GPU-24xCPU-480GB-2xH100 by UpCloud
(All-cores)
(Single-core)
Specifications #
Server Metadata #
Vendor ID | upcloud |
Name | GPU-24xCPU-480GB-2xH100 |
Description | GPU (24 vCPUs, 480 GiB RAM, 2x H100) |
Family | GPU |
Series | H100 |
Hw Virt | |
Average Time To Start | 62 |
Status | inactive |
Observed At | 2026-11-18T15:26:59.371355 |
Availability #
| Region / ID | Spot | Ondemand |
|---|---|---|
Sydney #1 (AU) / au-syd1 | 3.9156 USD/h | 3.927 USD/h |
Frankfurt #1 (DE) / de-fra1 | 3.9156 USD/h | 3.927 USD/h |
Copenhagen #1 (DK) / dk-cph1 | 3.9156 USD/h | 3.927 USD/h |
Madrid #1 (ES) / es-mad1 | 3.9156 USD/h | 3.927 USD/h |
Helsinki #1 (FI) / fi-hel1 | 3.9156 USD/h | 3.927 USD/h |
Amsterdam #1 (NL) / nl-ams1 | 3.9156 USD/h | 3.927 USD/h |
Stavanger #1 (NO) / no-svg1 | 3.9156 USD/h | 3.927 USD/h |
Warsaw #1 (PL) / pl-waw1 | 3.9156 USD/h | 3.927 USD/h |
Stockholm #1 (SE) / se-sto1 | 3.9156 USD/h | 3.927 USD/h |
Singapore #1 (SG) / sg-sin1 | 3.9156 USD/h | 3.927 USD/h |
London #1 (GB) / uk-lon1 | 3.9156 USD/h | 3.927 USD/h |
Chicago #1 (US) / us-chi1 | 3.9156 USD/h | 3.927 USD/h |
New York #1 (US) / us-nyc1 | 3.9156 USD/h | 3.927 USD/h |
San Jose #1 (US) / us-sjo1 | 3.9156 USD/h | 3.927 USD/h |
Helsinki #2 (FI) / fi-hel2 | 3.9265 USD/h | 4.7601 USD/h |
Processor #
vCPUs | 24 |
Hypervisor | KVM |
CPU Allocation | Shared |
CPU Cores | 24 |
CPU Speed | 2 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | Intel |
CPU Family | Xeon |
CPU Model | 8462Y+ |
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 | 4 MiB |
CPU L2 Cache Total | 96 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, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, arch_perfmon, rep_good, nopl, xtopology, cpuid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pdcm, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, cpuid_fault, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, 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, avx_vnni, avx512_bf16, wbnoinvd, arat, avx512vbmi, umip, pku, ospke, waitpkg, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, bus_lock_detect, cldemote, movdiri, movdir64b, fsrm, md_clear, serialize, tsxldtrk, amx_bf16, avx512_fp16, amx_tile, amx_int8, arch_capabilities |
Ecpus | 23.8 |
Scalability | 99.17 |
System Resources and Accelerators #
| Memory | |
|---|---|
Memory Amount | 480 GiB |
Memory Amount Actual | 480 GiB |
| Accelerators | |
|---|---|
Accelerator Count | 2 |
Accelerator Memory Min | 80 GiB |
Accelerator Memory Total | 160 GiB |
Accelerator Type | GPU |
Accelerator Manufacturer | NVIDIA |
Accelerator Family | Hopper |
Accelerator Model | H100 |
Accelerators |
|
| Storage | |
|---|---|
Storage Size | 0 GB |
Storages | |
Compatible Storage IDs | maxiops, standard, hdd |
| Network | |
|---|---|
Inbound Traffic | 0 GB/month |
Outbound Traffic | 61440 GB/month |
IPv4 | 1 |
CPU and System Topology #
Server Description #
A high-density GPU server featuring dual NVIDIA H100 accelerators and massive system memory for demanding artificial intelligence and parallel computing workloads.
UpCloud GPU-24xCPU-480GB-2xH100 is a high-end GPU-accelerated server designed for intensive computational tasks. It features 24 Intel Xeon 8462Y+ physical cores running at 2.0 GHz, paired with 480.0 GB of system memory and two NVIDIA Hopper H100 GPUs delivering 160 GB of total VRAM. The server lacks local storage, requiring network-attached storage solutions. Benchmark results show top-tier performance in LLM inference, with prompt processing speeds of 10457.59 tokens/sec, alongside strong memory bandwidth and database operations. Supported by advanced hardware instruction sets like Intel AMX and AVX-512, this server is optimized for parallel processing. It is best suited for deep learning, large language model inference, high-performance computing, and memory-intensive database workloads.
