logo

hpc8a.96xlarge by Amazon Web Services

hpc8a.96xlarge is a High performance computing [AMD processors] Gen8 96xlarge server offered by Amazon Web Services with 192 vCPUs, 768 GiB of memory and 0 GB of storage. The pricing starts at 7.92 USD per hour.
192 vCPU
768 GiB Memory
Spare SCore
713516
(All-cores)
3790
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
hpc8a.96xlarge
Description
High performance computing [AMD processors] Gen8 96xlarge
Family
hpc8a
Hw Virt
Status
active
Observed At
2026-07-29T08:53:58.074118

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
- 7.92 USD/h
Stockholm (SE) / eu-north-1
- 8.4977 USD/h
Tokyo (JP) / ap-northeast-1
- 10.2299 USD/h

Processor

vCPUs
192
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
192
CPU Speed
4.5 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9R45
CPU L1D Cache
48 KiB
CPU L1D Cache Total
9 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
6 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
192 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
768 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, nonstop_tsc, cpuid, extd_apicid, amd_dcm, 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, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, topoext, perfctr_core, 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, avx_vnni, avx512_bf16, clzero, xsaveerptr, rdpru, wbnoinvd, arat, avx512vbmi, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, movdiri, movdir64b, fsrm, avx512_vp2intersect, flush_l1d
Ecpus
188.3
Scalability
98.07

System Resources and Accelerators

MEMORY
Memory Amount
768 GiB
Memory Amount Actual
768 GiB
Memory Generation
DDR5
Memory Speed
6400 Mhz
GPU
GPU Count
0
GPU Memory Min
0 MiB
GPU Memory Total
0 MiB
GPUs
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Network Speed Baseline
      300 Gbps
      Network Speed Max
      300 Gbps
      Network Storage Speed Baseline
      0.087 Gbps
      Network Storage Speed Max
      2.085 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      Server Description

      A dedicated 192-core high-performance computing platform featuring high-speed DDR5 memory and 300 Gbps network bandwidth for intensive parallel processing.

      Compute OptimizedGeneral Purpose

      Amazon Web Services hpc8a.96xlarge is a high-performance computing instance featuring 192 dedicated physical cores on an AMD EPYC 9R45 processor running at 4.5 GHz. Built on the x86_64 architecture and managed by the Nitro hypervisor, it includes 768.0 GB of high-speed DDR5 memory but lacks local storage and GPU accelerators. The instance delivers top-tier CPU and memory bandwidth performance, ranking in the top 10% across stress-ng, Geekbench, and database benchmarks. With a baseline network bandwidth of 300 Gbps, it is highly optimized for compute-intensive workloads. The lack of local storage requires reliance on network-attached storage, representing a key architectural tradeoff. This instance is best suited for high-performance computing, scientific simulations, and parallel processing workloads.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      15.5Score
      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) 59,038,196 ops/sec 1,896,415 ops/sec 31.1 50.00% 50.00% +458.00%
      Redis RPS (pipeline=16, SET) 380,823,271 ops/sec 11,539,523 ops/sec 33 20.00% 20.00% +101.00%
      PassMark Memory Mark (composite) 3,017 2,411 1.25 10.00% 10.00% +2.26%
      Memory bandwidth (read, 16 MB ~ L3) 1,316,625 MB/sec 107,368 MB/sec 12.3 10.00% 10.00% +28.50%
      PassMark single-thread CPU 3,833 Mops/s 2,363 Mops/s 1.62 10.00% 10.00% +4.94%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,848

      Geekbench Multi-Core

      Score: 26,076

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 192943
      Compression
      		 5580930
      Encryption
      		 297617
      Extended Instructions
      		 485306
      Floating Point Maths
      		 1431109
      Integer Maths
      		 1457953
      Physics
      		 64486
      Prime Numbers
      		 4617
      Single Threaded
      		 3833
      String Sorting
      		 756922

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 3017
      Database Operations
      		 46618
      Memory Latency
      		 79
      Memory Read Cached
      		 33900
      Memory Read Uncached
      		 32323
      Memory Write
      		 28918

      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

      INSTANCEvCPUsMEMORYGPUs

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYGPUs

      hpc8a.96xlarge FAQs