Overclock.net › Forums › Industry News › Hardware News › [TH] Tom's CPU Architecture Shootout: 16 CPUs, One Core Each, And 3 GHz
New Posts  All Forums:Forum Nav:

[TH] Tom's CPU Architecture Shootout: 16 CPUs, One Core Each, And 3 GHz - Page 9

post #81 of 223
Quote:
Originally Posted by DuckieHo View Post
Core physical size doesn't really matter.... what it can do is more important than how big it is. (LOL.... )

You can't accurately measure the single-core energy consumption of a multi-core and multi-function CPU. You have to account for the cache, memory controller, IGP, PCIe controller, etc which will skew any results.

i.e. Is it fair to compare a SB with a PCIe controller vs a Phenom II without one?
It went right over your head. Everything u just mentioned is already understood.

The importance of ONE core is pointless without knowing how many transisters are in each core.. and useing that as a reletive comparison.

If intel & amd have the same size cpu. But one is 6 cores, the other is 10... the one with less cores most likely has biggers & more robust cores... by virtue of it size. (If same nm)

How can u fail so bad @ understanding a simple premis of transistor count? Or how this test is even valid illustration of anything? Effeciency is the key metric... cause everything scales off of that. Without knowing size.. we don't know effeciency.
post #82 of 223
Quote:
Originally Posted by formula m View Post
It went right over your head. Everything u just mentioned is already understood.

The importance of ONE core is pointless without knowing how many transisters are in each core.. and useing that as a reletive comparison.

If intel & amd have the same size cpu. But one is 6 cores, the other is 10... the one with less cores most likely has biggers & more robust cores... by virtue of it size. (If same nm)

How can u fail so bad @ understanding a simple premis of transistor count? Or how this test is even valid illustration of anything? Effeciency is the key metric... cause everything scales off of that. Without knowing size.. we don't know effeciency.
There is no need to take the number of cores into account. Price, number of transistors, core count, fab process, etc. have nothing to do with this test, except in explaining the results.

The article is about single thread performance on 16 different CPUs.
 
Benching
(17 items)
 
 
CPUMotherboardGraphicsRAM
[i7 5960X @ 4.8GHz] [Rampage V Extreme] [Titan 1400MHz (1500MHz bench)] [Various] 
Hard DriveCoolingCoolingCooling
[250GB 840EVO +2x SpinpointF3 1TB RAID0] [LD PC-V2 SS Phase Change] [XSPC X2O 750 pump/res] [Monsta 360 full copper + EK XT 360 + XT 240] 
MonitorPowerCaseAudio
[Crossover 27Q LED-P 1440p+ASUS 1200p+LG 1080p] [Corsair AX1200] [Dimastech Easy v3.0] [Sennheiser HD558s] 
CPUCPUMotherboardGraphics
FX 8320, FX 8350, Phenom II x2 555BE i7 3930K, i7 860, i7 4770K, 68x Celeron D CVF, commando, 2x RIVE, Z87X-OC Asus 4870x2, Sapphire 4870 
GraphicsGraphicsGraphicsGraphics
2x 5870, 5850, 5830, 5770 2x 3870x2, 3870 GTX Titan, GTX 480, GTX 590 GTX 285, GTX 260, 4x 9800GT, 8800GTX 
RAMHard DriveCoolingCooling
4x4GB vengeance, 2x4GB predatorX, 2x1GB OCZ DDR2 Intel X25-M 80GB LD PC-V2 SS Phase Change OCN Marksman 
CoolingCoolingOSPower
2x old tek slims (GPU) Various watercooling stuff win7, winxp AX1200 
Case
test bench / cardboard box 
  hide details  
Reply
 
Benching
(17 items)
 
