![]() |
|
|
#1 |
|
Aug 2002
7·1,237 Posts |
YOLO?
This build will make very little sense from a price-to-performance POV, but we think it will be an interesting journey.
We don't have any specific goals (yet) other than to have fun. We haven't built a long-term computer in a very long time, so we will keep this setup for five years. (That way we can kinda justify the costs involved!) We are toying with the idea of liquid cooling. We will first see how well the system does with air cooling. If you have any questions please ask. Also, we appreciate tips and suggestions. We will list the prices we paid for components including shipping and taxes. We think that in a few years this data will be fun (?) to look back on. What we are building will not have bleeding-edge hardware. Our number one priority is stability/reliability. We won't be overclocking except to run the memory at XMP. Our thought process for all of this is a bit weird. Over time we will try to explain why we are choosing specific components and stuff.
|
|
|
|
|
|
#2 |
|
Aug 2002
7·1,237 Posts |
1× https://www.gskill.com/product/165/3...256GB-(8x32GB)
https://www.tomshardware.com/reviews...les-get-faster $1330.41 including shipping and taxes.
|
|
|
|
|
|
#3 |
|
Aug 2002
7×1,237 Posts |
https://www.techpowerup.com/gpu-specs/quadro-rtx-4000.c3336 https://hothardware.com/reviews/nvidia-quadro-rtx-4000-review https://www.storagereview.com/review/nvidia-quadro-rtx-4000-review https://www.servethehome.com/nvidia-quadro-rtx-4000-review-a-versatile-ai-and-professional-gpu/ $766.50 including shipping and taxes.
|
|
|
|
|
|
#4 |
|
Aug 2002
7·1,237 Posts |
1× https://rog.asus.com/us/motherboards...-encore-model/
https://www.guru3d.com/articles-page...re-review.html $828.74 including shipping and taxes.
|
|
|
|
|
|
#5 |
|
"Serge"
Mar 2008
San Diego, Calif.
32·7·163 Posts |
Maybe a naive question: but how would such a high end build rank against a server-class build (and with ECC that comes with it)? Have you considered to build a server?
Goes without saying: that is an intimidatingly gusto build.
|
|
|
|
|
|
#6 | |
|
Aug 2002
207238 Posts |
https://blogs.gnome.org/uraeus/2021/...orkstation-34/
Quote:
|
|
|
|
|
|
|
#7 | |
|
Aug 2002
7·1,237 Posts |
Quote:
Enterprise-level hardware gets really exotic and really expensive really fast. We are looking at this as a HEDT/enthusiast computer, with slightly exotic hardware. Maybe top-of-the-line-but-not-server stuff? Enthusiast hardware looks cooler, too.
|
|
|
|
|
|
|
#8 |
|
Aug 2002
7×1,237 Posts |
1× https://www.intel.com/content/www/us...fications.html
https://www.tomshardware.com/reviews...ore-i9-10980xe https://www.guru3d.com/articles-page...-review,1.html https://www.anandtech.com/show/15039...10980xe-review $999.99 including shipping and taxes.
|
|
|
|
|
|
#9 |
|
Romulan Interpreter
"name field"
Jun 2011
Thailand
1029110 Posts |
Go on aliexpress and search "LGA 2011 set".
