Overclock.net › Forums › Intel › Intel CPUs › Intel Core i7-3930K vs Xeon E5-2630 For Long-duration Financial Calculations
New Posts  All Forums:Forum Nav:

Intel Core i7-3930K vs Xeon E5-2630 For Long-duration Financial Calculations - Page 9

post #81 of 100
Quote:
Originally Posted by kweechy View Post

I thought that as they got smaller though, the likelihood that such a tiny thing gets hit with a neutron/proton is lower and lower since the target is shrinking.

Our company's CTO told me the number of fatal bit flips we experience seems to drop every time memory sizes drop a few nm. Our render farm with 4,200 cores and 19.2TB of memory is all non-ECC and produces an extremely huge sample size as it's 100% load for 51 weeks a year...so it should be a pretty good indicator of average, fatal bit flips over time.

The particles aren't shrinking though..... so it means there are more possible things to hit within the same given area.


How would you know there are bitflips at all since you're not using memory controllers that detect them? You need E5 or E7 Xeons to get that information. (Or a system/app crash in case a of a fatal bitflip).
Edited by DuckieHo - 12/1/12 at 8:41am
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
post #82 of 100
Thread Starter 
do not e3 XEONs have similar memory controllers that can detect memory errors?

I also wanted to ask - are the xeon processors as a CPU type more immune to system crashes (they have some corresponding instructions to stabilize themselves)?
post #83 of 100
Quote:
Originally Posted by DuckieHo View Post


The particles aren't shrinking though..... so it means there are more possible things to hit within the same given area.
How would you know there are bitflips at all since you're not using memory controllers that detect them? You need E5 or E7 Xeons to get that information. (Or a system/app crash in case a of a fatal bitflip).

I think they just check bitflips against crashed or broken render jobs.

 

The particles aren't shrinking no, but there's always a similar amount of them bombarding things...so by reducing the available area to bombard, you would combat the issue I'd imagine.

 

It'd be like having a kid hitting baseballs into a field. If you put a barn there, it'll get hit a lot, but if you put a can of coke, it might not get hit for months.

2P Workstation
(13 items)
 
  
CPUCPUMotherboardGraphics
Xeon E5 2699 v3 Xeon E5 2699 v3 ASUS Z10PE-D16 EVGA TITAN X 
RAMHard DriveHard DriveCooling
128GB Crucial DDR4 @ 2133MHz Intel 750 Series 1.2TB 4 x 4TB Constellation RAID5 2 x XSPC Raystorms 
CoolingCoolingMonitorMonitor
RS480 MCP655 Dell U3011 Dell U3011 
Case
Silverstone TJ07 
  hide details  
Reply
2P Workstation
(13 items)
 
  
CPUCPUMotherboardGraphics
Xeon E5 2699 v3 Xeon E5 2699 v3 ASUS Z10PE-D16 EVGA TITAN X 
RAMHard DriveHard DriveCooling
128GB Crucial DDR4 @ 2133MHz Intel 750 Series 1.2TB 4 x 4TB Constellation RAID5 2 x XSPC Raystorms 
CoolingCoolingMonitorMonitor
RS480 MCP655 Dell U3011 Dell U3011 
Case
Silverstone TJ07 
  hide details  
Reply
post #84 of 100
Quote:
Originally Posted by dima777 View Post

do not e3 XEONs have similar memory controllers that can detect memory errors?
I also wanted to ask - are the xeon processors as a CPU type more immune to system crashes (they have some corresponding instructions to stabilize themselves)?
No, Xeons are just binned chips with unlocked features. They are basically identical to desktop chips. Xeons may have ECC, RAS, VT-x, additional QPI... They also all have extended life cycles for longer term availability.

A function of ECC is to detect and correct a single bit flip.

Quote:
Originally Posted by kweechy View Post

I think they just check bitflips against crashed or broken render jobs.

The particles aren't shrinking no, but there's always a similar amount of them bombarding things...so by reducing the available area to bombard, you would combat the issue I'd imagine.