Economics #
Performance #
GPU Bandwidth and Latency #
| Node (all GPUs) | |
|---|---|
Node baseline directional bandwidth | 61.3 GB/s |
Node GPU-to-host bandwidth | 100.6 GB/s |
Node host-to-GPU bandwidth | 108.5 GB/s |
| Peer-to-peer | |
|---|---|
GPU-to-GPU P2P duplex bandwidth | 393.1 GB/s |
GPU-to-GPU P2P gather bandwidth | 397.6 GB/s |
GPU-to-GPU P2P latency | 827 ns |
GPU-to-GPU P2P bandwidth | 397.4 GB/s |
| Single GPU slot | |
|---|---|
Per-GPU GPU-to-host bandwidth | 55.2 GB/s |
Per-GPU host-to-GPU bandwidth | 55.2 GB/s |
Per-GPU host-device latency | 1,179 ns |
Per-GPU device memory copy bandwidth | 1489.5 GB/s |
| Benchmark Environment | |
|---|---|
Driver Version | 595.71.05 |
CUDA Version (driver) | 13.2 |
nvbandwidth Version | v0.8 |
GPU Count | 2 |
P2P Supported | Yes |
| Efficiency | |
|---|---|
SM/CE copy efficiency | 0.62 |
Memory Bandwidth#
Compression #
OpenSSL #
Geekbench Single-Core #
Geekbench Multi-Core #
Passmark CPU Scores #
| BENCHMARK | SCORE |
|---|---|
Mark | 55,981 |
Compression | 649,290 |
Encryption | 36,835 |
Extended Instructions | 68,492 |
Floating Point Maths | 173,218 |
Integer Maths | 146,595 |
Physics | 8,483 |
Prime Numbers | 497 |
Single Threaded | 3,288 |
String Sorting | 89,212 |
Passmark Memory Scores #
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 2,060 |
Database Operations | 24,760 |
Memory Latency | 85 |
Memory Read Cached | 29,236 |
Memory Read Uncached | 8,422 |
Memory Write | 7,764 |
Stress-ng Stressors #
| CPU integer | Single | Multi | Scaling |
|---|---|---|---|
atomic | 225.89 | 253.57 | 1.12× |
bitops | 169,861 | 4,009,767 | 23.61× |
branch | 157,772 | 3,753,054 | 23.79× |
funccall | 857.91 | 20,211 | 23.56× |
funcret | 14,193 | 340,105 | 23.96× |
hash | 202,874 | 4,804,820 | 23.68× |
intmath | 72,852 | 1,731,406 | 23.77× |
nop | 301,556 | 7,147,132 | 23.70× |
prime | 533,812 | 12,551,487 | 23.51× |
rotate | 113,412 | 2,701,460 | 23.82× |
str | 1,071,338 | 25,146,407 | 23.47× |
wcs | 792,996 | 18,356,933 | 23.15× |
| Cryptography | Single | Multi | Scaling |
|---|---|---|---|
crypt | 3,856 | 86,079 | 22.32× |
| Compression | Single | Multi | Scaling |
|---|---|---|---|
jpeg | 960.01 | 22,376 | 23.31× |
zlib | 76.58 | 1,500 | 19.58× |
| Hypervisor | Single | Multi | Scaling |
|---|---|---|---|
clock | 52,760 | 228,259 | 4.33× |
clone | 417.67 | 7,851 | 18.80× |
context | 5,207 | 123,522 | 23.72× |
cpu-sched | 59.99 | 1,557 | 25.96× |
eventfd | 75,830 | 894,529 | 11.80× |
fault | 31,719 | 166,099 | 5.24× |
fork | 4,706 | 58,758 | 12.49× |
getrandom | 68,550 | 1,620,534 | 23.64× |
hrtimers | 175,359 | 4,547,086 | 25.93× |
mprotect | 733,981 | 9,501,054 | 12.94× |
mtx | 18,682,077 | 1,697,881,055 | 90.88× |
munmap | 3,449 | 50,951 | 14.77× |
null | 810,122 | 19,303,363 | 23.83× |
pipe | 957,210 | 14,450,798 | 15.10× |
