GT200 to become 9900GTX and 9900GX2, launch date set to July

[becco]

Tweet

leaked ES pic

make IHS guys





make 6+8 pin, I smell 512bit downthere

http://en.expreview.com/2008/05/20/n...y-picssort-of/

[Buaya-kun]

Tweet

wah udah pake metal heat spreader ya? keliatannya panasnya bakal edan edanan

[ascetic]

Tweet

waaw.... 1 lagi mesin global warming segera dirilis

[prof_gamer]

Tweet

Dari modelnya kelihatan gak jauh jauh dari 9800 GTX ,saya mencium adanya penambahan performa sekitar 15 % overall dibanding dengan 9800 GTX tapi dengan sedikit penambahan teknologi di GPU kemungkinan pake 55Nm production

[Dimdom]

Tweet

Menurut berita yang ada di VR-Zone, GT200 alias GeForce 9900Series belum mendukung DirectX 10.1, kebenaran berita ini sendiri masih simpang siur, jika berita ini benar, tentunya bakalan menjadi salah satu nilai minus dari Nvidia, untuk menghadapi gempuran dari Ati dengan R770nya

[madyasiwi]

Tweet

Dari modelnya kelihatan gak jauh jauh dari 9800 GTX ,saya mencium adanya penambahan performa sekitar 15 % overall dibanding dengan 9800 GTX tapi dengan sedikit penambahan teknologi di GPU kemungkinan pake 55Nm production

Ketuker kali prof, itu mah G92b a.k.a G92 Mark II...

Kalo yg ini beda lagi:

• Nvidia's GT200 chip to pack about 1 billion transistors into 576 mm2
• Next-gen NVIDIA GeForce Specifications Unveiled

Must be the 1 TFlops, 1 billion transistors, The "Real" G92 yg sempat mau dikeluarin akhir 2007 kemaren. Tapi nggak jadi karena satu dan lain hal. Dan karena barang 'simpenan', maka baru support DX10 dan DDR3.

Kalo dipikir-pikir, akhir 2007 ketika ATI baru bisa menyempurnakan HD 2900 jadi HD 3800, NVidia sudah punya monster ini under their sleeves. Geez . The "can of whoop ass", "only Brits care about ATI now", "CPU is dead", and thoose other things seems started to make some sense now.

[sungdah]

Tweet

The upcoming GeForce GTX 260/280 GPUs are based on the GT200 (NV60) core and will be built using a 65 nm manufacturing process at TSMC. However, we heard that not many chips will actually fit on a 300 mm wafer, since Nvidia has come up with a huge die measuring 24 x 24 mm, resulting in a die area size of 576 mm2.

This area is almost 100 mm2 larger than Nvidia’s previous 90 nm high-end GPU (G80) and a consequence of 16 processing blocks (G80 came with nine blocks, eight were enabled for GTX models, six for GTS versions) and a new 512-bit memory controller, which replaces the old 384-bit model (the GTS260 will integrate a 448-bit version).

The current G92 or GeForce 8800GT/8800GTS512/9800GTX/9800GX2 CPUs are built in a 65 nm process and end up at a die size of 330 mm2. The original G80 (NV50) GPU, better known as the GeForce 8800, was manufactured in 90 nm and delivered a die size of 484 mm2.

With its new GPU generation, Nvidia is going to continue on the safe route and plan with enough spare transistors for 240 shader units (actually, 240FP+240MADD). Just like ATI's graphics parts and Sony Cell processor, this should not be considered odd. Keep in mind that the G92 chip debuted with 112 shader units and, after production had ramped up, Nvidia unlocked all the shader and texture units to create GeForce 8800GTS512, followed by the 9800GTX and GX2.

The same will be the case with the GeForce GTX 280 and 260. The GPU will have 15 processing units (240 shader processors) available on the GTX280, while the GTX260 will come with 12 units for a grand total of 192 shader processors. This may be an indication for the complexity involved in manufacturing such a part – especially if you think about the fact that Nvidia has a tradition of designing its GPUs completely in software and a massive supercomputer system in Santa Clara, California. The company always has been proud of the fact that every GeForce chip you buy essentially is “first silicon.”

Our sources state that the manufacturing cost of the GT200 die is somewhere between $100 to $110 per piece. It is pricey and you will be getting a lot more processing logic inside this core than with any other semiconductor part in the short history of the IT industry.

Typically, the CPU die spends about 66-80% of its real estate on cache and the remainder on logic; in the world of GPUs it is vice versa. Our sources indicated that the number of transistors on the GT200 will settle somewhere in the neighborhood of 1 billion – north of 900 million and south of 1.1 billion.

The production cost of a chip is determined on the amount of chips that fit on a wafer. In light of the fact that a 300mm (12") wafer carried less than 120 G80 GPUs, Nvidia will see even fewer GT200s, apparently about 100, according to what he heard.

GT 200 Core

[babao]

Tweet

Tunggu seri setelah seri 9 aja dah tanggung soalnya apalagi yg udah punya seri 8800 keatas mending sabar aja, seri 10 nvidia bakal jadi apa namanya yah 10800GTX?
ato kaya ati lagi namanya X1XXX hehe.

I agree with u dude.
klo dah punya seri 8800-an sih menurut gw msh mumpuni.
secara dr issyu yg eredar seri GF 9 series jg lom ada yg support dx 10.1

peningkatan performa cm 15%
tp pengeluaran duid > 15%
bener2 ga worth...kecuali buat orang2 maniak yg duitnya dah ga ber-seri

[jack daniels]

Tweet

ya kalo saya bilang 8800GTX lama aja sdh lebih dr cukup

damn straight

dari linknya katanya AGEIA Physx udh dibeli sm nVidia, nah bagusnya sih biar gak cm rilis produk baru tapi jg sekaligus game baru (mkn berbasis Physx) yg work better with the new VGA, biar jadinya VGAnya gak buat benching aja

Sport Car aja gak cm buat Dyno Test hehhe

[jomblosejati]

Tweet

Sekedar hitung2an bodoh, dari die size & proses fabrikasi yg sama, berarti :

576/330 *754 juta = 1.316 MILYAR transistor ! Wakz ! Pantes TDPnya 250w. Tapi performa pasti sangat maknyuzz !

Hmm, itu di PCBnya kok spt ada second chip ala NV I/O chip di G80 yah ? Apa saking banyaknya transistor dan gedenya die size, buat sebagian chip harus terpisah ala G80 ?

EDIT: Dari sisi harga, sptnya akan spt ini

GTX 280 MSRP USA 649 US$
GTX 260 MSRP USA 499 US$

EDIT2: Hmm, menurut artikel berikutnya, kalo ternyata transistor countnya masih di bawah 1.1 Milyar, berarti GT200 ini akan lebih besar komposisi core logic nya dibanding cache, relatif dibanding G92, mengingat secara teoritis, densitas cache jauh lebih tinggi dibanding core logic per suatu satuan luas.