| Newsgroups |
gmane.linux.lfs.automated |
| Message-ID |
<[email protected]> |
On 18/06/2022 00:01, Bruce Dubbs ([email protected] via alfs-discuss
Mailing List) wrote:
> On 6/17/22 15:17, Dragan ([email protected] via alfs-discuss Mailing
> List) wrote:
>>
>> On 17/06/2022 01:57, Bruce Dubbs ([email protected] via
>> alfs-discuss Mailing List) wrote:
>>> On 6/16/22 16:04, Dragan ([email protected] via alfs-discuss Mailing
>>> List) wrote:
>>>
>>>> Thanks for the scripts.
>>>>
>>>> About timing: SBU of 75 sec was based on -j1 and not -j16. I have
>>>> set binutils to be built without optimisation.
>>>> On the same system in VM I got SBU between 20 aand 22 when building
>>>> using my own scripts and that is inclusief unpacking source code
>>>> and logging using -j16. But maintaining scripts between dev
>>>> releases is just to much time consuming and mistake prone.
>>>>
>>>> On wsl using -j24 I got times between 18,9 and 19,5 sec using full
>>>> scale virtualization available using the same script. But with wsl
>>>> enabled is Virtual Box practically useless, it feels like "good old
>>>> time" of 8080 and I have thrown it away.
>>>>
>>>> What have realy surprised me is surprisingly low time of Kernel
>>>> build 93 seconds. I have already booted in the system and it's
>>>> looks ok. I will take deeper look at the issue in chroot.
>>>>
>>>> Total build time is not issue. Multitasking with some power to spare...
>>>
>>> That HW is interesting. What is your output of
>>>
>>> $ lscpu | head -n18
>>>
>>> What I have is:
>>>
>>> Architecture: x86_64
>>> CPU op-mode(s): 32-bit, 64-bit
>>> Address sizes: 43 bits physical, 48 bits virtual
>>> Byte Order: Little Endian
>>> CPU(s): 24
>>> On-line CPU(s) list: 0-23
>>> Vendor ID: AuthenticAMD
>>> Model name: AMD Ryzen 9 3900X 12-Core Processor
>>> CPU family: 23
>>> Model: 113
>>> Thread(s) per core: 2
>>> Core(s) per socket: 12
>>> Socket(s): 1
>>> Stepping: 0
>>> Frequency boost: enabled
>>> CPU max MHz: 4672.0698
>>> CPU min MHz: 2200.0000
>>> BogoMIPS: 7585.83
>>>
>>> -- Bruce
>>
>> I have today finished my fourth build with logging an all possible
>> tests run once and al logging enabled duration just above three hours
>> while I have used host quite intensively.
>>
>> But my fifth build while I have not used host at al finished in 124.1
>> SBU of 19 sec as defined by binutils compiled with -j16. If I have
>> didn't calculated wrongly that means build time of 39 min 30 sec
>> build time. I will submit report to the list tomorrow.
>>
>> That was real unexpected (from my side) for VM. My virtual hardware
>> spec is below.
>>
>> lscpu | head -n18
>> Architecture: x86_64
>> CPU op-mode(s): 32-bit, 64-bit
>> Address sizes: 46 bits physical, 48 bits virtual
>> Byte Order: Little Endian
>> CPU(s): 16
>> On-line CPU(s) list: 0-15
>> Vendor ID: GenuineIntel
>> Model name: 12th Gen Intel(R) Core(TM) i9-12900K
>> CPU family: 6
>> Model: 151
>> Thread(s) per core: 1
>> Core(s) per socket: 16
>> Socket(s): 1
>> Stepping: 2
>> BogoMIPS: 6374.38
>> 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 rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc
>> cpuid tsc_known_freq pni pclmulqdq vmx ssse3 cx16 pcid sse4_1 sse4_2
>> x2apic movbe popcnt aes xsave avx rdrand hypervisor lahf_lm abm
>> 3dnowprefetch invpcid_single tpr_shadow vnmi flexpriority vpid
>> fsgsbase avx2 invpcid rdseed clflushopt md_clear flush_l1d
>> arch_capabilities
>> Virtualization: VT-x
>>
>> Hypervisor vendor: KVM
>>
>> And on the host extract from CPU-Z report:
>>
>> Processors Information
>> -------------------------------------------------------------------------
>>
>> Socket 1 ID = 0
>> Number of cores 16 (max 64)
>> Number of threads 24 (max 24)
>> Hybrid yes, 2 coresets
>> Core Set 0 P-Cores, 8 cores, 16 threads
>> Core Set 1 E-Cores, 8 cores, 8 threads
>> Manufacturer GenuineIntel
>> Name Intel Core i9 12900K
>> Codename Alder Lake
>> Specification 12th Gen Intel(R) Core(TM) i9-12900K
>> Package Socket 1700 LGA
>> CPUID 6.7.2
>> Extended CPUID 6.97
>> Core Stepping C0
>> Technology 10 nm
>> Tjmax 100.0 °C
>> Core Speed 3187.2 MHz
>> Stock frequency 3200 MHz
>> Max frequency 5200 MHz
>> Instructions sets MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1,
>> SSE4.2, EM64T, VT-x, AES, AVX, AVX2, FMA3, SHA
>> L1 Data cache 8 x 48 KB (12-way, 64-byte line) + 8 x 32
>> KB (8-way, 64-byte line)
>> L1 Instruction cache 8 x 32 KB (8-way, 64-byte line) + 8 x 64
>> KB (8-way, 64-byte line)
>> L2 cache 8 x 1.25 MB (10-way, 64-byte line) + 2 x 2 MB
>> (16-way, 64-byte line)
>> L3 cache 30 MB (12-way, 64-byte line)
>> Max CPUID level 00000020h
>> Max CPUID ext. level 80000008h
>> FID/VID Control yes
>>
>> Dragan
>>
>> PS: I have postponed build of new machine waiting for Alder Lake
>> because of performance.
>
> Very interesting. I'll have to consider getting one of those.
>
> -- Bruce
My advice is to build your own machine if you can. I'm using Z690 UD
DDR4 motherboard with 32 GB DDR4 memory
and old NVIDIA GeForce GTX 1050 Ti video card. I'm planing to switch to
onboard Intel(R) UHD Graphics 770. More than enough firepower there for
my purposes.
You can go for DDR5 memory for 2 to 5% increase in performance but I
don't believe that price/performance ratio will be justified you better
double the memory and invest difference in motherboard price in one or
two fast hard drive.
Dragan
--
http://lists.linuxfromscratch.org/sympa/info/alfs-discuss
Unsubscribe: See the above information page