Les partenaires NVIDIA commencent à se tailler RTX 3070 Ti à partir de plus grandes matrices GA102

NVIDIA manufactured a heap of large “GA102” Ampere silicon to cater to demand from the crypto-mining boom; only to see that demand vanish. With next-gen RTX 40-series awaiting ramp; the company has to digest these GA102 chips somehow, and is apparently letting its partners use them on performance-segment SKUs such as the GeForce RTX 3070 Ti. Le RTX 3070 Ti is normally based on the GA104 silicon, which it maxes out, permettre à tous 6,144 couleurs CUDA, 48 noyaux RT, 192 tenseur de couleur, 192 UGT, et 96 POR, besides the chip’s full 256-bit wide GDDR6X memory interface. This SKU is now being carved out on the larger GA102, by enabling 48 sur 84 La prochaine carte graphique phare de NVIDIA (juste 57% of the CUDA cores enabled); and narrowing the memory bus from its normal 384-bit, down to 256-bit.

The memory size remains at 8 GB, memory type at GDDR6X, and memory speed at 19 Gbit/s, travailler à 608 Go/s de bande passante. The most interesting aspect of carving the RTX 3070 Ti out of the GA102 has to be board power; with a ZOTAC-branded card listing it at 320 W, plus élevé que le 290 W of GA104-based cards from the company. Malheureusement,, this is a China-only SKU. Every custom-design graphics card, especially from a reputed AIC such as ZOTAC, has to go through qualification with NVIDIA; which means NVIDIA is not only aware of GA102-based RTX 3070 Ti cards, but is behind fusing the SMs to carve out the SKU, and developing the video BIOS and driver support. ZOTAC is kind enough to list the ASIC code on its website, and for this SKU it is “GA102-150-xx.”