Page 1 of 3 123 LastLast
Results 1 to 25 of 72

Thread: AMD shows 28nm wafer GlobalFoundries to meet new card?

  1. #1
    Xtreme Addict
    Join Date
    Jan 2009
    Posts
    1,445

    AMD shows 28nm wafer GlobalFoundries to meet new card?

    AMD split came from the foundry, today once again demonstrated the GlobalFoundries wafer 28nm process, and not a simple repetition of half a year ago.

    2009年6月初,GlobalFoundries刚刚宣布纽约工厂Fab 2即将正式动工,就拿出了45nm、32nm、28nm等多种工艺的晶圆,其中最先进的28nm还支持SR AM Bulk测试品,没有实际用途。 Early June 2009, GlobalFoundries just announced that Fab 2 facility in New York will soon commence work on the come up with 45nm, 32nm, 28nm wafer process etc., which also supports the most advanced 28nm test SRAM Bulk goods, there is no practical purpose.

    http://translate.google.com/translat...&sl=auto&tl=en


    translation is not that great but, it looks like later this year 28nm products will be launched...yay!
    [MOBO] Asus CrossHair Formula 5 AM3+
    [GPU] ATI 6970 x2 Crossfire 2Gb
    [RAM] G.SKILL Ripjaws X Series 16GB (4 x 4GB) 240-Pin DDR3 1600
    [CPU] AMD FX-8120 @ 4.8 ghz
    [COOLER] XSPC Rasa 750 RS360 WaterCooling
    [OS] Windows 8 x64 Enterprise
    [HDD] OCZ Vertex 3 120GB SSD
    [AUDIO] Logitech S-220 17 Watts 2.1

  2. #2
    Xtreme Enthusiast
    Join Date
    Feb 2009
    Location
    Lima, Peru
    Posts
    600
    So it possible to see HD6000 before xmas, great.

    Even a HD5000 improved chip.


    ---
    About the 890GX, is it the same RV620 or a RV710?
    Athlon II X4 620 2.6Ghz @1.1125v | Foxconn A7DA-S (790GX) | 2x2GB OCZ Platinum DDR2 1066
    | Gigabyte HD4770 | Seagate 7200.12 3x1TB | Samsung F4 HD204UI 2x2TB | LG H10N | OCZ StealthXStream 500w| Coolermaster Hyper 212+ | Compaq MV740 17"

    Stock HSF: 18°C idle / 37°C load (15°C ambient)
    Hyper 212+: 16°C idle / 29°C load (15°C ambient)

    Why AMD Radeon rumors/leaks "are not always accurate"
    Reality check

  3. #3
    Xtreme Member
    Join Date
    Aug 2009
    Posts
    244
    This chinese article is translated from semiaccurate....

    http://www.semiaccurate.com/2010/01/...wafer-spotted/

  4. #4
    Xtreme Member
    Join Date
    Oct 2009
    Location
    Santos(São Paulo), Brasil.
    Posts
    202
    Quote Originally Posted by Nintendork View Post
    About the 890GX, is it the same RV620 or a RV710?
    Since it's capable of hybrid crossfire with cedar, it should be a "RV810".
    AMD Phenom II X6 1055T @ 4009MHz
    NB @ 2673MHz
    Corsair H50 + Scythe Ultra Kaze 3k
    Gigabyte GA-MA790X-UD4P
    2X2GB DDR2 OCZ Gold
    XFX Radeon HD5850 XXX @ 900MHz Core
    OCZ Agility2 60GB
    2x500GB HDD WD Blue
    250GB Samsung
    SevenTeam 620W PAF
    CoolerMaster CM690

  5. #5
    Xtreme Mentor
    Join Date
    Apr 2005
    Posts
    2,550
    translation sux!
    Adobe is working on Flash Player support for 64-bit platforms as part of our ongoing commitment to the cross-platform compatibility of Flash Player. We expect to provide native support for 64-bit platforms in an upcoming release of Flash Player following the release of Flash Player 10.1.

  6. #6
    Xtreme Enthusiast
    Join Date
    Oct 2007
    Location
    Singapore
    Posts
    970
      
    GlobalFoundries表示,28nm工艺进展顺利,今年下半年就会正式投产
    This sentence says that 28nm process is in good progress, second half of this year would be in mass production
    Main Rig:
    Processor & Motherboard:AMD Ryzen5 1400 ' Gigabyte B450M-DS3H
    Random Access Memory Module:Adata XPG DDR4 3000 MHz 2x8GB
    Graphic Card:XFX RX 580 4GB
    Power Supply Unit:FSP AURUM 92+ Series PT-650M
    Storage Unit:Crucial MX 500 240GB SATA III SSD
    Processor Heatsink Fan:AMD Wraith Spire RGB
    Chasis:Thermaltake Level 10GTS Black

  7. #7
    I am Xtreme
    Join Date
    Dec 2008
    Location
    France
    Posts
    9,060
    Quote Originally Posted by haylui View Post
      

    This sentence says that 28nm process is in good progress, second half of this year would be in mass production
    Amazing! Really good news!
    Donate to XS forums
    Quote Originally Posted by jayhall0315 View Post
    If you are really extreme, you never let informed facts or the scientific method hold you back from your journey to the wrong answer.

  8. #8
    Xtreme X.I.P. Particle's Avatar
    Join Date
    Apr 2008
    Location
    Kansas
    Posts
    3,219
    Lower numbers are always exciting. Makes sense for 6Ks due to the timing.
    Particle's First Rule of Online Technical Discussion:
    As a thread about any computer related subject has its length approach infinity, the likelihood and inevitability of a poorly constructed AMD vs. Intel fight also exponentially increases.

    Rule 1A:
    Likewise, the frequency of a car pseudoanalogy to explain a technical concept increases with thread length. This will make many people chuckle, as computer people are rarely knowledgeable about vehicular mechanics.

    Rule 2:
    When confronted with a post that is contrary to what a poster likes, believes, or most often wants to be correct, the poster will pick out only minor details that are largely irrelevant in an attempt to shut out the conflicting idea. The core of the post will be left alone since it isn't easy to contradict what the person is actually saying.

    Rule 2A:
    When a poster cannot properly refute a post they do not like (as described above), the poster will most likely invent fictitious counter-points and/or begin to attack the other's credibility in feeble ways that are dramatic but irrelevant. Do not underestimate this tactic, as in the online world this will sway many observers. Do not forget: Correctness is decided only by what is said last, the most loudly, or with greatest repetition.

    Rule 3:
    When it comes to computer news, 70% of Internet rumors are outright fabricated, 20% are inaccurate enough to simply be discarded, and about 10% are based in reality. Grains of salt--become familiar with them.

    Remember: When debating online, everyone else is ALWAYS wrong if they do not agree with you!

    Random Tip o' the Whatever
    You just can't win. If your product offers feature A instead of B, people will moan how A is stupid and it didn't offer B. If your product offers B instead of A, they'll likewise complain and rant about how anyone's retarded cousin could figure out A is what the market wants.

  9. #9
    Xtreme Member
    Join Date
    Nov 2008
    Posts
    117
    This is ?
    Attached Thumbnails Attached Thumbnails Click image for larger version. 

Name:	GF28nm.jpg 
Views:	3005 
Size:	164.7 KB 
ID:	100427  
    When AMD had 64-bit and Intel had only 32-bit, they tried to tell the world there was no need for 64-bit. Until they got 64-bit.
    When AMD had IMC and Intel had FSB, they told the world "there is plenty of life left in the FSB" (actual quote, and yes, they had *math* to show it had more bandwidth). Until they got an IMC.
    When AMD had dual core and Intel had single core, they told the world that consumers don't need multi core. Until they got dual core.
    When intel was using MCM, they said it was a better solution than native dies. Until they got native dies. (To be fair, we knocked *unconnected* MCM, and still do, we never knocked MCM as a technology, so hold your flames.)
    by John Fruehe

  10. #10
    Registered User
    Join Date
    Oct 2009
    Location
    Zagreb, Croatia
    Posts
    8
    excellent news

    looking foward to new GPUs
    Intel E8400 @ 4.2 GHz @ Thermalright ultra 120 extreme - lapped @ TR IFX-10
    Asus P5Q-E, Corsair Dominator 2x2 GB 1120 MHz CL5 @ 2.00 V
    BFG 7900GS, Antec 1200, Asus PW201, Corsair TX 750W
    WD6400AAKS, RAZER Lachesis & eXactMat & Tarantula
    Logitech Z-5500, CREATIVE SB X-Fi Fatal1ty & Gaming Headset, Linksys WRT54GL @250 MHz, D-LINK DSL-321B
    MSI GX720

  11. #11
    Xtreme Member
    Join Date
    Dec 2005
    Location
    NC, USA
    Posts
    285
    I believe i saw a roadmap somewhere that put the 5890 on 28nm process- Should be the refresh for later this year.

    That die looks more like the small gpus you guys mentioned, but it is good to see that they have the process working well enough for production, at least.
    Current: 2500k@ 4.0 // 8g Gskill // TZ68k+ // 5850 @ 900
    Best way to catch me is by PM // AKA Harmavoidance0


  12. #12
    Xtreme Cruncher
    Join Date
    Jan 2007
    Location
    VA, USA
    Posts
    932
    God damn it... I was about to hit the buy button on 5870 though 28NM looks even better.
    I'll never be able to buy a new Video card at this rate.

  13. #13
    Xtreme X.I.P. Particle's Avatar
    Join Date
    Apr 2008
    Location
    Kansas
    Posts
    3,219
    Quote Originally Posted by Kurz View Post
    God damn it... I was about to hit the buy button on 5870 though 28NM looks even better.
    I'll never be able to buy a new Video card at this rate.
    You'll be waiting a long time if you hold off.

    ---

    ATI historically has tried new processes on small GPUs like when the 4770 came out. It would make sense that that's the case here as well.
    Particle's First Rule of Online Technical Discussion:
    As a thread about any computer related subject has its length approach infinity, the likelihood and inevitability of a poorly constructed AMD vs. Intel fight also exponentially increases.

    Rule 1A:
    Likewise, the frequency of a car pseudoanalogy to explain a technical concept increases with thread length. This will make many people chuckle, as computer people are rarely knowledgeable about vehicular mechanics.

    Rule 2:
    When confronted with a post that is contrary to what a poster likes, believes, or most often wants to be correct, the poster will pick out only minor details that are largely irrelevant in an attempt to shut out the conflicting idea. The core of the post will be left alone since it isn't easy to contradict what the person is actually saying.

    Rule 2A:
    When a poster cannot properly refute a post they do not like (as described above), the poster will most likely invent fictitious counter-points and/or begin to attack the other's credibility in feeble ways that are dramatic but irrelevant. Do not underestimate this tactic, as in the online world this will sway many observers. Do not forget: Correctness is decided only by what is said last, the most loudly, or with greatest repetition.

    Rule 3:
    When it comes to computer news, 70% of Internet rumors are outright fabricated, 20% are inaccurate enough to simply be discarded, and about 10% are based in reality. Grains of salt--become familiar with them.

    Remember: When debating online, everyone else is ALWAYS wrong if they do not agree with you!

    Random Tip o' the Whatever
    You just can't win. If your product offers feature A instead of B, people will moan how A is stupid and it didn't offer B. If your product offers B instead of A, they'll likewise complain and rant about how anyone's retarded cousin could figure out A is what the market wants.

  14. #14
    I am Xtreme
    Join Date
    Dec 2007
    Posts
    7,750
    Quote Originally Posted by Particle View Post
    You'll be waiting a long time if you hold off.

    ---

    ATI historically has tried new processes on small GPUs like when the 4770 came out. It would make sense that that's the case here as well.
    not sure they could do that this time. they already use 128bit on their mid range cards, they cant get that much lower. if anything they might ONLY make mobile gpus on 28nm to test it out, where 64bit super slow gddr5 wont be missed as much.

  15. #15
    Xtreme Addict
    Join Date
    Jan 2008
    Location
    Puerto Rico
    Posts
    1,374
    Seems ATi is preparing Anti-Fermi weapon, maybe will not win by a large margin to fermi (all depends how "overpowered" fermi is going to be) then wham suddenly the marketing team comes in action and says "hey we have 28nm they don't and at a better price too!" and price is the key to success...
    ░█▀▀ ░█▀█ ░█ ░█▀▀ ░░█▀▀ ░█▀█ ░█ ░█ ░░░
    ░█▀▀ ░█▀▀ ░█ ░█ ░░░░█▀▀ ░█▀█ ░█ ░█ ░░░
    ░▀▀▀ ░▀ ░░░▀ ░▀▀▀ ░░▀ ░░░▀░▀ ░▀ ░▀▀▀ ░

  16. #16
    Xtreme Addict
    Join Date
    Nov 2004
    Posts
    1,363
    Given that the fab process is going well; what does this mean for Dozer? Does this mean Bulldozer is now going to be made on a 28nm fab later this year?
    NZXT Tempest | Corsair 1000W
    Creative X-FI Titanium Fatal1ty Pro
    Intel i7 2500K Corsair H100
    PNY GTX 470 SLi (700 / 1400 / 1731 / 950mv)
    Asus P8Z68-V Pro
    Kingston HyperX PC3-10700 (4x4096MB)(9-9-9-28 @ 1600mhz @ 1.5v)

    Heatware: 13-0-0

  17. #17
    Xtreme Addict
    Join Date
    Nov 2006
    Posts
    1,402
    28nm is bulk i think.

  18. #18
    Xtreme X.I.P. Particle's Avatar
    Join Date
    Apr 2008
    Location
    Kansas
    Posts
    3,219
    Bulldozer will be on 32nm HKMG SOI. AMD and Intel don't make CPUs on half nodes. 45 > 32 > 22
    Particle's First Rule of Online Technical Discussion:
    As a thread about any computer related subject has its length approach infinity, the likelihood and inevitability of a poorly constructed AMD vs. Intel fight also exponentially increases.

    Rule 1A:
    Likewise, the frequency of a car pseudoanalogy to explain a technical concept increases with thread length. This will make many people chuckle, as computer people are rarely knowledgeable about vehicular mechanics.

    Rule 2:
    When confronted with a post that is contrary to what a poster likes, believes, or most often wants to be correct, the poster will pick out only minor details that are largely irrelevant in an attempt to shut out the conflicting idea. The core of the post will be left alone since it isn't easy to contradict what the person is actually saying.

    Rule 2A:
    When a poster cannot properly refute a post they do not like (as described above), the poster will most likely invent fictitious counter-points and/or begin to attack the other's credibility in feeble ways that are dramatic but irrelevant. Do not underestimate this tactic, as in the online world this will sway many observers. Do not forget: Correctness is decided only by what is said last, the most loudly, or with greatest repetition.

    Rule 3:
    When it comes to computer news, 70% of Internet rumors are outright fabricated, 20% are inaccurate enough to simply be discarded, and about 10% are based in reality. Grains of salt--become familiar with them.

    Remember: When debating online, everyone else is ALWAYS wrong if they do not agree with you!

    Random Tip o' the Whatever
    You just can't win. If your product offers feature A instead of B, people will moan how A is stupid and it didn't offer B. If your product offers B instead of A, they'll likewise complain and rant about how anyone's retarded cousin could figure out A is what the market wants.

  19. #19
    Xtreme Member
    Join Date
    Nov 2008
    Posts
    117
    Quote Originally Posted by Particle View Post
    Bulldozer will be on 32nm HKMG SOI. AMD and Intel don't make CPUs on half nodes. 45 > 32 > 22
    If BUlldozer die is too big, I think AMD will do...........
    28nm SOI+high-k meta gate.
    When AMD had 64-bit and Intel had only 32-bit, they tried to tell the world there was no need for 64-bit. Until they got 64-bit.
    When AMD had IMC and Intel had FSB, they told the world "there is plenty of life left in the FSB" (actual quote, and yes, they had *math* to show it had more bandwidth). Until they got an IMC.
    When AMD had dual core and Intel had single core, they told the world that consumers don't need multi core. Until they got dual core.
    When intel was using MCM, they said it was a better solution than native dies. Until they got native dies. (To be fair, we knocked *unconnected* MCM, and still do, we never knocked MCM as a technology, so hold your flames.)
    by John Fruehe

  20. #20
    Xtreme Addict
    Join Date
    Jul 2009
    Posts
    1,023
    what's the harm of doing bulldozer on 28nm?

    I hope 6K comes out before Christmas, amazing GPU for me and high sales for AMD.
    i7 920 @ 4GHz 1.25v
    GTX 470 @ 859MHz 1062mv

  21. #21
    Xtreme X.I.P. Particle's Avatar
    Join Date
    Apr 2008
    Location
    Kansas
    Posts
    3,219
    It just won't happen. I can't recall them ever making a CPU on a half node. It's not like GF can just pick up and start doing 28nm HKMG SOI because they have bulk. Nor can AMD simply decide they want to move their design to bulk if it was developed for SOI. It isn't that simple.
    Particle's First Rule of Online Technical Discussion:
    As a thread about any computer related subject has its length approach infinity, the likelihood and inevitability of a poorly constructed AMD vs. Intel fight also exponentially increases.

    Rule 1A:
    Likewise, the frequency of a car pseudoanalogy to explain a technical concept increases with thread length. This will make many people chuckle, as computer people are rarely knowledgeable about vehicular mechanics.

    Rule 2:
    When confronted with a post that is contrary to what a poster likes, believes, or most often wants to be correct, the poster will pick out only minor details that are largely irrelevant in an attempt to shut out the conflicting idea. The core of the post will be left alone since it isn't easy to contradict what the person is actually saying.

    Rule 2A:
    When a poster cannot properly refute a post they do not like (as described above), the poster will most likely invent fictitious counter-points and/or begin to attack the other's credibility in feeble ways that are dramatic but irrelevant. Do not underestimate this tactic, as in the online world this will sway many observers. Do not forget: Correctness is decided only by what is said last, the most loudly, or with greatest repetition.

    Rule 3:
    When it comes to computer news, 70% of Internet rumors are outright fabricated, 20% are inaccurate enough to simply be discarded, and about 10% are based in reality. Grains of salt--become familiar with them.

    Remember: When debating online, everyone else is ALWAYS wrong if they do not agree with you!

    Random Tip o' the Whatever
    You just can't win. If your product offers feature A instead of B, people will moan how A is stupid and it didn't offer B. If your product offers B instead of A, they'll likewise complain and rant about how anyone's retarded cousin could figure out A is what the market wants.

  22. #22
    Xtreme Enthusiast
    Join Date
    Dec 2009
    Posts
    846
    Quote Originally Posted by Helloworld_98 View Post
    what's the harm of doing bulldozer on 28nm?
    To build a 28nm product you need to start with a 28nm toolkit and 28nm components.

    You can't just shrink a 32nm design to 28nm like you shrink the font in a document.
    While I work for AMD, my posts are my own opinions.

    http://blogs.amd.com/work/author/jfruehe/

  23. #23
    Xtreme Member
    Join Date
    Sep 2009
    Location
    Czech Republic, 50°4'52.22"N, 14°23'30.45"E
    Posts
    474
    Quote Originally Posted by Particle View Post
    It just won't happen. I can't recall them ever making a CPU on a half node. It's not like GF can just pick up and start doing 28nm HKMG SOI because they have bulk. Nor can AMD simply decide they want to move their design to bulk if it was developed for SOI. It isn't that simple.
    But the graphics part of Fusion would be shrink from bulk to SOI, right?

  24. #24
    Xtreme Addict
    Join Date
    Jul 2008
    Location
    US
    Posts
    1,379
    Quote Originally Posted by Particle View Post
    ATI historically has tried new processes on small GPUs like when the 4770 came out. It would make sense that that's the case here as well.
    The 3870 was the first product on 55nm, was it not?

    --Matt
    My Rig :
    Core i5 4570S - ASUS Z87I-DELUXE - 16GB Mushkin Blackline DDR3-2400 - 256GB Plextor M5 Pro Xtreme

  25. #25
    Xtreme Addict
    Join Date
    Apr 2007
    Posts
    1,870
    Quote Originally Posted by mattkosem View Post
    The 3870 was the first product on 55nm, was it not?
    3870 was a midrange GPU.

Page 1 of 3 123 LastLast

Bookmarks

Bookmarks

Posting Permissions

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