 
CPUMotherboardGraphicsRAM
[i7 5960X @ 4.8GHz] [Rampage V Extreme] [Titan 1400MHz (1500MHz bench)] [Various] 
Hard DriveCoolingCoolingCooling
[250GB 840EVO +2x SpinpointF3 1TB RAID0] [LD PC-V2 SS Phase Change] [XSPC X2O 750 pump/res] [Monsta 360 full copper + EK XT 360 + XT 240] 
MonitorPowerCaseAudio
[Crossover 27Q LED-P 1440p+ASUS 1200p+LG 1080p] [Corsair AX1200] [Dimastech Easy v3.0] [Sennheiser HD558s] 
CPUCPUMotherboardGraphics
FX 8320, FX 8350, Phenom II x2 555BE i7 3930K, i7 860, i7 4770K, 68x Celeron D CVF, commando, 2x RIVE, Z87X-OC Asus 4870x2, Sapphire 4870 
GraphicsGraphicsGraphicsGraphics
2x 5870, 5850, 5830, 5770 2x 3870x2, 3870 GTX Titan, GTX 480, GTX 590 GTX 285, GTX 260, 4x 9800GT, 8800GTX 
RAMHard DriveCoolingCooling
4x4GB vengeance, 2x4GB predatorX, 2x1GB OCZ DDR2 Intel X25-M 80GB LD PC-V2 SS Phase Change OCN Marksman 
CoolingCoolingOSPower
2x old tek slims (GPU) Various watercooling stuff win7, winxp AX1200 
Case
test bench / cardboard box 
  hide details  
Reply
post #83 of 223
I had better throw this Thuban away and get myself a Athlon 64 X2, incredible performance, almost matching a SB . . . /s

Either they messed up the graph or their testing is off by a large margin.
    
CPUMotherboardGraphicsRAM
Intel 3570K ASUS Sabertooth Z77 KFA2 GTX 570 932/2000 @ 1.1v 8 GB Corsair 1600 MHz 
Hard DriveCoolingOSMonitor
64Gb Crucial M4 + 2 x Samsung F3 1TB Corsair H100 Windows 8 RP 2 x AOC e2343F 23" LED 1920x1080 
PowerCaseMouse
OCZ StealthXstream II 600W CM HAF 932 Saitek GM3200 
  hide details  
Reply
    
CPUMotherboardGraphicsRAM
Intel 3570K ASUS Sabertooth Z77 KFA2 GTX 570 932/2000 @ 1.1v 8 GB Corsair 1600 MHz 
Hard DriveCoolingOSMonitor
64Gb Crucial M4 + 2 x Samsung F3 1TB Corsair H100 Windows 8 RP 2 x AOC e2343F 23" LED 1920x1080 
PowerCaseMouse
OCZ StealthXstream II 600W CM HAF 932 Saitek GM3200 
  hide details  
Reply
post #84 of 223
Quote:
Originally Posted by Alatar View Post
There is no need to take the number of cores into account. Price, number of transistors, core count, fab process, etc. have nothing to do with this test, except in explaining the results.

The article is about single thread performance on 16 different CPUs.
No it is not! It is about 16 cpus, all using 1 core. Single thread has nothing to do with it.
post #85 of 223
Quote:
Originally Posted by formula m View Post
No it is not! It is about 16 cpus, all using 1 core. Single thread has nothing to do with it.
Yeah I meant to type single core performance. But the point stands, it's about performance. You can use all kinds of other factors to explain the results but the tests article is about performance.
 
Benching
(17 items)
 
