Šta je novo?

nVidia Pascal

Ima i tema za Polaris
 
Cudi me da Titana nisu opremili sa kompletnim cipom ako vec u Quadro ide.

NVIDIA Quadro P6000

Meanwhile P6000 features Pascal GP102 with 3840 CUDA cores (yikes, that’s more than TITAN XP!). The P6000 also features 24 GB GDDR5X memory (that’s why I think it’s GP102 not GP100).

According to NVIDIA it should be able to deliver five 5K streams to separate monitors.

Both models will be available in October.

http://videocardz.com/62649/nvidia-quadro-p6000-and-p5000-pictured
 
Ipak je Quadro bitniji proizvod, a čip sa malo škarta u Titana. Ko zna možda se GP102 pojavi u još nekoj varijanti.
 
Cudi me da Titana nisu opremili sa kompletnim cipom ako vec u Quadro ide.

Mozda zbog 250W TDP? Znas da uvek hoce Titana/high-end kartu da uglave u 250W...

Ipak je Quadro bitniji proizvod, a čip sa malo škarta u Titana. Ko zna možda se GP102 pojavi u još nekoj varijanti.

Pojavice se sigurno, pa zato su ga i pravili :)

Na Anand-u update-ovali clanak o Titanu:

Update 07/25: NVIDIA has given us a few answers to the question above. We have confirmation that the FP64 and FP16 rates are identical to GP104, which is to say very slow, and primarily there for compatibility/debug purposes. With the exception of INT8 support, this is a bigger GP104 throughout.

Meanwhile we have a die size for GP102: 471mm2, which is 139mm2 smaller than GP100. Given that both (presumably) have the same number of FP32 cores, the die space savings and implications are significant. This is as best of an example as we're ever going to get on the die space cost of the HPC features limited to GP100: NVLInk, fast FP64/FP16 support, larger register files, etc. By splitting HPC and graphics/inference into two GPUs, NVIDIA can produce GP102 at what should be a significantly lower price (and higher yield), something they couldn't do until the market for compute products based on GP100 was self-sustaining.

Finally, NVIDIA has clarified the branding a bit. Despite GeForce.com labeling it "the world’s ultimate graphics card," NVIDIA this morning has stated that the primary market is FP32 and INT8 compute, not gaming. Though gaming is certainly possible - and I fully expect they'll be happy to sell you $1200 gaming cards - the tables have essentially been flipped from the past Titan cards, where they were treated as gaming first and compute second. This of course opens the door to a proper GeForce branded GP102 card later on, possibly with neutered INT8 support to enforce the market segmentation.

Dakle sad ide prica da je ovaj Titan X primarno compute karta pa tek onda gaming.

Od ovog Titana sam imao velika ocekivanja ali sada mi deluje kao najslabiji Titan do sada, evo zasto:

- ovo je prvi Titan koji nema barem 50% vise shejdera od high-end karte bazirane na srednjem chipu (prvi Titan je bio skresan ali je GK110 imao skoro 2 x puta vise shejdera od GK104; Titan Z je fail-ovao; Titan X (Maxwell) je bio tacno 50% vise od GTX 980 ali je izasao kao full chip)
- ovo je prvi Titan koji nema dupliranu memoriju (12GB ce biti standardna memorija za GTX 1080Ti model, prosli Titan X je imao 12GB dok je GTX 980Ti imao 6GB)
- cena podignuta na 1200$

Od pozitivnih stvari, ovo je prvi Titan koji izlazi samo 2 meseca nakon predstavljanja high-end karte koja je nosilac nove arhitekture. Takodje, mislim da ce lepo da se klokuje.

GP102, koji je bukvalno GP104 +50% (isto kao sto je GM200 bio u odnosu na GM204) definitivno ide u sledeci high-end Geforce (GTX 1080Ti). Izgleda nista od HBM2 u gaming kartama kod Pascal-a...
 
Poslednja izmena:
Zašto tolika kuknjava za HBM2?
 
Update 07/25: NVIDIA has given us a few answers to the question above. We have confirmation that the FP64 and FP16 rates are identical to GP104, which is to say very slow, and primarily there for compatibility/debug purposes. With the exception of INT8 support, this is a bigger GP104 throughout.

Meanwhile we have a die size for GP102: 471mm2, which is 139mm2 smaller than GP100. Given that both (presumably) have the same number of FP32 cores, the die space savings and implications are significant. This is as best of an example as we're ever going to get on the die space cost of the HPC features limited to GP100: NVLInk, fast FP64/FP16 support, larger register files, etc. By splitting HPC and graphics/inference into two GPUs, NVIDIA can produce GP102 at what should be a significantly lower price (and higher yield), something they couldn't do until the market for compute products based on GP100 was self-sustaining.

Finally, NVIDIA has clarified the branding a bit. Despite GeForce.com labeling it "the world’s ultimate graphics card," NVIDIA this morning has stated that the primary market is FP32 and INT8 compute, not gaming. Though gaming is certainly possible - and I fully expect they'll be happy to sell you $1200 gaming cards - the tables have essentially been flipped from the past Titan cards, where they were treated as gaming first and compute second. This of course opens the door to a proper GeForce branded GP102 card later on, possibly with neutered INT8 support to enforce the market segmentation.

Generalno sam govorio o ovakvom scenariju, cini mi se da me je DusanK demantovao rekavsi da je to nemoguce.