The idea is that after the "spectre" issue, as well as Intel launching their new series of Xeons (E7, etc), the market was "flooded" with E5 v1, v2, and v3 Xeons that you practically get for free. I mean, they have wagons full of such toys (both second hand and new) which they sell for scrap or melt to recover the gold (which is not really profitable...). So some "entrepreneurs" decided to make cheap mobos for them, to sell them (in fact, to sell their mobos!) and you can get a full "set" (mobo, cpu, plus ECC RAM !!) by only paying the price of the mobo. That means, like 90 bucks for the whole set, including a 8-cores E5-2450 v2 Xeon that runs at 3G3 and 8 gigs of ECC RAM. If you afford to double that price, you may even get a 12 cores and 16 gigs of ECC RAM. Some people here bought them and they really fly at LL and P-1. The only issue is that they are power hungry... Of course there are some risks, and there are known problems with the mobos (did I say "cheap"?) like for example the SATA are too slow (there are many youtube videos that discuss the issues and the risks, try the same search, or try "lga 2011 vs lga 1356" on youtube). (edit: yes, read well the descriptions, when they say they ship the cpu's "random", you may get a lga 1356 with your 2011 mobo, which would be a serious waste). You buy 10, add some coolers and a shelf, and you have a 80 or 120 cores machine for a thousand bucks, crunching primes and melting your kilowatts... Last fiddled with by LaurV on 2021-04-11 at 05:15 |
|
|
|
|
|
#10 |
|
∂2ω=0
Sep 2002
República de California
22·2,939 Posts |
|
|
|
|
|
|
#11 |
|
Aug 2002
7×1,237 Posts |
Code:
$ lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
Address sizes: 46 bits physical, 48 bits virtual
CPU(s): 36
On-line CPU(s) list: 0-35
Thread(s) per core: 2
Core(s) per socket: 18
Socket(s): 1
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 85
Model name: Intel(R) Core(TM) i9-10980XE CPU @ 3.00GHz
Stepping: 7
CPU MHz: 3000.000
CPU max MHz: 4800.0000
CPU min MHz: 1200.0000
BogoMIPS: 6000.00
Virtualization: VT-x
L1d cache: 576 KiB
L1i cache: 576 KiB
L2 cache: 18 MiB
L3 cache: 24.8 MiB
NUMA node0 CPU(s): 0-35
Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; TSX disabled
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon p
ebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcn
t tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpri
ority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveo
pt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512_vnni md_clear flush_l1d arch_capabi
lities
Code:
$ cat results.bench.txt | grep 6144 Timings for 6144K FFT length (1 core, 1 worker): 16.34 ms. Throughput: 61.19 iter/sec. Timings for 6144K FFT length (2 cores, 1 worker): 9.09 ms. Throughput: 110.02 iter/sec. Timings for 6144K FFT length (3 cores, 1 worker): 6.17 ms. Throughput: 162.12 iter/sec. Timings for 6144K FFT length (4 cores, 1 worker): 4.72 ms. Throughput: 211.66 iter/sec. Timings for 6144K FFT length (5 cores, 1 worker): 3.88 ms. Throughput: 257.52 iter/sec. Timings for 6144K FFT length (6 cores, 1 worker): 3.24 ms. Throughput: 308.30 iter/sec. Timings for 6144K FFT length (7 cores, 1 worker): 3.08 ms. Throughput: 324.85 iter/sec. Timings for 6144K FFT length (8 cores, 1 worker): 2.72 ms. Throughput: 367.45 iter/sec. Timings for 6144K FFT length (9 cores, 1 worker): 2.51 ms. Throughput: 397.73 iter/sec. Timings for 6144K FFT length (10 cores, 1 worker): 2.35 ms. Throughput: 425.97 iter/sec. Timings for 6144K FFT length (11 cores, 1 worker): 2.24 ms. Throughput: 445.69 iter/sec. Timings for 6144K FFT length (12 cores, 1 worker): 2.16 ms. Throughput: 462.68 iter/sec. Timings for 6144K FFT length (13 cores, 1 worker): 2.10 ms. Throughput: 476.71 iter/sec. Timings for 6144K FFT length (14 cores, 1 worker): 2.02 ms. Throughput: 494.89 iter/sec. Timings for 6144K FFT length (15 cores, 1 worker): 1.96 ms. Throughput: 510.61 iter/sec. Timings for 6144K FFT length (16 cores, 1 worker): 1.93 ms. Throughput: 519.39 iter/sec. Timings for 6144K FFT length (17 cores, 1 worker): 1.90 ms. Throughput: 525.97 iter/sec. Timings for 6144K FFT length (18 cores, 1 worker): 1.88 ms. Throughput: 531.20 iter/sec. |
|
|
|