+- +-
Say hello if visiting :) by Gecko
11 Jan 2023, 07:43:05 pm

Seti is down again by Mike
09 Aug 2017, 10:02:44 am

Some considerations regarding OpenCL MultiBeam app tuning from algorithm view by Raistmer
11 Dec 2016, 06:30:56 am

Loading APU to the limit: performance considerations by Mike
05 Nov 2016, 06:49:26 am

Better sleep on Windows - new round by Raistmer
26 Aug 2016, 02:02:31 pm

Author Topic: optimized sources  (Read 548430 times)

Offline _heinz

  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 2117
Re: optimized sources
« Reply #525 on: 21 Dec 2009, 06:53:17 pm »
Thanks Papa

Nothing did help, my tunnel for the RV670, the tube for fresh air, a plate for airstream.
The REVO Cyclone can not cooling the FB-DIMM's down when I running 8 x akv8
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
roomtemp: 21 grd celsius
running:
8 x akv8
2 x collatz

Informationsliste   Wert
Sensor Eigenschaften   
Sensortyp   Dual ADT7490  (SMBus 2Ch, 2Eh)
GPU Sensortyp   Diode  (ATI-Diode)
Motherboard Name   Intel D5400XS
   
Temperaturen   
CPU1   57 °C  (135 °F)
CPU2   60 °C  (140 °F)
1. CPU / 1. Kern   53 °C  (127 °F)
1. CPU / 2. Kern   43 °C  (109 °F)
1. CPU / 3. Kern   49 °C  (120 °F)
1. CPU / 4. Kern   49 °C  (120 °F)
2. CPU / 1. Kern   47 °C  (117 °F)
2. CPU / 2. Kern   43 °C  (109 °F)
2. CPU / 3. Kern   45 °C  (113 °F)
2. CPU / 4. Kern   46 °C  (115 °F)
DIMM   79 °C  (174 °F)
GPU Diode   77 °C  (171 °F)
Temperatur 1   54 °C  (129 °F)
Temperatur 2   54 °C  (129 °F)
Temperatur 3   55 °C  (131 °F)
FB-DIMM1   92 °C  (198 °F)
FB-DIMM2   86 °C  (187 °F)
FB-DIMM3   82 °C  (180 °F)
FB-DIMM4   81 °C  (178 °F)

Seagate ST31000340NS   42 °C  (108 °F)
Seagate ST31000340NS   40 °C  (104 °F)
Seagate ST31000340NS   42 °C  (108 °F)
   
Kühllüfter   
CPU1   668 RPM
CPU2   655 RPM
North Bridge   4995 RPM
South Bridge   4182 RPM
DIMM   4285 RPM
Aux   1037 RPM
Grafikprozessor (GPU)   100%
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

full report with different runs is attached

[attachment deleted by admin]

Offline Pappa

  • Alpha Tester
  • Knight o' The Round Table
  • ***
  • Posts: 216
Re: optimized sources
« Reply #526 on: 21 Dec 2009, 11:37:08 pm »
imagine rather than a tube a "Funnel" large enough to mount a 120mm fan down to the memory fan.

I would almost be tempted to try a 120 mm fan with the larger airflow capacity. It is three times as much as the 55mm fan on the ram cooler. Teh funnel changing from 120mm to 55mm should cause teh air to accerate faster as it passes teh RMA ro carry heat away more effeciently.


