Overclock.net › Forums › General Hardware › General Processor Discussions › amd vs intel confused still
New Posts  All Forums:Forum Nav:

amd vs intel confused still - Page 3

post #21 of 99
Quote:
Originally Posted by Blameless View Post

The task mentioned was a serial one and nothing could make it multi-threaded.

That was the point. No matter how much you devote to multithreading, there will always been tasks that will benefit from a single powerful core. Yes, multithreading can, should, and will improve, but strong individual cores will never be useless.
Hyperthreading uses a second front-end to run a thread in what would otherwise be gaps in the execution pipeline, allowing more efficient use of a core's execution resources.
Hyperthreading is damn good in terms of performance per watt and performance for the die area it requires. Even in raw performance terms, it's quite handy in most well threaded scenarios.
First point: Exactly what you said.

Second point, yeah, but what I was getting at is that it does not improve IPC, it only improve multithreading performance.

Third point: It is useful, but it only real shines for immaculately well coded and well threaded programs, which there is a distinctive lack of.
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
post #22 of 99
not sure how good this comparison is...

But the jump from 950 to 3770k is pretty good.
%30 - %40 faster for only 77 watts, from 130w.
http://cpu.userbenchmark.com/Compare/Intel-Core-i7-950-vs-Intel-Core-i7-3770K/617vs1317

Intel has been making improvements in energy efficiency and iGPU power, and instruction sets. I wouldn't say Intel has stagnated, but what they have been improving has varied away from pure core speed.
Rig 2.0
(16 items)
 
  
CPUMotherboardGraphicsRAM
i7 3770k Asus P8Z77-V EVGA GTX780 SC ACX Samsung DDR 3 (2 DIMMS) MV-3V4G3D/US 
Hard DriveHard DriveOptical DriveCooling
Samsung 830 SSD WD Caviar Black Asus DVD/RW Xigmatek s-1283 HDT (Air Cooling) 
CoolingCoolingOSMonitor
Scythe Slipstream 1200RPM (x2) Antec 140mm + Antec 120mm + Xigmatek 120mm (x2) Win 7 64bit Acer S243HL bmii - 24" 
PowerCaseMouseAudio
Corsair TX750 Corsair Carbide 300R MX 518 Auzentek X-Fi Forte 7.1 
  hide details  
Reply
Rig 2.0
(16 items)
 
  
CPUMotherboardGraphicsRAM
i7 3770k Asus P8Z77-V EVGA GTX780 SC ACX Samsung DDR 3 (2 DIMMS) MV-3V4G3D/US 
Hard DriveHard DriveOptical DriveCooling
Samsung 830 SSD WD Caviar Black Asus DVD/RW Xigmatek s-1283 HDT (Air Cooling) 
CoolingCoolingOSMonitor
Scythe Slipstream 1200RPM (x2) Antec 140mm + Antec 120mm + Xigmatek 120mm (x2) Win 7 64bit Acer S243HL bmii - 24" 
PowerCaseMouseAudio
Corsair TX750 Corsair Carbide 300R MX 518 Auzentek X-Fi Forte 7.1 
  hide details  
Reply
post #23 of 99
Quote:
Originally Posted by Aparition View Post

not sure how good this comparison is...

But the jump from 950 to 3770k is pretty good.
%30 - %40 faster for only 77 watts, from 130w.
http://cpu.userbenchmark.com/Compare/Intel-Core-i7-950-vs-Intel-Core-i7-3770K/617vs1317

Intel has been making improvements in energy efficiency and iGPU power, and instruction sets. I wouldn't say Intel has stagnated, but what they have been improving has varied away from pure core speed.
Is it possible you could compare the i7 950 and i7 4770k? Because that would show a bit better difference. I'm not sure about you guys, but I believe most would consider AMD not competetive at or during the sandy bridge series of CPUs. (also that bench you showed is a 09 processor vs a 2013 processor, 4 years, barely 50% better over 4 years, I compared it from the i7 4770k and it wasn't much different over 5-6 years)

Also another thing I have to note, is that intel started using TIM instead of their normal solder for inbetween the IHS, so while the power usage is down, the heat output is higher.
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
post #24 of 99
Quote:
Originally Posted by Dantron View Post

Second point, yeah, but what I was getting at is that it does not improve IPC, it only improve multithreading performance.

