D96als_v7 by Microsoft Azure

D96als_v7 is a Dalsv7 family [AMD processor] [Low Memory] [Premium Storage capable] 96 vCPUs server offered by Microsoft Azure with 96 vCPUs, 192 GiB of memory and 0 GB of storage. The pricing starts at 0.4613 USD per hour.
96 vCPU
192 GiB Memory
Spare SCore
168,120
(All-cores)
3,524
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_D96als_v7
Name
D96als_v7
API Reference
Standard_D96als_v7
Description
Dalsv7 family [AMD processor] [Low Memory] [Premium Storage capable] 96 vCPUs
Family
Dalsv7
Hw Virt
Average Time To Start
12
Status
active
Observed At
2026-10-22T17:57:13.786878

Availability

REGION / IDSPOTONDEMAND
Central India (IN) / centralindia
0.4613 USD/h 2.496 USD/h
Jio India West (IN) / jioindiawest
- 2.496 USD/h
Central US (US) / centralus
0.712 USD/h 3.859 USD/h
East US 2 (US) / eastus2
0.7131 USD/h 3.859 USD/h
North Central US (US) / northcentralus
0.7131 USD/h 3.859 USD/h
West US 2 (US) / westus2
0.7131 USD/h 3.859 USD/h
West US 3 (US) / westus3
0.7131 USD/h 3.859 USD/h
East US (US) / eastus
0.7486 USD/h 3.859 USD/h
Sweden Central (SE) / swedencentral
0.7629 USD/h 4.128 USD/h
Mexico Central (ZA) / mexicocentral
0.7841 USD/h 4.243 USD/h
Canada Central (CA) / canadacentral
0.7948 USD/h 4.301 USD/h
North Europe (IE) / northeurope
0.7948 USD/h 4.301 USD/h
UK South (GB) / uksouth
0.8285 USD/h 4.483 USD/h
France Central (FR) / francecentral
0.8373 USD/h 4.531 USD/h
Italy North (IT) / italynorth
0.8373 USD/h 4.531 USD/h
Spain Central (ES) / spaincentral
0.8373 USD/h 4.531 USD/h
West US (US) / westus
0.8373 USD/h 4.531 USD/h
South Central US (US) / southcentralus
0.8534 USD/h 4.618 USD/h
Germany West Central (DE) / germanywestcentral
0.8623 USD/h 4.666 USD/h
Poland Central (PL) / polandcentral
0.8623 USD/h 4.666 USD/h
West Europe (NL) / westeurope
0.8623 USD/h 4.666 USD/h
Korea Central (KR) / koreacentral
0.8782 USD/h 4.752 USD/h
UAE North (AE) / uaenorth
0.8782 USD/h 4.752 USD/h
Australia East (AU) / australiaeast
0.8941 USD/h 4.838 USD/h
Southeast Asia (SG) / southeastasia
0.8941 USD/h 4.838 USD/h
Japan East (JP) / japaneast
0.9279 USD/h 5.021 USD/h
Japan West (JP) / japanwest
0.9279 USD/h 5.021 USD/h
South Africa North (ZA) / southafricanorth
0.9526 USD/h 5.155 USD/h
East Asia (HK) / eastasia
0.9865 USD/h 5.338 USD/h
Norway East (NO) / norwayeast
1.0182 USD/h 5.51 USD/h
Switzerland North (CH) / switzerlandnorth
1.0182 USD/h 5.51 USD/h
Brazil South (BR) / brazilsouth
1.1443 USD/h 6.192 USD/h

Processor

vCPUs
96
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
48
CPU Speed
4.5 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9V45
CPU L1D Cache
48 KiB
CPU L1D Cache Total
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
48 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
192 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, nopl, xtopology, tsc_reliable, nonstop_tsc, cpuid, extd_apicid, aperfmperf, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, svm, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, topoext, vmmcall, fsgsbase, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, user_shstk, avx_vnni, avx512_bf16, clzero, xsaveerptr, rdpru, arat, npt, nrip_save, tsc_scale, vmcb_clean, flushbyasid, decodeassists, pausefilter, pfthreshold, v_vmsave_vmload, avx512vbmi, umip, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, fsrm, avx512_vp2intersect
Ecpus
47.7
Scalability
49.69

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
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A high-frequency, compute-optimized virtual machine designed for processing-heavy workloads requiring dense CPU allocation and rapid multi-threaded execution.

      Compute OptimizedGeneral Purpose

      Microsoft Azure D96als_v7 is a compute-optimized virtual machine powered by a 4.5 GHz AMD EPYC 9V45 processor. It provides 96 dedicated vCPUs across 48 physical cores, paired with 192.0 GB of RAM, resulting in a low memory-to-core ratio of 2.0 GB. Running on the Microsoft Hyper-V hypervisor, this x86_64 instance lacks local storage and bundled GPUs but supports premium storage. Benchmarks place its CPU performance in the top 10%, with a multi-core stress-ng score of 168119.86 and a Passmark CPU score of 109958.38. It delivers high-throughput memory bandwidth and strong integer performance, making it highly efficient for compute-bound workloads. The low memory allocation per core represents a tradeoff that reduces cost for processing-heavy tasks but limits memory-intensive applications. It is best suited for multi-threaded decompression, static web serving, and moderate-scale LLM inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      3.7Score
      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) 9,090,356 ops/sec 1,918,343 ops/sec 4.8 50.00% 50.00% +120.00%
      Redis RPS (pipeline=16, SET) 74,967,425 ops/sec 11,704,734 ops/sec 6.2 20.00% 20.00% +44.00%
      PassMark Memory Mark (composite) 2,898 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 343,820 MB/sec 108,420 MB/sec 3.1 10.00% 10.00% +12.00%
      PassMark single-thread CPU 3,582 Mops/s 2,365 Mops/s 1.5 10.00% 10.00% +4.10%

