Displaying 6 results from an estimated 6 matches for "diophantine".
2011 Feb 15
0
[LLVMdev] LLVMdev Digest, Vol 80, Issue 13
Peter Lawrence <peterl95124 at sbcglobal.net> writes:
> Andrew, your response highlights a naming problem in LLVM, which is
> that "array" and "vector" mean the same thing in normal computer
> language and compiler theory usage, so it is inconvenient and
> misleading within LLVM to give one a very specific meaning that is
> different from the other....
I
2012 Feb 06
0
[LLVMdev] Vectorization: Next Steps
...neral consensus
would be on having a core analysis pass carry an LGPL dependency.
>
> These would be my preferred choices to implement the dependence test:
> on the GCC side I have implemented a stand alone dependence tester
> that does not use ILP (i.e., sets the dependence test as a Diophantine
> equation and then solves it) and I can say that it was quite painful
> to write it and to clean the code of bugs.
>
> >> 2. the dependence-graph builder that looks over the complete
> >> function and finds pairs of memory references to pass to the
> >...
2012 Feb 06
7
[LLVMdev] Vectorization: Next Steps
...L
http://freecode.com/projects/isl to set up the dependence problem and
use ISL's ILP to solve it.
These would be my preferred choices to implement the dependence test:
on the GCC side I have implemented a stand alone dependence tester
that does not use ILP (i.e., sets the dependence test as a Diophantine
equation and then solves it) and I can say that it was quite painful
to write it and to clean the code of bugs.
>> 2. the dependence-graph builder that looks over the complete
>> function and finds pairs of memory references to pass to the
>> dependence test,...
2012 Feb 04
0
[LLVMdev] Vectorization: Next Steps
On Fri, 2012-02-03 at 20:59 -0800, Preston Briggs wrote:
> Hal wrote:
> > 3. Loop vectorization - It would be nice to have, in addition to
> > basic-block vectorization, a more-traditional loop vectorization
> pass. I
> > think that we'll need a better loop analysis pass in order for this
> to
> > happen. Some of this was started in LoopDependenceAnalysis, but
2012 Feb 04
2
[LLVMdev] Vectorization: Next Steps
Hal wrote:
> 3. Loop vectorization - It would be nice to have, in addition to
> basic-block vectorization, a more-traditional loop vectorization pass. I
> think that we'll need a better loop analysis pass in order for this to
> happen. Some of this was started in LoopDependenceAnalysis, but that
> pass is not yet finished. We'll need something like this to recognize
>
2011 Feb 14
8
[LLVMdev] LLVMdev Digest, Vol 80, Issue 13
Andrew,
your response highlights a naming problem in LLVM,
which is that "array" and "vector"
mean the same thing in normal computer language and compiler theory
usage, so it is
inconvenient and misleading within LLVM to give one a very specific
meaning that is different
from the other....
to the LLVM developers I would suggest using the term