It does improve the number of instructions a single core can retire at a given clock speed, with the caveat that there needs to be at least two threads executing them.

You are right in stating that single-threaded performance is not improved.
Quote:
Originally Posted by Dantron View Post

Third point: It is useful, but it only real shines for immaculately well coded and well threaded programs, which there is a distinctive lack of.

Immaculately well coded programs (those with near ideal ILP and designed to take best advantage of the hardware they are run on) don't leave as many gaps for HT to take advantage of. HT is generally most efficient for well threaded, but not perfectly optimized tasks.

In general, if it's a situation where more cores would help, HT will also help. HT won't help anywhere near as much as a second core would, but it's a lot less costly in die-area and power.
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 #25 of 99
Quote:
Originally Posted by Dantron View Post

Yes you can compare a subaru to a mclaren, but does that make much sense? Not in the slightest, they are for different people and different workloads. I wasn't saying the 8 core was better than the 4 core, I'm saying comparing a top of the line i7 makes very little sense to compare it to an fx 8350.
Utter trash and absolute bollocks. Hyper threading does not improve IPC and does not involve a shorter pipeline. Hyper threading simply uses the same cache and execution areas as a normal core. It is out of order execution to improve multitasking, it does not improve IPC in any possible way.
I'm not saying it needs a "participation trophy" or a "fairness doctrine". I'm simply stating that the top end CPU from AMD is two years old now, it should be very obvious that intel is able to improve on its cpus, while AMD hasn't changed since then.

You are acting absolutely silly, this isn't a mentality, it's bloody logic to understand that in two years can make a lot of a difference. You're basically telling me it is stupid to say that a pentium 4 user should suck it up and not need logic when comparing to a core 2 duo, one much older than the other, similar to the fx 8350 vs i7 4770k or the i7 970. Those 3 CPUs also were for different markets, and the funny thing is the i7 970 barely beats out the fx.
If you looked past blatant fanboyism for a moment, you'd realize that intel HAS been stagnating, performance gains have dropped significantly since AMD stopped competing well. Please show me benchmarks from a reliable source that shows the the i7 4770k is nearly double as fast as the i7 950, because I haven't found any. Considering semi-conductor tech has been improving both with different methods and die shrinking, that statement is invalid.

Yes AMD processors are definitely worse than intel ones. But the arguments you have provided are absolute and total bollocks.

Well ATM you can buy that Mclaren for less then you could that Subaru. Yeah that X5650 is only like $130 on ebay, though the cost of a x58 motherboard is a different story. But Really with a higher end FX Chip you need a expensive board just to overclock it anyways.


And Ivy Bride and PileDriver are not 2 years apart, And a Piledriver module at best completes with a Ivy Bride core in Multithread situations that favor it. Ivy is around twice as fast in single thread clock for clock compared to piledriver.

Problem is a Piledriver module still has less single thread power then a equally clocked 45nm core2quad. And Peak Multithread performance around the same as a equally clocked ivy bridge HT chip. Though on avg you are getting slightly more Multithread performance then a i5, and that is the problem. Personally unless your workload needs it a i5 is a better all around CPU.

http://www.anandtech.com/bench/product/701?vs=698
Edited by DzillaXx - 4/3/14 at 1:14pm
Red Dragon
(19 items)
 
HTPC
(20 items)
 
HomeServer
(13 items)
 
