Changes between Version 97 and Version 98 of DataParallel/BenchmarkStatus

Timestamp:

12/12/10 17:30:45 (3 years ago)

Author:

benl

Comment:

--

DataParallel/BenchmarkStatus

@@ -139 +139 @@
 
  [[br]]
- [http://darcs.haskell.org/packages/dph/examples/smvm/ SMVM] '''(BROKEN)'''::
+ [http://darcs.haskell.org/packages/dph/examples/smvm/ SMVM] '''(BROKEN - Fusion)'''::
  Multiplies a dense vector with a sparse matrix represented in the ''compressed sparse row format (CSR).'' [[br]]
 
@@ -155 +155 @@
 
 [[br]]
- [http://darcs.haskell.org/libraries/dph/dph-examples/spectral/QuickSort/ QuickSort] '''(BROKEN) (SLOWDOWN)'''::
+ [http://darcs.haskell.org/libraries/dph/dph-examples/spectral/QuickSort/ QuickSort] '''(BROKEN - SpecConstr) (SLOWDOWN)'''::
   Sort a vector of doubles by recursively splitting it and sorting the two halves. This is a naive benchmark used for regression testing only. We divide right down to two-point vectors and construct the result using copying append. A production algorithm would switch to an in-place sort once the size of the vector reaches a few thousand elements. N=100k.
 
@@ -191 +191 @@
 These programs also use user defined algebraic data types. Vectorization of these programs is still a work in progress.
 
- [http://darcs.haskell.org/libraries/dph/dph-examples/imaginary/Words/ Words] '''(BROKEN)'''::
+ [http://darcs.haskell.org/libraries/dph/dph-examples/imaginary/Words/ Words] '''(BROKEN - SpecConstr)'''::
   Counts the number of words in a string. This is a naive divide-and-conquer benchmark that divides right down to a single character. A production program would switch to a simple sequential algorithm once the string chunks were small enough. It's a good stress test for the vectoriser though.
 
@@ -198 +198 @@
 
 [[br]]
- [http://darcs.haskell.org/libraries/dph/dph-examples/real/NBody/ BarnesHut] '''(SLOWLORIS)'''::
+ [http://darcs.haskell.org/libraries/dph/dph-examples/real/NBody/ BarnesHut] '''(BROKEN - LLVM)''' '''(SLOWLORIS)'''::
   This benchmark implements the Barnes-Hut algorithm to solve the ''n''-body problem in two dimensions. There is a naive O(n^2^) version in the same package.
 
@@ -207 +207 @@
   A : Time stated is end-to-end, not just for the kernel.
 
-  '''Status''':  Compiles, but fusion doesn't work so it's very slow. [[br]]
+  '''Status''':  Compiles, but fusion doesn't work so it's very slow. LLVM version takes 30min to compile. [[br]]
   '''!ToDo''': Make the vectorised version give the same output as the vector version. The benchmark setup is a bit different. Fixing this won't cause a 50x speed difference though.