725 字
4 分钟
双路 9754 计算服务器 与8*A800 GPU服务器 测试
非专业人士,仅供娱乐。
9754 服务器:
-
Processor : AMD EPYC 9754 128-Core Processor
-
_Num of Core : 256 Cor_e
-
Memory : 1024 GB
-
Storage : 1T NVMe
测试
CPU
root@VM-0-7-ubuntu:~# lscpuArchitecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 48 bits virtual Byte Order: Little EndianCPU(s): 256 On-line CPU(s) list: 0-255Vendor ID: AuthenticAMD Model name: AMD EPYC 9754 128-Core Processor CPU family: 25 Model: 160 Thread(s) per core: 1 Core(s) per socket: 256 Socket(s): 1 Stepping: 2 BogoMIPS: 4493.24 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 r dtscp lm rep_good nopl cpuid extd_apicid amd_dcm tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_d eadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr _core invpcid_single ibpb vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflus hopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 avx512_bf16 clzero xsaveerptr wbnoinvd arat avx512vbmi umip avx512_vb mi2 vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrmVirtualization features: Hypervisor vendor: KVM Virtualization type: fullCaches (sum of all): L1d: 8 MiB (256 instances) L1i: 8 MiB (256 instances) L2: 128 MiB (128 instances) L3: 256 MiB (16 instances)NUMA: NUMA node(s): 1 NUMA node0 CPU(s): 0-255Vulnerabilities: Itlb multihit: Not affected L1tf: Not affected Mds: Not affected Meltdown: Not affected Mmio stale data: Not affected Retbleed: Not affected Spec store bypass: Vulnerable Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Spectre v2: Mitigation; Retpolines, IBPB conditional, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected Srbds: Not affected Tsx async abort: Not affected
GeekBench 5

GeekBench 6

X265 BenchMark

UnixBench
核心太多,无法测试

8338+8*A800 服务器
-
Processor : 2*Intel(R) Xeon(R) Platinum 8338C CPU @ 2.60GHz
-
_Num of Core : 128 Cor_e
-
Memory : 1024 GB
-
Storage : 1.5T NVMe
-
GPU : 4*A800

CPU
ubuntu@VM-8-2-ubuntu:~/Geekbench-5.4.3-Linux$ lscpuArchitecture: x86_64CPU op-mode(s): 32-bit, 64-bitByte Order: Little EndianAddress sizes: 46 bits physical, 48 bits virtualCPU(s): 128On-line CPU(s) list: 0-127Thread(s) per core: 1Core(s) per socket: 64Socket(s): 2NUMA node(s): 2Vendor ID: GenuineIntelCPU family: 6Model: 106Model name: Intel(R) Xeon(R) Platinum 8338C CPU @ 2.60GHzStepping: 6CPU MHz: 2593.884BogoMIPS: 5187.76Hypervisor vendor: KVMVirtualization type: fullL1d cache: 3 MiBL1i cache: 2 MiBL2 cache: 80 MiBL3 cache: 96 MiBNUMA node0 CPU(s): 0-63NUMA node1 CPU(s): 64-127Vulnerability Itlb multihit: Not affectedVulnerability L1tf: Not affectedVulnerability Mds: Not affectedVulnerability Meltdown: Not affectedVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccompVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitizationVulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB fillingVulnerability Srbds: Not affectedVulnerability Tsx async abort: Not affectedFlags: 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 rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault invpcid_single ssbd ibrs ibpb ibrs _enhanced fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 wbnoinvd arat avx512vbmi umip avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx5 12_bitalg avx512_vpopcntdq arch_capabilities
GeekBench 5

GeekBench 6

X265 BenchMark

FIO 测试
Block Size | 4k (IOPS) | 64k (IOPS) |
---|---|---|
Read | 656.75 MB/s (164.1k) | 1.59 GB/s (24.9k) |
Write | 658.48 MB/s (164.6k) | 1.60 GB/s (25.0k) |
Total | 1.31 GB/s (328.8k) | 3.19 GB/s (49.9k) |
Block Size | 512k (IOPS) | 1m (IOPS) |
------ | --- ---- | ---- ---- |
Read | 2.12 GB/s (4.1k) | 2.27 GB/s (2.2k) |
Write | 2.23 GB/s (4.3k) | 2.42 GB/s (2.3k) |
Total | 4.35 GB/s (8.5k) | 4.69 GB/s (4.5k) |
UnixBench
核心太多,无法测试

双路 9754 计算服务器 与8*A800 GPU服务器 测试
https://catcat.blog/9754-a800.html