CPUMotherboardGraphicsRAM
Intel Core i7 2600K @4.8ghz Asrock p67 Extreme4 GTX1080 G.SKILL Ripjaws X Series 16GB 9-11-11-31 2133MHz 
Hard DriveHard DriveHard DriveHard Drive
3x 640 WD blacks Raid 0 Mushkin Enhanced Reactor 512GB SSD Sandisk 1TB SSD Samsung 470 Series 128GB SSD 
CoolingOSMonitorKeyboard
XSPC Raystorm Windows 10 64bit Microboard m340clz 100hz 3440x1440 Corsair K70 
PowerCaseMouseAudio
TX850 HAF922 Logitech G502 Creative Sound Blaster Z  
AudioAudioAudio
Elac B6 & Dayton Audio SUB-800 Yamaha HTR-5790 Audio Technica ATH-A700 headphones 
CPUMotherboardGraphicsRAM
Q9550 @ 4GHZ Gigabyte EP45 UD3P GTX470 4GB OCZ Reaper 1150mhz 
Hard DriveHard DriveOptical DriveCooling
Western Digital Blue 500gb OCZ Vertex 2 60GB LG Bluray Corsair H50 
OSKeyboardPowerCase
Windows 7 Home Premium  Logitech K400 Corsair CX500 nMEDIAPC 6000B 
AudioOtherOtherOther
Yamaha HTR-5063 PS3 80GB BC PS3 with 250GB hard drive. Polk Audio Monitor 60s Bi-AMP Front Polk Audio Monitor 30s Rear 
OtherOther
Polk Audio CS1 Center Polk Audio PSW10 
CPUMotherboardGraphicsRAM
Xeon Harpertown 3.6ghz Asus P5Q SE/R HD7770 4GB DDR2 800mhz Corsair 
Hard DriveHard DriveHard DriveHard Drive
5TB Toshiba 5TB Toshiba 5TB Toshiba 2TB Hitachi 
Hard DriveHard DriveHard DriveOS
2TB Seagate 2TB Western Digital 1TB Hitachi Windows Home Server 2011 
Power
Corsair CX500 
  hide details  
Reply
Red Dragon
(19 items)
 
HTPC
(20 items)
 
HomeServer
(13 items)
 
CPUMotherboardGraphicsRAM
Intel Core i7 2600K @4.8ghz Asrock p67 Extreme4 GTX1080 G.SKILL Ripjaws X Series 16GB 9-11-11-31 2133MHz 
Hard DriveHard DriveHard DriveHard Drive
3x 640 WD blacks Raid 0 Mushkin Enhanced Reactor 512GB SSD Sandisk 1TB SSD Samsung 470 Series 128GB SSD 
CoolingOSMonitorKeyboard
XSPC Raystorm Windows 10 64bit Microboard m340clz 100hz 3440x1440 Corsair K70 
PowerCaseMouseAudio
TX850 HAF922 Logitech G502 Creative Sound Blaster Z  
AudioAudioAudio
Elac B6 & Dayton Audio SUB-800 Yamaha HTR-5790 Audio Technica ATH-A700 headphones 
CPUMotherboardGraphicsRAM
Q9550 @ 4GHZ Gigabyte EP45 UD3P GTX470 4GB OCZ Reaper 1150mhz 
Hard DriveHard DriveOptical DriveCooling
Western Digital Blue 500gb OCZ Vertex 2 60GB LG Bluray Corsair H50 
OSKeyboardPowerCase
Windows 7 Home Premium  Logitech K400 Corsair CX500 nMEDIAPC 6000B 
AudioOtherOtherOther
Yamaha HTR-5063 PS3 80GB BC PS3 with 250GB hard drive. Polk Audio Monitor 60s Bi-AMP Front Polk Audio Monitor 30s Rear 
OtherOther
Polk Audio CS1 Center Polk Audio PSW10 
CPUMotherboardGraphicsRAM
Xeon Harpertown 3.6ghz Asus P5Q SE/R HD7770 4GB DDR2 800mhz Corsair 
Hard DriveHard DriveHard DriveHard Drive
5TB Toshiba 5TB Toshiba 5TB Toshiba 2TB Hitachi 
Hard DriveHard DriveHard DriveOS
2TB Seagate 2TB Western Digital 1TB Hitachi Windows Home Server 2011 
Power
Corsair CX500 
  hide details  
Reply
post #26 of 99
Quote:
Originally Posted by Blameless View Post

It does improve the number of instructions a single core can retire at a given clock speed, with the caveat that there needs to be at least two threads executing them.

You are right in stating that single-threaded performance is not improved.
Immaculately well coded programs (those with near ideal ILP and designed to take best advantage of the hardware they are run on) don't leave as many gaps for HT to take advantage of. HT is generally most efficient for well threaded, but not perfectly optimized tasks.

In general, if it's a situation where more cores would help, HT will also help. HT won't help anywhere near as much as a second core would, but it's a lot less costly in die-area and power.

