D48ps_v5 by Microsoft Azure
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | azure |
Server ID | Standard_D48ps_v5 |
Name | D48ps_v5 |
API Reference | Standard_D48ps_v5 |
Description | DPSv5 family [ARM processor] [Premium Storage capable] 48 vCPUs |
Family | General Purpose |
Series | Dpsv5 |
Hw Virt | |
Average Time To Start | 25 |
Status | active |
Observed At | 2026-11-16T01:51:27.293503 |
Availability
| Region / ID | Spot | Ondemand |
|---|---|---|
Central India (IN) / centralindia | 0.2243 USD/h | 1.214 USD/h |
Jio India Central (IN) / jioindiacentral | - | 1.214 USD/h |
Jio India West (IN) / jioindiawest | - | 1.214 USD/h |
East US 2 (US) / eastus2 | 0.3415 USD/h | 1.848 USD/h |
North Central US (US) / northcentralus | 0.3415 USD/h | 1.848 USD/h |
West US 2 (US) / westus2 | 0.3415 USD/h | 1.848 USD/h |
West US 3 (US) / westus3 | 0.3415 USD/h | 1.848 USD/h |
East US (US) / eastus | 0.3907 USD/h | 1.848 USD/h |
Sweden Central (SE) / swedencentral | 0.3637 USD/h | 1.968 USD/h |
Canada Central (CA) / canadacentral | 0.3796 USD/h | 2.054 USD/h |
North Europe (IE) / northeurope | 0.3814 USD/h | 2.064 USD/h |
Central US (US) / centralus | 0.3857 USD/h | 2.088 USD/h |
UK South (GB) / uksouth | 0.3744 USD/h | 2.131 USD/h |
West US (US) / westus | 0.3973 USD/h | 2.15 USD/h |
France Central (FR) / francecentral | 0.3992 USD/h | 2.16 USD/h |
Germany West Central (DE) / germanywestcentral | 0.408 USD/h | 2.208 USD/h |
West Europe (NL) / westeurope | 0.408 USD/h | 2.208 USD/h |
South Central US (US) / southcentralus | 0.4099 USD/h | 2.218 USD/h |
West Central US (US) / westcentralus | 0.4099 USD/h | 2.218 USD/h |
Australia East (AU) / australiaeast | 0.4258 USD/h | 2.304 USD/h |
Southeast Asia (SG) / southeastasia | 0.4258 USD/h | 2.304 USD/h |
Japan East (JP) / japaneast | 0.4391 USD/h | 2.376 USD/h |
Switzerland North (CH) / switzerlandnorth | 0.4489 USD/h | 2.429 USD/h |
East Asia (HK) / eastasia | 0.4701 USD/h | 2.544 USD/h |
Processor
vCPUs | 48 |
Hypervisor | Microsoft Hyper-V |
CPU Allocation | Dedicated |
CPU Cores | 48 |
CPU Speed | 3 GHz |
CPU Architecture | arm64 |
CPU Manufacturer | Ampere |
CPU Family | ARMv8 |
CPU Model | Neoverse-N1 |
CPU L1D Cache | 64 KiB |
CPU L1D Cache Total | 3 MiB |
CPU L1I Cache | 64 KiB |
CPU L1I Cache Total | 3 MiB |
CPU L2 Cache | 1 MiB |
CPU L2 Cache Total | 48 MiB |
CPU L3 Cache | 32 MiB |
CPU L3 Cache Total | 32 MiB |
CPU Flags | fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, lrcpc, dcpop, asimddp |
Ecpus | 46.7 |
Scalability | 97.29 |
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 | |
Compatible Storage IDs | PremiumV2_LRS, Premium_LRS, Premium_ZRS, StandardSSD_LRS, StandardSSD_ZRS, Standard_LRS, UltraSSD_LRS |
| Network | |
|---|---|
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
CPU and System Topology
Server Description
An ARM-based forty-eight core virtual machine delivering strong multi-threaded performance and balanced memory allocation for scale-out workloads.
The Microsoft Azure D48ps_v5 is an ARM-based virtual machine from the DPSv5 family, powered by a 48-core Ampere Neoverse-N1 processor running at 3.0 GHz. It features 192.0 GB of RAM, providing a balanced 4.0 GB per core, with no local storage or GPUs. Operating under Microsoft Hyper-V, this server delivers strong multi-core performance, as demonstrated by a stress-ng multi-core score of 85,033.61 and strong Clang software compilation results. However, single-core performance is weaker, with a Geekbench single-core score of 1,118.0. The architecture lacks AVX and AMX extensions but supports AES cryptography. This server is suited for multi-threaded workloads such as software compilation, static web serving, and database operations, offering a balanced resource density without the overhead of hyperthreading.