priv-instr | 847,086 | 9,752,577 | 11.51× |
resched | 12,862,865 | 9,702,362 | 0.75× |
switch | 110,260 | 8,519,194 | 77.26× |
timermix | 257,814 | 6,030,302 | 23.39× |
tlb-shootdown | 11,316 | 116,441 | 10.29× |
tsc | 662,654 | 15,645,799 | 23.61× |
usersyscall | 729,043 | 9,459,430 | 12.98× |
vdso | 90,776,650 | 2,143,585,789 | 23.61× |
vfork | 34,315 | 184,291 | 5.37× |
x86syscall | 9,079,368 | 214,983,266 | 23.68× |
yield | 28,863,724 | 37,945,159 | 1.31× |
zero | 5,128,496 | 120,520,100 | 23.50× |
| CPU float/SIMD | Single | Multi | Scaling |
|---|---|---|---|
eigen | 18,725 | 440,892 | 23.55× |
expmath | 4,039 | 95,260 | 23.58× |
fma | 1,579,641 | 37,219,193 | 23.56× |
fp | 353.98 | 8,296 | 23.44× |
fractal | 8 | 186.62 | 23.33× |
hyperbolic | 4,660 | 109,457 | 23.49× |
logmath | 5,962 | 140,680 | 23.60× |
matrix | 6,018 | 147,146 | 24.45× |
matrix-3d | 913.51 | 10,235 | 11.20× |
monte-carlo | 291.26 | 6,970 | 23.93× |
mpfr | 1,972 | 46,884 | 23.77× |
powmath | 2,218 | 52,571 | 23.70× |
trig | 3,017 | 71,948 | 23.84× |
veccmp | 29,523 | 695,007 | 23.54× |
vecfp | 2,735 | 64,255 | 23.49× |
vecmath | 4,476 | 106,422 | 23.78× |
vecshuf | 4,403 | 104,089 | 23.64× |
vecwide | 95,846 | 2,264,668 | 23.63× |
| Algorithms | Single | Multi | Scaling |
|---|---|---|---|
bitonicsort | 10.2 | 240 | 23.53× |
bsearch | 327.63 | 7,777 | 23.74× |
bubblesort | 1.2 | 28.8 | 24.00× |
fibsearch | 347.51 | 8,370 | 24.09× |
heapsort | 11.6 | 267.8 | 23.09× |
hsearch | 9,662 | 231,007 | 23.91× |
insertionsort | 14.6 | 341.4 | 23.38× |
malloc | 2,983,629 | 34,479,676 | 11.56× |
mcontend | 68.74 | 3,926 | 57.12× |
mergesort | 35.2 | 831.79 | 23.63× |
qsort | 25.2 | 590.59 | 23.44× |
skiplist | 6,171 | 147,924 | 23.97× |
tree | 2 | 41.16 | 20.58× |
| Memory | Single | Multi | Scaling |
|---|---|---|---|
cache | 675,760 | 1,553,756 | 2.30× |
cachehammer | 164,934 | 4,749,213 | 28.79× |
cacheline | 51.37 | 1,186 | 23.09× |
l1cache | 357.85 | 8,667 | 24.22× |
memcpy | 505.54 | 11,916 | 23.57× |
memrate | 0.13 | 3.16 | 24.31× |
memthrash | 230.92 | 1,058 | 4.58× |
ptr-chase | 36,122,496 | 255,746,900 | 7.08× |
spinmem | 222.79 | 1,391 | 6.24× |
stream | 161.18 | 38,328 | 237.80× |
vm | 133,635 | 294,885 | 2.21× |
Stress-ng Raw Scores #
Stress-ng Relative Multicore Performance #
Static Web Server#
Redis#
Alternatives #
Servers of the Same Family #
| INSTANCE | vCPUs | MEMORY | Accelerators |
|---|---|---|---|
| GPU-8xCPU-64GB-1xL40S | 8 | 64 GiB | 1 |
| GPU-12xCPU-128GB-1xL40S | 12 | 128 GiB | 1 |
| GPU-12xCPU-128GB-2xL40S | 12 | 128 GiB | 2 |
| GPU-16xCPU-192GB-1xL40S | 16 | 192 GiB | 1 |
| GPU-16xCPU-192GB-2xL40S | 16 | 192 GiB | 2 |
| GPU-20xCPU-256GB-1xL40S | 20 | 256 GiB | 1 |
| GPU-20xCPU-256GB-2xL40S | 20 | 256 GiB | 2 |
Similar Servers #
| INSTANCE | VENDOR | vCPUs | MEMORY | Accelerators |
|---|