Offline _heinz

  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 2117
Re: optimized sources
« Reply #527 on: 23 Dec 2009, 06:38:03 pm »
Thanks Papa for your reply.
Till I have done it, I run now a mixed work of wu's  to hold temps a little down.
4 x akv8,
4 x docking,
2 x collatz
~~~~~~~~~~~~~~~~
DIMM   78 °C  (172 °F)
FB-DIMM1   80 °C  (176 °F)
FB-DIMM2   75 °C  (167 °F)
FB-DIMM3   72 °C  (162 °F)
FB-DIMM4   69 °C  (156 °F)
DIMM   4163 RPM
-------------------------------------
roomtemp= 22 °C
EVO shows 24 °C and 4025 RPM on its LED display
Case is open.
 ;)


Offline _heinz

  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 2117
Re: optimized sources
« Reply #528 on: 02 Jan 2010, 07:15:03 pm »
no work from seti on all my machines now.
running collatz and milkyway...
time to compile something for the ION platform  :)
1>AP SSE3ATOM Win32 (Microsoft VC++ Environment)
1>Post Build revision number extraction
1>
1>APREV IS 298
1>Renaming Output Files
1>
1>Build log was saved at "file://C:\I\SC\apwk\astropulse\client\WinBuild\ICC11_2k8\Win32\Output_ext\ap_client\AP SSE3_ATOM\Intermediate\BuildLog.htm"
1>ap_client - 0 error(s), 0 warning(s)
========== Alles neu erstellen: 1 erfolgreich, Fehler bei 0, 0 übersprungen ==========

Compiled a special build of Astropulse for the ATOM Processor

Offline Raistmer

  • Working Code Wizard
  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 14349
Re: optimized sources
« Reply #529 on: 03 Jan 2010, 10:03:07 am »
could you attach it? I have Atom-based netbook so can test if there is any speed differencies.

Offline Jason G

  • Construction Fraggle
  • Knight who says 'Ni!'
  • *****
  • Posts: 8980
Re: optimized sources
« Reply #530 on: 03 Jan 2010, 10:12:58 am »
Go to the development thread  ;)

Offline _heinz

  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 2117
Re: optimized sources
« Reply #531 on: 03 Jan 2010, 02:41:58 pm »
for all others who have no access to the developer area:

What we can expect ?

testrun against our latest public published astropulse  ap_5.05r168_SSE3.exe
Quick timetable
 
WU : ap_18se08aa_B6_P1_00046_1LC25.wu
ap_5.05r168_SSE3.exe : 410.609 secs CPU
ap_5.05r303_SSE3_ICC_ATOM.exe : 340.719 secs CPU
Speedup     : 17.02%
Ratio       : 1.21 x
 
WU : Raistmer's_tiny.wu
ap_5.05r168_SSE3.exe : 150.547 secs CPU
ap_5.05r303_SSE3_ICC_ATOM.exe : 144.781 secs CPU
Speedup     : 3.83%
Ratio       : 1.04 x
 
WU : sigind_v5.wu
ap_5.05r168_SSE3.exe : 912.922 secs CPU
ap_5.05r303_SSE3_ICC_ATOM.exe : 727.484 secs CPU
Speedup     : 20.31%
Ratio       : 1.25 x

All results strongly similar.
This is basis for our further optimization process.
Some more in the developer area.
 ;)

Offline KarVi

  • Alpha Tester
  • Knight Templar
  • ***
  • Posts: 252
Re: optimized sources
« Reply #532 on: 03 Jan 2010, 06:34:36 pm »
I have been running the various R303 SSE3 builds on my Phenom.

Strangely enough none of the Atom builds work proberly, allthough they are SSE3, and should be compatible.

Some quick results:

Sigind.wu

ap_5.05r168_SSE3.exe : 845.703 secs CPU
ap_5.05r293_SSE.exe : 775.766 secs CPU
ap_5.05r303_SSE3_ICC_Qopt.exe : 694.078 secs CPU
ap_5.05r303_ATOM_ICC_Qopt.exe : 17.031 secs CPU
ap_5.05r303_SSE3_ICC_ATOM.exe : 0.031 secs CPU

The first 3 give strongly similar, the last 2 clearly don't.

But still 303_SSE3 is much faster than r168_SSE3 and 293_SSE.

[attachment deleted by admin]
A smile is the shortest distance between two peoble (Victor Borge).

Offline Jason G

  • Construction Fraggle
  • Knight who says 'Ni!'
  • *****
  • Posts: 8980
Re: optimized sources
« Reply #533 on: 03 Jan 2010, 06:42:58 pm »
Strangely enough none of the Atom builds work proberly, allthough they are SSE3, and should be compatible.
...
  'Should be', though I believe ATOM has an extra instruction (MOVBE) which is available in our 45nM Core2's (at least)... So ATOM builds are really ATOM specific, though they should run on later Intels OK. (The SSE3 Qopt one uses the generic SSE3 options ... nice to know it works on Phenom II)

