ Family of Workload Optimized Compute Processors

    Processor Sub-System:
    • Scales from 24 to 48 cores with up to 2.5GHz frequency
    • 78K-Icache and 32K-D cache per core, 16 MB shared L2 cache
    • Single and Dual socket conguration support via CCPI™

    Memory Interfaces:
    • Up to 4 DDR3/4 memory controller
    • Up to 1 TB of memory capacity in dual socket cong

    I/ O Interfaces:
    • Multiple 10/40GE ports
    • Multiple independent SATAv3 controllers
    • Multiple PCIe – x4 , x8 support

    Virtualization:
    • End-to-End virtualization from I/O to core (virtSoC™)
    Accelerators:
    • Integrated accelerators for virtualization
    Operating System and Related Software Support:
    • Server Base Boot Requirements (SBBR), UEFI, ACPI support
    • IPMI 2.0 and SBSA compliant
    • Ubuntu V14.04 LTS and later
    • Red Hat Early Access for ARMv8
    • Fedora F20
    • OpenSUSE v13

    Management:
    • External Baseband Management Controller (BMC)
    • Supports standard BMC interfaces & functions
    • IPMI 2.0 compliant

    Reference Platforms:
    • StratusX: 1U1S in ATX form factor (Single Socket)
    • CirrusX: 2U4N in ½ SSI form factor (Dual Socket per Node)

    http://www.cavium.com/pdfFiles/Thund...B_Rev1.pdf?x=2

Permissões de Postagem

  • Você não pode iniciar novos tópicos
  • Você não pode enviar respostas
  • Você não pode enviar anexos
  • Você não pode editar suas mensagens
  •