Tesla M1060 Processor

The heart of the world’s fastest 1U computing servers and engineered to meet the requirements of enterprise-class data centers, NVIDIA® Tesla™ M1060 processors shatter your performance per watt expectations.

Buy Tesla Preconfigured Cluster

Print page

The World’s Fastest 1U Server! Click here to learn more.

An integral part of the world’s fastest 1U computing servers engineered to meet the requirements of enterprise-class data centers, Tesla M1060 processors deliver supercomputing performance while requiring less power and space. Featuring the revolutionary NVIDIA® CUDA™ parallel computing architecture and powered by 240 parallel processing cores, the Tesla M1060 shatters your performance per watt expectations to help you solve the toughest computing problems faster.

The Performance to Solve the Toughest Computing Problems Faster
Uses the NVIDIA® CUDA™ parallel computing architecture to deliver nearly a teraflop of peak performance.

Cut your Energy Bill without Sacrificing Performance
8x the performance per watt for 1RU servers with Tesla processors relative to 1RU x86 Servers without Tesla processors*.

Engineered for Enterprise-Class Data Center Requirements
Passive heatsink design enables redundancy from multiple system fans and system integration extends the host system’s monitoring capabilities to include the Tesla processor. Also, fewer external cables simplify data center installation and operation.

Available Integrated into Compute Servers from Leading OEMs
Leading OEMs have engineered compute servers around this new processor and are only available through these OEMs.

*Assumption is 600W for a CPU only server with dual-socket quad-core. Perf level is 170.24 GFLOPS per 600W, or 0.284 GFLOPS/Watt. Add 2 M1060 GPUs to that system, and system power increases to 880W, but performance equals 1996 GFLOPS, or 2.268 GFLOPS/Watt. 2.218 is 8.0x of 0.284.


Features	Benefits
4 GB High-Speed Memory per Processor	Enables larger datasets to be stored locally for each processor to maximize benefit from the 102GB/s memory transfer speeds and minimize data movement around the system.
512-Bit Memory Interface	Fast GDDR3, 512-bit memory interface delivers 102 GB/sec memory bandwidth for blistering data transfer.
64-bit ALUs for Double-Precision Math	Meets the precision requirements of your most demanding applications with 64-bit ALUs.
Asynchronous Transfer Capability	Turbocharges system performance because data transfers can be executed concurrently with computation.
Avoid External PCIe Cables	Built into the host system eliminating external PCIe cables.
IEEE 754 single & double precision floating point units	Achieve the highest floating point performance from a single chip, while meeting the precision requirements of your application.
High Reliability	System fans provide redundancy for high reliability, so a single fan failure will not cause a GPU cooling problem.
Massively-Parallel Many-Core Architecture	240 processor cores per GPU capable of executing thousands of concurrent threads.
Widely accepted, easy to learn NVIDIA® CUDA™ C programming environment	Easily express application parallelism to take advantage of the GPU’s many core architecture.
Remote Monitoring	Integrated into the monitoring and management capabilities of the host system, so the GPUs appear as another processor in the system.
Scale to multiple GPUs and harness the performance of thousands of processor cores	Solve large-scale problems by scaling to thousands of cores across multiple GPUs.

Main | Features

Form Factor	Embedded Module
# of Tesla GPUs	1
# of Streaming Processor Cores	240
Frequency of processor cores	1.3 GHz
Single Precision floating point performance (peak)	933
Double Precision floating point performance (peak)	78
Floating Point Precision	IEEE 754 single & double
Total Dedicated Memory	4 GDDR3
Memory Speed	800 MHz
Memory Interface	512-bit
Memory Bandwidth	102 GB/sec
System Interface	PCIe. See OEM system specification for implementation details.
Thermal Solution	Passive heatsink with airflow managed by host sytem. See OEM system specification for implementation details.
Software Development Tools	C-based CUDA Toolkit