It'd be like having a kid hitting baseballs into a field. If you put a barn there, it'll get hit a lot, but if you put a can of coke, it might not get hit for months.

Yes, but you are assuming DRAM density isn't increasing though.... A few hundred cans of coke may be about the same chance of getting hit as a barn.

(Found a old Google white paper on errors of DDR1 vs DDR2 vs FBD: http://www.cs.toronto.edu/~bianca/papers/sigmetrics09.pdf)
Edited by DuckieHo - 12/2/12 at 8:45am
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
post #85 of 100
Thread Starter 
yes thanks...I have been thinking of that...)

I wonder if any one with i7 3930K or XEON E3 127V2 can comment on the multi-threading boost to EXCEL 2010 or EXCEL 2007 performance???? I need this to make the final decision between these two setups...do you think the multi-threaded EXCEL 2010 in the case of i7 3930K or XEON E3 127V2 can be significantly faster than the single threaded EXCEL 2003?
thanks a lot!)
post #86 of 100
Quote:
Originally Posted by dima777 View Post

yes thanks...I have been thinking of that...)
I wonder if any one with i7 3930K or XEON E3 127V2 can comment on the multi-threading boost to EXCEL 2010 or EXCEL 2007 performance???? I need this to make the final decision between these two setups...do you think the multi-threaded EXCEL 2010 in the case of i7 3930K or XEON E3 127V2 can be significantly faster than the single threaded EXCEL 2003?
thanks a lot!)

I'm not sure how a Xeon E3 would be much faster at single threaded considering you could put a very conservative OC on a 3930 with 100% guaranteed stability and wipe the floor with the Xeon E3's thread speeds.

 

A 3930 will run all day long at 4.2 - 4.5 without hiccup...in fact there's OEMs out there selling them in rigs at 4.5GHz from them.

2P Workstation
(13 items)
 
  
CPUCPUMotherboardGraphics
Xeon E5 2699 v3 Xeon E5 2699 v3 ASUS Z10PE-D16 EVGA TITAN X 
RAMHard DriveHard DriveCooling
128GB Crucial DDR4 @ 2133MHz Intel 750 Series 1.2TB 4 x 4TB Constellation RAID5 2 x XSPC Raystorms 
CoolingCoolingMonitorMonitor
RS480 MCP655 Dell U3011 Dell U3011 
Case
Silverstone TJ07 
  hide details  
Reply
2P Workstation
(13 items)
 
  
CPUCPUMotherboardGraphics
Xeon E5 2699 v3 Xeon E5 2699 v3 ASUS Z10PE-D16 EVGA TITAN X 
RAMHard DriveHard DriveCooling
128GB Crucial DDR4 @ 2133MHz Intel 750 Series 1.2TB 4 x 4TB Constellation RAID5 2 x XSPC Raystorms 
CoolingCoolingMonitorMonitor
RS480 MCP655 Dell U3011 Dell U3011 
Case
Silverstone TJ07 
  hide details  
Reply
post #87 of 100
Thread Starter 
Quote:
Originally Posted by kweechy View Post

I'm not sure how a Xeon E3 would be much faster at single threaded considering you could put a very conservative OC on a 3930 with 100% guaranteed stability and wipe the floor with the Xeon E3's thread speeds.

A 3930 will run all day long at 4.2 - 4.5 without hiccup...in fact there's OEMs out there selling them in rigs at 4.5GHz from them.

YES.....THANK YOU FOR YOUR REPLY....I am not plannign to overclock the 3930 - you do over-clock them on your render farm and they work stably for many months on end?
thanks!)
post #88 of 100
Quote:
Originally Posted by dima777 View Post


YES.....THANK YOU FOR YOUR REPLY....I am not plannign to overclock the 3930 - you do over-clock them on your render farm and they work stably for many months on end?
thanks!)

