<div dir="ltr">Hi Andrew,<div><br></div><div>Please take a look at: <a href="https://fast.dpdk.org/doc/perf/DPDK_25_11_Intel_crypto_performance_report.pdf">https://fast.dpdk.org/doc/perf/DPDK_25_11_Intel_crypto_performance_report.pdf</a></div><div><br></div><div>You have a 4xxx QAT device on the intel-1 server which you are running the DTS dpdk-test-crypto-perf testsuite on, right? I think it is a good idea for you to review the performance report above to check their performance tuning and configuration section, the test methodology section, and compare your 4xxx results against the 4xxx results in this report. Your 4xxx device may differ from the specific SKU the Intel team used, but I imagine they will be within an order of magnitude (or probably much closer). </div></div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Thu, Apr 30, 2026 at 5:36 AM Thomas Monjalon <<a href="mailto:thomas@monjalon.net">thomas@monjalon.net</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">29/04/2026 17:21, Yingya.Han:<br>
> +- [DPDK 25.11 Intel Crypto Performance Report]<br>
> + (//<a href="http://fast.dpdk.org/doc/perf/DPDK_25_11_Intel_crypto_performance_report.pdf" rel="noreferrer" target="_blank">fast.dpdk.org/doc/perf/DPDK_25_11_Intel_crypto_performance_report.pdf</a>)<br>
<br>
Applied, thanks.<br>
<br>
<br>
</blockquote></div>