Re[2]: GHC vs. GCC on raw vector addition

2006-01-19 Thread Bulat Ziganshin
Hello John, Thursday, January 19, 2006, 4:42:47 AM, you wrote: >> sorry, with the "gcc -O3 -ffast-math -fstrict-aliasing -funroll-loops" >> the C version is 50 times faster than best Haskell one... it's the >> loop from C version: JM> I believe something similar to what I noted here is the culpr

Re[2]: GHC vs. GCC on raw vector addition

2006-01-18 Thread Bulat Ziganshin
Hello Simon, Wednesday, January 18, 2006, 5:31:25 PM, you wrote: >> 2) generating random values takes about 1.5-2 seconds by itself. >> Haskell's RNG is very different from C's one SM> I squeezed a bit more out (see attached). > x `seq` v `seq` return () it's new trick for me :) now

Re[2]: GHC vs. GCC on raw vector addition

2006-01-18 Thread Bulat Ziganshin
Hello Malcolm, Wednesday, January 18, 2006, 4:22:23 PM, you wrote: >> I'm running GHC and GCC head-to-head on the task of adding a bunch of >> long IOUArray-Vectors really fast. My machine is a Linux-ppc PowerBook >> and gets a runtime for the GHC-compiled binary that's about 10x as long >> as for