Yep, all my 3930s run at 4.5GHz without issue and will happily render for as long as I want at that speed. I could probably get them higher, but 4.5 is rock solid and stays under 75C so I'm happy with that.

2P Workstation
(13 items)
 
  
CPUCPUMotherboardGraphics
Xeon E5 2699 v3 Xeon E5 2699 v3 ASUS Z10PE-D16 EVGA TITAN X 
RAMHard DriveHard DriveCooling
128GB Crucial DDR4 @ 2133MHz Intel 750 Series 1.2TB 4 x 4TB Constellation RAID5 2 x XSPC Raystorms 
CoolingCoolingMonitorMonitor
RS480 MCP655 Dell U3011 Dell U3011 
Case
Silverstone TJ07 
  hide details  
Reply
2P Workstation
(13 items)
 
  
CPUCPUMotherboardGraphics
Xeon E5 2699 v3 Xeon E5 2699 v3 ASUS Z10PE-D16 EVGA TITAN X 
RAMHard DriveHard DriveCooling
128GB Crucial DDR4 @ 2133MHz Intel 750 Series 1.2TB 4 x 4TB Constellation RAID5 2 x XSPC Raystorms 
CoolingCoolingMonitorMonitor
RS480 MCP655 Dell U3011 Dell U3011 
Case
Silverstone TJ07 
  hide details  
Reply
post #89 of 100
Quote:
Originally Posted by DuckieHo View Post

The particles aren't shrinking though..... so it means there are more possible things to hit within the same given area.

The number of particles is shrinking.

Many of these flips are caused by the decay of radioactive isotopes in the ICs themselves. As time has gone by, ICs have gotten cleaner, both from improved production quality, and from gradually declining levels of isotopes in the environment (because nuclear weapons testing peaked in the 50s and 60s).

If it were only cosmic rays responsible for these flips, enough radiation shielding would completely stop them, but it doesn't.
Edited by Blameless - 12/6/12 at 9:29am
Primary
(15 items)
 
Secondary
(13 items)
 
In progress
(10 items)
 
CPUMotherboardGraphicsRAM
5820K @ 4.3/3.6GHz core/uncore, 1.225/1.2v Gigabyte X99 SOC Champion (F22n) 2x Sapphire R9 290X Tri-X OC New Edition (10036... 4x4GiB Crucial @ 2667, 12-11-12-27-T1, 1.37v 
Hard DriveHard DriveHard DriveCooling
Plextor M6e 128GB (fw 1.05) M.2 (PCI-E 2.0 2x) 2x Crucial M4 256GB 4x WD Scorpio Black 500GB Cooler Master Nepton 280L 
OSMonitorKeyboardPower
Windows 7 Professional x64 SP1 BenQ BL3200PT Filco Majestouch Tenkeyless (MX Brown) Corsair RM1000x 
CaseMouseAudio
Fractal Design Define R4 Logitech G402 Realtek ALC1150 + M-Audio AV40 
CPUMotherboardGraphicsRAM
X5670 @ 4.4/3.2GHz core/uncore, 1.36 vcore, 1.2... Gigabyte X58A-UD5 r2.0 w/FF3mod10 BIOS Reference R9 290X w/Stilt's MLU 1000e / 1375m E... 2x Samsung MV-3V4G3D/US @ 2000, 10-11-11-30-T1,... 
RAMHard DriveHard DriveHard Drive
1x Crucial BLT4G3D1608ET3LX0 @ 2000, 10-11-11-3... OCZ (Toshiba) Trion 150 120GB Hyundai Sapphire 120GB 3x Hitachi Deskstar 7k1000.C 1TB 
CoolingOSPowerCase
Noctua NH-D14 Windows 7 Pro x64 SP1 Antec TP-750 Fractal Design R5 
Audio
ASUS Xonar DS 
CPUMotherboardGraphicsRAM
i7-6800K @ 4.3/3.5GHz core/uncore, 1.36/1.2v ASRock X99 OC Formula (P3.10) GTX 780 (temporary) 4x4GiB Crucial DDR4-2400 @ 11-13-12-28-T2, 1.33v 
Hard DriveHard DriveCoolingOS
Intel 600p 256GB NVMe 2x HGST Travelstar 7k1000 1TB Corsair H55 (temporary) Windows Server 2016 Datacenter 
PowerCase
Seasonic SS-860XP2 Corsair Carbide Air 540 
  hide details  
Reply
Primary
(15 items)
 