Offline KarVi

  • Alpha Tester
  • Knight Templar
  • ***
  • Posts: 252
Re: optimized sources
« Reply #534 on: 03 Jan 2010, 06:47:44 pm »
Thats OK, but then they should be marked (S)SSE3 or something to that effect, since they are not really SSE3 compatible.

But I do like the improvements of the real SSE3 build, its all very promising :)
A smile is the shortest distance between two peoble (Victor Borge).

Offline Jason G

  • Construction Fraggle
  • Knight who says 'Ni!'
  • *****
  • Posts: 8980
Re: optimized sources
« Reply #535 on: 03 Jan 2010, 06:53:45 pm »
Thats OK, but then they should be marked (S)SSE3 or something to that effect, since they are not really SSE3 compatible.

I agree, that's why my ATOM one doesn't have SSE3 in the name  ;D
« Last Edit: 03 Jan 2010, 06:56:40 pm by Jason G »

Gecko_R7

  • Guest
Re: optimized sources
« Reply #536 on: 04 Jan 2010, 09:15:30 am »
FYI, started running a full bench suite on Atom N270 last eve via both Atom compiles of 303 apps.
Taking a while, but working fine.

Will upload result file when finished today.

FWIW, the netbook runs great w/ Win7 + 2GB.  I also did the obligatory system optimizing/uninstalls and service/process pruning.
Using latest google chrome as primary browser.  Very snappy & responsive for browsing and normal activities.
Am pretty impressed with the little guy.
It's kinda cute  :P  Should work well for my folks.

Offline Raistmer

  • Working Code Wizard
  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 14349
Re: optimized sources
« Reply #537 on: 04 Jan 2010, 04:52:49 pm »
still leaved damned Vista on my netbook so can't say it works fast, but Chrome is nice brower indeed. Started to use it on netbook firstly and now switched to it on my home desktop too :)

And for record: Atom is SSSE3-compatible CPU. In lacks x64 mode and SSE4.* only.

Gecko_R7

  • Guest
Re: optimized sources
« Reply #538 on: 04 Jan 2010, 05:12:22 pm »
still leaved damned Vista on my netbook so can't say it works fast, but Chrome is nice brower indeed. Started to use it on netbook firstly and now switched to it on my home desktop too :)

And for record: Atom is SSSE3-compatible CPU. In lacks x64 mode and SSE4.* only.

re: SSSE3.  Funny you mention that.  Yes, it supports it, but Intel associates their Atom-specific compiler switch as -xSSE3_ATOM.
It's supposed to make changes better suited for in-order execution processing of Atom.
Wonder why they attached that to SSE3 vs. SSSE3 instruction set?  :-\

Offline _heinz

  • Volunteer Developer
  • Knight who says 'Ni!'
  • *****
  • Posts: 2117
Re: optimized sources
« Reply #539 on: 04 Jan 2010, 05:40:09 pm »
a short look for all who are interested
Informationsliste   Wert
CPU-Eigenschaften   
CPU Typ   Intel Atom 230, 1600 MHz (12 x 133)
CPU Bezeichnung   Diamondville-SC
CPU stepping   C0
Befehlssatz   x86, x86-64, MMX, SSE, SSE2, SSE3, SSSE3
Vorgesehene Taktung   1600 MHz
Min / Max CPU Multiplikator   6x / 12x
Engineering Sample   Nein
L1 Code Cache   32 KB
L1 Datencache   24 KB
L2 Cache   512 KB  (On-Die, ECC, ASC, Full-Speed)
   
Multi CPU   
Motherboard ID   nVidia MCP79
CPU #1   Intel(R) Atom(TM) CPU 230 @ 1.60GHz, 1600 MHz
CPU #2   Intel(R) Atom(TM) CPU 230 @ 1.60GHz, 1600 MHz
   
CPU Technische Informationen   
Gehäusetyp   437 Ball FC-BGA
Gehäusegröße   2.2 cm x 2.2 cm
Transistoren   47 Mio.
Fertigungstechnologie   45 nm, CMOS, Cu, High-K + Metal Gate
Gehäusefläche   25 mm2
Typische Leistung   4 W @ 1.60 GHz
   
CPU Hersteller   
Firmenname   Intel Corporation
Produktinformation   http://www.intel.com/products/processor
   
CPU Auslastung   
1. CPU / 1. HTT Einheit   6 %
1. CPU / 2. HTT Einheit   6 %
~~~~~~~~~~~~~~~~~~~~~~~
Informationsliste   Wert
CPUID Eigenschaften   
CPUID Hersteller   GenuineIntel
CPUID CPU Name   Intel(R) Atom(TM) CPU 230 @ 1.60GHz
CPUID Revision   000106C2h
IA Markenzeichen ID   00h  (Unbekannt)
Plattform ID   E1h / MC 04h  (FCBGA8)
Microcode Update Revision   212
HTT / CMP Einheiten   2 / 1
Tjmax Temperatur   125 °C  (257 °F)
   
