AMD R9 3x0Χ Καθ'οδόν!

[Dj_ALeX]

Λέω να ξεκινήσουμε νέο θέμα για να μην χάσουμε τον μπούσουλα με τα παλαιότερα threads!
Έχουμε και λέμε... Τι γνωρίζουμε μέχρι και σήμερα για τις νεές σειρές R9 380 & R9 390!
Παραθέτω μερικά πρώτα links για να δούμε που βρισκόμαστε μέχρι αυτήν την στιγμή που μιλάμε και τι στο περίπου να περιμένουμε φέτος απο πλευράς κοκκινούλας.
 

 

November 10th, 2014 at 10:52 pm - Author

Anton Shilov

 

Advanced Micro Devices has begun internal testing of what is believed to be the company’s next-generation flagship graphics processing unit. Earlier this month the company’s subsidiary in India received a graphics card based on the code-named Fiji XT graphics processing unit.

According to Zauba.com database, which monitors imports and exports to and from India, where high-tech companies employ many engineers, AMD’s office in India received a “printed circuit board assembly (video graphic card) C880 Fiji XT P/N.102-C88001-00” on the 7th of November, 2014.

Videocardz web-site believes that AMD’s code-named Fiji XT graphics processing unit is the company’s next-generation flagship GPU that will power the Radeon R9 390X graphics card. It is believed that Fiji XT is based on the GCN 1.2 architecture and is made using 28nm or 20nm fabrication process.Given the fact that this is the first Fiji XT sample that AMD sent to its office in India, it is highly likely that commercial graphics cards based on the GPU are at least three to four months away.

AMD did not comment on the news-story.

 

 

Πηγή
 

November 12th, 2014 at 10:33 pm - AuthorAnton Shilov

 

Advanced Micro Devices’ next-generation graphics processing unit is still several months away, but it looks like it is worth waiting. According to unofficial information from SiSoft Sandra benchmark’s database, the forthcoming GPU features unprecedented compute horsepower as well as uses multi-layer high-bandwidth memory with extreme bandwidth.
If the listing in Sandra’s database is correct and really describes a prototype of the Radeon R9 390X “Fiji XT” graphics card, the next-generation offering from AMD will feature 4096 stream processors (SPs) (which, in case of the GCN 1.2 architecture, means 64 compute units and 256 texture units) and 4096-bit memory bus. The memory sub-system will rely on SK Hynix’s stacked high bandwidth memory (HBM) chips with 1024-bit input/output interface (compliant with the JESD235 standard [and, possibly, with the Wide IO protocol]).The graphics card allegedly sports only 4GB of memory since the first-generation HBM features 2Gb DRAM dies and comes in 1GB memory devices, reports Wccftech. Only the second-generation HBM is expected to use 8Gb dies and therefore support 4GB and 8GB configurations.
If AMD’s Radeon R9 390X actually uses four first-generation HBM DRAM chips with 4096-bit memory bus operating at 1.25GHz, then the actual memory bandwidth the graphics card will sport will be whopping 640GB/s.With 4096 stream processors and amount of bandwidth never before seen on a single-chip graphics cards, the Radeon R9 390X will be the fastest graphics adapter on the market. In fact, with such extreme amount of stream processors, it will clearly leave behind any graphics solution based on Nvidia Corp.’s GM200 graphics processing unit.While performance-wise the Radeon R9 390X “Fiji XT” seems to be very powerful, it remains to be seen how expensive will it be. New types of memory tend to cost a lot. Moreover, given that memory devices have to be placed on the same piece of substrate with the GPU, the whole graphics card has to be redesigned.

 

 

 

 

 
Πηγή







Πηγή
 

 
Πηγή
 

December 17th, 2014 at 4:31 pm - AuthorAnton Shilov

 