Excellent point, it does definitely improve the MIPS. Well coded programs will indeed not get much help from HT and will probably use as much as the core's execution parts to the maximum potential, poorly coded ones will tie up the resources a core can have and render HT useless, a middle of the road coded one will take advantage of HT the best, but it itself won't run as well as the amazingly well made one. So we have to see if a awesome coded program is better than two threads of a middling coded one.
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
post #27 of 99
Quote:
Originally Posted by Dantron View Post

Is it possible you could compare the i7 950 and i7 4770k? Because that would show a bit better difference. I'm not sure about you guys, but I believe most would consider AMD not competetive at or during the sandy bridge series of CPUs.

Also another thing I have to note, is that intel started using TIM instead of their normal solder for inbetween the IHS, so while the power usage is down, the heat output is higher.


Here is the 950 vs 4770k.
Slightly higher numbers for the 4770k, as it should be expected, from the 3770k comparison.
http://cpu.userbenchmark.com/Compare/Intel-Core-i7-950-vs-Intel-Core-i7-4770K/617vs1537

For the Tim, the stock cooling efficiency is a wall but I find stock performance still very good. I think it is also a little misleading to say heat output is higher as your still only dealing with a 77w or 84w CPU, so the efficiency to remove heat is bad but the chips are not as hot as a 130w chip. Semantics really but if you mod the CPU and remove the inefficient TIM application temps are very low.
Also the newest shelved 3770k's seem to be much much cooler than the first release chips.
Rig 2.0
(16 items)
 
  
CPUMotherboardGraphicsRAM
i7 3770k Asus P8Z77-V EVGA GTX780 SC ACX Samsung DDR 3 (2 DIMMS) MV-3V4G3D/US 
Hard DriveHard DriveOptical DriveCooling
Samsung 830 SSD WD Caviar Black Asus DVD/RW Xigmatek s-1283 HDT (Air Cooling) 
CoolingCoolingOSMonitor
Scythe Slipstream 1200RPM (x2) Antec 140mm + Antec 120mm + Xigmatek 120mm (x2) Win 7 64bit Acer S243HL bmii - 24" 
PowerCaseMouseAudio
Corsair TX750 Corsair Carbide 300R MX 518 Auzentek X-Fi Forte 7.1 
  hide details  
Reply
Rig 2.0
(16 items)
 
  
CPUMotherboardGraphicsRAM
i7 3770k Asus P8Z77-V EVGA GTX780 SC ACX Samsung DDR 3 (2 DIMMS) MV-3V4G3D/US 
Hard DriveHard DriveOptical DriveCooling
Samsung 830 SSD WD Caviar Black Asus DVD/RW Xigmatek s-1283 HDT (Air Cooling) 
CoolingCoolingOSMonitor
Scythe Slipstream 1200RPM (x2) Antec 140mm + Antec 120mm + Xigmatek 120mm (x2) Win 7 64bit Acer S243HL bmii - 24" 
PowerCaseMouseAudio
Corsair TX750 Corsair Carbide 300R MX 518 Auzentek X-Fi Forte 7.1 
  hide details  
Reply
post #28 of 99
Quote:
Originally Posted by Aparition View Post

Here is the 950 vs 4770k.
Slightly higher numbers for the 4770k, as it should be expected, from the 3770k comparison.
http://cpu.userbenchmark.com/Compare/Intel-Core-i7-950-vs-Intel-Core-i7-4770K/617vs1537

For the Tim, the stock cooling efficiency is a wall but I find stock performance still very good. I think it is also a little misleading to say heat output is higher as your still only dealing with a 77w or 84w CPU, so the efficiency to remove heat is bad but the chips are not as hot as a 130w chip. Semantics really but if you mod the CPU and remove the inefficient TIM application temps are very low.
Also the newest shelved 3770k's seem to be much much cooler than the first release chips.
Intel's and AMD's TDP differ. AMD's is the maximum heat output while running at maximum, while it seems intel's is the maximum heat it can handle.
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
post #29 of 99
Quote:
Originally Posted by DzillaXx View Post

Well ATM you can buy that Mclaren for less then you could that Subaru. Yeah that X5650 is only like $130 on ebay, though the cost of a x58 motherboard is a different story. But Really with a higher end FX Chip you need a expensive board just to overclock it anyways.


