Data Transfer Rate on Swabian Instruments

CPU Performance Impact on Transfer Rate

Tue, 20 Aug 2024 00:00:00 +0000

We conducted tests to determine the maximum transfer rate achievable with different CPUs using either Time Tagger Ultra or Time Tagger X. The transfer rate for the Time Tagger 20 is limited by USB 2.0 and, therefore, does not depend on CPU performance.

These results are indicative only and may vary with system load (background processes), power mode (plugged in vs on battery), thermal throttling, and OS/driver settings. To reproduce the measurements, use the example scripts included with the installation (default path):

Effects of USB Hubs and Docking Stations on Transfer Rate

Tue, 20 Aug 2024 00:00:00 +0000

High-quality USB hubs and docking stations do not reduce the data transfer rate from Time Taggers to the PC. We conducted tests using both a USB hub (MCD Elektronik GmbH, model: USB 3.0 HUB 6 ) and a docking station ( Lenovo ThinkPad Tunderbolt 4 Docking Station ) to connect the Time Tagger X to a PC. In both cases, we found that the transfer rate was similar to that of the Time Tagger X when it was directly connected to the computer.

Impact of Registered Channels on Transfer Rate

Tue, 20 Aug 2024 00:00:00 +0000

The number of registered channels does not affect the overall transfer rate of a Time Tagger.

To demonstrate this, we enabled the test signals and aligned them in time. We measured the transfer rate for all Time Taggers models. Until Software version v2.16, the transfer rate for Time Tagger Ultra used to decrease by aligning more than 4 channels, reaching a max transfer rate of 36 MTags/s with 18 channels aligned.

Low Count Rate Due to CPU Overload

Tue, 20 Aug 2024 00:00:00 +0000

A low countrate may occur due to CPU overload, especially during computationally intensive measurements.

Each initialized measurement runs on its own thread, but only a few of our API measurements, such as HistogramLogBins , can utilize multiple cores. If a single measurement consumes excessive CPU time, the Time Tagger's hardware buffer can fill up, leading to an overflow event and data loss.

Example Scenario

Consider a time-resolved imaging experiment with 500 pixels × 500 pixels × 1000 bins per histogram, resulting in approximately 1 GByte of data. Modern high-performance computers (e.g., processors with DDR5 RAM) have a CPU-to-RAM bandwidth of about 38.4 GByte/s.

Transfer Rate Limits for Each Time Tagger Model

Tue, 20 Aug 2024 00:00:00 +0000

Time Tagger Ultra (TTU) and Time Tagger X (TTX) utilize a USB 3 interface, allowing a maximum transfer rate of approximately 90 MTags/s . On the other hand, Time Tagger 20 (TT20) uses a USB 2 interface, which limits the maximum transfer rate to about 9 MTags/s . It is worth noting that the transfer rates depend on many different variables, e.g., CPU performance, workload from other running processes, power and performance settings, etc. The results mentioned above can only be achieved using a high-performance CPU with minimal workload from other applications running on the same computer.

Transfer Rate Using Time Tagger Network

Tue, 20 Aug 2024 00:00:00 +0000

The maximum transfer rate using Time Tagger Network is limited to the transmission speed of your local network. A widely adopted transmission technology in modern network infrastructures is the Gigabit Ethernet (GbE) that enables data rate of 1 Gbps. This limits the transfer rate from the Time Tagger Ultra or Time Tagger X to PC over the network up to 29 MTags/s.

USB Extenders and Their Impact on Transfer Rate

Tue, 20 Aug 2024 00:00:00 +0000

High-quality USB extenders and hubs do not reduce the data transfer rate from Time Taggers to the PC.

We tested several USB extenders using a Time Tagger X and Time Tagger Ultra, connected to a USB 3.0 port on a PC (CPU AMD Ryzen 9 5950X 16-Core 3.40GHz) with only essential background processes running. The maximum data transfer rates achieved aligned with the Time Tagger Specifications .

Data Transfer Rate on Swabian Instruments

CPU Performance Impact on Transfer Rate

Effects of USB Hubs and Docking Stations on Transfer Rate

Impact of Registered Channels on Transfer Rate

Low Count Rate Due to CPU Overload

Example Scenario

Transfer Rate Limits for Each Time Tagger Model

Transfer Rate Using Time Tagger Network

USB Extenders and Their Impact on Transfer Rate

Recommended USB 3.x Extenders (Copper):

Lindy Active Extension Pro Series - available lengths: 8 / 10/ 15 / 20 / 30m
E.g., 10m extender: Lindy 43157

Recommended USB 3.x Optical Extenders:

For galvanically isolated extenders, we tested the following model:

Data Transfer Rate on Swabian Instruments

CPU Performance Impact on Transfer Rate

Effects of USB Hubs and Docking Stations on Transfer Rate

Impact of Registered Channels on Transfer Rate

Low Count Rate Due to CPU Overload

Example Scenario

Transfer Rate Limits for Each Time Tagger Model

Transfer Rate Using Time Tagger Network

USB Extenders and Their Impact on Transfer Rate

Recommended USB 3.x Extenders (Copper):

Lindy Active Extension Pro Series - available lengths: 8 / 10/ 15 / 20 / 30m E.g., 10m extender: Lindy 43157

Recommended USB 3.x Optical Extenders:

For galvanically isolated extenders, we tested the following model:

Lindy Active Extension Pro Series - available lengths: 8 / 10/ 15 / 20 / 30m
E.g., 10m extender: Lindy 43157