The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →NVIDIA unveiled the Tesla K40 GPU accelerator at SC13 in Denver on November 17, 2013. The Kepler-based card was aimed at scientific and engineering computing, high-performance computing (HPC), enterprise workloads and big-data analytics. At launch, NVIDIA listed 2,880 CUDA cores, 12 GB of GDDR5 memory, and peak performance of 4.29 teraflops for single precision and 1.43 teraflops for double precision.
What the Tesla K40 launch announced
NVIDIA’s November 17, 2013 launch announcement introduced the Tesla K40 at the SC13 supercomputing conference. NVIDIA positioned it as a Kepler-architecture accelerator for large-scale scientific work and big-data analysis. The company said the K40 was shipping at the time through server manufacturers and reseller partners; that statement describes availability in 2013, not present-day stock.
The release said more than 240 software applications were using GPU acceleration at the time. That was NVIDIA’s launch-era count, not a current tally. The company also announced that the Texas Advanced Computing Center planned to use K40 accelerators in Maverick, an interactive remote visualization and data-analysis system then expected to be fully operational in January 2014. This was a planned deployment as reported at launch.
NVIDIA Tesla K40 specifications
NVIDIA’s 2013 Tesla K-Series datasheet lists these board specifications for the K40:
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
#1 Best Overall
- Bus Type: PCI Express 3.0 x16
- Graphics Engine: NVIDIA Tesla K40
- Memory: 12 GB GDDR5
| Specification | Tesla K40 |
|---|---|
| GPU | One GK110B |
| CUDA cores | 2,880 |
| Memory | 12 GB GDDR5 |
| Peak single-precision performance | 4.29 teraflops |
| Peak double-precision performance | 1.43 teraflops |
| Memory bandwidth | 288 GB/s with ECC off |
These are manufacturer specifications, not independent application benchmarks. Peak throughput figures do not predict how much faster a particular program will run; results depend on the workload and system configuration. The datasheet also names SMX, Dynamic Parallelism and Hyper-Q among the K40’s architecture features.
Tesla K40 vs. Tesla K20X
NVIDIA’s launch materials compared the K40 with the earlier Tesla K20X. The datasheet figures show the specified differences:
Rank #2
- Core Clock: 745 MHz
- Boost Clock: 810 Mhz, 875 MHz
- CUDA Cores: 2880
- Memory: 12GB GDDR5
| Datasheet specification | Tesla K40 | Tesla K20X |
|---|---|---|
| Memory | 12 GB | 6 GB |
| CUDA cores | 2,880 | 2,688 |
| Peak single precision | 4.29 teraflops | 3.95 teraflops |
| Peak double precision | 1.43 teraflops | 1.31 teraflops |
NVIDIA described the K40 as offering twice the memory and claimed performance improvements of up to 40 percent over the K20X. That “up to” statement is NVIDIA’s launch-era promotional claim; the peak figures above do not establish a universal speedup for software or modern workloads.
How NVIDIA described the K40’s role
The K40 was presented as a data-center and HPC accelerator, not a general consumer graphics card. NVIDIA’s launch announcement emphasized scientific and engineering workloads, supercomputing and big-data analytics. It also listed Appro, ASUS, Bull, Cray, Dell, Eurotech, HP, IBM, Inspur, SGI, Sugon, Supermicro and Tyan among manufacturers expected to offer K40-equipped systems at launch. That list is historical and does not establish current sales or support.
Free tools Windows power users keep installed
One-click scans. No signup required.
Rank #3
- Series: Tesla P40, Model: 900-2G610-0000-000
- GPU Architecture: NVIDIA Pascal, Single-Precision Performance:12 TeraFLOPS
- Integer Operations (INT8):47 TOPS (Tera-Operations per Second), GPU Memory:24 GB
- Memorty Bandwidth:346 GB/s, System Interface:PCI Express 3.0 x16
- Max Power:250W, Enhanced Programmability with Page Migration Engine:Yes, ECC Protection:Yes, Server-Optimized for Data Center Deployment:Yes, Hardware-Accelerated Video Engine:1x Decode Engine, 2x Encode Engine
What the launch does not establish today
The announcement and datasheet document what NVIDIA launched in 2013. They do not establish that the K40 is currently available, supported by current software, compatible with a particular modern system, or suitable for a present-day workload. Buyers or researchers evaluating legacy equipment should verify those questions against the specific server, software stack and workload rather than infer them from launch specifications.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