A web-site has published alleged benchmark results of next-generation graphics cards from Advanced Micro Devices and Nvidia Corp., such as code-named “Bermuda XT”, “Fiji XT” as well as GM200. Without a lot of surprises, the new single-chip graphics solutions from AMD and Nvidia will offer a noticeable performance improvement compared to today’s solutions, but all of them will be slower than the Radeon R9 295X2.
Chiphell, a Chinese web-site with mixed track-record when it comes to leaking details about unannounced hardware, has published what it claims to be benchmark results of multiple next-generation graphics cards – including “Bermuda XT”, “Fiji XT”, “GM200” and cut-down “GM200” – in five benchmarks, including Battlefield 4, Call of Duty: Advanced Warfare, Dragon Age: Inquisition, Ryse: Son of Rom and Watch Dogs: Bad Blood. Exact benchmark settings have not been revealed, but they are claimed to be “high” or “max” and the resolution was 3840*2160.If performance results are to be believed, then it is noteworthy that the supposed AMD Radeon R9 390X “Bermuda XT” is faster than the next-generation GeForce GTX Titan “GM200”, whereas the alleged Radeon R9 380X “Fiji XT” is faster than Nvidia’s GeForce GTX 980.
While the alleged benchmark results pose certain interest, it should be noted that their authenticity is under a huge question mark. While it is possible that an employee of a graphics cards supplier has decided to test several unreleased graphics adapters and share results with media, this does not happen often. At present, very few third parties outside of graphics cards supply chain own next-generation graphics cards from AMD and Nvidia. Those third parties mainly include software developers, who also rarely share test results with the press.
Given the fact that neither the “Bermuda XT”, nor the “Fiji XT” nor the “GM200” are commercial products, their specifications (e.g., GPU configuration, clock-rates, etc.) are subject to change and so is performance.

 

 
 

• By Joel Hruska on January 13, 2015 at 5:01 pm

Two new tidbits on AMD’s next-generation GPU architectures have surfaced courtesy of LinkedIn — and while that’s not our typical avenue for discovering new data, past information cribbed from profiles has indeed panned out. In this case, it’s a pair of profiles — one from Linglan Zhang, a system architect manager at AMD, and one from Ilana Shternshain, an ASIC physical design engineer.
The two profiles collectively point to two things. First, that the upcoming R9 380X GPU from AMD has already taped out and gone to manufacturing. This is welcome news, given that Nvidia’s Maxwell shipped months ago, but it doesn’t tell us much in and of itself. It was always a given that AMD would build a new GPU architecture, and we don’t have any information (yet) on whether the R9 380X jumped for 20nm technology or stayed on 28nm. Since new nodes aren’t a guaranteed advantage for large, complex chips the way they used to be, it’s harder to predict what AMD might do.
Second, and arguably more interesting, is Zhang’s profile, which includes the following:

So, what is “High Bandwidth Memory,” and how could it change the future of AMD’s graphics?

 

 

Understanding HBM
High-Bandwidth Memory is a specialized application of the Wide I/O memory standard we’ve previously discussed as a long-term replacement for DDR4. Hynix, AMD’s co-partner in developing the standard, describes it as “Wide I/O stacked DRAM with TSV” (through-silicon vias). In this configuration, the GPU RAM would be implemented directly around the GPU itself for optimal routing and minimal cost. One difference between 3D Wide I/O and HBM is that Wide I/O can be stacked directly on top of the SoC — you wouldn’t want to do that with HBM, due to the GPU’s phenomenal heat output.

  

 

One thing to keep in mind is that this charge is intrinsically designed to make HBM look good. They’re comparing a DDR3 DIMM of just 8 bits (traditional implementations are 64-bits) and an GDDR5 bus of just 32-bits (most modern GPUs gang 8-12 memory controllers together). In other words, the 128-256GB/s worth of bandwidth off HBM isn’t the only benefit — the benefit is in cost, trace complexity, latencies, and power.

Is AMD ready to deploy HBM in next-gen Radeons?
We know HBM can bring substantial performance improvements, and we know that AMD is working on the technology. The question is, is it ready to deploy on next-generation hardware yet? That’s where a macro-economic perspective is more helpful, and the information there, more tenuous. According to multiple sources, TSMC only began ramping up its TSV support quite recently. The next graph comes directly from TSMC’s own projections of wafer start times for various types of standards:

  

  

The “HBM” block takes up most of 2015, but tilts towards the back half of the year. Since these are wafer starts as opposed to volume production, it implies that there’s going to be lag time between the launch of these parts and full availability. GlobalFoundries is also building HBM capabilities, but is rumored to be behind TSMC in deploying the technology.
This suggests one of two things: Either the R9 380X will not use HBM and that technology will be reserved for a second, follow-up GPU (possibly an R9 390X coming later this year or early next year), or that the R9 380X will use HBM, but will not deploy until later in the year to give the technology time to mature.
There is a third option, though it would be fairly out-of-band for AMD, given its current financial situation. The company could have opted to aggressively adopt HBM, sacrificing costs for performance and early availability. If AMD managed to steal a year on Nvidia’s Pascal, it could tilt the competitive landscape sharply back towards Team Red and give the company a welcome shot of good news.

