5 mesi dopo scopriamo le vere specifiche della GTX 970. Finto bus a 256-bit e solo 56 ROPs

[Sasha]

ti va di gestirlo te?

[Fottemberg]

L'ha fatto notare un anon su 4chan.

KitGuru Says: Looks like the memory allocation issue of the GeForce GTX 970 graphics cards is not a bug, but rather a feature.

http://www.kitguru.net/components/graph ... h-drivers/

[Alessio89]

[Fottemberg]

La GTX980m potrebbe avere il medesimo problema: http://tech4gamers.com/nvidia-geforce-g ... y-problem/

Non solo: "Interestingly, according to the editors, the GeForce GTX 970 and GTX 980m are not only the NVIDIA graphics cards with the problem of memory access. It’s getting interesting ...".

[Il nabbo di turno]

Se per questo, anche la 670.

[mafferri]

Se per questo, anche la 670.

non ci credo -.-
spiega please XD

[Il nabbo di turno]

Se per questo, anche la 670.

non ci credo -.-
spiega please XD

C'è poco da spiegare,
Nai's Benchmark, edited by VultureX
Device: GeForce GTX 670 (2.00 GB)
Memory Bus Width (bits): 256
Peak Theoretical DRAM Bandwidth (GB/s): 198.656000

Allocating Memory . . .
Chunk Size: 128 MiByte
Allocated 15 Chunks
Allocated 1920 MiByte
Benchmarking DRAM
DRAM-Bandwidth of Chunk no. 0 (0 MiByte to 128 MiByte):159.01 GByte/s
DRAM-Bandwidth of Chunk no. 1 (128 MiByte to 256 MiByte):159.26 GByte/s
DRAM-Bandwidth of Chunk no. 2 (256 MiByte to 384 MiByte):159.23 GByte/s
DRAM-Bandwidth of Chunk no. 3 (384 MiByte to 512 MiByte):159.20 GByte/s
DRAM-Bandwidth of Chunk no. 4 (512 MiByte to 640 MiByte):158.92 GByte/s
DRAM-Bandwidth of Chunk no. 5 (640 MiByte to 768 MiByte):158.97 GByte/s
DRAM-Bandwidth of Chunk no. 6 (768 MiByte to 896 MiByte):158.92 GByte/s
DRAM-Bandwidth of Chunk no. 7 (896 MiByte to 1024 MiByte):159.45 GByte/s
DRAM-Bandwidth of Chunk no. 8 (1024 MiByte to 1152 MiByte):159.45 GByte/s
DRAM-Bandwidth of Chunk no. 9 (1152 MiByte to 1280 MiByte):159.54 GByte/s
DRAM-Bandwidth of Chunk no. 10 (1280 MiByte to 1408 MiByte):159.37 GByte/s
DRAM-Bandwidth of Chunk no. 11 (1408 MiByte to 1536 MiByte):159.27 GByte/s
DRAM-Bandwidth of Chunk no. 12 (1536 MiByte to 1664 MiByte):159.15 GByte/s
DRAM-Bandwidth of Chunk no. 13 (1664 MiByte to 1792 MiByte):15.84 GByte/s
DRAM-Bandwidth of Chunk no. 14 (1792 MiByte to 1920 MiByte):12.71 GByte/s
Benchmarking L2-Cache
L2-Cache-Bandwidth of Chunk no. 0 (0 MiByte to 128 MiByte):263.34 GByte/s
L2-Cache-Bandwidth of Chunk no. 1 (128 MiByte to 256 MiByte):263.35 GByte/s
L2-Cache-Bandwidth of Chunk no. 2 (256 MiByte to 384 MiByte):263.35 GByte/s
L2-Cache-Bandwidth of Chunk no. 3 (384 MiByte to 512 MiByte):263.35 GByte/s
L2-Cache-Bandwidth of Chunk no. 4 (512 MiByte to 640 MiByte):263.35 GByte/s
L2-Cache-Bandwidth of Chunk no. 5 (640 MiByte to 768 MiByte):263.36 GByte/s
L2-Cache-Bandwidth of Chunk no. 6 (768 MiByte to 896 MiByte):263.35 GByte/s
L2-Cache-Bandwidth of Chunk no. 7 (896 MiByte to 1024 MiByte):263.35 GByte/s
L2-Cache-Bandwidth of Chunk no. 8 (1024 MiByte to 1152 MiByte):263.35 GByte/s
L2-Cache-Bandwidth of Chunk no. 9 (1152 MiByte to 1280 MiByte):263.35 GByte/s
L2-Cache-Bandwidth of Chunk no. 10 (1280 MiByte to 1408 MiByte):263.34 GByte/
L2-Cache-Bandwidth of Chunk no. 11 (1408 MiByte to 1536 MiByte):263.35 GByte/
L2-Cache-Bandwidth of Chunk no. 12 (1536 MiByte to 1664 MiByte):263.35 GByte/
L2-Cache-Bandwidth of Chunk no. 13 (1664 MiByte to 1792 MiByte):16.09 GByte/s
L2-Cache-Bandwidth of Chunk no. 14 (1792 MiByte to 1920 MiByte):12.73 GByte/s

[FedeGata]

Azz, con la 670 non han fatto in tempo a sgamarlo, perchè tutti si limitavano al full-hd.
Con il 4k piano piano si scoprono le features delle gtx*70 rispetto alle gtx*80 (da questo punto di vista la gtx770 dovrebbe esser immune...)

[Il nabbo di turno]

Se continua così, temo che un po' tutte le nvidia kepler/maxwell non full chip ne soffrano di questo problema.

[FedeGata]

Possibile che anche le Fermi ne siano affette?