 
CPUMotherboardGraphicsRAM
[i7 5960X @ 4.8GHz] [Rampage V Extreme] [Titan 1400MHz (1500MHz bench)] [Various] 
Hard DriveCoolingCoolingCooling
[250GB 840EVO +2x SpinpointF3 1TB RAID0] [LD PC-V2 SS Phase Change] [XSPC X2O 750 pump/res] [Monsta 360 full copper + EK XT 360 + XT 240] 
MonitorPowerCaseAudio
[Crossover 27Q LED-P 1440p+ASUS 1200p+LG 1080p] [Corsair AX1200] [Dimastech Easy v3.0] [Sennheiser HD558s] 
CPUCPUMotherboardGraphics
FX 8320, FX 8350, Phenom II x2 555BE i7 3930K, i7 860, i7 4770K, 68x Celeron D CVF, commando, 2x RIVE, Z87X-OC Asus 4870x2, Sapphire 4870 
GraphicsGraphicsGraphicsGraphics
2x 5870, 5850, 5830, 5770 2x 3870x2, 3870 GTX Titan, GTX 480, GTX 590 GTX 285, GTX 260, 4x 9800GT, 8800GTX 
RAMHard DriveCoolingCooling
4x4GB vengeance, 2x4GB predatorX, 2x1GB OCZ DDR2 Intel X25-M 80GB LD PC-V2 SS Phase Change OCN Marksman 
CoolingCoolingOSPower
2x old tek slims (GPU) Various watercooling stuff win7, winxp AX1200 
Case
test bench / cardboard box 
  hide details  
Reply
 
Benching
(17 items)
 
 
CPUMotherboardGraphicsRAM
[i7 5960X @ 4.8GHz] [Rampage V Extreme] [Titan 1400MHz (1500MHz bench)] [Various] 
Hard DriveCoolingCoolingCooling
[250GB 840EVO +2x SpinpointF3 1TB RAID0] [LD PC-V2 SS Phase Change] [XSPC X2O 750 pump/res] [Monsta 360 full copper + EK XT 360 + XT 240] 
MonitorPowerCaseAudio
[Crossover 27Q LED-P 1440p+ASUS 1200p+LG 1080p] [Corsair AX1200] [Dimastech Easy v3.0] [Sennheiser HD558s] 
CPUCPUMotherboardGraphics
FX 8320, FX 8350, Phenom II x2 555BE i7 3930K, i7 860, i7 4770K, 68x Celeron D CVF, commando, 2x RIVE, Z87X-OC Asus 4870x2, Sapphire 4870 
GraphicsGraphicsGraphicsGraphics
2x 5870, 5850, 5830, 5770 2x 3870x2, 3870 GTX Titan, GTX 480, GTX 590 GTX 285, GTX 260, 4x 9800GT, 8800GTX 
RAMHard DriveCoolingCooling
4x4GB vengeance, 2x4GB predatorX, 2x1GB OCZ DDR2 Intel X25-M 80GB LD PC-V2 SS Phase Change OCN Marksman 
CoolingCoolingOSPower
2x old tek slims (GPU) Various watercooling stuff win7, winxp AX1200 
Case
test bench / cardboard box 
  hide details  
Reply
post #86 of 223
Quote:
Originally Posted by Alatar View Post
Yeah I meant to type single core performance. But the point stands, it's about performance. You can use all kinds of other factors to explain the results but the tests article is about performance.
Performance of what..? A single core right?. Is that core 1/4 the size of the die, or 1/6th the size?

Are u actually saying a single large core (in a 1 core test) doesn't have an advantage over a smaller core? (That the size of the piston has no bearing on the engine?)

Please don't tell me that core size, has no factor on a cores computational ability.
post #87 of 223
Core size doesn't make as big of a difference as architecture and fabrication size.

And you can take a small 4-cylinder engine, beef it up and slap on a turbo, and let it run with a V6. But that isn't the same as a CPU.
Little Black Box
(18 items)
 
Vostro
(7 items)
 
Galaxy S4
(7 items)
 
CPUMotherboardGraphicsRAM
i5 6600k AsRock Fatal1ty Z170 ITX EVGA GTX 980 SC G. Skill Trident Z 16GB(2x8GB) 
Hard DriveHard DriveHard DriveHard Drive
Samsung 830 64GB Samsung 840 Evo 120GB Seagate ST 2TB Seagate ST 500GB 
CoolingOSMonitorMonitor
Corsair H60 Win 10 Pro Planar PX2710MW AOC U2868PQU 
KeyboardPowerCaseMouse
Rosewill RGB80 Corsair HX850 Corsair Obsidian 250D Logitech M705 
Mouse Pad
XTrac Ripper XL 
CPUMotherboardGraphicsRAM
Core 2 Duo T5670 Dell OEM Intel GMA 950 3Gb DDR2-667 
Hard DriveOSMonitor
WD Scorpio Blue 250Gb Linux Ubuntu 12.10 x64 15.4" Tru-Bright 1280x800 
CPUMotherboardGraphicsRAM
Snapdragon 600 MSM8960 Adreno 320 2GB LPDDR 
Hard DriveOSMonitor
16GB+16GB Jelly Bean 4.2.2 JDQ 1080p 
  hide details  
Reply
Little Black Box
(18 items)
 
