ЭВМ клуб
228 subscribers
299 photos
14 videos
57 files
208 links
Обсуждаем любые процессоры, архитектуры на русском. #x86, #arm, #mips, #e2k, #ia64, #riscv, #sparc, #power, #m68k
加入频道
Forwarded from tёmix
❯ ./convert_to_json.sh amd64
"amd64": {
"Coremark": 53294.573643,
"CoremarkMP": 1103344.513055,
"Dhrystone": 50797.91,
"Linpack": 15982.85,
"Scimark2": 6294.56,
"Whetstone": 14243.247,
"MP MFLOPS": 3290562,
"WhetstoneMP": 359670,
"WhetstoneMP Pessimistic": 356467,
"Stream ST Copy": 37155.5
"Stream ST Scale": 33257.0
"Stream ST Add": 36048.2
"Stream ST Triad": 36047.6
"Stream MT Copy": 50906.6
"Stream MT Scale": 33926.1
"Stream MT Add": 37262.7
"Stream MT Triad": 37161.8
"SuperPI 4M": 3.41
"gsynth": 275.725
"LLoops maximum": -1
"LLoops average": 8928.93
"LLoops geometric": 8278.23
"LLoops harmonic": 5942.33
"LLoops minimum": 2421.35
}
Forwarded from tёmix
❯ lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 48 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 32
On-line CPU(s) list: 0-31
Vendor ID: AuthenticAMD
Model name: AMD Ryzen 9 7950X 16-Core Processor
CPU family: 25
Model: 97
Thread(s) per core: 2
Core(s) per socket: 16
Socket(s): 1
Stepping: 2
Frequency boost: enabled
CPU(s) scaling MHz: 23%
CPU max MHz: 5881.0000
CPU min MHz: 400.0000
BogoMIPS: 8982.62
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 nonstop_tsc cpuid
extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3d
nowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bm
i2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_
mbm_local avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload
vgif x2avic v_spec_ctrl avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid overflow_recov succor smca fsrm flush_l1d
Virtualization features:
Virtualization: AMD-V
Caches (sum of all):
L1d: 512 KiB (16 instances)
L1i: 512 KiB (16 instances)
L2: 16 MiB (16 instances)
L3: 64 MiB (2 instances)
NUMA:
NUMA node(s): 1
NUMA node0 CPU(s): 0-31
Vulnerabilities:
Itlb multihit: Not affected
L1tf: Not affected
Mds: Not affected
Meltdown: Not affected
Mmio stale data: Not affected
Retbleed: Not affected
Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected
Srbds: Not affected
Tsx async abort: Not affected
ЭВМ клуб
ЕС1033-ЭВМ.pdf
ЕС 1033 book.pdf
1000.8 KB
Я тут решил начать оцифровывать книжку по ЕС ЭВМ, как вам?) Фанатом мейнфреймов стал))
🔥6
Сравнение теста ZHAOXIN KaiXian KX-6640MA от Д. Бачило с Эльбрус 8СВ 1550 МГц: https://browser.geekbench.com/v4/cpu/compare/15659957?baseline=16637381

https://browser.geekbench.com/v4/cpu/compare/15659957?baseline=16637355
👏5
Бенчмарки процессора ZHAOXIN KaiXian KX-6640MA в 7z

7-Zip 22.01 (x64) : Copyright (c) 1999-2022 Igor Pavlov : 2022-07-15

Windows 10.0 19044
x64 7.B00 cpus:4 128T f:F11082774C
ZHAOXIN KaiXian [email protected]+GHz (307B0)

1T CPU Freq (MHz): 2494 2436 2540 2575 2567 2287 2476
2T CPU Freq (MHz): 200% 2186 200% 2185

RAM size: 7669 MB, # CPU hardware threads: 4
RAM usage: 889 MB, # Benchmark threads: 4

Compressing | Decompressing
Dict Speed Usage R/U Rating | Speed Usage R/U Rating
KiB/s % MIPS MIPS | KiB/s % MIPS MIPS

22: 6987 295 2302 6798 | 129162 398 2771 11019
23: 6745 308 2229 6873 | 126901 397 2767 10981
24: 6625 315 2261 7124 | 121533 391 2726 10665
25: 6499 322 2306 7421 | 121551 397 2726 10818
---------------------------------- | ------------------------------
Avr: 6714 310 2275 7054 | 124787 396 2748 10871
Tot: 353 2511 8962

7-Zip 22.01 (x64) : Copyright (c) 1999-2022 Igor Pavlov : 2022-07-15

mt1
Windows 10.0 19044
x64 7.B00 cpus:4 128T f:F11082774C
ZHAOXIN KaiXian [email protected]+GHz (307B0)

