Overclock.net › Forums › Industry News › Hardware News › [Xbit] Intel Begins Work on 7nm, 5nm Process Technologies
New Posts  All Forums:Forum Nav:

[Xbit] Intel Begins Work on 7nm, 5nm Process Technologies - Page 10

post #91 of 132
I hate silicon...
post #92 of 132
Quote:
Originally Posted by Riou View Post

Larabee says hello. tongue.gif

I meant it all the way around, Intel announces stuff 5 years before developing anything, unlike TSMC/GF XD
   
AGP bencher
(14 items)
 
CPUMotherboardGraphicsRAM
Ryzen R7 1700 Gigabyte GA-AX370-Gaming 5 Sapphire HD 6950 2GiB 2x8GB KFA2 HOF DDR4-3600 
Hard DriveHard DriveHard DriveHard Drive
Crucial MX100 256GB Seagate 600 Series 240GB Seagate 7200.14 2TB Samsung F3 1TB 
CoolingCoolingCoolingCooling
EKWB Supreme HF XSPC Rasa GPU EK XT360 EK 4.0 
OSMonitorMonitorKeyboard
W10 Pro LG IPS235 LG E2250V KUL ES-87 
PowerCaseMouseAudio
SF Leadex II 650W Lian Li PC-A05NB Logitech G9 Xonar DX 
AudioAudio
SMSL SA-S3+Technics CB-250 Sennheiser HD555 
CPUMotherboardRAMHard Drive
AMD A10-5700 Gigabyte F2A75M-HD2 G.SKILL Ares 2133 CL9 Hitachi 5K750 
Hard DriveCoolingOSMonitor
Momentus .7 200GB Noctua NH-L9a Server 2012 R2 Standard AUO B156HW01 
PowerCaseOther
PicoPSU-80-WI-25V AIO Aluminium Handmade TP-Link Archer Something Something Wi-Fi AC 
CPUCPUCPUMotherboard
Core2Duo E6400 Core2Quad Q6600 Pentium Dual Core E5200 AsRock 4COREDUAL-SATA2 R2.0 
GraphicsRAMHard DriveOptical Drive
A dumpload of ancient AGP cards Kingston Value DDR2-667 CL4 2T @CL3 1T Seagate 160GB 7200.10 LG IDE DVD-ROM 
CoolingCoolingOSMonitor
Ghettomade CPU waterblock 49cc 2stroke engine copper radiator WinXP SP2 32bit ProView 17" 
PowerCase
Tacens Radix V 550W Ghetto aluminium bench 
  hide details  
Reply
   
AGP bencher
(14 items)
 
CPUMotherboardGraphicsRAM
Ryzen R7 1700 Gigabyte GA-AX370-Gaming 5 Sapphire HD 6950 2GiB 2x8GB KFA2 HOF DDR4-3600 
Hard DriveHard DriveHard DriveHard Drive
Crucial MX100 256GB Seagate 600 Series 240GB Seagate 7200.14 2TB Samsung F3 1TB 
CoolingCoolingCoolingCooling
EKWB Supreme HF XSPC Rasa GPU EK XT360 EK 4.0 
OSMonitorMonitorKeyboard
W10 Pro LG IPS235 LG E2250V KUL ES-87 
PowerCaseMouseAudio
SF Leadex II 650W Lian Li PC-A05NB Logitech G9 Xonar DX 
AudioAudio
SMSL SA-S3+Technics CB-250 Sennheiser HD555 
CPUMotherboardRAMHard Drive
AMD A10-5700 Gigabyte F2A75M-HD2 G.SKILL Ares 2133 CL9 Hitachi 5K750 
Hard DriveCoolingOSMonitor
Momentus .7 200GB Noctua NH-L9a Server 2012 R2 Standard AUO B156HW01 
PowerCaseOther
PicoPSU-80-WI-25V AIO Aluminium Handmade TP-Link Archer Something Something Wi-Fi AC 
CPUCPUCPUMotherboard
Core2Duo E6400 Core2Quad Q6600 Pentium Dual Core E5200 AsRock 4COREDUAL-SATA2 R2.0 
GraphicsRAMHard DriveOptical Drive
A dumpload of ancient AGP cards Kingston Value DDR2-667 CL4 2T @CL3 1T Seagate 160GB 7200.10 LG IDE DVD-ROM 
CoolingCoolingOSMonitor
Ghettomade CPU waterblock 49cc 2stroke engine copper radiator WinXP SP2 32bit ProView 17" 
PowerCase
Tacens Radix V 550W Ghetto aluminium bench 
  hide details  
Reply
post #93 of 132
Quote:
Originally Posted by Artikbot View Post

I meant it all the way around, Intel announces stuff 5 years before developing anything, unlike TSMC/GF XD

They announce roadmaps years in advance:
346

338
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 #94 of 132
Quote:
Originally Posted by Strat79 View Post

Make them faster? Everyone seems to forget we have a whole other path to go down still. Even if they hit a wall for shrinking somewhere between 10-5nm, they can come up with something that would allow much faster switching of transistors, as in faster clocks/more IPS. Everyone is quick to dismiss faster clocks probably due to the whole P4 debacle. Given an impending dead end for shrinking, you can bet they are looking into ways to improve IPS, whether it be faster clocks or IPC. Just throwing out graphene because it is widely known already. Apparently it can increase the transistors switching speeds by an order of magnitude compared to current method's. Not saying it will be used, just given an example of a whole other path to think about.
If we can't shrink the transistor to allow more in the same space and power envelope or find any other method of adding more transistors(stacking, etc), then the logical choice would be to increase the rate at which they can switch on and off and/or increase how many instructions can be executed with each on/off cycle. I'm sure given enough money and time spent, they can find a way to increase clock speeds, IPC or whatever it takes to increase IPS overall. They don't do it now, because it is easier and much cheaper to just do the same tried and true shrink, pack more in strategy. I could be completely wrong, they may come up with something new that we would never think of. I'm just thinking of, what seems to me, the most logical way to go once we reach the shrink limit....speed those things up!

