@repi AMD won't give you shit for tweeting that image?
Nope they are fine with it, which is fun! Great guys
AMD: Pirate Islands (R* 3** series) Speculation/Rumor Thread
- Thread starter iMacmatician
- Start date
-
- Tags
- amd
Nope they are fine with it, which is fun! Great guys
This is your first infraction, so I shall forgive you! But ye shall never do it again
So what do this litte switch on the side on the end ? dual bios ?
Well, now I'm shocked by how much interposer is "going to waste". Dare say it looks more like 19 x 22mm. Error margin in die area is well over 10%, I suppose, which is arguably more than the area that might be saved in PHY going from GDDR5 to HBM
Maybe it's some sort of RV770 like magic that they manage to cram so much performance into a die that's about the same size as Hawaii. (Tonga, against Tahiti perhaps, is indicative of gains in transistor density per mm² - some of which would be helped though by Tonga's smaller and slower GDDR5 bus.)
EDIT: pixel counting on this image indicates to me that the "height" of the interposer featured there is only 23mm. This is based on the 107 pixel length of the HBM, which is 7.3mm. The GPU height appears to be 21mm.
2nd EDIT: (sorry, got distracted by a 918 v P1 argument), if the interposer is 32mm wide, then the GPU can be 20mm. Widthwise, the distance from GPU edge to interposer edge appears to be precisely 6mm.
So as far as I can tell, Fiji is no more than 21 x 20mm = 420mm².
VZ and WCC have done their own calculations, far different result.. this said i have absolutely not check their methods .
http://wccftech.com/amd-fiji-die-reconstructed-hbms-huge-gpu-uncovered/
http://videocardz.com/55561/editorial-how-big-is-fiji
Oxide has some new toys too.
Graham Sellers @grahamsellers 13h13 hours ago
@dankbaker @repi @AMDRadeon Oh that. That disables the HCF instruction.
https://twitter.com/dankbaker/status/601803058289496064
HCF = Halt and catch fire.
It is just Cape Verde with DDR5. GCN 1.0, released back in 2012 ...
Probably doesn't translate well. Graham was just making a joke.
Halt and catch fire
Edit- I'm pretty sure it is a dual bios switch, it is in roughly the same spot as the switch on Hawaii cards.
ok lol. Its too early, my brain is not awake for jokes before my first cofee.
Last edited:
Turns out that was a typo, it now says
- Native Mini DisplayPort output
- DVI, VGA, dual-link DVI, and HDMI output supported using Mini DisplayPort adapters (sold separately)
- Support for up to 5120-by-2880 resolution at 60Hz on a single external display (model with AMD Radeon R9 M370X only)
Jawed
Legend
If UMC can make interposers larger than 32 x 26mm, then those Fiji die sizes are possible.
WCCF has taken VC's work as far as I can tell and tried to be more accurate. He failed at the first hurdle, stating that the HBM chip is 5mm wide. It's 5.5mm wide. That's a 9% error. That's enough for 2mm of error in the width. He states 21-23mm and I think it's 20mm.
As for the height, I haven't seen most of the source images that VC used so I don't have numbers derived from them. If we take the 26-28mm estimate and adjust for the 9% error, we get 24.5mm.
20 x 24.5 = 491mm².
And all of these numbers (mine, included, from earlier posts) ignore packaging related dimensions. The GPU die is smaller.
WCCF has taken VC's work as far as I can tell and tried to be more accurate. He failed at the first hurdle, stating that the HBM chip is 5mm wide. It's 5.5mm wide. That's a 9% error. That's enough for 2mm of error in the width. He states 21-23mm and I think it's 20mm.
As for the height, I haven't seen most of the source images that VC used so I don't have numbers derived from them. If we take the 26-28mm estimate and adjust for the 9% error, we get 24.5mm.
20 x 24.5 = 491mm².
And all of these numbers (mine, included, from earlier posts) ignore packaging related dimensions. The GPU die is smaller.
You need the tracing for the PHY and TSV .. i imagine you have one on a side and the other who come on the other side of the memory package chip, hence why this configuration. Due to the nature of the interposer, i imagine you have too a bit of redundancy on thoses tracing inside the interposer.
it seems all tracing are at the same level, tomorrow, i can imagine the interposer could be made with multiple layers for the tracing.
Seriously, im amazed by all the engineer work and things who have need to be solved for get HBM... so i somewhat trust the work who have been made. The interposer, the TSV's, etc.. On this aspect, i like a lot the Anand article who take everything point by point.
Last edited:
LOL! Hella oldskool computing humor!
Jawed
Legend
That was pretty interesting. I dare say it's hard to argue with it, since distinct topologies clearly favour a variety of workloads and peer-types. As a way to cut back on metal layers in the logic die it seems pretty much perfect, if you are going to use an interposer anyway. So really it boils down to the costs and limitations of interposers.
They talk about a 36 x 24mm interposer, which is radically larger than we've been discussing. That increase in width could put Fiji well over 500mm².
In the PDF from Xilinx I linked earlier, there's talk of a technology call SLIT (Silicon-less Interconnect Technology). This is potentially a large saving on interposer costs, because it has no TSVs.
http://electroiq.com/insights-from-...-215-stats-acquisition-will-slit-replace-tsv/
iMacmatician
Regular
It should be the other way. The HBM real width is larger than the HBM rounded width, so the real Fiji width should also be larger than the estimated Fiji width.
According to this PDF (page 13), a HBM Gen 1 module is 5.48 mm x 7.29 mm ( ± 25 µm each).
WCCFTech's calculation is as follows:
So using the 5.48 mm x 7.29 mm numbers, we get a width of "exactly" 23.0 mm and lengths from 27.1 mm to 29.2 mm. Then the range of die sizes are from 623 mm^2 to 671 mm^2. (You can also use the real and rounded areas of the HBM stacks, 39.9 mm^2 and 35 mm^2 respectively, take their quotient, and multiply that by each of WCCFTech's estimates. So 567 mm^2 x (39.9/35) = 647 mm^2.)
Videocardz's calculation is harder to correct because they appear to be using a 5 mm x 7 mm box as their measuring tool and they have thick borders around the relevant elements in their collage. I can only get a very rough estimate of ~ 637 mm^2.
Effectively i will not base any calculation, on draw, 3D render or schema who could be really far of the reality.
Jawed
Legend
I'm sorry, you're absolutely right. I saw the 9% error and didn't even stop to think about the sign
Yes, those are the dimensions I have been using.
My problem with both sites' numbers is that they've both ignored the possible size of an interposer.
But since I wrote my criticism of their numbers in post 1092, I've realised two things:
- AMD itself seems to be under the impression that an interposer can be 36 x 24mm. Simply by allowing 12mm for the gaps around the HBM, the GPU can be 24mm wide. Hence my comment in post 1097 that the GPU could be over 500mm². I had used 32mm as the maximum width earlier, which is why I suggested it could be 20mm wide.
- I ignored the possibility that the spacing of the HBMs along each edge are asymmetric, therefore my height estimate was too low. The collage even shows this, but I ignored it.