 
Πηγή
 
 

 

January 14th, 2015 at 11:59 pm - AuthorAnton Shilov
Two employees of Advanced Micro Devices have revealed in their LinkedIn profiles that they had worked on AMD Radeon R9 380X graphics processing units with vertically-stacked high bandwidth memory (HBM). The engineers at AMD essentially confirmed that the company’s next-generation flagship graphics processor will use HBM memory and will carry the “R9 380X” model number.
Linglan Zhang, a principal member of technical staff at AMD, wrote in his profile at LinkedIn that he was involved in development of the “world’s first 300W 2.5D discrete GPU SOC using stacked die high bandwidth memory and silicon interposer.” The engineer also revealed that the Radeon R9 380X is the “largest in ‘King of the hill’ line of products.” Previously it was believed that this year’s flagship GPU from AMD carries the “R9 390X” model number. The employee of AMD has already deleted the information regarding the next-generation AMD Radeon.
Ilana Shternshain, ASIC physical design engineer from AMD, also revealed in her profile that she was responsible for “taping out state of the art products like Intel Pentium processor with MMX technology and AMD R9 290X and 380X GPUs.”

 
Πηγή

Οτιδήποτε βρώ επιπλέον θα το παραθέσω επίσης! Σιγά σιγά πιστευώ και επειδή και ο καιρός πλησιάζει όλο και κάτι καινούργιο θα βγεί στην επιφάνεια για τις νεές κάρτες της AMD!
Stay tuned!
Όποιος βρεί κάτι παραπάνω ή κάτι διαφορετικό είναι φυσικά καλοδεχούμενος να το παραθέσει!
Ελπίζω να διατηρηθεί το thread on topic και σε αυτό θα πρέπει να βοηθήσουμε όλοι!
Ευχαριστώ!

[Trexx]

Απαραίτητο, ωραίο και ενημερωμένο. Άντε να δούμε. Το μόνο σίγουρο είναι ότι (σχεδόν) όλοι επιζητούμε τον ανταγωνισμό, ώστε να μην καταντήσει η κατάσταση όπως στις cpu.

[AKISSS]

Για 300 watt που ακούγεται ελπίζω να είναι πολύ πιο γρήγορη από 980 GTX...

[giorgos2187]

Πολυ τουμπανα χαρακτηριστικα βλεπω και μαλλον δικαιολουν τα 300 watt.. Νταξει 300 ειναι , δεν ειναι δα και 600! Μαλλον γλυκοκοιταει αποκλειστικα τις πολυ μεγαλες αναλυσεις η AMD και παει να θεσει πρωτη τα δικα της θεμελια. Για να δουμε και τις τιμες που θα παιξουν, εχγ μεφαλη περιεργεια.

[amdnikos]

@Lazy Dog Ελαμωρετωρα με τη σομπα...παλι καλα που θα ερθει χειμωνας μεχρι να βγει, και θα ζεσταθειτε με τη μπουρουχα που πηγατε και πηρατε... 

[Trexx]

@Lazy Dog Ελαμωρετωρα με τη σομπα...παλι καλα που θα ερθει χειμωνας μεχρι να βγει, και θα ζεσταθειτε με τη μπουρουχα που πηγατε και πηρατε... 

 

Eσύ μπορεί να κάνεις πλάκα, αλλά η κατανάλωση είναι κριτήριο και μάλιστα μεγάλο για τις εταιρίες και ας μην είναι για μας. Μια κάρτα των 300W, ανεξαρτήτως επιδόσεων, δείχνει τεχνολογική υστέρηση. Η τεχνολογία δεν προχωράει με τα fps (επίδοση) αλλά με τα fps/watt (απόδοση)

[amdnikos]

Eσύ μπορεί να κάνεις πλάκα, αλλά η κατανάλωση είναι κριτήριο και μάλιστα μεγάλο για τις εταιρίες και ας μην είναι για μας. Μια κάρτα των 300W, ανεξαρτήτως επιδόσεων, δείχνει τεχνολογική υστέρηση. Η τεχνολογία δεν προχωράει με τα fps (επίδοση) αλλά με τα fps/watt (απόδοση)

Τρολαρω βρε! Ασε με να το χαρω λιγο.