Secondary
(13 items)
 
In progress
(10 items)
 
CPUMotherboardGraphicsRAM
5820K @ 4.3/3.6GHz core/uncore, 1.225/1.2v Gigabyte X99 SOC Champion (F22n) 2x Sapphire R9 290X Tri-X OC New Edition (10036... 4x4GiB Crucial @ 2667, 12-11-12-27-T1, 1.37v 
Hard DriveHard DriveHard DriveCooling
Plextor M6e 128GB (fw 1.05) M.2 (PCI-E 2.0 2x) 2x Crucial M4 256GB 4x WD Scorpio Black 500GB Cooler Master Nepton 280L 
OSMonitorKeyboardPower
Windows 7 Professional x64 SP1 BenQ BL3200PT Filco Majestouch Tenkeyless (MX Brown) Corsair RM1000x 
CaseMouseAudio
Fractal Design Define R4 Logitech G402 Realtek ALC1150 + M-Audio AV40 
CPUMotherboardGraphicsRAM
X5670 @ 4.4/3.2GHz core/uncore, 1.36 vcore, 1.2... Gigabyte X58A-UD5 r2.0 w/FF3mod10 BIOS Reference R9 290X w/Stilt's MLU 1000e / 1375m E... 2x Samsung MV-3V4G3D/US @ 2000, 10-11-11-30-T1,... 
RAMHard DriveHard DriveHard Drive
1x Crucial BLT4G3D1608ET3LX0 @ 2000, 10-11-11-3... OCZ (Toshiba) Trion 150 120GB Hyundai Sapphire 120GB 3x Hitachi Deskstar 7k1000.C 1TB 
CoolingOSPowerCase
Noctua NH-D14 Windows 7 Pro x64 SP1 Antec TP-750 Fractal Design R5 
Audio
ASUS Xonar DS 
CPUMotherboardGraphicsRAM
i7-6800K @ 4.3/3.5GHz core/uncore, 1.36/1.2v ASRock X99 OC Formula (P3.10) GTX 780 (temporary) 4x4GiB Crucial DDR4-2400 @ 11-13-12-28-T2, 1.33v 
Hard DriveHard DriveCoolingOS
Intel 600p 256GB NVMe 2x HGST Travelstar 7k1000 1TB Corsair H55 (temporary) Windows Server 2016 Datacenter 
PowerCase
Seasonic SS-860XP2 Corsair Carbide Air 540 
  hide details  
Reply
post #90 of 100
Thread Starter 
Quote:
Originally Posted by Blameless View Post

The number of particles is shrinking.
Many of these flips are caused by the decay of radioactive isotopes in the ICs themselves. As time has gone by, ICs have gotten cleaner, both from improved production quality, and from gradually declining levels of isotopes in the environment (because nuclear weapons testing peaked in the 50s and 60s).
If it were only cosmic rays responsible for these flips, enough radiation shielding would completely stop them, but it doesn't.

very interesting)))

You know...I can theoretically get away with the ecc memory by doing the following steps - I create a single calculation loop and perform it after say each of the 50 loops to see if the results match - to make sure there is no corruption in the files itself......and will always save it clean with no data to made bit by bit comparision with the original file to make sure it was not corrupted while saving.....btw - do you think ECC memory errors are frequent enough to have a hight chance of occurring in a 6-hour calculation session?
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Intel CPUs
Overclock.net › Forums › Intel › Intel CPUs › Intel Core i7-3930K vs Xeon E5-2630 For Long-duration Financial Calculations