Befehlssatz   
64-bit x86-Erweiterung (AMD64, Intel64)   Unterstützt
AMD 3DNow!   Nicht unterstützt
AMD 3DNow! Professional   Nicht unterstützt
AMD 3DNowPrefetch   Nicht unterstützt
AMD Enhanced 3DNow!   Nicht unterstützt
AMD Extended MMX   Nicht unterstützt
AMD MisAligned SSE   Nicht unterstützt
AMD SSE4A   Nicht unterstützt
AMD SSE5   Nicht unterstützt
Cyrix Extended MMX   Nicht unterstützt
IA-64   Nicht unterstützt
IA MMX   Unterstützt
IA SSE   Unterstützt
IA SSE 2   Unterstützt
IA SSE 3   Unterstützt
IA Supplemental SSE 3   Unterstützt

IA SSE 4.1   Nicht unterstützt
IA SSE 4.2   Nicht unterstützt
IA AVX   Nicht unterstützt
IA FMA   Nicht unterstützt
IA AES Extensions   Nicht unterstützt
VIA Alternate Instruction Set   Nicht unterstützt
CLFLUSH Befehl   Unterstützt
CMPXCHG8B Befehl   Unterstützt
CMPXCHG16B Befehl   Unterstützt
Conditional Move Befehl   Unterstützt

LZCNT Befehl   Nicht unterstützt
MONITOR / MWAIT Befehl   Unterstützt
MOVBE Befehl   Unterstützt

PCLMULQDQ Befehl   Nicht unterstützt
POPCNT Befehl   Nicht unterstützt
RDTSCP Befehl   Nicht unterstützt
SYSCALL / SYSRET Befehl   Nicht unterstützt
SYSENTER / SYSEXIT Befehl   Unterstützt
VIA FEMMS Befehl   Nicht unterstützt
   
Sicherheits Besonderheiten   
Advanced Cryptography Engine (ACE)   Nicht unterstützt
Advanced Cryptography Engine 2 (ACE2)   Nicht unterstützt
Dateiausführungsverhinderung (DEP, NX, EDB)   Unterstützt
Hardware Zufallsnummern Generator (RNG)   Nicht unterstützt
PadLock Hash Engine (PHE)   Nicht unterstützt
PadLock Montgomery Multiplier (PMM)   Nicht unterstützt
Prozessor Seriennummer (PSN)   Nicht unterstützt
   
Energieverwaltungs Fähigkeiten   
Automatic Clock Control   Unterstützt
Digital Thermometer   Unterstützt

Dynamic FSB Frequency Switching   Nicht unterstützt
Enhanced Halt State (C1E)   Unterstützt, Deaktiviert
Enhanced SpeedStep Technology (EIST, ESS)   Nicht unterstützt
Frequency ID Control   Nicht unterstützt
Hardware P-State Control   Nicht unterstützt
LongRun   Nicht unterstützt
LongRun Table Interface   Nicht unterstützt
PowerSaver 1.0   Nicht unterstützt
PowerSaver 2.0   Nicht unterstützt
PowerSaver 3.0   Nicht unterstützt
Processor Duty Cycle Control   Unterstützt
Software Thermal Control   Nicht unterstützt
Temperatur Sensing Diode   Nicht unterstützt
Thermal Monitor 1   Unterstützt
Thermal Monitor 2   Unterstützt

Thermal Monitoring   Nicht unterstützt
Thermal Trip   Nicht unterstützt
Voltage ID Control   Nicht unterstützt
   
CPUID Besonderheiten   
1 GB Page Size   Nicht unterstützt
36-bit Page Size Extension   Nicht unterstützt
Address Region Registers (ARR)   Nicht unterstützt
CPL Qualified Debug Store   Unterstützt
Debug Trace Store   Unterstützt
Debugging Extension   Unterstützt

Direct Cache Access   Nicht unterstützt
Dynamic Acceleration Technology (IDA)   Nicht unterstützt
Fast Save & Restore   Unterstützt
Hyper-Threading Technology (HTT)   Unterstützt, Aktiviert
Invariant Time Stamp Counter   Unterstützt
L1 Context ID   Nicht unterstützt
Local APIC On Chip   Unterstützt
Machine Check Architecture (MCA)   Unterstützt
Machine Check Exception (MCE)   Unterstützt

Memory Configuration Registers (MCR)   Nicht unterstützt
Memory Type Range Registers (MTRR)   Unterstützt
Model Specific Registers (MSR)   Unterstützt

Nested Paging   Nicht unterstützt
Page Attribute Table (PAT)   Unterstützt
Page Global Extension   Unterstützt
Page Size Extension (PSE)   Unterstützt
Pending Break Event   Unterstützt
Physical Address Extension (PAE)   Unterstützt

Safer Mode Extensions (SMX)   Nicht unterstützt
Secure Virtual Machine Extensions (Pacifica)   Nicht unterstützt
Self-Snoop   Unterstützt
Time Stamp Counter (TSC)   Unterstützt

Turbo Boost   Nicht unterstützt
Virtual Machine Extensions (Vanderpool)   Nicht unterstützt
Virtual Mode Extension   Unterstützt
x2APIC   Nicht unterstützt
XSAVE / XRSTOR Extended States   Nicht unterstützt
« Last Edit: 04 Jan 2010, 06:06:19 pm by _heinz »

 

Welcome, Guest.
Please login or register.
 
 
 
Forgot your password?
Members
Total Members: 97
Latest: ToeBee
New This Month: 0
New This Week: 0
New Today: 0
Stats
Total Posts: 59559
Total Topics: 1672
Most Online Today: 40
Most Online Ever: 983
(20 Jan 2020, 03:17:55 pm)
Users Online
Members: 0
Guests: 33
Total: 33
Powered by EzPortal