>>>>> On Wed, 15 Dec 2004 23:17:17 +0900, Izumi Tsutsui <tsutsui@ceres.dti.ne.jp> said: > Maybe we should try some benchmark to see if the CPU_MIPS_VCE (or so) > flag makes some performance benefits. The effectiveness depends on applications. But shouldn't it be always faster, if VCE can be handled by L2 cache? -- soda