To believe this couldn't be equalized in the future. Nothing that we know of in Mojave's technology which would lead us Performance currently is not a primary concern for us, and there is Nature of our compute environment being primarily Xeons, optimizing Opteron (which we've been told will be addressed in future releases.) Due to the Seemed to be due to the dataprep stage of Quartz DRC being IO bound ~30% speedup for Quartz DRC) in our current binary. One thing to point out here is the Opterons did seem to favor Calibre These came along late in the game, and it would have taken a month or so toĬollect full data for both tools over the entire test suite. I did have access to 4-CPU Opterons, unfortunately, In-depth during our timeframe), we are limited with Calibre to the number Only runs multi-threaded (except for MTFlex, which was not looked at much Our typical Calibre jobs are run on 2-CPU Xeon machines. Our criteria was that Mojove should be competitive with Calibre at theġ/2/4 CPU block level, and we should see Mojave win hands down at large :)Īnyways, we split our runtime eval into 2 levels, chip level & block level. I can just see ourįrontend team yelling at us for killing our LSF farm. While scalability is good, you can't rely on Lot of our Calibre runs are not full-chip, 12 hour runs. Interesting, we have a hierarchical design style. while those 50 CPU slides Magma showed looked Our currentĬalibre jobs take 8 to 12 hours on multiple CPU machines. Tell the Magma marketing guy to shut up and get real. OK, when we saw in their slides "any chip in 2 hours", it made us want to Subject: Magma Mojave Quartz DRC Pummels Calibre in User Benchmark (II) Synopsys Mentor Cadence TSMC GlobalFoundries SNPS MENT CDNS
0 kommentar(er)
