Man from Atlantis
Veteran
Hmm just saw this:
http://read2ch.com/r/poverty/1330742326/
It's got a nice pic in it with specs which finally look real (no more of that 24 ROP bs...).
http://www.gdm.or.jp/image/voices_image/201203/02a_800x445.jpg
32 ROPs
16/20 CUs for 7850/7870
860/1000 Mhz
1200Mhz gddr5 (for both)
130W/175W
That's really a 2xCV... (ok only 2.8 billion transistors that's not exactly 2xCV but close enough)
Even power consumption (which looks similar to Barts levels) would be 2xCV...
Targeted die-size?The memory speed is a bit surprising. Pitcairn appears to be roughly equal (maybe even a tad superior) to Cayman, but has significantly lower bandwidth. I wonder what motivated that choice… perhaps power?
Targeted die-size?
btw.
7950: 200W maximum board power
7870: ~175W typical board power
Could be HD 7870 real world consumption above HD 7950?
Targeted die-size?
btw.
7950: 200W maximum board power
7870: ~175W typical board power
Could be HD 7870 real world consumption above HD 7950?
->@->
I'd say incredibly bogus if you compare non-OC versions.
7870 only 50 USD less than the 7950?
and then...
7850 is a whopping 120 USD less than 7870?
Whoever made up those bogus rumors isn't doing a very good job.
Personally, if I was to take a guess 7970 is going to be between 329-349 USD. Potentially as low as 299 USD, but that's fairly unlikely. And 7850 somewhere between 229-289 USD.
Pricing is likely to be governed by where GK104 ends up being priced as I'm expecting 78xx and GK104 to have similar performance with GK 104 being slightly higher but definitely lower than 79xx. BTW - that's just an educated guess and in no way represents actual knowledge of performance.
Regards,
SB
Speaking of that, I think the chip should be rather small (below 250mm²), if that's 2xCV.Targeted die-size?
AMD didn't give a number for Typical Board Power for HD7950, but for HD7970 it was 210W (compared to 250W Max Board Power). So keeping similar ratios between Typical and Maximum for HD7950, I'd say the 7870 should draw about the same. We'll see how that turns out in practice.Could be HD 7870 real world consumption above HD 7950?
That speculated 0.5MB of L2 cache difference is only good for ~24 million transistors (ok probably a bit more), not ~200 million. Though granted the transistor count numbers may use generous rounding.it probably have same amount of L2 Cache that would explain the missing transistors..
Just based on specs I would say it should be a bit faster than that. The 7850 should imho beat a 6950, with the 7870 ending up between gtx570 and gtx580.according to CV CF numbers, 7850 should be faster than 6870 and 7870 more or less 6970..
im quite impressed, 114W card performance around GTX580
http://www.forum-3dcenter.org/vbulletin/showpost.php?p=9193514&postcount=195
These scores are right around my predictions. I guess I was too optimistic though, in that thread they also have overall performance scores and there the 7850/7870 did quite a bit worse (the 7850 below 6950, the 7870 below 6970), strange.im quite impressed, 114W card performance around GTX580
http://www.forum-3dcenter.org/vbulletin/showpost.php?p=9193514&postcount=195
These scores are right around my predictions. I guess I was too optimistic though, in that thread they also have overall performance scores and there the 7850/7870 did quite a bit worse (the 7850 below 6950, the 7870 below 6970), strange.
Photoshop tells me they are not in scale in that slide.And also the die-size can be measured, if the dies are in scale.
Photoshop tells me they are not in scale in that slide.