1T CPU Freq (MHz): 2479 2508 2497 2542 2566 2574 2550

RAM size: 7669 MB, # CPU hardware threads: 4
RAM usage: 437 MB, # Benchmark threads: 1

Compressing | Decompressing
Dict Speed Usage R/U Rating | Speed Usage R/U Rating
KiB/s % MIPS MIPS | KiB/s % MIPS MIPS

22: 2464 100 2398 2397 | 38482 100 3296 3286
23: 2396 100 2447 2442 | 37781 100 3267 3270
24: 2314 100 2493 2488 | 36768 100 3227 3228
25: 1834 98 2133 2094 | 37211 100 3328 3312
---------------------------------- | ------------------------------
Avr: 2252 99 2368 2355 | 37560 100 3280 3274
Tot: 100 2824 2815
🔥1🤔1
Сравнение Эльбрус-16С и Байкал-S
👍12👎21
да, похоже на то; вот на инженерном e16c (60 битых пикселей строк кэша) с 8x Micron MTA18ASF2G72PZ-3G2J3 (DDR4-3200) на 3200, бутом от 15.09.2022 и поднятым десктопом (с которого опять же и пишу):

e16c:~/src> OMP_NUM_THREADS=4 ./stream
-------------------------------------------------------------
STREAM version $Revision: 5.10 $
-------------------------------------------------------------
This system uses 8 bytes per array element.
-------------------------------------------------------------
Array size = 10000000 (elements), Offset = 0 (elements)
Memory per array = 76.3 MiB (= 0.1 GiB).
Total memory required = 228.9 MiB (= 0.2 GiB).
Each kernel will be executed 10 times.
The *best* time for each kernel (excluding the first iteration)
will be used to compute the reported bandwidth.
-------------------------------------------------------------
Number of Threads requested = 4
Number of Threads counted = 4
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 1531 microseconds.
(= 1531 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function Best Rate MB/s Avg time Min time Max time
Copy: 78508.3 0.002084 0.002038 0.002160
Scale: 75760.7 0.002138 0.002112 0.002176
Add: 87685.8 0.002762 0.002737 0.002820
Triad:
87746.9 0.002770 0.002735 0.002862
-------------------------------------------------------------
Solution Validates: avg error less than 1.000000e-13 on all three arrays
https://browser.geekbench.com/v5/cpu/compare/12234693?baseline=12917278

Внимание: сравнение с 2х процессорным 48 ядерным процессором TaiShan200
Провёл тесты HPL (зелёное сам, остальное считал)
HPL Benchmark     
Cpu Year Freq Cores 1 thread Multithread
🔹 Elbrus 2C+ 2011 500 2 3.8 6.8
🔹 Elbrus 4C 2014 800 4 6 21.6
🔹 Elbrus 1C+ 2015 1000 1 10 10.0
🔹 Elbrus 8C 2016 1300 8 13 96.00
🔹 Elbrus 8C 2016 1200 8 12 82.5
🔹 Elbrus 8CB 2018 1550 8 32.3 232.6
🔹 Elbrus 16C 2021 2000 16 39 561.6
🔹 Elbrus 2C3 2021 2000 2 39 70.2
🔹 Elbrus 12C 2022 2000 12 40 432.0
🟢 Baikal S 2022 2000 48 6.9 294.6
🔴 TaiShan 2020 2600 48 5.1 194

4C x4: https://2016.russianscdays.org/files/pdf16/373.pdf
8C : http://www.mcst.ru/files/5a9eb2/a10cd8/501810/000003/kim_a.k._perekatov_v.i._feldman_v.m._na_puti_k_rossiyskoy_ekzasisteme_plany_razrabotchikov2.pdf
8СВ: http://www.mes-conference.ru/data/year2020/pdf/D016.pdf
Kunpeng: https://yadi.sk/d/xQbqabor3l1p1w
Baikal: https://drive.google.com/file/d/1g_QMwhTo6uHtb5pR0ntY87JEkK3LyMux/view

Страница 74
👍2
ЭВМ клуб
https://browser.geekbench.com/v5/cpu/compare/12234693?baseline=12917278 Внимание: сравнение с 2х процессорным 48 ядерным процессором TaiShan200
Выходит, что ядра Kunpeng 920 TaiShan v110 базируются на основе Cortex-A72, но 7 нм техпроцесс.

Похоже, ядра состоят по 4 штуки на кластер

https://en.wikichip.org/wiki/hisilicon/microarchitectures/taishan_v110