Overclock.net › Forums › Intel › Intel CPUs › I wonder if the "secret card" of Intel is a complete Fiasco of the FinFET design.
New Posts  All Forums:Forum Nav:

I wonder if the "secret card" of Intel is a complete Fiasco of the FinFET design.

post #1 of 3
Thread Starter 
Think about it. There comes Ivy Bridge after a successful Sandy Bridge and what does it do? It uses tri-gate FinFET design on 22nm. But wait a minute, the shrinking in considerable, yet the speedup is tiny, a miserable 10%, and Haswell follows. One could claim it's genuinely harder to properly shrink the transistor nowadays but wait a minute, they already did it there, they already reached the shrinking, so how is it so low in performance improvement?

The answer: If they did NOTHING AT ALL and didn't touch the flat non-FinFET design, it might had been enormously faster. thumb.gif

One could claim the technology might be new and might need the next iterations to be improved though that still makes the first iterations bad in theory. Plus, Haswell had the chance to do something big, it still was only a petty 10% improvement.

Then again, it might be genuinely necessary to go to such directions once we go to the dreaded 10nm and beyond, where electrons start playing poker with Heisenberg, but we'll see.
PC
(9 items)
 
  
CPUMotherboardGraphicsRAM
4790K 4.6G 1.24v/1.74v, 5.1G 1.35v validation. GA-Z97X-Gaming 7 Tri-X R9 290 1100/1350 +0.012v G.Skill 2400 c10 
CoolingMonitorPowerCase
Noctua NH-D15 24EA53 IPS 76Hz OC EVGA 1000 G2 Phanteks Enthoo Pro 
Audio
SoundMagic E10 
  hide details  
Reply
PC
(9 items)
 
  
CPUMotherboardGraphicsRAM
4790K 4.6G 1.24v/1.74v, 5.1G 1.35v validation. GA-Z97X-Gaming 7 Tri-X R9 290 1100/1350 +0.012v G.Skill 2400 c10 
CoolingMonitorPowerCase
Noctua NH-D15 24EA53 IPS 76Hz OC EVGA 1000 G2 Phanteks Enthoo Pro 
Audio
SoundMagic E10 
  hide details  
Reply
post #2 of 3
Quote:
Originally Posted by fateswarm View Post

Think about it. There comes Ivy Bridge after a successful Sandy Bridge and what does it do? It uses tri-gate FinFET design on 22nm. But wait a minute, the shrinking in considerable, yet the speedup is tiny, a miserable 10%, and Haswell follows. One could claim it's genuinely harder to properly shrink the transistor nowadays but wait a minute, they already did it there, they already reached the shrinking, so how is it so low in performance improvement?

The answer: If they did NOTHING AT ALL and didn't touch the flat non-FinFET design, it might had been enormously faster. thumb.gif

One could claim the technology might be new and might need the next iterations to be improved though that still makes the first iterations bad in theory. Plus, Haswell had the chance to do something big, it still was only a petty 10% improvement.

Then again, it might be genuinely necessary to go to such directions once we go to the dreaded 10nm and beyond, where electrons start playing poker with Heisenberg, but we'll see.

22nm 3D Finfet's main aim is not to increase performance. It is to increase the the processor's energy efficiency at mobile voltages & clocks (<1V, <3Ghz). Both Haswell Mobile and Silvermont Atoms will benefit from this advantage. How 22nm process scales with voltage & clock at Desktop Overcloker voltage & clocks(>1.3V, 4.5Ghz+) is not something Intel cares much about given the trend of the market.

From Anandtech's Silvermont preview artcile




Quote:
This part is huge. The move to 22nm 3D transistors lets Intel drop threshold voltage by approximately 100mV at the same leakage level. Remember that power scales with the square of voltage, so a 100mV savings depending on what voltage you’re talking about can be very huge. Intel’s numbers put the power savings at anywhere from 25 - 35% at threshold voltage. The gains don’t stop there either. At 1V, Intel’s 22nm process gives it an 18% improvement in transistor performance or at the same performance Intel can run the transistors at 0.8V - a 20% power savings. The benefits are even more pronounced at lower voltages: 37% faster performance at 0.7V or less than half the active power at the same performance.

Edited by sherlock - 7/7/13 at 10:46am
Skylake 1080 FTW
(18 items)
 
XPS 15
(7 items)
 
 
CPUMotherboardGraphicsRAM
i7-6700K  ASUS Maximus VIII Ranger EVGA 1080 FTW TridentZ DDR4-3000 
Hard DriveHard DriveHard DriveHard Drive
Samsung SM951 128GB Samsung 840 Pro 256 GB Muskin Reactor 1TB Seagate Baracuda 2TB ST2000DM001 HDD 
Hard DriveCoolingOSMonitor
Seagate Baracuda 2TB ST2000DM001 HDD Corsair H110i GT Windows 10 Pro  Acer XB321HK 32" 4K G-sync 
KeyboardPowerCaseMouse
Corsair K70 Rapid Fire EVGA SuperNova 650 P2 NZXT H440 Black Logitech G900  
Mouse PadOther
Razer Vespula CyberPower CP1500PFCLCD - PFC Sinewave UPS Syst... 
CPUMotherboardGraphicsRAM
i7-6700HQ 2.6Ghz(3.5Ghz Turbo) Dell XPS 15 Nvidia GTX 960M 8GB DDR4-2133 
Hard DriveOSMonitor
256GB PCIE SSD Windows 10 Pro 15.6" 1080p 
  hide details  
Reply
Skylake 1080 FTW
(18 items)
 
XPS 15
(7 items)
 
 
CPUMotherboardGraphicsRAM
i7-6700K  ASUS Maximus VIII Ranger EVGA 1080 FTW TridentZ DDR4-3000 
Hard DriveHard DriveHard DriveHard Drive
Samsung SM951 128GB Samsung 840 Pro 256 GB Muskin Reactor 1TB Seagate Baracuda 2TB ST2000DM001 HDD 
Hard DriveCoolingOSMonitor
Seagate Baracuda 2TB ST2000DM001 HDD Corsair H110i GT Windows 10 Pro  Acer XB321HK 32" 4K G-sync 
KeyboardPowerCaseMouse
Corsair K70 Rapid Fire EVGA SuperNova 650 P2 NZXT H440 Black Logitech G900  
Mouse PadOther
Razer Vespula CyberPower CP1500PFCLCD - PFC Sinewave UPS Syst... 
CPUMotherboardGraphicsRAM
i7-6700HQ 2.6Ghz(3.5Ghz Turbo) Dell XPS 15 Nvidia GTX 960M 8GB DDR4-2133 
Hard DriveOSMonitor
256GB PCIE SSD Windows 10 Pro 15.6" 1080p 
  hide details  
Reply
post #3 of 3
+rep sherlock.

Fateswarm is just a hater rolleyes.gif
Edited by adamlee05 - 7/7/13 at 3:23am
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Intel CPUs
Overclock.net › Forums › Intel › Intel CPUs › I wonder if the "secret card" of Intel is a complete Fiasco of the FinFET design.