I am now up to 50 phoronix workloads as summarized on the workloads page. For each one I have a graph and some pages of information. My general idea is to take the benchmark-based Phoronix articles and see if I … Continue reading →
I have not enhanced the topdown tool with ability to print process trees. This enables the key features of my previous “wspy” command. The interfaces is as follows. I added the following options to topdown to record process information: The … Continue reading →
I have made several enhancements to the topdown tool. I also have some fragile things I still need to sort out along the way. The net combination is best seen below where I include both a topdown metrics summary (created … Continue reading →
By default, counters were not available to measure l3 and df counters on AMD. With some help from likwid documentation I figured out what is going on and how to get it enabled. The first thing to do is see … Continue reading →
I have looked through the Family 19h PPR reference, output from “perf list -v –detail” and also some likwid counter groups to figure out combinations of counters I might be able to add as instrumentation options for a topdown command. … Continue reading →
I have updated and enhanced the topdown tool and also used this as an occasion to explore Zen4 topdown performance counters, Intel hybrid CPU while building something to compare Intel i5-13500H and Ryzen 7940 processor metrics. The interface might change, … Continue reading →
I have set up a new Intel performance machine for experiments. The processor is a i5-13500H in a Geekom MiniIT13 mini-PC. Following are some of the major parameters. This comparison is with Ryzen 7840 which will be my AMD comparison … Continue reading →
I have set up a new AMD performance machine for experiments. The processors is a Ryzen 7840 (Phoenix) in a Beelink SER7 mini-PC. Following are some of the major parameters. This comparison is with Intel i5-13500H which will be my … Continue reading →
I copied Stream from https://www.cs.virginia.edu/stream/ and put a copy in https://github.com/cycletourist/perf. This suggested the following compilation flags On my system with a Ryzen 7 7800X3D this results in the following performance: The question is what is the sensitivity of various … Continue reading →
From past work, we know the five counters required to compute the first level topdown metrics on Intel processors: CLK_UNHALTED_CORE = 0x00 IDQ_UOPS_NOT_DELIVERED_CORE = 0x9C, umask=1 UOPS_RETIRED_RETIRE_SLOTS = 0xC2, umask=2 UOPS_ISSUED_ANY = 0x0E, umask=1 INT_MISC_RECOVERY_CYCLES = 0x0d, umask=3, cmask=1 These … Continue reading →