I'm pretty sure switching speed is the only thing that is limiting the frequency. Smaller transistors switch faster because they are smaller, it's like a violin vs a contrabass. Violin is small so it vibrates a lot faster. The reason you can run 32nm and 22nm at the same frequency is voltage. You force the transistor to switch faster with brute force in the case of 32nm.
Increasing the IPC is also not really easy to do, it's mostly tricks like branch predicting, pipelining, .... But there is always some sort of limit. Just as there is a limit to splitting programs in multiple threads. Thats why i think stacking wont solve much either as stacking would have no effect on clk speeds but would only mean an increase in cores/cache size.
2013
(11 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7 2700k GIGABYTE GA-Z77-D3H Sapphire HD 7870 XT Boost G.SKILL 1866 Sniper 2x4 GB 
Hard DriveHard DriveOSMonitor
Samsung 840 Basic Crucial MX200 Windows 10 HP IPS 23-inch 1080p 
PowerCaseMouse
Be quiet! BN144 System Power 7 500W NZXT Tempest 210 Zowie FK1 
  hide details  
Reply
2013
(11 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7 2700k GIGABYTE GA-Z77-D3H Sapphire HD 7870 XT Boost G.SKILL 1866 Sniper 2x4 GB 
Hard DriveHard DriveOSMonitor
Samsung 840 Basic Crucial MX200 Windows 10 HP IPS 23-inch 1080p 
PowerCaseMouse
Be quiet! BN144 System Power 7 500W NZXT Tempest 210 Zowie FK1 
  hide details  
Reply
post #95 of 132
Quote:
Originally Posted by Sisaroth View Post

I'm pretty sure switching speed is the only thing that is limiting the frequency. Smaller transistors switch faster because they are smaller, it's like a violin vs a contrabass. Violin is small so it vibrates a lot faster. The reason you can run 32nm and 22nm at the same frequency is voltage. You force the transistor to switch faster with brute force in the case of 32nm.
Increasing the IPC is also not really easy to do, it's mostly tricks like branch predicting, pipelining, .... But there is always some sort of limit. Just as there is a limit to splitting programs in multiple threads. Thats why i think stacking wont solve much either as stacking would have no effect on clk speeds but would only mean an increase in cores/cache size.

Switching speeds is only one thing limiting frequency. The signals between components and transistors need to not be too noisy as well. As the signal gets faster and lower power, noise becomes more of an issue.
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 #96 of 132
HOW can things get smaller..... and faster at the same time?
Air Force 1
(17 items)
 
  
CPUMotherboardGraphicsRAM
i5 7600k @4.8 ASUS z170 Sabertooth S EVGA GTX 980ti Ref 2x8gb Ripjaw-X @3200 
Hard DriveHard DriveHard DriveOptical Drive
WD 2tb Black WD 1tb Blue Sandisk 120 Asus 
CoolingOSMonitorKeyboard
CM Nepton 280L Windows 10 x64 lg 34uc69g-b Patriot v760 
PowerCaseMouseMouse Pad
OCZ ZX 850 Phanteks Entho Pro Green Mionix Naos 7000 Custom 36"x12" starcitizen mat 
Audio
Dayton BR-1 
  hide details  
Reply
Air Force 1
(17 items)
 
  
CPUMotherboardGraphicsRAM
i5 7600k @4.8 ASUS z170 Sabertooth S EVGA GTX 980ti Ref 2x8gb Ripjaw-X @3200 
Hard DriveHard DriveHard DriveOptical Drive
WD 2tb Black WD 1tb Blue Sandisk 120 Asus 
CoolingOSMonitorKeyboard
CM Nepton 280L Windows 10 x64 lg 34uc69g-b Patriot v760 
PowerCaseMouseMouse Pad
OCZ ZX 850 Phanteks Entho Pro Green Mionix Naos 7000 Custom 36"x12" starcitizen mat 
Audio
Dayton BR-1 
  hide details  
Reply
post #97 of 132
Quote:
Originally Posted by xFALL3Nx View Post

HOW can things get smaller..... and faster at the same time?
Seriously?
post #98 of 132
Quote:
Originally Posted by xFALL3Nx View Post

HOW can things get smaller..... and faster at the same time?

Smaller.... less distance to travel.... less energy required to move things...

(Also, less propagation delay)
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 #99 of 132
As far as I know, smaller processes result in lower production costs, therefore, with equal sells, profit increase. That is the soul purpose of new node sizes. Oh, and as a result, better products, brought faster than the competition (tick tock). Side result would be bringing down the competition. From all the cpu companies I knew when a boy, only AMD and VIA survived.

Side note, if better products would not come out, no one would buy them. I remembered the 8086 to 486 era. It took AGES for a processor to evolve. Only after AMD brought Duron and Athlon, the competition (therefore the evolution) began.
post #100 of 132
Quote:
Originally Posted by levathar View Post

As far as I know, smaller processes result in lower production costs, therefore, with equal sells, profit increase.
To add... Initial yields on immature processes tend to be lower than prior processes even if more dies fit per wafer. However, once the process matures... the yields increase again. thumb.gif
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
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Hardware News
Overclock.net › Forums › Industry News › Hardware News › [Xbit] Intel Begins Work on 7nm, 5nm Process Technologies