Nvidia Unveils Ampere-based RTX A6000, A40 GPUs for Workstations, Data Centers

In a motility that many believe could exist the finish of the road for its 'Quadro'-branded professional person graphics cards, Nvidia on Mon unveiled the RTX A6000 and A40 'Ampere' GPUs for high-end workstations and data-centers without the familiar branding. The move follows the company'southward recent decision to replace the Tesla V100 with the Nvidia A100 and possibly discontinue the 'Titan' branding for its tiptop-end consumer cards.

Nvidia RTX A6000 and Nvidia A40: Specifications and Features

The new GPUs bring heavy-duty computing ability that the company says will advance rendering, AI, VR/AR and compute workloads for artists, designers and engineers. Built on the NVIDIA Ampere architecture, they feature new RT Cores, Tensor Cores and CUDA cores.

Nvidia Unveils Ampere-based RTX A6000, A40 GPUs for Workstations, Data Centers — Image Courtesy: Nvidia

According to Nvidia, the 2d-gen RT cores offer up to 2x the throughput of the previous generation, plus concurrent ray tracing, shading and compute. The third-gen Tensor cores, meanwhile, provide up to 5x the throughput of the previous generation, upwards to 10X with sparsity, with support for new TF32 and BF16 data formats. As for the new CUDA cores, they evangelize up to 2x the FP32 throughput of the previous generation for meaning increases in graphics and compute.

In terms of difficult numbers, both cards come up with Nvidia's Ampere architecture and pack 10,572 CUDA cores alongside 48GB of VRAM. Other specs are relatively similar likewise, including 336 tensor cores, 384-fleck retention motorbus width and 300W TDP. Yet, while the former is meant for standard workstations, the latter is intended for employ in commercial information-centers and server farms. Also, while both come with GDDR6 RAM, the A600 is clocked at 16Gbps, while the A40 comes with a memory clock of 14.5Gbps. The cards will merely apply DisplayPort for video output and will connect to computers through PCIe Gen 4.

Nvidia RTX A6000 and Nvidia A40: Price and Availability

Nvidia is yet to announce either an exact release date or prices for its new GPUs, just says that the RTX A6000 will be available from a number of channel partners, including PNY, Leadtek, Ingram Micro, Ryoyo and on nvidia.com starting mid-December. They will too be available from leading systems manufacturers, like Dell, HP, Lenovo and Boxx, from adjacent twelvemonth.

Every bit for the A40, information technology will also be available from OEM workstation and server vendors, including Cisco, Dell, Fujitsu, Hewlett Packard Enterprise and Lenovo, starting early side by side year.

Featured Image Courtesy: Nvidia