ecs.g8a.12xlarge by Alibaba Cloud

ecs.g8a.12xlarge is a ecs.g8a family (48 vCPUs, 192 GiB RAM, 0 GB storage) server offered by Alibaba Cloud with 48 vCPUs, 192 GiB of memory and 0 GB of storage. The pricing starts at 1.8962 USD per hour.
48 vCPU
192 GiB Memory
Spare SCore
73,784
(All-cores)
3,072
(Single-core)

Specifications

Server Metadata

Vendor ID
alicloud
Name
ecs.g8a.12xlarge
Description
ecs.g8a family (48 vCPUs, 192 GiB RAM, 0 GB storage)
Family
ecs.g8a
Hw Virt
Average Time To Start
11
Status
active
Observed At
2026-10-16T13:33:29.238304

Availability

REGION / IDSPOTONDEMAND
Shanghai (CN) / cn-shanghai
- 1.8962 USD/h
Shenzhen (CN) / cn-shenzhen
- 1.8962 USD/h

Processor

vCPUs
48
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
24
CPU Speed
2.7 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9T24
CPU L1D Cache
32 KiB
CPU L1D Cache Total
768 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
24 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
96 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, constant_tsc, rep_good, amd_lbr_v2, nopl, nonstop_tsc, cpuid, extd_apicid, aperfmperf, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, extapic, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, ibs, topoext, perfctr_core, perfctr_llc, mwaitx, ssbd, perfmon_v2, ibrs, ibpb, stibp, ibrs_enhanced, vmmcall, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx512_bf16, clzero, irperf, xsaveerptr, rdpru, wbnoinvd, arat, avx512vbmi, umip, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, fsrm
Ecpus
24
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
192 GiB
Memory Amount Actual
192 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Network Speed Baseline
      16 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A balanced general-purpose server featuring dedicated AMD EPYC processors and top-tier memory performance for enterprise workloads and database operations.

      General Purpose

      Alibaba Cloud ecs.g8a.12xlarge is a general-purpose x86_64 server powered by a 2.7 GHz AMD EPYC 9T24 processor with 48 dedicated vCPUs (24 physical cores) and 192.0 GB of RAM. Lacking local storage and GPUs, it relies on network-attached storage and a 16 Gbps baseline network bandwidth. Benchmarks indicate strong performance, with single-core and multi-core CPU metrics in the top 25% and a Passmark memory score in the top 10%. It excels in memory bandwidth and multi-threaded decompression, though uncached large-block memory operations are average. This instance is highly suitable for database operations, Redis caching, software compilation, and general-purpose enterprise applications requiring balanced compute and memory resources.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2Score
      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) 4,370,527 ops/sec 1,919,289 ops/sec 2.3 50.00% 50.00% +52.00%
      Redis RPS (pipeline=16, SET) 33,891,164 ops/sec 11,728,058 ops/sec 2.8 20.00% 20.00% +23.00%
      PassMark Memory Mark (composite) 2,987 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 123,510 MB/sec 108,466 MB/sec 1.1 10.00% 10.00% +0.96%
      PassMark single-thread CPU 2,880 Mops/s 2,365 Mops/s 1.2 10.00% 10.00% +1.80%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,009

      Geekbench Multi-Core

      Score: 18,584

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 63,051
      Compression
      		 924,755
      Encryption
      		 57,805
      Extended Instructions
      		 65,953
      Floating Point Maths
      		 127,562
      Integer Maths
      		 227,919
      Physics
      		 7,447
      Prime Numbers
      		 371
      Single Threaded
      		 2,880
      String Sorting
      		 133,046

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,987
      Database Operations
      		 23,153
      Memory Latency
      		 69
      Memory Read Cached
      		 27,513
      Memory Read Uncached
      		 26,357
      Memory Write
      		 25,897

