Lighthouse has a new layout. Prefer the old one? Return to the old layout, and switch back any time from the link at the top of each page.

All changesets

Changeset [cd77853c485eaa41c369e17806924123e4308648] by Jed Brown

Revision cd77853c485eaa41c369e17806924123e4308648, committed by Jed Brown · November 28th, 2008 @ 01:29 AM

First pass optimizing TensorMult_Hex.

  • Speedup from <500 MFLOPS to 1150 MFLOPS. When unrolled over last dimension and possibly hand optimized for SSE, 3 GFLOPS or more should be possible up until the working set no longer fits in L1D.

Signed-off-by: Jed Brown jed@59A2.org http://github.com/jedbrown/dohp/...

1 changed file

  • M src/jacobi/impls/tensor/efstopo.c