Economics
Performance
Memory Bandwidth
Compression
OpenSSL
Geekbench Single-Core
Geekbench Multi-Core
Passmark CPU Scores
| BENCHMARK | SCORE |
|---|---|
Mark | 27,166 |
Compression | 266,749 |
Encryption | 7,686 |
Extended Instructions | 34,862 |
Floating Point Maths | 168,400 |
Integer Maths | 221,147 |
Physics | 3,516 |
Prime Numbers | 215 |
Single Threaded | 1,334 |
String Sorting | 154,092 |
Passmark Memory Scores
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 2,002 |
Database Operations | 21,371 |
Memory Latency | 68 |
Memory Read Cached | 11,370 |
Memory Read Uncached | 9,098 |
Memory Write | 15,013 |
Stress-ng Stressors
| CPU integer | Single | Multi | Scaling |
|---|---|---|---|
atomic | 88.04 | 27.69 | 0.31× |
bitops | 108,465 | 5,196,844 | 47.91× |
branch | 220,876 | 10,592,147 | 47.96× |
funccall | 1,338 | 64,164 | 47.97× |
funcret | 20,914 | 1,000,431 | 47.84× |
hash | 128,100 | 6,139,843 | 47.93× |
intmath | 32,024 | 1,501,946 | 46.90× |
nop | 173,570 | 8,318,386 | 47.93× |
prime | 336,448 | 16,151,829 | 48.01× |
rotate | 96,525 | 4,627,481 | 47.94× |
str | 514,876 | 24,668,374 | 47.91× |
wcs | 119,199 | 5,711,803 | 47.92× |
| Cryptography | Single | Multi | Scaling |
|---|---|---|---|
crypt | 2,908 | 139,480 | 47.97× |
| Compression | Single | Multi | Scaling |
|---|---|---|---|
jpeg | 523.41 | 23,010 | 43.96× |
zlib | 46.97 | 1,778 | 37.85× |
| Hypervisor | Single | Multi | Scaling |
|---|---|---|---|
clock | 21,641 | 232,080 | 10.72× |
clone | 206.49 | 6,841 | 33.13× |
context | 2,594 | 124,468 | 47.99× |
cpu-sched | 71.61 | 3,030 | 42.31× |
eventfd | 51,139 | 1,249,391 | 24.43× |
fault | 12,846 | 302,200 | 23.52× |
fork | 3,596 | 56,872 | 15.82× |
getrandom | 49,074 | 2,352,476 | 47.94× |
hrtimers | 286,258 | 7,191,001 | 25.12× |
mprotect | 908,585 | 14,856,549 | 16.35× |
mtx | 7,740,853 | 1,757,253,395 | 227.01× |
munmap | 2,588 | 65,465 | 25.30× |
null | 462,714 | 22,194,817 | 47.97× |
pipe | 787,676 | 19,787,571 | 25.12× |
priv-instr | 735,788 | 13,770,912 | 18.72× |
resched | 5,517,588 | 7,594,481 | 1.38× |
switch | 77,923 | 14,892,314 | 191.12× |
timermix | 403,364 | 19,300,411 | 47.85× |
tlb-shootdown | 4,692 | 5,280 | 1.13× |
vdso | 46,818,631 | 2,243,471,956 | 47.92× |
vfork | 23,533 | 250,007 | 10.62× |
yield | 40,745,640 | 47,464,998 | 1.16× |
zero | 2,077,765 | 99,382,849 | 47.83× |
| CPU float/SIMD | Single | Multi | Scaling |
|---|---|---|---|
eigen | 1,336 | 64,006 | 47.90× |
expmath | 240.05 | 11,516 | 47.97× |
fma | 641,110 | 30,704,368 | 47.89× |
fp | 103.2 | 4,946 | 47.93× |
fractal | 6.6 | 309.12 | 46.84× |
hyperbolic | 244.33 | 11,705 | 47.91× |
logmath | 293.61 | 14,079 | 47.95× |
matrix | 5,350 | 256,369 | 47.92× |
matrix-3d | 538.13 | 5,920 | 11.00× |
monte-carlo | 193.04 | 9,255 | 47.94× |
mpfr | 641.9 | 30,774 | 47.94× |
powmath | 176.54 | 8,464 | 47.95× |
trig | 329.61 | 15,798 | 47.93× |
veccmp | 17,142 | 822,715 | 48.00× |
vecfp | 745.69 | 35,735 | 47.92× |
vecmath | 3,090 | 148,112 | 47.93× |
vecshuf | 672.29 | 32,256 | 47.98× |
vecwide | 18,423 | 882,248 | 47.89× |
| Algorithms | Single | Multi | Scaling |
|---|---|---|---|
bitonicsort | 5.4 | 259.15 | 47.99× |
bsearch | 258.36 | 12,391 | 47.96× |
bubblesort | 0.8 | 38 | 47.50× |
fibsearch | 273.66 | 13,111 | 47.91× |
heapsort | 8.2 | 394.75 | 48.14× |
hsearch | 4,928 | 235,742 | 47.84× |
insertionsort | 4.6 | 220.4 | 47.91× |
malloc | 2,885,188 | 71,291,403 | 24.71× |
mcontend | 190.75 | 99,993 | 524.21× |
mergesort | 27.4 | 1,313 | 47.91× |
qsort | 19.4 | 937.11 | 48.30× |
skiplist | 5,347 | 256,361 | 47.94× |
tree | 1.2 | 28.75 | 23.96× |
| Memory | Single | Multi | Scaling |
|---|---|---|---|
cache | 384,548 | 652,486 | 1.70× |
cachehammer | 154,992 | 453,858 | 2.93× |
cacheline | 20.19 | 2,781 | 137.73× |
l1cache | 182.29 | 8,617 | 47.27× |
memcpy | 443.75 | 21,294 | 47.99× |
memrate | 3.15 | 29.14 | 9.25× |
memthrash | 178.22 | 345.11 | 1.94× |
ptr-chase | 21,597,664 | 410,818,446 | 19.02× |
spinmem | 846.96 | 1,891 | 2.23× |
stream | 66.46 | 55,784 | 839.37× |
vm | 59,069 | 2,449,260 | 41.46× |
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
| INSTANCE | vCPUs | MEMORY | Accelerators |
|---|---|---|---|
| B2ats_v2 | 2 | 1 GiB | 0 |
| B2pts_v2 | 2 | 1 GiB | 0 |
| B2ts_v2 | 2 | 1 GiB | 0 |
| B2als_v2 | 2 | 4 GiB | 0 |
| B2ls_v2 | 2 | 4 GiB | 0 |
| B2pls_v2 | 2 | 4 GiB | 0 |
| D2alds_v6 | 2 | 4 GiB | 0 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | Accelerators |
|---|