And Ivy Bride and PileDriver are not 2 years apart, And a Piledriver module at best completes with a Ivy Bride core in Multithread situations that favor it. Ivy is around twice as fast in single thread clock for clock compared to piledriver.

Problem is a Piledriver module still has less single thread power then a equally clocked 45nm core2quad. And Peak Multithread performance around the same as a equally clocked ivy bridge HT chip. Though on avg you are getting slightly more Multithread performance then a i5, and that is the problem. Personally unless your workload needs it a i5 is a better all around CPU.

http://www.anandtech.com/bench/product/701?vs=698

Your argument still makes no sense at all. Why did you bring it up if the mclaren is cheaper than the subaru. Once again, the mclaren and subaru are for different people and different workloads.

It doesn't make sense to buy a x5650 and a x58 motherboard that supports it, they are outdated, and the cpu might not actually be as good as it used to be, because of degradation.

I don't remember the exact IPC difference from phenom 2/core 2 quad and fx8350, or nehalem/whatever the tick was called. But the fx 8350 is very close, and since it clocks much much higher, it is irrelevant that the IPC is less.

http://www.anandtech.com/bench/product/49?vs=697

The core 2 quad is much worse than the fx 8350 btw, it's quite obvious you are very biased towards Intel.
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
Ol' Reliable
(16 items)
 
   
CPUMotherboardGraphicsRAM
Core 2 duo e6600 Asus p5n8 None 2gb corsair 
Hard DriveOptical DriveOSCase
1999 called, they want their 60gb back. none Arch Linux Free willy 
CPUMotherboardGraphicsRAM
Phenom II X2 N620 2.8ghz Socketed HP SGS1 HD 4250 4 gb DDR3 1333 
Hard DriveOptical DriveCoolingOS
500gb 5400 RPM DVD writer with LIGHTSCRIBE :D! Laptop cooling ftl Debian Lenny 
MonitorKeyboardPowerCase
15in 1378x768 Rubber dome chiclet keys Red ceramic brick HP 15inch 
  hide details  
Reply
post #30 of 99
Quote:
Originally Posted by Dantron View Post

Your argument still makes no sense at all. Why did you bring it up if the mclaren is cheaper than the subaru. Once again, the mclaren and subaru are for different people and different workloads.

It doesn't make sense to buy a x5650 and a x58 motherboard that supports it, they are outdated, and the cpu might not actually be as good as it used to be, because of degradation.

I don't remember the exact IPC difference from phenom 2/core 2 quad and fx8350, or nehalem/whatever the tick was called. But the fx 8350 is very close, and since it clocks much much higher, it is irrelevant that the IPC is less.

http://www.anandtech.com/bench/product/49?vs=697

The core 2 quad is much worse than the fx 8350 btw, it's quite obvious you are very biased towards Intel.

Not in single thread clock for clock.
Last time I checked PileDriver and Phenom II are still around the same clock for clock single thread wise and the Phenom II required a extra 200mhz to be equal to a equally clocked c2q. Takes 4.2ghz on a PII to equal a 4ghz C2Q, this is well known.


And I wouldn't call AM3+ new tech. Infact compared to even the old x58 AM3+ is about equal to that chipset using their 990fx chipset. Later in life X58 mobo's have everything current high end AM3+ mobo's have.



I'm not biased against AMD. I tell people get get amd cpu's like the fx6300 all the time. Also have had a few phenom II rigs in my time, no to mention pretty much using AMD from the Athlon XP to Athlon X2 era. Until I bought my Q9550 the last intel chip I had was a Pentium 3. Personally I just feel AMD has a crappy high end CPU lineup.

What AMD needs to do is release a FX chip using 6-8 Modules. Atleast then they would have something going from them.

