Relentless Demand For HPC Performance
The importance of performance and productivity in the technical workplace cannot be overstated. As datasets grow increasingly complex, the path to great discovery gets more and more computationally challenging. Today’s scientists, engineers, and other technical professionals need massive horsepower to crunch these complex datasets fast, efficiently, and accurately. Feeding this relentless demand for HPC performance are resource-prohibitive CPU-based clusters. What if supercomputing was easily accessible and affordable?
Supercomputer For Everyone
Introduction of Colfax CXT4000 PSC democratizes HPC by providing today’s professionals an affordable personal supercomputing resource on their desktop that is much faster and more energy-efficient than a shared cluster in the data center.
Supercomputing Performance Shrink Wrapped In-a-Box
The Colfax CXT4000 PSC leverages NVIDIA® Tesla™ C2050 / C1060 Computing Processors, offering massive parallel processing capabilities to speed calculations and solve problems impossible with current computing approaches. Powered by 1792 cores and nearly 4 Teraflops of peak performance, the CXT4000 delivers cluster level computing performance — up to 250 times faster than standard PCs and workstations — right at your desk.
NVIDIA CUDA™ Architecture Unlocks the Power Of GPU Parallel Computing
The CUDA parallel computing architecture enhances performance by offloading computationally-intensive activities from the CPU to the GPU — unlocking the many-core processing power of NVIDIA GPUs to solve the most complex computation-intensive challenges such as protein docking, molecular dynamics, financial analysis, fluid dynamics, structural analysis and many others.
Visual Supercomputing Right On Your Workstation
The Colfax CXT4000 PSC also features NVIDIA Quadro® professional graphics option, providing a powerful versatile solution that has been engineered to meet the graphics and high-performance computing demands of professional users. Working together, Colfax integrates NVIDIA Quadro and Tesla solutions to ensure optimized system performance.
High-Performance Computing
Expertly Designed and Engineered
Your Own Supercomputer
Dedicated computing resource for every computational researcher and technical professional.
Cluster Performance on Your Desktop
The performance of a cluster in a desktop system. Up to Four Tesla GPU computing processors deliver nearly 4 teraflops of performance.
Designed for Office Use
Plugs into a standard office power socket and quiet enough for use at your desk.
Massively Parallel Many Core GPU Architecture
Up to 448 parallel processor cores per GPU that can execute thousands of concurrent threads.
Up to 4GB High-Speed Memory per GPU
Dedicated compute memory enables larger datasets to be stored locally for each processor minimizing data movement around the system.
NVIDIA Quadro® Professional Graphics
Powerful versatile solution, engineered to meet your graphics and high-performance computing demands
IEEE 754 Floating Point Precision (Single-Precision and Double-Precision)
Provides results that are consistent across platforms and meet industry standards.
64-bit ALUs for Double -Precision Math
Meets the precision requirements of your most demanding applications with 64-bit ALUs.
Technical Specifications
| Total Tesla C2050 / C1060 Computing Processors | • # of Tesla processors - 4 |
| CPU | • Dual LGA 1366 sockets • Intel® Xeon® (Nehalem) 5500 Series processors • Intel® QuickPath Interconnect (up to 6.4 GT/s) |
| Chipset | • Northbridge: Dual Intel® 5520 (Tylersburg) • Southbridge: Intel® ICH10R |
| Memory |
• 12 240-pin DDR3 sockets • Supports DDR3 800/1066/1333 RDIMM/UDIMM • Supports up to 96GB max |
| Expansion Slots |
• 4 PCI Express x16 2.0 slots • 2 PCI Express x4 2.0 slots (in x16 slots) • 1 PCI Express x4 slot (in x8 slot) • 2 33MHz PCI slots |
| LAN | • 2 Intel 82574L GbE NICs • Intel® I/OAT 3 support for fast, scaleable, and reliable networking • VMDq support for better performance of virtualization |
| Integrated SATA | • 6 SATA-II ports from Intel ICH10R • RAID 0, 1, 5, 10 support |
| Integrated Graphics | • Onboard Matrox G200eW VGA controller |
| Super I/O | • Winbond 83827HF chip |
| Input / Output |
LAN • 2x RJ45 LAN ports USB • 4x USB rear ports • 2x USB on-board • 1x USB internal header - 2 ports • Total 8 USB 2.0 Compliant VGA • 1x VGA port Keyboard / Mouse • PS/2 keyboard and mouse ports Serial Port / Header • 1 Fast UART 16550 serial port • 1 Fast UART 16550 serial header (Option) |
| PC Health Monitoring |
CPU • Monitors for CPU Cores, +1.8V, +3.3V, +5V, ±12V, +3.3V Standby, +5V Standby, VBAT, HT, Memory, Chipset Voltages • 6-Phase-switching voltage regulator Fans • Total of eight fan headers supporting up to 8 fans • Eight 4-pin fan headers • 8x fans with tachometer status monitoring • Supports 3-pin fans (w/o speed control) • Low noise fan speed control Temperature • Monitoring for CPU and chassis environment • Thermal Control for 8x fan connectors • PECI Other Features • Chassis intrusion detection • Chassis intrusion header |
| BIOS | • 32Mb SPI Flash EEPROM with AMI® BIOS • Plug and Play (PnP) • PCI 2.2 • Supports ACPI up to 3.0 • USB keyboard support |
| Chassis |
Form Factor • Tower (4U rackmountable w/ optional kit) Drive Bays • 8x 3.5" hot-swap SAS/SATA drive bays • 3x 5.25" drive bays in storage module - rotates 90° for rackmount • 1x 3.5" fixed drive bay System Cooling • 4x 5000 RPM hot-swap cooling fans • 2x 5000 RPM hot-swap rear exhaust fans Front Panel Buttons • Power On/Off button • System Reset button LEDs • Hard drive activity LED • 2x Network activity LEDs • System overheat LED • Power fail LED Ports • 2x Front side USB Ports Power Supply • 1400W high-efficiency redundant power supply with PMBus • 80 PLUS Gold Certified • AC Input - 1100W: 100 - 140V, 50 - 60Hz, 9.5 - 13.5 Amp - 1400W: 180 - 240V, 50 - 60Hz, 7.0 - 9.5 Amp Dimensions HxWxD: 7" (178mm) x 17.8" (452mm) x 29.4" (746mm) |


Colfax CXT4000 PSC Datasheet
Click here to download the CXT4000 datasheet PDF
NVIDIA CUDA™ NVIDIA CUDA™ technology is the world’s only C language environment that enables programmers and developers to write software to solve complex computational problems in a fraction of the time by tapping into the many-core parallel processing power of GPUs. With millions of CUDA-capable GPUs already deployed, thousands of software programmers are already using the free CUDA software tools to accelerate applications—from video and audio encoding to oil and gas exploration, product design, medical imaging, and scientific research. Click here to learn more
NVIDIA CUDA Development Tools NVIDIA’s CUDA development tools provide three key components to help you get started: the latest CUDA driver, a complete CUDA Toolkit, and CUDA SDK code samples. Click here to download CUDA driver and toolkit