Vostro
(7 items)
 
Galaxy S4
(7 items)
 
CPUMotherboardGraphicsRAM
i5 6600k AsRock Fatal1ty Z170 ITX EVGA GTX 980 SC G. Skill Trident Z 16GB(2x8GB) 
Hard DriveHard DriveHard DriveHard Drive
Samsung 830 64GB Samsung 840 Evo 120GB Seagate ST 2TB Seagate ST 500GB 
CoolingOSMonitorMonitor
Corsair H60 Win 10 Pro Planar PX2710MW AOC U2868PQU 
KeyboardPowerCaseMouse
Rosewill RGB80 Corsair HX850 Corsair Obsidian 250D Logitech M705 
Mouse Pad
XTrac Ripper XL 
CPUMotherboardGraphicsRAM
Core 2 Duo T5670 Dell OEM Intel GMA 950 3Gb DDR2-667 
Hard DriveOSMonitor
WD Scorpio Blue 250Gb Linux Ubuntu 12.10 x64 15.4" Tru-Bright 1280x800 
CPUMotherboardGraphicsRAM
Snapdragon 600 MSM8960 Adreno 320 2GB LPDDR 
Hard DriveOSMonitor
16GB+16GB Jelly Bean 4.2.2 JDQ 1080p 
  hide details  
Reply
post #88 of 223
Quote:
Originally Posted by Heavy MG View Post

/facepalm. I never said such a thing,you did. Toms is often Intel biased.
PHII is on par with the C2Q and Core i5,both are modern CPU's.
Not their fault if Intel is just better than AMD .. wuts wrong with u.
post #89 of 223
Ahhh so glad i dumped my 1090T for my i5-2500k back in late December, nothing makes me happier than knowing I ended up paying less for my i5-2500k than I did for my 1090T.
    
CPUMotherboardGraphicsGraphics
Intel Core i5 2500K P8P67 PRO NVIDIA GeForce GTX 470 NVIDIA GeForce GTX 470 
GraphicsRAMRAMRAM
NVIDIA GeForce 9800 GT G-Skill A-Data G-Skill 
RAMHard DriveOptical DriveOS
A-Data Crucial M4 64GB + 1TB F3 Spinpoint $155 LS/DL DVD RW $?? Windows 8 64-bit "Epic Registry" Edition 
MonitorPowerCase
ASUS 21.5 1920x1080 2ms $135 CORSAIR HX850 $120 Mother Earth $free 
  hide details  
Reply
    
CPUMotherboardGraphicsGraphics
Intel Core i5 2500K P8P67 PRO NVIDIA GeForce GTX 470 NVIDIA GeForce GTX 470 
GraphicsRAMRAMRAM
NVIDIA GeForce 9800 GT G-Skill A-Data G-Skill 
RAMHard DriveOptical DriveOS
A-Data Crucial M4 64GB + 1TB F3 Spinpoint $155 LS/DL DVD RW $?? Windows 8 64-bit "Epic Registry" Edition 
MonitorPowerCase
ASUS 21.5 1920x1080 2ms $135 CORSAIR HX850 $120 Mother Earth $free 
  hide details  
Reply
post #90 of 223
IB4 arguments about how IPC and single-threaded performance doesn't matter even though 99% of the apps out there are reliant upon it.

edit: looks like I"m too late...
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Hardware News
Overclock.net › Forums › Industry News › Hardware News › [TH] Tom's CPU Architecture Shootout: 16 CPUs, One Core Each, And 3 GHz