I'm a big fan of their APU's though and low power chips.
Red Dragon
(19 items)
 
HTPC
(20 items)
 
HomeServer
(13 items)
 
CPUMotherboardGraphicsRAM
Intel Core i7 2600K @4.8ghz Asrock p67 Extreme4 GTX1080 G.SKILL Ripjaws X Series 16GB 9-11-11-31 2133MHz 
Hard DriveHard DriveHard DriveHard Drive
3x 640 WD blacks Raid 0 Mushkin Enhanced Reactor 512GB SSD Sandisk 1TB SSD Samsung 470 Series 128GB SSD 
CoolingOSMonitorKeyboard
XSPC Raystorm Windows 10 64bit Microboard m340clz 100hz 3440x1440 Corsair K70 
PowerCaseMouseAudio
TX850 HAF922 Logitech G502 Creative Sound Blaster Z  
AudioAudioAudio
Elac B6 & Dayton Audio SUB-800 Yamaha HTR-5790 Audio Technica ATH-A700 headphones 
CPUMotherboardGraphicsRAM
Q9550 @ 4GHZ Gigabyte EP45 UD3P GTX470 4GB OCZ Reaper 1150mhz 
Hard DriveHard DriveOptical DriveCooling
Western Digital Blue 500gb OCZ Vertex 2 60GB LG Bluray Corsair H50 
OSKeyboardPowerCase
Windows 7 Home Premium  Logitech K400 Corsair CX500 nMEDIAPC 6000B 
AudioOtherOtherOther
Yamaha HTR-5063 PS3 80GB BC PS3 with 250GB hard drive. Polk Audio Monitor 60s Bi-AMP Front Polk Audio Monitor 30s Rear 
OtherOther
Polk Audio CS1 Center Polk Audio PSW10 
CPUMotherboardGraphicsRAM
Xeon Harpertown 3.6ghz Asus P5Q SE/R HD7770 4GB DDR2 800mhz Corsair 
Hard DriveHard DriveHard DriveHard Drive
5TB Toshiba 5TB Toshiba 5TB Toshiba 2TB Hitachi 
Hard DriveHard DriveHard DriveOS
2TB Seagate 2TB Western Digital 1TB Hitachi Windows Home Server 2011 
Power
Corsair CX500 
  hide details  
Reply
Red Dragon
(19 items)
 
HTPC
(20 items)
 
HomeServer
(13 items)
 
CPUMotherboardGraphicsRAM
Intel Core i7 2600K @4.8ghz Asrock p67 Extreme4 GTX1080 G.SKILL Ripjaws X Series 16GB 9-11-11-31 2133MHz 
Hard DriveHard DriveHard DriveHard Drive
3x 640 WD blacks Raid 0 Mushkin Enhanced Reactor 512GB SSD Sandisk 1TB SSD Samsung 470 Series 128GB SSD 
CoolingOSMonitorKeyboard
XSPC Raystorm Windows 10 64bit Microboard m340clz 100hz 3440x1440 Corsair K70 
PowerCaseMouseAudio
TX850 HAF922 Logitech G502 Creative Sound Blaster Z  
AudioAudioAudio
Elac B6 & Dayton Audio SUB-800 Yamaha HTR-5790 Audio Technica ATH-A700 headphones 
CPUMotherboardGraphicsRAM
Q9550 @ 4GHZ Gigabyte EP45 UD3P GTX470 4GB OCZ Reaper 1150mhz 
Hard DriveHard DriveOptical DriveCooling
Western Digital Blue 500gb OCZ Vertex 2 60GB LG Bluray Corsair H50 
OSKeyboardPowerCase
Windows 7 Home Premium  Logitech K400 Corsair CX500 nMEDIAPC 6000B 
AudioOtherOtherOther
Yamaha HTR-5063 PS3 80GB BC PS3 with 250GB hard drive. Polk Audio Monitor 60s Bi-AMP Front Polk Audio Monitor 30s Rear 
OtherOther
Polk Audio CS1 Center Polk Audio PSW10 
CPUMotherboardGraphicsRAM
Xeon Harpertown 3.6ghz Asus P5Q SE/R HD7770 4GB DDR2 800mhz Corsair 
Hard DriveHard DriveHard DriveHard Drive
5TB Toshiba 5TB Toshiba 5TB Toshiba 2TB Hitachi 
Hard DriveHard DriveHard DriveOS
2TB Seagate 2TB Western Digital 1TB Hitachi Windows Home Server 2011 
Power
Corsair CX500 
  hide details  
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: General Processor Discussions
Overclock.net › Forums › General Hardware › General Processor Discussions › amd vs intel confused still