- ovo je prvi Titan koji nema dupliranu memoriju (12GB ce biti standardna memorija za GTX 1080Ti model, prosli Titan X je imao 12GB dok je GTX 980Ti imao 6GB)
Dakle sad ide prica da je ovaj Titan X primarno compute karta pa tek onda gaming.

I dalje tvrdim da su maheri za manipulaciju i izmisljanje tople vode. Samo cekaj da izadje GTX 1080 Ti :D

GP102, koji je bukvalno GP104 +50% (isto kao sto je GM200 bio u odnosu na GM204) definitivno ide u sledeci high-end Geforce (GTX 1080Ti)

I ovo sam takodje rekao a opet se odnosilo na podesavanje cipa. Cak sam i kodno ime pogodio, haha.
 
Inace, sanjao sam da je Titan X brzi od GTX 1080 za 22% :D :D :D
 
Ovako stoji za Quadro P6000 na sajtu nVidia-e:

QUADRO P6000 SPECS
CUDA Parallel-Processing Cores 3840
GPU Memory 24 GB GDDR5X
FP 32 Performance 12 TFLOPs
Max Power Consumption 250 W
Graphics Bus PCI Express 3.0 x 16
Display Connectors DP 1.4 (4) DVI-D (1) Optional Stereo (1)
Form Factor 4.4" H x 10.5" L Dual Slot

http://www.nvidia.com/object/quadro-graphics-with-pascal.html

Nekako mi jadno deluje Titan X koji nece imati ceo GP102...
 
Ovako stoji za Quadro P6000 na sajtu nVidia-e:

QUADRO P6000 SPECS
CUDA Parallel-Processing Cores 3840
GPU Memory 24 GB GDDR5X
FP 32 Performance 12 TFLOPs
Max Power Consumption 250 W
Graphics Bus PCI Express 3.0 x 16
Display Connectors DP 1.4 (4) DVI-D (1) Optional Stereo (1)
Form Factor 4.4" H x 10.5" L Dual Slot

http://www.nvidia.com/object/quadro-graphics-with-pascal.html

Nekako mi jadno deluje Titan X koji nece imati ceo GP102...


a sto su klosari stavili na sliku cip sa HBM memorijom :)
 
Krenule su da se pojavljuju u cenovnicima Gainward i Palit GTX1060 3GB kartice.
Ipak ostaje ta numeracija? :trust:
 
znaci da ce 1080ti biti prava zverina a ove sto su izasle pre nje su samo male igracke
 
I pretpostavio sam da nece biti zvanicnih review-a za Titana jer ga sada vise ne prodaju kao primarno gaming kartu (izbacili su Geforce iz naziva karte).
Titan X je za nVidia-u sada nesto slicno sto je za AMD Radeon Pro Duo.

Ovo je za nas mozda i bolje jer ce Titan ostati 'sa strane' a nadam se, izbacice ranije nekog GTX 1080Ti sa istim chipom ali sa prednoscu nereferentnih karti i eventualnom celim chipom. I naravno nizom cenom :p

Za sada su jedino Gamestar.de i PC World izbacili neke testove:

http://www.gamestar.de/hardware/gra...news-artikel/nvidia_titan_x,1010,3276621.html

NVIDIA-TITAN-X-Witcher-3-4K.png


NVIDIA-TITAN-X-Rise-of-the-Tomb-Raider-4K.png


NVIDIA-TITAN-X-Far-Cry-Primal-4K.png


U ovim igrama dosta je brza od GTX 1080
Izgleda da 50% veci bandwidth znaci dosta za 4K.
I dalje zalim sto ovo nije GP100 sa HBM2 memorijom :p
 
Poslednja izmena:
Ali se ne zove GeForce GTX Titan X ili GeForce Titan X, vec samo nVidia Titan X. :d
 
Novi titan nema nikakvog smisla i neće se prodavati kao prošli modeli.
Koje bi specifikacije 1080ti imao i koju cenu pa da bude bitan?
 
a dobro ne znam racunati znaci oko 30% pa ocekivano, nista po meni veliko, niti bitno...jos nema preko 60 fps za 4k, znaci sledeci titan ce to omoguciti da bude full uzivanje :D

I te kako je rezultat impresivan. Karta odvaljuje a jos nije potpun cip.

Pogledaj samo razliku u frejmovima.

Witcher 3, snaznija od GTX 1080 za 16 frejmova, Rise of the Tomb Raider - razlika 11 frejmova,
Far Cry Primal - razlika 14 frejmova.. Kida. A gde je overklok? ;)
 
Poslednja izmena:
I te kako je rezultat impresivan. Karta odvaljuje a jos nije potpun cip.

Pogledaj samo razliku u frejmovima.

Witcher 3, snaznija od GTX 1080 za 16 frejmova, Rise of the Tomb Raider - razlika 11 frejmova,
Far Cry Primal - razlika 14 frejmova.. Kida. A gde je overklok? ;)

ja dok ne vidim 75 average fps na 4k meni je ovo sve slabo, to je neka granica da ne pada puno ispod 60, a karta je dobra u svakom slucaju to stoji ali nije za 4k full uzivanje preko 60 fps...
 
ja dok ne vidim 75 average fps na 4k meni je ovo sve slabo, to je neka granica da ne pada puno ispod 60, a karta je dobra u svakom slucaju to stoji ali nije za 4k full uzivanje preko 60 fps...

Nista prodaj tu GTX 1070 i uzmi dva ovakva Titana. Taman imas za toliko posto su limitirani na po 2 komada po jednom licu :)
 
Nazad
Vrh Dno