I am going to test ooo_2_th config with more SMT threads per core. I modified "theads" option with 1 2 and 4 respectively, and qemu cpu_contexts is 4. I thought benchmark performance could be benifit with more hardware thread contexts. But the results are very wierd.
More SMT threads per core, More Cycles Benchmark takes !? Who can give me a reasonableexplanation? Thanks very much.
_______________________________________________ http://www.marss86.org Marss86-Devel mailing list [email protected] https://www.cs.binghamton.edu/mailman/listinfo/marss86-devel