[giorgos2187]

Η τεχνολογία δεν προχωράει με τα fps (επίδοση) αλλά με τα fps/watt (απόδοση)

 

Θα διαφωνησω λιγο εδω. Δυστυχως δεν προκειται για μια απλη ηλεκτρικη συσκευη για να μετρησουμε μοναδα αποδοσης/watt. Το προιον μπορει απο αποψη harware να ειναι πολυ αποδοτικο ενεργειακα αλλα να το "κοβει" η υποστηριξη απο το software, και οταν μιλαμε για AMD νομιζω ενα τετοιο κοψιμο στην αρχη τουλαχιστον ειναι σιγουρο. Στα 1080p περιμενω να σαρωνουν οι 2 αυτες καρτες γιατι βλεπω οτι εχουν πολλα "πνευμονια", επομενως ισως και ο λογος fps/watt να ειναι πολυ ικανοποιητικος. Ξαναλεω ομως πως με τετοια specs οι νεες AMD στοχευουν σε μεγαλυτερες αναλυσεις.  

[Kostas18s]

Μπάβο φίλε....Εξαιρετικό το Thread σου.

[Delijohn]

i'm just gonna leave it here.. 

και ΜΑΚΑΡΙ να'ναι αλήθεια!

 

[sebastian]

http://linustechtips.com/main/topic/293664-amd-radeon-r9-300-series-3dmark-11-extreme-score-revealed/

gpu score 7.788 στο extreme 3d mark 2011

Η 980gtx βγαζει αυτο το score στα:1,750MHz/2,150MHz

Τωρα τι και πως θα τα δουμε στη πορεία....

[csaris]

Πωωω κτηνος φαινεται.. απο τιμη κανενα 650αρι υπολογιζω..

[sebastian]

Πωωω κτηνος φαινεται.. απο τιμη κανενα 650αρι υπολογιζω..

 

....βεβαια λενε οτι ειναι fake!

 

Αν παιξει τετοιο νουμερο σε stock συχνοτητες και με tessellation θα ειναι μπομπα!

[csaris]

....βεβαια λενε οτι ειναι fake!

Αν παιξει τετοιο νουμερο σε stock συχνοτητες και με tessellation θα ειναι μπομπα!

Ναι ειχα ξεχασει τις μαιμουδιες που κανει η amd με το tessellation.[emoji12]

[Delijohn]

Μη ξεχνάτε πως είναι ήδη στο νερό, πράγμα που ίσως σημαίνει πως είναι ήδη κοντά στα όριά της. Αλλιώς ποιο και το νόημα να την έχουν ήδη έτοιμη με "μπρατσάκια".

[sebastian]

Το οτι διωξανε υψηλόβαθμα στελέχη τωρα μονο χαρμόσυνο γεγονος δεν είναι. Αλλα και ολα αυτα που ακούγονται για πωλητήριο.

Ειμαι αρκετα περιεργος το τι θα βγαλει...

[Delijohn]

Τελικά ήταν fake το σκοράκι.

Όπως επίσης κι εμφανίστηκαν φήμες για καθυστέρηση.

[sebastian]

Οι ΜΟΥΡΜΟΥΡΕΣ θελουν τον TITANA X στα 1.200+ ευρω τιμη εκκίνησης με 12Gb ram.

Πολυ φοβαμαι οτι η ΑMD δεν εχει κατι πραγματικα ισχυρο για να χτυπήσει την Nvidia. Αλλιώς θα χρεωσω οσο θέλω δεν θα ίσχυε...

[Delijohn]

Νέο "leak".. κι αυτό ψέμα; Θα δείξει! 4*390x!

 

 

το τωρινό record είναι: (4*980)

[yanni]

Όλα σε ένα και νοικοκυρεμένα. όλες οι φήμες που θέλετε να διαβάσετε για τις επερχόμενες κάρτες της σειράς 300. Νομίζω είναι καλύτερα να το βάλω εδώ

 

AMD Radeon R9 300 series rumors | VideoCardz.com