search for: heroism

...iple times. I have since had some insights which have changed my mind. <4 x i32> on a machine with <8 x i32> vectors misses out on 50% of the theoretical performance. <8 x i32> on a machine with only <4 x i32> takes on unneeded code bloat and register pressure. No amount of heroism in LegalizeTypes can change this basic situation. The further you go, either in the conceptual distance between code and target machine, or in diversity of target machines, the worse the problem gets. Also, all of the proposed solutions for fixing exotic vector types have substantial downsides....

Please ignore my concurrent post :-) Lets proceed in this branch. > do you understand what it means in the non-vector case? I'm beginning to understand it now. It means the type that should be in abstract VM memory. Isn't it? The main question about MemoryVT is: should it be original always (as it was defined in .ll) or not? About vectors with element size less than 8 bits. This

...iple times. I have since had some insights which have changed my mind. <4 x i32> on a machine with <8 x i32> vectors misses out on 50% of the theoretical performance. <8 x i32> on a machine with only <4 x i32> takes on unneeded code bloat and register pressure. No amount of heroism in LegalizeTypes can change this basic situation. The further you go, either in the conceptual distance between code and target machine, or in diversity of target machines, the worse the problem gets. Also, all of the proposed solutions for fixing exotic vector types have substantial downsides....

Ralph, ScottRobbins has a useful note to add to the FreeNX article. You can see it in this Forum post: http://www.centos.org/modules/newbb/viewtopic.php?viewmode=thread&topic_id=14875&forum=40&post_id=51846 Could you give him edit rights to that page? Thanks, Akemi