AceleMax DL-E142
Single Socket AMD EPYC Processor 4x GPU Workstation
- Powerful performance with one AMD EPYC™ 7002, EPYC 7003, and 7003 with AMD 3D V-Cache series processor family and up to 280W TDP
- Supports four double-width GPUs for maximum computing power
- Support PCIe Gen 4, delivering 2x PCIe lanes than the competition
- Supports up to 2TB RDIMM/LRDIMM DDR4-3200 memory
- Integrated with 2000W redundant power supply for continuous operations
- Comprehensive Deep Learning software tools
- Optimized for Deep Learning, AI Inference, and Graphics Intensive workloads
Request a Quote
Reference #: Q718716
Processor
- 1 x Socket SP3
- Supports one AMD EPYC™ 7003/7002 Series with up to 64 cores, 128 threads, and 256MB L3 cache per processor
- Also supports one EPYC™ 7003 with AMD 3D V-Cache Series, with up to 64 cores, 128 threads, and 768MB L3 cache per processor
Memory
- 8 DIMM slots
- Supports DDR4 ECC RDIMM/RDIMM 3DS/LRDIMM/LRDIMM 3DS 3200 memory
- Supports up to 512GB RDIMM, 1,024GB LRDIMM, 2,048GB LRDIMM 3DS
GPU
- 4 x double-width GeForce RTX or NVIDIA RTX GPUs
Storage
- 2 x SATA / 2 x SFF-8643 for 12 x SATA ports
Expansion Slots
- 5 x PCI-E 4.0 x16
Management
- AST2500 iKVM Feature: 24-bit high quality video compression / Supports storage over IP and remote platform-flash / USB 2.0 virtual hub
- AST2500 IPMI Feature: IPMI 2.0 compliant baseboard management controller (BMC) / 10/100/1000 Mb/s MAC interface
Chassis
- 4U Rackmountable Tower
Drive Bays
- External: 2 x 5.25” and 1 x 3.5”
- Hot-swap: 2 x 4-bay 3.5” SAS/SATA Hot-swap Module
Power Supply
- 2000W 1+1 redundant 80+, Platinum PSU
Chassis Cooling Fans
- Middle (Default): 4 x 80 (mm), PWM, 11000 RPM, Hot-Swap
- Rear CPU Fan Module for Internal: 2 x 80 (mm), PWM, 8200 RPM, Fixed (Option)
- Rear GPU Hot-swap Fan for External: 2 x 80 (mm), PWM, 11000 RPM, Hot-Swap (Option)
System Dimensions
(D x W x H)
- 77″ x 17.24″ x 6.89″
680.0 x 438.0 x 175.0 mm
Optimized for Turnkey Solutions
Enable powerful design, training, and visualization with built-in software tools including TensorFlow, Caffe, Torch, Theano, BIDMach cuDNN, NVIDIA CUDA Toolkit and NVIDIA DIGITS.