AMAX’s HPC and AI Solution Group announced that it is now offering a wide selection of AceleMax™ workstations for AI, rendering and visualization featuring the new NVIDIA® RTX™ A6000 GPU. These powerful professional GPU workstations deliver unprecedented performance and features that will allow researchers, scientists and designers to accelerate deep learning training workloads, simulations, and ray-traced renderings with enterprise-level stability and reliability.
The NVIDIA RTX A6000 GPU is part of the new Ampere architecture with 48GB of GPU memory, expandable to 96GB using NVLink when connected to two GPUs. These GPUs feature new RT Cores that deliver up to 2x throughput for concurrent ray tracing, shading and compute; the third-generation Tensor Cores provide up to 5x throughput; and the new CUDA Cores deliver up to 2x the FP32 that accelerate graphics, rendering, compute, and AI significantly faster than previous generations.
The AMAX AceleMax workstations feature PCIe Gen 4 with 31.5 GB/sec versus previous generation of 15.75 GB/sec, which improves data transfer speeds from CPU memory for data-intensive tasks such as AI, data science, and creation of 3D models from large datasets. Faster PCIe performance also accelerates GPU direct memory access (DMA) transfers, provides faster video data transfers from GPUDirect® for video-enabled devices and faster input/output (I/O) with GPUDirect Storage. The AceleMax workstations available with the new NVIDIA RTX A6000 GPUs include:
DL-E110A, Single AMD Ryzen AM4 Processor, 1x GPU
DL-E120A, Single AMD Ryzen Threadripper Processor, 2x GPU
DL-E140A, Single AMD EPYC 7002 Series Processor, 4x GPU
DL-E440, Dual Intel Xeon Processor, 4x GPU