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 760.01 207.99 0.27×
      bitops
      		 160,321 4,625,707 28.85×
      branch
      		 212,455 9,108,222 42.87×
      funccall
      		 617.3 20,669 33.48×
      funcret
      		 21,308 735,919 34.54×
      hash
      		 163,033 5,873,520 36.03×
      intmath
      		 67,095 2,151,493 32.07×
      nop
      		 626,214 15,264,837 24.38×
      prime
      		 476,787 15,257,273 32.00×
      rotate
      		 87,860 2,120,364 24.13×
      str
      		 1,058,456 32,253,549 30.47×
      wcs
      		 686,479 19,318,039 28.14×
      CryptographySingleMultiScaling
      crypt
      		 3,452 96,221 27.87×
      CompressionSingleMultiScaling
      jpeg
      		 884.31 27,257 30.82×
      zlib
      		 62.21 2,692 43.27×
      HypervisorSingleMultiScaling
      clock
      		 17,902 281,996 15.75×
      clone
      		 298.78 7,299 24.43×
      context
      		 1,754 63,966 36.47×
      cpu-sched
      		 70.29 3,055 43.47×
      eventfd
      		 68,228 2,214,754 32.46×
      fault
      		 11,092 245,027 22.09×
      fork
      		 3,649 82,338 22.56×
      getrandom
      		 50,108 1,597,005 31.87×
      hrtimers
      		 129,879 4,827,651 37.17×
      mprotect
      		 651,987 6,648,916 10.20×
      mtx
      		 32,420,716 2,568,332,597 79.22×
      munmap
      		 2,710 65,325 24.11×
      null
      		 189,977 6,627,359 34.89×
      pipe
      		 873,686 14,081,243 16.12×
      priv-instr
      		 326,839 11,583,737 35.44×
      resched
      		 6,522,746 4,949,881 0.76×
      switch
      		 142,576 5,419,521 38.01×
      timermix
      		 180,305 7,272,142 40.33×
      tlb-shootdown
      		 13,502 162,281 12.02×
      tsc
      		 783,158 36,842,345 47.04×
      usersyscall
      		 235,470 8,449,702 35.88×
      vdso
      		 92,364,105 3,594,678,780 38.92×
      vfork
      		 23,853 149,491 6.27×
      x86syscall
      		 2,164,400 74,648,146 34.49×
      yield
      		 25,470,538 26,030,453 1.02×
      zero
      		 1,657,338 59,422,563 35.85×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 16,242 415,533 25.58×
      expmath
      		 2,860 107,331 37.53×
      fma
      		 917,549 36,297,893 39.56×
      fp
      		 251.32 9,220 36.68×
      fractal
      		 7.4 303.29 40.99×
      hyperbolic
      		 3,806 137,190 36.04×
      logmath
      		 4,548 156,488 34.41×
      matrix
      		 4,924 138,123 28.05×
      matrix-3d
      		 960.34 6,198 6.45×
      monte-carlo
      		 106.85 3,644 34.10×
      mpfr
      		 1,694 51,502 30.41×
      powmath
      		 1,359 52,887 38.90×
      trig
      		 1,868 68,414 36.63×
      veccmp
      		 18,947 596,543 31.49×
      vecfp
      		 1,809 64,677 35.75×
      vecmath
      		 4,023 156,360 38.86×
      vecshuf
      		 637.86 18,917 29.66×
      vecwide
      		 28,550 919,910 32.22×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 10.2 285.99 28.04×
      bsearch
      		 304.95 10,285 33.73×
      bubblesort
      		 1 29.4 29.40×
      fibsearch
      		 379.4 11,196 29.51×
      heapsort
      		 11 364.79 33.16×
      hsearch
      		 11,033 295,655 26.80×
      insertionsort
      		 12.8 310.8 24.28×
      malloc
      		 3,867,635 81,608,755 21.10×
      mcontend
      		 120.74 8,084 66.95×
      mergesort
      		 33.6 1,216 36.19×
      qsort
      		 22 756.38 34.38×
      skiplist
      		 7,007 272,926 38.95×
      tree
      		 2 38.35 19.18×
      MemorySingleMultiScaling
      cache
      		 874,407 1,124,351 1.29×
      cachehammer
      		 284,062 10,822,409 38.10×
      cacheline
      		 56.96 3,648 64.05×
      l1cache
      		 246.92 6,906 27.97×
      memcpy
      		 447.28 11,008 24.61×
      memrate
      		 3.71 17.94 4.84×
      memthrash
      		 195.56 1,515 7.75×
      ptr-chase
      		 45,137,864 389,042,514 8.62×
      spinmem
      		 286.79 2,924 10.20×
      stream
      		 135.76 30,323 223.36×
      vm
      		 60,046 298,237 4.97×

      Stress-ng Raw Scores

      Stress-ng Relative Multicore Performance

      Static Web Server

      Redis

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYAccelerators
      ecs.g8a.large 28 GiB0
      ecs.g8a.xlarge 416 GiB0
      ecs.g8a.2xlarge 832 GiB0
      ecs.g8a.4xlarge 1664 GiB0
      ecs.g8a.8xlarge 32128 GiB0
      ecs.g8a.16xlarge 64256 GiB0
      ecs.g8a.24xlarge 96384 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      ecs.g8a.12xlarge FAQs