Results 1 to 9 of 9

Thread: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

  1. #1
    HEXUS.admin
    Join Date
    Apr 2005
    Posts
    30,402
    Thanks
    0
    Thanked
    1,943 times in 684 posts

    Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    Der8auer sliced up some CPUs and put them under a scanning electron microscope.
    Read more.

  2. Received thanks from:

    Corky34 (22-09-2020)

  3. #2
    <Insert witty one liner> Kanoe's Avatar
    Join Date
    Dec 2005
    Posts
    854
    Thanks
    72
    Thanked
    82 times in 57 posts
    • Kanoe's system
      • Motherboard:
      • Asus Z9PE-D8 WS (Custom BIOS for NVMe Booting)
      • CPU:
      • 2x Intel Xeon E5-2667v2 @ Stock
      • Memory:
      • Samsung ECC RDIMM DDR3 PC-14900 128GB (8 x 16GB) @ Stock
      • Storage:
      • 960GB M.2, 960GB M.2, 960GB SSD, 2TB HDD
      • Graphics card(s):
      • MSI Sea Hawk X 1080Ti (2012MHz @1.012V)
      • PSU:
      • Superflower 1200W
      • Case:
      • Phanteks Enthoo Primo v2
      • Operating System:
      • Win 10 Pro 64bit
      • Monitor(s):
      • 28" ASUS PB287Q 4k + 24" Dell U2412M
      • Internet:
      • VM @ 940/45

    Re: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    It was a very interesting mini series of videos. The equipment they use is as facinating as the findings.

    I love the fact the conculsion was that process node numbers are complete b******s and cant be used for comparing one manufactues process versus another.

  4. #3
    root Member DanceswithUnix's Avatar
    Join Date
    Jan 2006
    Location
    In the middle of a core dump
    Posts
    11,181
    Thanks
    604
    Thanked
    1,223 times in 1,039 posts
    • DanceswithUnix's system
      • Motherboard:
      • Asus X470-PRO
      • CPU:
      • 3700X
      • Memory:
      • 16GB 3200MHz
      • Storage:
      • 1TB Linux, 1TB Games (Win 10)
      • Graphics card(s):
      • Asus Strix RX Vega 56
      • PSU:
      • 650W Corsair TX
      • Case:
      • Antec 300
      • Operating System:
      • Fedora 30 + Win 10 Pro 64 (yuk)
      • Monitor(s):
      • Benq XL2730Z 1440p + Samsung 2343BW 2048x1152
      • Internet:
      • Zen 80Mb/20Mb VDSL

    Re: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    Quote Originally Posted by Kanoe View Post
    I love the fact the conculsion was that process node numbers are complete b******s and cant be used for comparing one manufactues process versus another.
    *shock*, You'll be saying TDP numbers can't be compared next, or even GHz numbers

  5. Received thanks from:

    Sumanji (25-09-2020)

  6. #4
    Senior Member
    Join Date
    Sep 2014
    Posts
    369
    Thanks
    0
    Thanked
    9 times in 9 posts

    Re: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    Quote Originally Posted by DanceswithUnix View Post
    Quote Originally Posted by Kanoe View Post
    I love the fact the conculsion was that process node numbers are complete b******s and cant be used for comparing one manufactues process versus another.
    *shock*, You'll be saying TDP numbers can't be compared next, or even GHz numbers
    I guess he didn't meant that, only that different manufactures node sizes are incomparable between manufacturers. its comparing apples to pears.
    TDP is also funny in recent years, this is why Intel decided to use another metric for chip power usage, as no one trusted the TDP anymore.

  7. #5
    Senior Member
    Join Date
    Dec 2013
    Posts
    3,138
    Thanks
    435
    Thanked
    396 times in 274 posts

    Re: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    Mind blown, something's wrong with me that the technology of looking at things that small gets my juices fizzing.

  8. #6
    Member
    Join Date
    Mar 2018
    Posts
    195
    Thanks
    8
    Thanked
    11 times in 10 posts

    Re: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    Quote Originally Posted by HEXUS View Post
    Another metric, probably worth closer consideration is transistor density, as revealed by the chip fabricators. Intel 10 nm and TSMC 7nm processes both produce dies with approx 90 million transistors per sq millimetre.
    The 10nm+ Sunny Cove core in Lakefield is ~50mT/mm2. Haven't seen any other actual calculated numbers for 10nm.

  9. #7
    Senior Member
    Join Date
    Dec 2013
    Posts
    3,138
    Thanks
    435
    Thanked
    396 times in 274 posts

    Re: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    Quote Originally Posted by edmundhonda View Post
    The 10nm+ Sunny Cove core in Lakefield is ~50mT/mm2. Haven't seen any other actual calculated numbers for 10nm.
    Not going on what wikichips worked out.
    For example, for Intel’s 10nm there are 8 diffusion lines with a fin pitch of 34nm giving us a cell height of 272. With a poly pitch is 54nm, we get [4 transistors] / [272 nm x (3 * 54 nm)] = 90.78 MTr/mm² for the NAND2 gate. For the complex flip-flop, Intel’s optimizations results in around 121 MTr/mm². The total density is thus around 102.9 MTr/mm² (note that Intel reported 100.8 MTr/mm²).
    If anyone questions that maths I'll cry BTW as what i just quoted is lost on me.

    I don't even understand what things like  and 'r' means.

  10. #8
    Registered+
    Join Date
    Sep 2020
    Posts
    23
    Thanks
    0
    Thanked
    3 times in 1 post

    Re: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    Never seen anything like this before, really insightful! Still can’t believe intel are still on 14nm though!

  11. #9
    Registered+
    Join Date
    Mar 2016
    Posts
    15
    Thanks
    0
    Thanked
    0 times in 0 posts

    Re: Intel 14nm and AMD/TSMC 7nm transistors micro-compared

    Quote Originally Posted by Corky34 View Post
    Not going on what wikichips worked out.

    If anyone questions that maths I'll cry BTW as what i just quoted is lost on me.

    I don't even understand what things like  and 'r' means.
    These low geometries are hard to follow sometimes. I suppose  is a typo on a malformed website - it does not make sense. I do not see 'r' on its own, only as part of MTr, that I assume means Million Transistors. So you get Mtr/mm2 = Million Transistors per square millimeter.
    If you want to get your head explode, a rough number for distance between atoms in many solid materials is 0.1nm or 0.2nm.

Thread Information

Users Browsing this Thread

There are currently 1 users browsing this thread. (0 members and 1 guests)

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •