4 chips in 6 months.

This is the schedule AMD’s GPU engineering teams committed themselves to for the launch of the Evergreen family. The entire family from top to bottom would be launched in a 6 month period.

Last month AMD took the first step of that plan with the launch of Cypress, the forebear of the family and the source of the Radeon HD 5870 and 5850. Today AMD is taking the next step in the launch of the Evergreen family by delivering the 2nd and final Evergreen chip of the year: Juniper. Or as the products based off of them are known as, the Radeon HD 5770 and 5750.

  ATI Radeon HD 5870 ATI Radeon HD 5850 ATI Radeon HD 5770 ATI Radeon HD 5750
ATI Radeon HD 4870
ATI Radeon HD 4850
Stream Processors 1600 1440 800 720 800 800
Texture Units 80 72 40 36 40 40
ROPs 32 32 16 16 16 16
Core Clock 850MHz 725MHz 850MHz 700MHz 750MHz 625MHz
Memory Clock 1.2GHz (4.8GHz data rate) GDDR5 1GHz (4GHz data rate) GDDR5 1.2GHz (4.8GHz data rate) GDDR5 1.15GHz (4.6GHz data rate) GDDR5 900MHz (3600MHz data rate) GDDR5 993MHz (1986MHz data rate) GDDR3
Memory Bus Width 256-bit 256-bit 128-bit 128-bit 256-bit 256-bit
Frame Buffer 1GB 1GB 1GB 1GB / 512MB 1GB 1GB / 512MB
Transistor Count 2.15B 2.15B 1.04B 1.04B 956M 956M
TDP 188W 151W 108W 86W 150W 110W
Manufacturing Process TSMC 40nm TSMC 40nm TSMC 40nm TSMC 40nm TSMC 55nm TSMC 55nm
Price Point $379 $259 $159 $129 / $109 $140-$160 $109-$129

In our 5800 series launch article, we briefly discussed Juniper and the other members of the Evergreen family. With Cypress a bit too big and a bit too expensive to hit mainstream prices, a new chip was introduced in to AMD’s usual 3 chip stack to cover that segment of the market, and that chip was Juniper.

What’s Juniper? In a nutshell, it’s all of Cypress’ features with half the functional units (and no Double Precision for you scientist types). DirectX 11, Eyefinity, angle-independent anisotropic filtering, HDMI bitstreaming, and supersample anti-aliasing are all accounted for. For more information on these features, please see our Radeon 5870 launch article from last month.

With half of the functional units left behind, we’re left with 10 SIMDs, giving us 800 stream processors and 40 texture units, while the ROP count has also been cut in half to 16, in turn giving us a 128-bit memory bus. If Cypress was 2 RV770s put together, then Juniper is the closest thing you’re going to see to RV770 coming out of the Evergreen family.


Juniper

With the reduction in functional units, Juniper becomes a leaner and meaner core. The transistor count is 1.04 billion, a little less than half of Cypress and about 100 million more than RV770. The die size of this resulting core is 166mm2, significantly less than both Cypress and RV770, the latter due to the smaller process size. RV770 for comparison was 260mm2.

From Juniper we are getting the 5770 and the 5750. The 5770 is a full Juniper, with all of Juniper’s functional units enabled and the card running at what amounts to a full speed of 850MHz (the same as 5850). The 5750 is slightly cut down, much like 5850 is compared to 5870. Here we have 1 SIMD disabled, and the core clock reduced to 700MHz. This is a notable departure from how AMD handled the 4870/4850 split, where 4850 was differentiated using a slightly slower core and much slower RAM, without the need to disable any SIMDs.

The smaller Juniper core also affords these cards lower power usage than the 5800 series. The 5770 is 108W at load and 18W at idle, meanwhile the 5750 is 86W at load and 16W at idle.

As an interesting aside, when AMD started sampling Evergreen cards to game development houses and other 3rd parties, they were Juniper based, and not Cypress based. The Juniper team was rather proud of this, particularly since Juniper came back from TSMC second. They also had less time to get their GPU up and working than the Cypress team did, since they had to wait on Cypress before being able to finish work on some elements. This is what makes AMD’s 6 month rollout all the more impressive, since it means the non-Cypress teams had less time to get their work done than they have in previous product cycles.

Meet The 5770
POST A COMMENT

117 Comments

View All Comments

  • Spoelie - Tuesday, October 13, 2009 - link

    The difference is obviously the memory bandwidth. It seems to me that ATi should have gone with a 192bit bus, this change alone would have made the HD57x0 a worthy successor to the HD48x0 range, without any performance caveats, while still being significantly cheaper to manufacture (40nm vs 55nm, 192bit vs 256bit). Reply
  • Skiprudder - Tuesday, October 13, 2009 - link

    I'm guessing your right, but I'd like to see Anand (or Ryan) do one of the track-down-the-engineers that this site is famous for, and hear the rational on AMD's part. Reply
  • CarrellK - Wednesday, October 14, 2009 - link

    Anand knows where I live...

    CarrellK
    Reply
  • futrtrubl - Tuesday, October 13, 2009 - link

    Or even just overclock the memory and see how performance scales. That would provide some evidence for the memory bottleneck theory. Reply
  • plague911 - Tuesday, October 13, 2009 - link

    At this price point it looks like the 5770 & 5750 are priced to pad AMD's pockets, not to provide increase performance (not that, that's a bad thing when in a war with Intel). With the smaller process size and smaller chip size and similar performance each new part sold will net AMD a substantialy higher profit. This is why AMD will likely kill off the older gen instead of droping the price point. Reply
  • MadMan007 - Tuesday, October 13, 2009 - link

    Yes I think that's where my mild disappointment comes from. Not that they aren't great cards for the launch MSRP, they just aren't great in light of street prices, but unlike HD4800 or even arguably HD5800 AMD doesn't seem interesting in shifting the price/performance curve with these cards. At best matching the current price/performance curve leaves me a bit cold. Reply
  • MonkeyPaw - Tuesday, October 13, 2009 - link

    That's been the trend from ATI lately with their mid-grade cards. The 5700 series is meant to offer roughly the same performance of the 4800 series for a cheaper price. The 4600 series last time was meant to match the 3800 series (the 4770 was quite an oddball though). It's not a bad system, really, as it allows ATI to migrate their lineup with some consistency. Reply
  • Lonyo - Tuesday, October 13, 2009 - link

    It might be that some of the cost does indeed come from the RAM though.
    Once GDDR5 chips drop some more, it will be easy for AMD to drop the prices on these cards, but that might (might) be what's limiting pricing options.

    Or AMD just want to try and get maximum profit from these cards.
    But even so, when GDDR5 prices drop it will be easier to extract profit at lower prices, so GDDR5 pricing will still be at least partly responsible.
    Reply
  • geok1ng - Tuesday, October 13, 2009 - link

    Reading the charts it gets obvious that it is upgrade time: lets get 4850s, 4870s, and even 4850X2-4870X2 on the next weeks before these cards phase out: they are faster and a LOT cheaper than the 57xx series. As for the high end consumers, just wait for the 5870X2, now that is a card to roll eyes, when and IF it launches. Reply
  • codedivine - Tuesday, October 13, 2009 - link

    This is relevant only for compute folks like me, but does 57xx support double precision? Reply

Log in

Don't have an account? Sign up now