      Memory Bandwidth

      Compression

      OpenSSL

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 109,958
      Compression
      		 1,800,327
      Encryption
      		 110,970
      Extended Instructions
      		 118,940
      Floating Point Maths
      		 343,298
      Integer Maths
      		 583,290
      Physics
      		 15,384
      Prime Numbers
      		 807
      Single Threaded
      		 3,582
      String Sorting
      		 234,856

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,898
      Database Operations
      		 37,922
      Memory Latency
      		 80
      Memory Read Cached
      		 31,875
      Memory Read Uncached
      		 29,154
      Memory Write
      		 30,247

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 527.69 247.29 0.47×
      bitops
      		 218,242 10,518,831 48.20×
      branch
      		 162,963 12,438,756 76.33×
      funccall
      		 839.89 43,848 52.21×
      funcret
      		 25,156 1,381,108 54.90×
      hash
      		 204,407 13,087,216 64.03×
      intmath
      		 74,927 4,183,277 55.83×
      nop
      		 403,209 22,121,012 54.86×
      prime
      		 600,877 31,203,087 51.93×
      rotate
      		 134,307 6,133,404 45.67×
      str
      		 1,512,785 63,938,819 42.27×
      wcs
      		 948,470 39,308,800 41.44×
      CryptographySingleMultiScaling
      crypt
      		 5,157 223,114 43.26×
      CompressionSingleMultiScaling
      jpeg
      		 1,103 54,650 49.57×
      zlib
      		 88.71 5,331 60.10×
      HypervisorSingleMultiScaling
      clock
      		 20,680 158,187 7.65×
      clone
      		 1,117 34,072 30.49×
      context
      		 5,102 400,636 78.52×
      cpu-sched
      		 58.37 6,154 105.43×
      eventfd
      		 35,001 5,699,167 162.83×
      fault
      		 12,777 225,256 17.63×
      fork
      		 4,352 61,676 14.17×
      getrandom
      		 64,162 3,699,148 57.65×
      hrtimers
      		 492,451 9,514,672 19.32×
      mprotect
      		 711,654 20,403,794 28.67×
      mtx
      		 39,808,245 3,682,282,970 92.50×
      munmap
      		 3,323 71,238 21.44×
      null
      		 572,100 42,727,613 74.69×
      pipe
      		 2,567,352 59,047,690 23.00×
      priv-instr
      		 554,119 30,488,830 55.02×
      resched
      		 7,382,098 4,952,206 0.67×
      switch
      		 105,851 17,712,397 167.33×
      timermix
      		 209,164 14,235,244 68.06×
      tlb-shootdown
      		 16,947 241,710 14.26×
      tsc
      		 826,986 77,068,012 93.19×
      usersyscall
      		 432,082 27,666,781 64.03×
      vdso
      		 102,874,663 7,630,451,764 74.17×
      vfork
      		 22,517 185,860 8.25×
      x86syscall
      		 7,952,096 579,880,240 72.92×
      yield
      		 73,874,205 74,792,888 1.01×
      zero
      		 4,322,395 286,719,303 66.33×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 16,366 799,052 48.82×
      expmath
      		 3,751 210,110 56.02×
      fma
      		 1,464,799 76,749,186 52.40×
      fp
      		 206.39 12,694 61.51×
      fractal
      		 8.4 521.73 62.11×
      hyperbolic
      		 5,125 327,650 63.93×
      logmath
      		 5,376 344,019 63.99×
      matrix
      		 8,659 274,516 31.70×
      matrix-3d
      		 82.63 11,460 138.69×
      monte-carlo
      		 279.41 18,587 66.52×
      mpfr
      		 2,291 117,402 51.24×
      powmath
      		 1,731 117,112 67.65×
      trig
      		 2,308 136,917 59.33×
      veccmp
      		 28,102 1,418,970 50.49×
      vecfp
      		 2,220 139,544 62.86×
      vecmath
      		 4,429 289,563 65.38×
      vecshuf
      		 940.54 45,750 48.64×
      vecwide
      		 37,910 1,771,775 46.74×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 12.2 571.98 46.88×
      bsearch
      		 348.06 18,690 53.70×
      bubblesort
      		 1 57.6 57.60×
      fibsearch
      		 406.58 23,605 58.06×
      heapsort
      		 13.4 681.16 50.83×
      hsearch
      		 12,467 531,487 42.63×
      insertionsort
      		 15.2 600.99 39.54×
      malloc
      		 4,972,869 164,045,237 32.99×
      mcontend
      		 115.89 14,269 123.13×
      mergesort
      		 37 2,209 59.70×
      qsort
      		 24.6 1,388 56.40×
      skiplist
      		 7,857 499,795 63.61×
      tree
      		 2.4 81.57 33.99×
      MemorySingleMultiScaling
      cache
      		 959,636 1,998,418 2.08×
      cachehammer
      		 263,713 15,146,084 57.43×
      cacheline
      		 68.17 4,593 67.37×
      l1cache
      		 1,284 28,299 22.04×
      memcpy
      		 769.21 31,252 40.63×
      memrate
      		 4.74 37.13 7.83×
      memthrash
      		 234.46 1,913 8.16×
      ptr-chase
      		 87,370,874 763,049,792 8.73×
      spinmem
      		 313.59 2,526 8.05×
      stream
      		 75.75 65,101 859.42×
      vm
      		 238,541 304,237 1.28×

      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
      D2als_v7 24 GiB0
      D4als_v7 48 GiB0
      D8als_v7 816 GiB0
      D16als_v7 1632 GiB0
      D32als_v7 3264 GiB0
      D48als_v7 4896 GiB0
      D64als_v7 64128 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      D96als_v7 FAQs