NVIDIA Quadro P620 Compute Related Benchmarks
As we move along with the GPU testing we felt it was time to clean up our database and results in graphs, we have dropped the Silent and OC results for each card and kept the fresh out of box numbers. Doing so made our graphs much easier to read, many users here at STH do not run cards in those configurations or simply cannot do so in Linux based systems so this was warranted. We still have our test numbers and might revisit those settings later on.
Uses cases for the NVIDIA Quadro P620 would not be for high-end graphics, heavy compute tasks or major CAD/Render work, we do not expect to see benchmark results above the bottom of our charts, but none the less, the Quadro P620 handles lighter duty tasks fine. Also, our benchmarks are run on a 4K display which the P620 can handle for general purpose work. Lower screen resolutions might be better for more demanding workloads. Some users report using graphics cards like the P620 for proof of concepts with small data sets before pushing to higher-end costly larger systems to not waste available compute time.
Geekbench 4 measures the compute performance of your GPU using image processing to computer vision to number crunching.
Our first compute benchmark we see the NVIDIA Quadro P620 achieve results near an NVIDIA Quadro K5200 which is a much larger full-size double slot GPU, for OpenCL workloads. We expect to see this trend throughout our benchmarks.
LuxMark is an OpenCL benchmark tool based on LuxRender.
With LuxMark results, we find the Quadro P620, falls to the bottom of the chart, most modern GPU’s are able to achieve these results with ease.
These benchmarks are designed to measure GPGPU computing performance via different OpenCL workloads.
- Single-Precision FLOPS: Measures the classic MAD (Multiply-Addition) performance of the GPU, otherwise known as FLOPS (Floating-Point Operations Per Second), with single-precision (32-bit, “float”) floating-point data.
- Double-Precision FLOPS: Measures the classic MAD (Multiply-Addition) performance of the GPU, otherwise known as FLOPS (Floating-Point Operations Per Second), with double-precision (64-bit, “double”) floating-point data.
The next set of benchmarks from AIDA64 are:
- 24-bit Integer IOPS: Measures the classic MAD (Multiply-Addition) performance of the GPU, otherwise known as IOPS (Integer Operations Per Second), with 24-bit integer (“int24”) data. This particular data type defined in OpenCL on the basis that many GPUs are capable of executing int24 operations via their floating-point units.
- 32-bit Integer IOPS: Measures the classic MAD (Multiply-Addition) performance of the GPU, otherwise known as IOPS (Integer Operations Per Second), with 32-bit integer (“int”) data.
- 64-bit Integer IOPS: Measures the classic MAD (Multiply-Addition) performance of the GPU, otherwise known as IOPS (Integer Operations Per Second), with 64-bit integer (“long”) data. Most GPUs do not have dedicated execution resources for 64-bit integer operations, so instead, they emulate the 64-bit integer operations via existing 32-bit integer execution units.
If you think we are going to see a trend we are. These cards are running at about 1/10th the speed of an NVIDIA GeForce GTX 1660.
hashcat64 is a password cracking benchmarks that can run an impressive number of different algorithms. We used the windows version and a simple command of hashcat64 -b. Out of these results we used five results to the graph. Users who are interested in hashcat can find the download here.
We were a bit surprised in this test that the Quadro P620 was so close to the AMD Radeon PRO WX 4100. Typically this is a workload AMD performs very well in.
SPECviewperf 13 measures the 3D graphics performance of systems running under the OpenGL and Direct X application programming interfaces.
Again we see the Quadro P620 in direct competition with the AMD Radeon PRO WX 4100.
Let us move on and start our new tests with rendering-related benchmarks.